linux/tools/perf/util/stat-display.c

1655 lines
42 KiB
C
Raw Permalink Normal View History

#include <stdlib.h>
#include <stdio.h>
#include <inttypes.h>
#include <linux/string.h>
#include <linux/time64.h>
#include <math.h>
#include <perf/cpumap.h>
#include "color.h"
#include "counts.h"
perf stat: Remove evlist__add_default_attrs use strings add_default_atttributes would add evsels by having pre-created perf_event_attr, however, this needed fixing for hybrid as the extended PMU type was necessary for each core PMU. The logic for this was in an arch specific x86 function and wasn't present for ARM, meaning that default events weren't being opened on all PMUs on ARM. Change the creation of the default events to use parse_events and strings as that will open the events on all PMUs. Rather than try to detect events on PMUs before parsing, parse the event but skip its output in stat-display. The previous order of hardware events was: cycles, stalled-cycles-frontend, stalled-cycles-backend, instructions. As instructions is a more fundamental concept the order is changed to: instructions, cycles, stalled-cycles-frontend, stalled-cycles-backend. Closes: https://lore.kernel.org/lkml/CAP-5=fVABSBZnsmtRn1uF-k-G1GWM-L5SgiinhPTfHbQsKXb_g@mail.gmail.com/ Acked-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Ian Rogers <irogers@google.com> [Don't display unsupported default events except 'cycles'] Acked-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: James Clark <james.clark@linaro.org> Cc: Yang Jihong <yangjihong@bytedance.com> Cc: Dominique Martinet <asmadeus@codewreck.org> Cc: Colin Ian King <colin.i.king@gmail.com> Cc: Howard Chu <howardchu95@gmail.com> Cc: Ze Gao <zegao2021@gmail.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Cc: Weilin Wang <weilin.wang@intel.com> Cc: Will Deacon <will@kernel.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Yang Li <yang.lee@linux.alibaba.com> Cc: Leo Yan <leo.yan@linux.dev> Cc: ak@linux.intel.com Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: linux-arm-kernel@lists.infradead.org Cc: Sun Haiyong <sunhaiyong@loongson.cn> Cc: John Garry <john.g.garry@oracle.com> Link: https://lore.kernel.org/r/20240926144851.245903-4-james.clark@linaro.org Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-09-26 15:48:34 +01:00
#include "debug.h"
#include "evlist.h"
#include "evsel.h"
#include "stat.h"
#include "top.h"
#include "thread_map.h"
#include "cpumap.h"
#include "string2.h"
#include <linux/ctype.h>
#include "cgroup.h"
#include <api/fs/fs.h>
#include "util.h"
#include "iostat.h"
perf stat: Avoid hybrid PMU list perf_pmu__is_hybrid implicitly uses the hybrid PMU list. Instead return false if hybrid isn't present, if it is then see if any evsel's PMUs are core. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Ming Wang <wangming01@loongson.cn> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230527072210.2900565-23-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-27 00:21:58 -07:00
#include "pmu.h"
perf pmu: Separate pmu and pmus Separate and hide the pmus list in pmus.[ch]. Move pmus functionality out of pmu.[ch] into pmus.[ch] renaming pmus functions which were prefixed perf_pmu__ to perf_pmus__. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Ming Wang <wangming01@loongson.cn> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230527072210.2900565-28-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-27 00:22:03 -07:00
#include "pmus.h"
#include "tool_pmu.h"
#define CNTR_NOT_SUPPORTED "<not supported>"
#define CNTR_NOT_COUNTED "<not counted>"
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
#define MGROUP_LEN 50
#define METRIC_LEN 38
#define EVNAME_LEN 32
#define COUNTS_LEN 18
#define INTERVAL_LEN 16
#define CGROUP_LEN 16
#define COMM_LEN 16
#define PID_LEN 7
#define CPUS_LEN 4
static int aggr_header_lens[] = {
[AGGR_CORE] = 18,
perf stat: Setup the foundation to allow aggregation based on cache topology Processors based on chiplet architecture, such as AMD EPYC and Hygon do not expose the chiplet details in the sysfs CPU topology information. However, this information can be derived from the per CPU cache level information from the sysfs. 'perf stat' has already supported aggregation based on topology information using core ID, socket ID, etc. It'll be useful to aggregate based on the cache topology to detect problems like imbalance and cache-to-cache sharing at various cache levels. This patch lays the foundation for aggregating data in 'perf stat' based on the processor's cache topology. The cmdline option to aggregate data based on the cache topology is added in Patch 4 of the series while this patch sets up all the necessary functions and variables required to support the new aggregation option. The patch also adds support to display per-cache aggregation, or save it as a JSON or CSV, as splitting it into a separate patch would break builds when compiling with "-Werror=switch-enum" where the compiler will complain about the lack of handling for the AGGR_CACHE case in the output functions. Committer notes: Don't use perf_stat_config in tools/perf/util/cpumap.c, this would make code that is in util/, thus not really specific to a single builtin, use a specific builtin config structure. Move the functions introduced in this patch from tools/perf/util/cpumap.c since it needs access to builtin specific and is not strictly needed to live in the util/ directory. With this 'perf test python' is back building. Suggested-by: Gautham Shenoy <gautham.shenoy@amd.com> Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ananth Narayan <ananth.narayan@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Wen Pu <puwen@hygon.cn> Link: https://lore.kernel.org/r/20230517172745.5833-3-kprateek.nayak@amd.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-17 22:57:42 +05:30
[AGGR_CACHE] = 22,
[AGGR_CLUSTER] = 20,
[AGGR_DIE] = 12,
[AGGR_SOCKET] = 6,
[AGGR_NODE] = 6,
[AGGR_NONE] = 6,
[AGGR_THREAD] = 16,
[AGGR_GLOBAL] = 0,
};
static const char *aggr_header_csv[] = {
perf stat: Fix uncore aggregation number Follow up: lore.kernel.org/CAP-5=fVDF4-qYL1Lm7efgiHk7X=_nw_nEFMBZFMcsnOOJgX4Kg@mail.gmail.com/ The patch adds unit aggregation during evsel merge the aggregated uncore counters. Change the name of the column to `ctrs` and `counters` for json mode. Tested on a 2-socket machine with SNC3, uncore_imc_[0-11] and cpumask="0,120" Before: perf stat -e clockticks -I 1000 --per-socket # time socket cpus counts unit events 1.001085024 S0 1 9615386315 clockticks 1.001085024 S1 1 9614287448 clockticks perf stat -e clockticks -I 1000 --per-node # time node cpus counts unit events 1.001029867 N0 1 3205726984 clockticks 1.001029867 N1 1 3205444421 clockticks 1.001029867 N2 1 3205234018 clockticks 1.001029867 N3 1 3205224660 clockticks 1.001029867 N4 1 3205207213 clockticks 1.001029867 N5 1 3205528246 clockticks After: perf stat -e clockticks -I 1000 --per-socket # time socket ctrs counts unit events 1.001026071 S0 12 9619677996 clockticks 1.001026071 S1 12 9618612614 clockticks perf stat -e clockticks -I 1000 --per-node # time node ctrs counts unit events 1.001027449 N0 4 3207251859 clockticks 1.001027449 N1 4 3207315930 clockticks 1.001027449 N2 4 3206981828 clockticks 1.001027449 N3 4 3206566126 clockticks 1.001027449 N4 4 3206032609 clockticks 1.001027449 N5 4 3205651355 clockticks Tested with JSON output linter: perf test "perf stat JSON output linter" 94: perf stat JSON output linter : Ok Suggested-by: Ian Rogers <irogers@google.com> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Chun-Tse Shao <ctshao@google.com> Link: https://lore.kernel.org/r/20250627201818.479421-1-ctshao@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2025-06-27 13:16:41 -07:00
[AGGR_CORE] = "core,ctrs,",
[AGGR_CACHE] = "cache,ctrs,",
[AGGR_CLUSTER] = "cluster,ctrs,",
[AGGR_DIE] = "die,ctrs,",
[AGGR_SOCKET] = "socket,ctrs,",
[AGGR_NONE] = "cpu,",
[AGGR_THREAD] = "comm-pid,",
[AGGR_NODE] = "node,",
[AGGR_GLOBAL] = ""
};
static const char *aggr_header_std[] = {
[AGGR_CORE] = "core",
perf stat: Setup the foundation to allow aggregation based on cache topology Processors based on chiplet architecture, such as AMD EPYC and Hygon do not expose the chiplet details in the sysfs CPU topology information. However, this information can be derived from the per CPU cache level information from the sysfs. 'perf stat' has already supported aggregation based on topology information using core ID, socket ID, etc. It'll be useful to aggregate based on the cache topology to detect problems like imbalance and cache-to-cache sharing at various cache levels. This patch lays the foundation for aggregating data in 'perf stat' based on the processor's cache topology. The cmdline option to aggregate data based on the cache topology is added in Patch 4 of the series while this patch sets up all the necessary functions and variables required to support the new aggregation option. The patch also adds support to display per-cache aggregation, or save it as a JSON or CSV, as splitting it into a separate patch would break builds when compiling with "-Werror=switch-enum" where the compiler will complain about the lack of handling for the AGGR_CACHE case in the output functions. Committer notes: Don't use perf_stat_config in tools/perf/util/cpumap.c, this would make code that is in util/, thus not really specific to a single builtin, use a specific builtin config structure. Move the functions introduced in this patch from tools/perf/util/cpumap.c since it needs access to builtin specific and is not strictly needed to live in the util/ directory. With this 'perf test python' is back building. Suggested-by: Gautham Shenoy <gautham.shenoy@amd.com> Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ananth Narayan <ananth.narayan@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Wen Pu <puwen@hygon.cn> Link: https://lore.kernel.org/r/20230517172745.5833-3-kprateek.nayak@amd.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-17 22:57:42 +05:30
[AGGR_CACHE] = "cache",
[AGGR_CLUSTER] = "cluster",
[AGGR_DIE] = "die",
[AGGR_SOCKET] = "socket",
[AGGR_NONE] = "cpu",
[AGGR_THREAD] = "comm-pid",
[AGGR_NODE] = "node",
[AGGR_GLOBAL] = ""
};
const char *metric_threshold_classify__color(enum metric_threshold_classify thresh)
{
const char * const colors[] = {
"", /* unknown */
PERF_COLOR_RED, /* bad */
PERF_COLOR_MAGENTA, /* nearly bad */
PERF_COLOR_YELLOW, /* less good */
PERF_COLOR_GREEN, /* good */
};
static_assert(ARRAY_SIZE(colors) - 1 == METRIC_THRESHOLD_GOOD, "missing enum value");
return colors[thresh];
}
perf stat: Add metric-threshold to json output When the threshold isn't unknown add a value to the json like: "metric-threshold" : "good" A more complete example: ``` $ perf stat -a -j -I 1000 {"interval" : 1.001089747, "counter-value" : "16045.281449", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 16045355135, "pcnt-running" : 100.00, "metric-value" : "16.045281", "metric-unit" : "CPUs utilized"} {"interval" : 1.001089747, "counter-value" : "10003.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 16045314844, "pcnt-running" : 100.00, "metric-value" : "623.423156", "metric-unit" : "/sec"} {"interval" : 1.001089747, "counter-value" : "328.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 16045321403, "pcnt-running" : 100.00, "metric-value" : "20.442147", "metric-unit" : "/sec"} {"interval" : 1.001089747, "counter-value" : "20114.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 16045355927, "pcnt-running" : 100.00, "metric-value" : "1.253577", "metric-unit" : "K/sec"} {"interval" : 1.001089747, "counter-value" : "4066679471.000000", "unit" : "", "event" : "instructions", "event-runtime" : 16045369123, "pcnt-running" : 100.00, "metric-value" : "1.628330", "metric-unit" : "insn per cycle"} {"interval" : 1.001089747, "counter-value" : "2497454658.000000", "unit" : "", "event" : "cycles", "event-runtime" : 16045374810, "pcnt-running" : 100.00, "metric-value" : "0.155650", "metric-unit" : "GHz"} {"interval" : 1.001089747, "counter-value" : "914974294.000000", "unit" : "", "event" : "branches", "event-runtime" : 16045379877, "pcnt-running" : 100.00, "metric-value" : "57.024509", "metric-unit" : "M/sec"} {"interval" : 1.001089747, "counter-value" : "9237201.000000", "unit" : "", "event" : "branch-misses", "event-runtime" : 16045375017, "pcnt-running" : 100.00, "metric-value" : "1.009559", "metric-unit" : "of all branches", "metric-threshold" : "good"} {"interval" : 1.001089747, "event-runtime" : 16045397172, "pcnt-running" : 100.00, "metricgroup" : "TopdownL1"} {"interval" : 1.001089747, "metric-value" : "22.036686", "metric-unit" : "% tma_backend_bound", "metric-threshold" : "bad"} {"interval" : 1.001089747, "metric-value" : "7.610161", "metric-unit" : "% tma_bad_speculation", "metric-threshold" : "good"} {"interval" : 1.001089747, "metric-value" : "36.729687", "metric-unit" : "% tma_frontend_bound", "metric-threshold" : "bad"} {"interval" : 1.001089747, "metric-value" : "33.623465", "metric-unit" : "% tma_retiring"} ... ``` Signed-off-by: Ian Rogers <irogers@google.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Cc: Weilin Wang <weilin.wang@intel.com> Cc: Will Deacon <will@kernel.org> Cc: James Clark <james.clark@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Leo Yan <leo.yan@linux.dev> Cc: Sumanth Korikkar <sumanthk@linux.ibm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: John Garry <john.g.garry@oracle.com> Link: https://lore.kernel.org/r/20241017175356.783793-7-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-17 10:53:55 -07:00
static const char *metric_threshold_classify__str(enum metric_threshold_classify thresh)
{
const char * const strs[] = {
"unknown",
"bad",
"nearly bad",
"less good",
"good",
};
static_assert(ARRAY_SIZE(strs) - 1 == METRIC_THRESHOLD_GOOD, "missing enum value");
return strs[thresh];
}
static void print_running_std(struct perf_stat_config *config, u64 run, u64 ena)
{
if (run != ena)
fprintf(config->output, " (%.2f%%)", 100.0 * run / ena);
}
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
static void print_running_csv(struct perf_stat_config *config, u64 run, u64 ena)
{
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
double enabled_percent = 100;
if (run != ena)
enabled_percent = 100 * run / ena;
fprintf(config->output, "%s%" PRIu64 "%s%.2f",
config->csv_sep, run, config->csv_sep, enabled_percent);
}
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
struct outstate {
/* Std mode: insert a newline before the next metric */
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
bool newline;
/* JSON mode: track need for comma for a previous field or not */
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
bool first;
/* Num CSV separators remaining to pad out when not all fields are printed */
int csv_col_pad;
/*
* The following don't track state across fields, but are here as a shortcut to
* pass data to the print functions. The alternative would be to update the
* function signatures of the entire print stack to pass them through.
*/
/* Place to output to */
FILE * const fh;
/* Lines are timestamped in --interval-print mode */
char timestamp[64];
/* Num items aggregated in current line. See struct perf_stat_aggr.nr */
int aggr_nr;
/* Core/socket/die etc ID for the current line */
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
struct aggr_cpu_id id;
/* Event for current line */
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
struct evsel *evsel;
/* Cgroup for current line */
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
struct cgroup *cgrp;
};
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
static const char *json_sep(struct outstate *os)
{
const char *sep = os->first ? "" : ", ";
os->first = false;
return sep;
}
#define json_out(os, format, ...) fprintf((os)->fh, "%s" format, json_sep(os), ##__VA_ARGS__)
static void print_running_json(struct outstate *os, u64 run, u64 ena)
{
double enabled_percent = 100;
if (run != ena)
enabled_percent = 100 * run / ena;
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
json_out(os, "\"event-runtime\" : %" PRIu64 ", \"pcnt-running\" : %.2f",
run, enabled_percent);
}
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
static void print_running(struct perf_stat_config *config, struct outstate *os,
u64 run, u64 ena, bool before_metric)
{
if (config->json_output) {
if (before_metric)
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
print_running_json(os, run, ena);
} else if (config->csv_output) {
if (before_metric)
print_running_csv(config, run, ena);
} else {
if (!before_metric)
print_running_std(config, run, ena);
}
}
static void print_noise_pct_std(struct perf_stat_config *config,
double pct)
{
if (pct)
fprintf(config->output, " ( +-%6.2f%% )", pct);
}
static void print_noise_pct_csv(struct perf_stat_config *config,
double pct)
{
fprintf(config->output, "%s%.2f%%", config->csv_sep, pct);
}
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
static void print_noise_pct_json(struct outstate *os,
double pct)
{
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
json_out(os, "\"variance\" : %.2f", pct);
}
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
static void print_noise_pct(struct perf_stat_config *config, struct outstate *os,
double total, double avg, bool before_metric)
{
double pct = rel_stddev_stats(total, avg);
if (config->json_output) {
if (before_metric)
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
print_noise_pct_json(os, pct);
} else if (config->csv_output) {
if (before_metric)
print_noise_pct_csv(config, pct);
} else {
if (!before_metric)
print_noise_pct_std(config, pct);
}
}
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
static void print_noise(struct perf_stat_config *config, struct outstate *os,
struct evsel *evsel, double avg, bool before_metric)
{
struct perf_stat_evsel *ps;
if (config->run_count == 1)
return;
ps = evsel->stats;
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
print_noise_pct(config, os, stddev_stats(&ps->res_stats), avg, before_metric);
}
static void print_cgroup_std(struct perf_stat_config *config, const char *cgrp_name)
{
fprintf(config->output, " %-*s", CGROUP_LEN, cgrp_name);
}
static void print_cgroup_csv(struct perf_stat_config *config, const char *cgrp_name)
{
fprintf(config->output, "%s%s", config->csv_sep, cgrp_name);
}
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
static void print_cgroup_json(struct outstate *os, const char *cgrp_name)
{
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
json_out(os, "\"cgroup\" : \"%s\"", cgrp_name);
}
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
static void print_cgroup(struct perf_stat_config *config, struct outstate *os,
struct cgroup *cgrp)
{
if (nr_cgroups || config->cgroup_list) {
const char *cgrp_name = cgrp ? cgrp->name : "";
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
if (config->json_output)
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
print_cgroup_json(os, cgrp_name);
else if (config->csv_output)
print_cgroup_csv(config, cgrp_name);
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
else
print_cgroup_std(config, cgrp_name);
}
}
static void print_aggr_id_std(struct perf_stat_config *config,
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
struct evsel *evsel, struct aggr_cpu_id id, int aggr_nr)
{
FILE *output = config->output;
int idx = config->aggr_mode;
char buf[128];
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
switch (config->aggr_mode) {
case AGGR_CORE:
snprintf(buf, sizeof(buf), "S%d-D%d-C%d", id.socket, id.die, id.core);
break;
perf stat: Setup the foundation to allow aggregation based on cache topology Processors based on chiplet architecture, such as AMD EPYC and Hygon do not expose the chiplet details in the sysfs CPU topology information. However, this information can be derived from the per CPU cache level information from the sysfs. 'perf stat' has already supported aggregation based on topology information using core ID, socket ID, etc. It'll be useful to aggregate based on the cache topology to detect problems like imbalance and cache-to-cache sharing at various cache levels. This patch lays the foundation for aggregating data in 'perf stat' based on the processor's cache topology. The cmdline option to aggregate data based on the cache topology is added in Patch 4 of the series while this patch sets up all the necessary functions and variables required to support the new aggregation option. The patch also adds support to display per-cache aggregation, or save it as a JSON or CSV, as splitting it into a separate patch would break builds when compiling with "-Werror=switch-enum" where the compiler will complain about the lack of handling for the AGGR_CACHE case in the output functions. Committer notes: Don't use perf_stat_config in tools/perf/util/cpumap.c, this would make code that is in util/, thus not really specific to a single builtin, use a specific builtin config structure. Move the functions introduced in this patch from tools/perf/util/cpumap.c since it needs access to builtin specific and is not strictly needed to live in the util/ directory. With this 'perf test python' is back building. Suggested-by: Gautham Shenoy <gautham.shenoy@amd.com> Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ananth Narayan <ananth.narayan@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Wen Pu <puwen@hygon.cn> Link: https://lore.kernel.org/r/20230517172745.5833-3-kprateek.nayak@amd.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-17 22:57:42 +05:30
case AGGR_CACHE:
snprintf(buf, sizeof(buf), "S%d-D%d-L%d-ID%d",
id.socket, id.die, id.cache_lvl, id.cache);
break;
perf stat: Support per-cluster aggregation Some platforms have 'cluster' topology and CPUs in the cluster will share resources like L3 Cache Tag (for HiSilicon Kunpeng SoC) or L2 cache (for Intel Jacobsville). Currently parsing and building cluster topology have been supported since [1]. perf stat has already supported aggregation for other topologies like die or socket, etc. It'll be useful to aggregate per-cluster to find problems like L3T bandwidth contention. This patch add support for "--per-cluster" option for per-cluster aggregation. Also update the docs and related test. The output will be like: [root@localhost tmp]# perf stat -a -e LLC-load --per-cluster -- sleep 5 Performance counter stats for 'system wide': S56-D0-CLS158 4 1,321,521,570 LLC-load S56-D0-CLS594 4 794,211,453 LLC-load S56-D0-CLS1030 4 41,623 LLC-load S56-D0-CLS1466 4 41,646 LLC-load S56-D0-CLS1902 4 16,863 LLC-load S56-D0-CLS2338 4 15,721 LLC-load S56-D0-CLS2774 4 22,671 LLC-load [...] On a legacy system without cluster or cluster support, the output will be look like: [root@localhost perf]# perf stat -a -e cycles --per-cluster -- sleep 1 Performance counter stats for 'system wide': S56-D0-CLS0 64 18,011,485 cycles S7182-D0-CLS0 64 16,548,835 cycles Note that this patch doesn't mix the cluster information in the outputs of --per-core to avoid breaking any tools/scripts using it. Note that perf recently supports "--per-cache" aggregation, but it's not the same with the cluster although cluster CPUs may share some cache resources. For example on my machine all clusters within a die share the same L3 cache: $ cat /sys/devices/system/cpu/cpu0/cache/index3/shared_cpu_list 0-31 $ cat /sys/devices/system/cpu/cpu0/topology/cluster_cpus_list 0-3 [1] commit c5e22feffdd7 ("topology: Represent clusters of CPUs within a die") Tested-by: Jie Zhan <zhanjie9@hisilicon.com> Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yicong Yang <yangyicong@hisilicon.com> Cc: james.clark@arm.com Cc: 21cnbao@gmail.com Cc: prime.zeng@hisilicon.com Cc: Jonathan.Cameron@huawei.com Cc: fanghao11@huawei.com Cc: linuxarm@huawei.com Cc: tim.c.chen@intel.com Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/r/20240208024026.2691-1-yangyicong@huawei.com
2024-02-08 10:40:26 +08:00
case AGGR_CLUSTER:
snprintf(buf, sizeof(buf), "S%d-D%d-CLS%d", id.socket, id.die, id.cluster);
break;
case AGGR_DIE:
snprintf(buf, sizeof(buf), "S%d-D%d", id.socket, id.die);
break;
case AGGR_SOCKET:
snprintf(buf, sizeof(buf), "S%d", id.socket);
break;
case AGGR_NODE:
snprintf(buf, sizeof(buf), "N%d", id.node);
break;
case AGGR_NONE:
if (evsel->percore && !config->percore_show_thread) {
snprintf(buf, sizeof(buf), "S%d-D%d-C%d ",
id.socket, id.die, id.core);
fprintf(output, "%-*s ",
aggr_header_lens[AGGR_CORE], buf);
} else if (id.cpu.cpu > -1) {
fprintf(output, "CPU%-*d ",
aggr_header_lens[AGGR_NONE] - 3, id.cpu.cpu);
}
return;
case AGGR_THREAD:
fprintf(output, "%*s-%-*d ",
COMM_LEN, perf_thread_map__comm(evsel->core.threads, id.thread_idx),
PID_LEN, perf_thread_map__pid(evsel->core.threads, id.thread_idx));
return;
case AGGR_GLOBAL:
case AGGR_UNSET:
case AGGR_MAX:
default:
return;
}
perf stat: Fix uncore aggregation number Follow up: lore.kernel.org/CAP-5=fVDF4-qYL1Lm7efgiHk7X=_nw_nEFMBZFMcsnOOJgX4Kg@mail.gmail.com/ The patch adds unit aggregation during evsel merge the aggregated uncore counters. Change the name of the column to `ctrs` and `counters` for json mode. Tested on a 2-socket machine with SNC3, uncore_imc_[0-11] and cpumask="0,120" Before: perf stat -e clockticks -I 1000 --per-socket # time socket cpus counts unit events 1.001085024 S0 1 9615386315 clockticks 1.001085024 S1 1 9614287448 clockticks perf stat -e clockticks -I 1000 --per-node # time node cpus counts unit events 1.001029867 N0 1 3205726984 clockticks 1.001029867 N1 1 3205444421 clockticks 1.001029867 N2 1 3205234018 clockticks 1.001029867 N3 1 3205224660 clockticks 1.001029867 N4 1 3205207213 clockticks 1.001029867 N5 1 3205528246 clockticks After: perf stat -e clockticks -I 1000 --per-socket # time socket ctrs counts unit events 1.001026071 S0 12 9619677996 clockticks 1.001026071 S1 12 9618612614 clockticks perf stat -e clockticks -I 1000 --per-node # time node ctrs counts unit events 1.001027449 N0 4 3207251859 clockticks 1.001027449 N1 4 3207315930 clockticks 1.001027449 N2 4 3206981828 clockticks 1.001027449 N3 4 3206566126 clockticks 1.001027449 N4 4 3206032609 clockticks 1.001027449 N5 4 3205651355 clockticks Tested with JSON output linter: perf test "perf stat JSON output linter" 94: perf stat JSON output linter : Ok Suggested-by: Ian Rogers <irogers@google.com> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Chun-Tse Shao <ctshao@google.com> Link: https://lore.kernel.org/r/20250627201818.479421-1-ctshao@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2025-06-27 13:16:41 -07:00
fprintf(output, "%-*s %*d ", aggr_header_lens[idx], buf, /*strlen("ctrs")*/ 4, aggr_nr);
}
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
static void print_aggr_id_csv(struct perf_stat_config *config,
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
struct evsel *evsel, struct aggr_cpu_id id, int aggr_nr)
{
FILE *output = config->output;
const char *sep = config->csv_sep;
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
switch (config->aggr_mode) {
case AGGR_CORE:
fprintf(output, "S%d-D%d-C%d%s%d%s",
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
id.socket, id.die, id.core, sep, aggr_nr, sep);
break;
perf stat: Setup the foundation to allow aggregation based on cache topology Processors based on chiplet architecture, such as AMD EPYC and Hygon do not expose the chiplet details in the sysfs CPU topology information. However, this information can be derived from the per CPU cache level information from the sysfs. 'perf stat' has already supported aggregation based on topology information using core ID, socket ID, etc. It'll be useful to aggregate based on the cache topology to detect problems like imbalance and cache-to-cache sharing at various cache levels. This patch lays the foundation for aggregating data in 'perf stat' based on the processor's cache topology. The cmdline option to aggregate data based on the cache topology is added in Patch 4 of the series while this patch sets up all the necessary functions and variables required to support the new aggregation option. The patch also adds support to display per-cache aggregation, or save it as a JSON or CSV, as splitting it into a separate patch would break builds when compiling with "-Werror=switch-enum" where the compiler will complain about the lack of handling for the AGGR_CACHE case in the output functions. Committer notes: Don't use perf_stat_config in tools/perf/util/cpumap.c, this would make code that is in util/, thus not really specific to a single builtin, use a specific builtin config structure. Move the functions introduced in this patch from tools/perf/util/cpumap.c since it needs access to builtin specific and is not strictly needed to live in the util/ directory. With this 'perf test python' is back building. Suggested-by: Gautham Shenoy <gautham.shenoy@amd.com> Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ananth Narayan <ananth.narayan@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Wen Pu <puwen@hygon.cn> Link: https://lore.kernel.org/r/20230517172745.5833-3-kprateek.nayak@amd.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-17 22:57:42 +05:30
case AGGR_CACHE:
fprintf(config->output, "S%d-D%d-L%d-ID%d%s%d%s",
id.socket, id.die, id.cache_lvl, id.cache, sep, aggr_nr, sep);
break;
perf stat: Support per-cluster aggregation Some platforms have 'cluster' topology and CPUs in the cluster will share resources like L3 Cache Tag (for HiSilicon Kunpeng SoC) or L2 cache (for Intel Jacobsville). Currently parsing and building cluster topology have been supported since [1]. perf stat has already supported aggregation for other topologies like die or socket, etc. It'll be useful to aggregate per-cluster to find problems like L3T bandwidth contention. This patch add support for "--per-cluster" option for per-cluster aggregation. Also update the docs and related test. The output will be like: [root@localhost tmp]# perf stat -a -e LLC-load --per-cluster -- sleep 5 Performance counter stats for 'system wide': S56-D0-CLS158 4 1,321,521,570 LLC-load S56-D0-CLS594 4 794,211,453 LLC-load S56-D0-CLS1030 4 41,623 LLC-load S56-D0-CLS1466 4 41,646 LLC-load S56-D0-CLS1902 4 16,863 LLC-load S56-D0-CLS2338 4 15,721 LLC-load S56-D0-CLS2774 4 22,671 LLC-load [...] On a legacy system without cluster or cluster support, the output will be look like: [root@localhost perf]# perf stat -a -e cycles --per-cluster -- sleep 1 Performance counter stats for 'system wide': S56-D0-CLS0 64 18,011,485 cycles S7182-D0-CLS0 64 16,548,835 cycles Note that this patch doesn't mix the cluster information in the outputs of --per-core to avoid breaking any tools/scripts using it. Note that perf recently supports "--per-cache" aggregation, but it's not the same with the cluster although cluster CPUs may share some cache resources. For example on my machine all clusters within a die share the same L3 cache: $ cat /sys/devices/system/cpu/cpu0/cache/index3/shared_cpu_list 0-31 $ cat /sys/devices/system/cpu/cpu0/topology/cluster_cpus_list 0-3 [1] commit c5e22feffdd7 ("topology: Represent clusters of CPUs within a die") Tested-by: Jie Zhan <zhanjie9@hisilicon.com> Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yicong Yang <yangyicong@hisilicon.com> Cc: james.clark@arm.com Cc: 21cnbao@gmail.com Cc: prime.zeng@hisilicon.com Cc: Jonathan.Cameron@huawei.com Cc: fanghao11@huawei.com Cc: linuxarm@huawei.com Cc: tim.c.chen@intel.com Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/r/20240208024026.2691-1-yangyicong@huawei.com
2024-02-08 10:40:26 +08:00
case AGGR_CLUSTER:
fprintf(config->output, "S%d-D%d-CLS%d%s%d%s",
id.socket, id.die, id.cluster, sep, aggr_nr, sep);
break;
case AGGR_DIE:
fprintf(output, "S%d-D%d%s%d%s",
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
id.socket, id.die, sep, aggr_nr, sep);
break;
case AGGR_SOCKET:
fprintf(output, "S%d%s%d%s",
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
id.socket, sep, aggr_nr, sep);
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
break;
perf stat: Add --per-node agregation support Adding new --per-node option to aggregate counts per NUMA nodes for system-wide mode measurements. You can specify --per-node in live mode: # perf stat -a -I 1000 -e cycles --per-node # time node cpus counts unit events 1.000542550 N0 20 6,202,097 cycles 1.000542550 N1 20 639,559 cycles 2.002040063 N0 20 7,412,495 cycles 2.002040063 N1 20 2,185,577 cycles 3.003451699 N0 20 6,508,917 cycles 3.003451699 N1 20 765,607 cycles ... Or in the record/report stat session: # perf stat record -a -I 1000 -e cycles # time counts unit events 1.000536937 10,008,468 cycles 2.002090152 9,578,539 cycles 3.003625233 7,647,869 cycles 4.005135036 7,032,086 cycles ^C 4.340902364 3,923,893 cycles # perf stat report --per-node # time node cpus counts unit events 1.000536937 N0 20 9,355,086 cycles 1.000536937 N1 20 653,382 cycles 2.002090152 N0 20 7,712,838 cycles 2.002090152 N1 20 1,865,701 cycles 3.003625233 N0 20 6,604,441 cycles 3.003625233 N1 20 1,043,428 cycles 4.005135036 N0 20 6,350,522 cycles 4.005135036 N1 20 681,564 cycles 4.340902364 N0 20 3,403,188 cycles 4.340902364 N1 20 520,705 cycles Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexey Budankov <alexey.budankov@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Joe Mario <jmario@redhat.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20190904073415.723-4-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-08-28 10:17:43 +02:00
case AGGR_NODE:
fprintf(output, "N%d%s%d%s",
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
id.node, sep, aggr_nr, sep);
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
break;
case AGGR_NONE:
if (evsel->percore && !config->percore_show_thread) {
fprintf(output, "S%d-D%d-C%d%s",
id.socket, id.die, id.core, sep);
} else if (id.cpu.cpu > -1) {
fprintf(output, "CPU%d%s",
id.cpu.cpu, sep);
perf stat: Support 'percore' event qualifier With this patch, we can use the 'percore' event qualifier in perf-stat. root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000 1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%) 1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%) 1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%) In this example, we count the event 'ref-cycles' per-core and per-CPU in one perf stat command-line. From the output, we can see: S0-C0 = CPU0 + CPU4 S0-C1 = CPU1 + CPU5 S0-C2 = CPU2 + CPU6 S0-C3 = CPU3 + CPU7 So the result is expected (tiny difference is ignored). Note that, the 'percore' event qualifier needs to use with option '-A'. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 21:59:49 +08:00
}
break;
case AGGR_THREAD:
fprintf(output, "%s-%d%s",
perf_thread_map__comm(evsel->core.threads, id.thread_idx),
perf_thread_map__pid(evsel->core.threads, id.thread_idx),
sep);
break;
case AGGR_GLOBAL:
case AGGR_UNSET:
case AGGR_MAX:
default:
break;
}
}
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
static void print_aggr_id_json(struct perf_stat_config *config, struct outstate *os,
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
struct evsel *evsel, struct aggr_cpu_id id, int aggr_nr)
{
switch (config->aggr_mode) {
case AGGR_CORE:
perf stat: Fix uncore aggregation number Follow up: lore.kernel.org/CAP-5=fVDF4-qYL1Lm7efgiHk7X=_nw_nEFMBZFMcsnOOJgX4Kg@mail.gmail.com/ The patch adds unit aggregation during evsel merge the aggregated uncore counters. Change the name of the column to `ctrs` and `counters` for json mode. Tested on a 2-socket machine with SNC3, uncore_imc_[0-11] and cpumask="0,120" Before: perf stat -e clockticks -I 1000 --per-socket # time socket cpus counts unit events 1.001085024 S0 1 9615386315 clockticks 1.001085024 S1 1 9614287448 clockticks perf stat -e clockticks -I 1000 --per-node # time node cpus counts unit events 1.001029867 N0 1 3205726984 clockticks 1.001029867 N1 1 3205444421 clockticks 1.001029867 N2 1 3205234018 clockticks 1.001029867 N3 1 3205224660 clockticks 1.001029867 N4 1 3205207213 clockticks 1.001029867 N5 1 3205528246 clockticks After: perf stat -e clockticks -I 1000 --per-socket # time socket ctrs counts unit events 1.001026071 S0 12 9619677996 clockticks 1.001026071 S1 12 9618612614 clockticks perf stat -e clockticks -I 1000 --per-node # time node ctrs counts unit events 1.001027449 N0 4 3207251859 clockticks 1.001027449 N1 4 3207315930 clockticks 1.001027449 N2 4 3206981828 clockticks 1.001027449 N3 4 3206566126 clockticks 1.001027449 N4 4 3206032609 clockticks 1.001027449 N5 4 3205651355 clockticks Tested with JSON output linter: perf test "perf stat JSON output linter" 94: perf stat JSON output linter : Ok Suggested-by: Ian Rogers <irogers@google.com> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Chun-Tse Shao <ctshao@google.com> Link: https://lore.kernel.org/r/20250627201818.479421-1-ctshao@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2025-06-27 13:16:41 -07:00
json_out(os, "\"core\" : \"S%d-D%d-C%d\", \"counters\" : %d",
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
id.socket, id.die, id.core, aggr_nr);
break;
perf stat: Setup the foundation to allow aggregation based on cache topology Processors based on chiplet architecture, such as AMD EPYC and Hygon do not expose the chiplet details in the sysfs CPU topology information. However, this information can be derived from the per CPU cache level information from the sysfs. 'perf stat' has already supported aggregation based on topology information using core ID, socket ID, etc. It'll be useful to aggregate based on the cache topology to detect problems like imbalance and cache-to-cache sharing at various cache levels. This patch lays the foundation for aggregating data in 'perf stat' based on the processor's cache topology. The cmdline option to aggregate data based on the cache topology is added in Patch 4 of the series while this patch sets up all the necessary functions and variables required to support the new aggregation option. The patch also adds support to display per-cache aggregation, or save it as a JSON or CSV, as splitting it into a separate patch would break builds when compiling with "-Werror=switch-enum" where the compiler will complain about the lack of handling for the AGGR_CACHE case in the output functions. Committer notes: Don't use perf_stat_config in tools/perf/util/cpumap.c, this would make code that is in util/, thus not really specific to a single builtin, use a specific builtin config structure. Move the functions introduced in this patch from tools/perf/util/cpumap.c since it needs access to builtin specific and is not strictly needed to live in the util/ directory. With this 'perf test python' is back building. Suggested-by: Gautham Shenoy <gautham.shenoy@amd.com> Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ananth Narayan <ananth.narayan@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Wen Pu <puwen@hygon.cn> Link: https://lore.kernel.org/r/20230517172745.5833-3-kprateek.nayak@amd.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-17 22:57:42 +05:30
case AGGR_CACHE:
perf stat: Fix uncore aggregation number Follow up: lore.kernel.org/CAP-5=fVDF4-qYL1Lm7efgiHk7X=_nw_nEFMBZFMcsnOOJgX4Kg@mail.gmail.com/ The patch adds unit aggregation during evsel merge the aggregated uncore counters. Change the name of the column to `ctrs` and `counters` for json mode. Tested on a 2-socket machine with SNC3, uncore_imc_[0-11] and cpumask="0,120" Before: perf stat -e clockticks -I 1000 --per-socket # time socket cpus counts unit events 1.001085024 S0 1 9615386315 clockticks 1.001085024 S1 1 9614287448 clockticks perf stat -e clockticks -I 1000 --per-node # time node cpus counts unit events 1.001029867 N0 1 3205726984 clockticks 1.001029867 N1 1 3205444421 clockticks 1.001029867 N2 1 3205234018 clockticks 1.001029867 N3 1 3205224660 clockticks 1.001029867 N4 1 3205207213 clockticks 1.001029867 N5 1 3205528246 clockticks After: perf stat -e clockticks -I 1000 --per-socket # time socket ctrs counts unit events 1.001026071 S0 12 9619677996 clockticks 1.001026071 S1 12 9618612614 clockticks perf stat -e clockticks -I 1000 --per-node # time node ctrs counts unit events 1.001027449 N0 4 3207251859 clockticks 1.001027449 N1 4 3207315930 clockticks 1.001027449 N2 4 3206981828 clockticks 1.001027449 N3 4 3206566126 clockticks 1.001027449 N4 4 3206032609 clockticks 1.001027449 N5 4 3205651355 clockticks Tested with JSON output linter: perf test "perf stat JSON output linter" 94: perf stat JSON output linter : Ok Suggested-by: Ian Rogers <irogers@google.com> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Chun-Tse Shao <ctshao@google.com> Link: https://lore.kernel.org/r/20250627201818.479421-1-ctshao@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2025-06-27 13:16:41 -07:00
json_out(os, "\"cache\" : \"S%d-D%d-L%d-ID%d\", \"counters\" : %d",
perf stat: Setup the foundation to allow aggregation based on cache topology Processors based on chiplet architecture, such as AMD EPYC and Hygon do not expose the chiplet details in the sysfs CPU topology information. However, this information can be derived from the per CPU cache level information from the sysfs. 'perf stat' has already supported aggregation based on topology information using core ID, socket ID, etc. It'll be useful to aggregate based on the cache topology to detect problems like imbalance and cache-to-cache sharing at various cache levels. This patch lays the foundation for aggregating data in 'perf stat' based on the processor's cache topology. The cmdline option to aggregate data based on the cache topology is added in Patch 4 of the series while this patch sets up all the necessary functions and variables required to support the new aggregation option. The patch also adds support to display per-cache aggregation, or save it as a JSON or CSV, as splitting it into a separate patch would break builds when compiling with "-Werror=switch-enum" where the compiler will complain about the lack of handling for the AGGR_CACHE case in the output functions. Committer notes: Don't use perf_stat_config in tools/perf/util/cpumap.c, this would make code that is in util/, thus not really specific to a single builtin, use a specific builtin config structure. Move the functions introduced in this patch from tools/perf/util/cpumap.c since it needs access to builtin specific and is not strictly needed to live in the util/ directory. With this 'perf test python' is back building. Suggested-by: Gautham Shenoy <gautham.shenoy@amd.com> Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ananth Narayan <ananth.narayan@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Wen Pu <puwen@hygon.cn> Link: https://lore.kernel.org/r/20230517172745.5833-3-kprateek.nayak@amd.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-17 22:57:42 +05:30
id.socket, id.die, id.cache_lvl, id.cache, aggr_nr);
break;
perf stat: Support per-cluster aggregation Some platforms have 'cluster' topology and CPUs in the cluster will share resources like L3 Cache Tag (for HiSilicon Kunpeng SoC) or L2 cache (for Intel Jacobsville). Currently parsing and building cluster topology have been supported since [1]. perf stat has already supported aggregation for other topologies like die or socket, etc. It'll be useful to aggregate per-cluster to find problems like L3T bandwidth contention. This patch add support for "--per-cluster" option for per-cluster aggregation. Also update the docs and related test. The output will be like: [root@localhost tmp]# perf stat -a -e LLC-load --per-cluster -- sleep 5 Performance counter stats for 'system wide': S56-D0-CLS158 4 1,321,521,570 LLC-load S56-D0-CLS594 4 794,211,453 LLC-load S56-D0-CLS1030 4 41,623 LLC-load S56-D0-CLS1466 4 41,646 LLC-load S56-D0-CLS1902 4 16,863 LLC-load S56-D0-CLS2338 4 15,721 LLC-load S56-D0-CLS2774 4 22,671 LLC-load [...] On a legacy system without cluster or cluster support, the output will be look like: [root@localhost perf]# perf stat -a -e cycles --per-cluster -- sleep 1 Performance counter stats for 'system wide': S56-D0-CLS0 64 18,011,485 cycles S7182-D0-CLS0 64 16,548,835 cycles Note that this patch doesn't mix the cluster information in the outputs of --per-core to avoid breaking any tools/scripts using it. Note that perf recently supports "--per-cache" aggregation, but it's not the same with the cluster although cluster CPUs may share some cache resources. For example on my machine all clusters within a die share the same L3 cache: $ cat /sys/devices/system/cpu/cpu0/cache/index3/shared_cpu_list 0-31 $ cat /sys/devices/system/cpu/cpu0/topology/cluster_cpus_list 0-3 [1] commit c5e22feffdd7 ("topology: Represent clusters of CPUs within a die") Tested-by: Jie Zhan <zhanjie9@hisilicon.com> Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yicong Yang <yangyicong@hisilicon.com> Cc: james.clark@arm.com Cc: 21cnbao@gmail.com Cc: prime.zeng@hisilicon.com Cc: Jonathan.Cameron@huawei.com Cc: fanghao11@huawei.com Cc: linuxarm@huawei.com Cc: tim.c.chen@intel.com Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/r/20240208024026.2691-1-yangyicong@huawei.com
2024-02-08 10:40:26 +08:00
case AGGR_CLUSTER:
perf stat: Fix uncore aggregation number Follow up: lore.kernel.org/CAP-5=fVDF4-qYL1Lm7efgiHk7X=_nw_nEFMBZFMcsnOOJgX4Kg@mail.gmail.com/ The patch adds unit aggregation during evsel merge the aggregated uncore counters. Change the name of the column to `ctrs` and `counters` for json mode. Tested on a 2-socket machine with SNC3, uncore_imc_[0-11] and cpumask="0,120" Before: perf stat -e clockticks -I 1000 --per-socket # time socket cpus counts unit events 1.001085024 S0 1 9615386315 clockticks 1.001085024 S1 1 9614287448 clockticks perf stat -e clockticks -I 1000 --per-node # time node cpus counts unit events 1.001029867 N0 1 3205726984 clockticks 1.001029867 N1 1 3205444421 clockticks 1.001029867 N2 1 3205234018 clockticks 1.001029867 N3 1 3205224660 clockticks 1.001029867 N4 1 3205207213 clockticks 1.001029867 N5 1 3205528246 clockticks After: perf stat -e clockticks -I 1000 --per-socket # time socket ctrs counts unit events 1.001026071 S0 12 9619677996 clockticks 1.001026071 S1 12 9618612614 clockticks perf stat -e clockticks -I 1000 --per-node # time node ctrs counts unit events 1.001027449 N0 4 3207251859 clockticks 1.001027449 N1 4 3207315930 clockticks 1.001027449 N2 4 3206981828 clockticks 1.001027449 N3 4 3206566126 clockticks 1.001027449 N4 4 3206032609 clockticks 1.001027449 N5 4 3205651355 clockticks Tested with JSON output linter: perf test "perf stat JSON output linter" 94: perf stat JSON output linter : Ok Suggested-by: Ian Rogers <irogers@google.com> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Chun-Tse Shao <ctshao@google.com> Link: https://lore.kernel.org/r/20250627201818.479421-1-ctshao@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2025-06-27 13:16:41 -07:00
json_out(os, "\"cluster\" : \"S%d-D%d-CLS%d\", \"counters\" : %d",
perf stat: Support per-cluster aggregation Some platforms have 'cluster' topology and CPUs in the cluster will share resources like L3 Cache Tag (for HiSilicon Kunpeng SoC) or L2 cache (for Intel Jacobsville). Currently parsing and building cluster topology have been supported since [1]. perf stat has already supported aggregation for other topologies like die or socket, etc. It'll be useful to aggregate per-cluster to find problems like L3T bandwidth contention. This patch add support for "--per-cluster" option for per-cluster aggregation. Also update the docs and related test. The output will be like: [root@localhost tmp]# perf stat -a -e LLC-load --per-cluster -- sleep 5 Performance counter stats for 'system wide': S56-D0-CLS158 4 1,321,521,570 LLC-load S56-D0-CLS594 4 794,211,453 LLC-load S56-D0-CLS1030 4 41,623 LLC-load S56-D0-CLS1466 4 41,646 LLC-load S56-D0-CLS1902 4 16,863 LLC-load S56-D0-CLS2338 4 15,721 LLC-load S56-D0-CLS2774 4 22,671 LLC-load [...] On a legacy system without cluster or cluster support, the output will be look like: [root@localhost perf]# perf stat -a -e cycles --per-cluster -- sleep 1 Performance counter stats for 'system wide': S56-D0-CLS0 64 18,011,485 cycles S7182-D0-CLS0 64 16,548,835 cycles Note that this patch doesn't mix the cluster information in the outputs of --per-core to avoid breaking any tools/scripts using it. Note that perf recently supports "--per-cache" aggregation, but it's not the same with the cluster although cluster CPUs may share some cache resources. For example on my machine all clusters within a die share the same L3 cache: $ cat /sys/devices/system/cpu/cpu0/cache/index3/shared_cpu_list 0-31 $ cat /sys/devices/system/cpu/cpu0/topology/cluster_cpus_list 0-3 [1] commit c5e22feffdd7 ("topology: Represent clusters of CPUs within a die") Tested-by: Jie Zhan <zhanjie9@hisilicon.com> Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yicong Yang <yangyicong@hisilicon.com> Cc: james.clark@arm.com Cc: 21cnbao@gmail.com Cc: prime.zeng@hisilicon.com Cc: Jonathan.Cameron@huawei.com Cc: fanghao11@huawei.com Cc: linuxarm@huawei.com Cc: tim.c.chen@intel.com Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/r/20240208024026.2691-1-yangyicong@huawei.com
2024-02-08 10:40:26 +08:00
id.socket, id.die, id.cluster, aggr_nr);
break;
case AGGR_DIE:
perf stat: Fix uncore aggregation number Follow up: lore.kernel.org/CAP-5=fVDF4-qYL1Lm7efgiHk7X=_nw_nEFMBZFMcsnOOJgX4Kg@mail.gmail.com/ The patch adds unit aggregation during evsel merge the aggregated uncore counters. Change the name of the column to `ctrs` and `counters` for json mode. Tested on a 2-socket machine with SNC3, uncore_imc_[0-11] and cpumask="0,120" Before: perf stat -e clockticks -I 1000 --per-socket # time socket cpus counts unit events 1.001085024 S0 1 9615386315 clockticks 1.001085024 S1 1 9614287448 clockticks perf stat -e clockticks -I 1000 --per-node # time node cpus counts unit events 1.001029867 N0 1 3205726984 clockticks 1.001029867 N1 1 3205444421 clockticks 1.001029867 N2 1 3205234018 clockticks 1.001029867 N3 1 3205224660 clockticks 1.001029867 N4 1 3205207213 clockticks 1.001029867 N5 1 3205528246 clockticks After: perf stat -e clockticks -I 1000 --per-socket # time socket ctrs counts unit events 1.001026071 S0 12 9619677996 clockticks 1.001026071 S1 12 9618612614 clockticks perf stat -e clockticks -I 1000 --per-node # time node ctrs counts unit events 1.001027449 N0 4 3207251859 clockticks 1.001027449 N1 4 3207315930 clockticks 1.001027449 N2 4 3206981828 clockticks 1.001027449 N3 4 3206566126 clockticks 1.001027449 N4 4 3206032609 clockticks 1.001027449 N5 4 3205651355 clockticks Tested with JSON output linter: perf test "perf stat JSON output linter" 94: perf stat JSON output linter : Ok Suggested-by: Ian Rogers <irogers@google.com> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Chun-Tse Shao <ctshao@google.com> Link: https://lore.kernel.org/r/20250627201818.479421-1-ctshao@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2025-06-27 13:16:41 -07:00
json_out(os, "\"die\" : \"S%d-D%d\", \"counters\" : %d",
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
id.socket, id.die, aggr_nr);
break;
case AGGR_SOCKET:
perf stat: Fix uncore aggregation number Follow up: lore.kernel.org/CAP-5=fVDF4-qYL1Lm7efgiHk7X=_nw_nEFMBZFMcsnOOJgX4Kg@mail.gmail.com/ The patch adds unit aggregation during evsel merge the aggregated uncore counters. Change the name of the column to `ctrs` and `counters` for json mode. Tested on a 2-socket machine with SNC3, uncore_imc_[0-11] and cpumask="0,120" Before: perf stat -e clockticks -I 1000 --per-socket # time socket cpus counts unit events 1.001085024 S0 1 9615386315 clockticks 1.001085024 S1 1 9614287448 clockticks perf stat -e clockticks -I 1000 --per-node # time node cpus counts unit events 1.001029867 N0 1 3205726984 clockticks 1.001029867 N1 1 3205444421 clockticks 1.001029867 N2 1 3205234018 clockticks 1.001029867 N3 1 3205224660 clockticks 1.001029867 N4 1 3205207213 clockticks 1.001029867 N5 1 3205528246 clockticks After: perf stat -e clockticks -I 1000 --per-socket # time socket ctrs counts unit events 1.001026071 S0 12 9619677996 clockticks 1.001026071 S1 12 9618612614 clockticks perf stat -e clockticks -I 1000 --per-node # time node ctrs counts unit events 1.001027449 N0 4 3207251859 clockticks 1.001027449 N1 4 3207315930 clockticks 1.001027449 N2 4 3206981828 clockticks 1.001027449 N3 4 3206566126 clockticks 1.001027449 N4 4 3206032609 clockticks 1.001027449 N5 4 3205651355 clockticks Tested with JSON output linter: perf test "perf stat JSON output linter" 94: perf stat JSON output linter : Ok Suggested-by: Ian Rogers <irogers@google.com> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Chun-Tse Shao <ctshao@google.com> Link: https://lore.kernel.org/r/20250627201818.479421-1-ctshao@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2025-06-27 13:16:41 -07:00
json_out(os, "\"socket\" : \"S%d\", \"counters\" : %d",
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
id.socket, aggr_nr);
break;
case AGGR_NODE:
perf stat: Fix uncore aggregation number Follow up: lore.kernel.org/CAP-5=fVDF4-qYL1Lm7efgiHk7X=_nw_nEFMBZFMcsnOOJgX4Kg@mail.gmail.com/ The patch adds unit aggregation during evsel merge the aggregated uncore counters. Change the name of the column to `ctrs` and `counters` for json mode. Tested on a 2-socket machine with SNC3, uncore_imc_[0-11] and cpumask="0,120" Before: perf stat -e clockticks -I 1000 --per-socket # time socket cpus counts unit events 1.001085024 S0 1 9615386315 clockticks 1.001085024 S1 1 9614287448 clockticks perf stat -e clockticks -I 1000 --per-node # time node cpus counts unit events 1.001029867 N0 1 3205726984 clockticks 1.001029867 N1 1 3205444421 clockticks 1.001029867 N2 1 3205234018 clockticks 1.001029867 N3 1 3205224660 clockticks 1.001029867 N4 1 3205207213 clockticks 1.001029867 N5 1 3205528246 clockticks After: perf stat -e clockticks -I 1000 --per-socket # time socket ctrs counts unit events 1.001026071 S0 12 9619677996 clockticks 1.001026071 S1 12 9618612614 clockticks perf stat -e clockticks -I 1000 --per-node # time node ctrs counts unit events 1.001027449 N0 4 3207251859 clockticks 1.001027449 N1 4 3207315930 clockticks 1.001027449 N2 4 3206981828 clockticks 1.001027449 N3 4 3206566126 clockticks 1.001027449 N4 4 3206032609 clockticks 1.001027449 N5 4 3205651355 clockticks Tested with JSON output linter: perf test "perf stat JSON output linter" 94: perf stat JSON output linter : Ok Suggested-by: Ian Rogers <irogers@google.com> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Chun-Tse Shao <ctshao@google.com> Link: https://lore.kernel.org/r/20250627201818.479421-1-ctshao@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2025-06-27 13:16:41 -07:00
json_out(os, "\"node\" : \"N%d\", \"counters\" : %d",
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
id.node, aggr_nr);
break;
case AGGR_NONE:
if (evsel->percore && !config->percore_show_thread) {
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
json_out(os, "\"core\" : \"S%d-D%d-C%d\"",
id.socket, id.die, id.core);
} else if (id.cpu.cpu > -1) {
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
json_out(os, "\"cpu\" : \"%d\"",
id.cpu.cpu);
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
}
break;
case AGGR_THREAD:
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
json_out(os, "\"thread\" : \"%s-%d\"",
perf_thread_map__comm(evsel->core.threads, id.thread_idx),
perf_thread_map__pid(evsel->core.threads, id.thread_idx));
break;
case AGGR_GLOBAL:
case AGGR_UNSET:
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
case AGGR_MAX:
default:
break;
}
}
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
static void aggr_printout(struct perf_stat_config *config, struct outstate *os,
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
struct evsel *evsel, struct aggr_cpu_id id, int aggr_nr)
{
if (config->json_output)
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
print_aggr_id_json(config, os, evsel, id, aggr_nr);
else if (config->csv_output)
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
print_aggr_id_csv(config, evsel, id, aggr_nr);
else
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
print_aggr_id_std(config, evsel, id, aggr_nr);
}
static void new_line_std(struct perf_stat_config *config __maybe_unused,
void *ctx)
{
struct outstate *os = ctx;
os->newline = true;
}
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
static inline void __new_line_std_csv(struct perf_stat_config *config,
struct outstate *os)
{
fputc('\n', os->fh);
if (config->interval)
fputs(os->timestamp, os->fh);
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
aggr_printout(config, os, os->evsel, os->id, os->aggr_nr);
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
}
static inline void __new_line_std(struct outstate *os)
{
fprintf(os->fh, " ");
}
static void do_new_line_std(struct perf_stat_config *config,
struct outstate *os)
{
__new_line_std_csv(config, os);
if (config->aggr_mode == AGGR_NONE)
fprintf(os->fh, " ");
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
__new_line_std(os);
}
static void print_metric_std(struct perf_stat_config *config,
void *ctx, enum metric_threshold_classify thresh,
const char *fmt, const char *unit, double val)
{
struct outstate *os = ctx;
FILE *out = os->fh;
int n;
bool newline = os->newline;
const char *color = metric_threshold_classify__color(thresh);
os->newline = false;
if (unit == NULL || fmt == NULL) {
fprintf(out, "%-*s", METRIC_LEN, "");
return;
}
if (newline)
do_new_line_std(config, os);
n = fprintf(out, " # ");
if (color)
n += color_fprintf(out, color, fmt, val);
else
n += fprintf(out, fmt, val);
fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
}
static void new_line_csv(struct perf_stat_config *config, void *ctx)
{
struct outstate *os = ctx;
int i;
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
__new_line_std_csv(config, os);
for (i = 0; i < os->csv_col_pad; i++)
fputs(config->csv_sep, os->fh);
}
static void print_metric_csv(struct perf_stat_config *config __maybe_unused,
void *ctx,
enum metric_threshold_classify thresh __maybe_unused,
const char *fmt, const char *unit, double val)
{
struct outstate *os = ctx;
FILE *out = os->fh;
char buf[64], *vals, *ends;
if (unit == NULL || fmt == NULL) {
fprintf(out, "%s%s", config->csv_sep, config->csv_sep);
return;
}
snprintf(buf, sizeof(buf), fmt, val);
ends = vals = skip_spaces(buf);
while (isdigit(*ends) || *ends == '.')
ends++;
*ends = 0;
fprintf(out, "%s%s%s%s", config->csv_sep, vals, config->csv_sep, skip_spaces(unit));
}
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
static void print_metric_json(struct perf_stat_config *config __maybe_unused,
void *ctx,
perf stat: Add metric-threshold to json output When the threshold isn't unknown add a value to the json like: "metric-threshold" : "good" A more complete example: ``` $ perf stat -a -j -I 1000 {"interval" : 1.001089747, "counter-value" : "16045.281449", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 16045355135, "pcnt-running" : 100.00, "metric-value" : "16.045281", "metric-unit" : "CPUs utilized"} {"interval" : 1.001089747, "counter-value" : "10003.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 16045314844, "pcnt-running" : 100.00, "metric-value" : "623.423156", "metric-unit" : "/sec"} {"interval" : 1.001089747, "counter-value" : "328.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 16045321403, "pcnt-running" : 100.00, "metric-value" : "20.442147", "metric-unit" : "/sec"} {"interval" : 1.001089747, "counter-value" : "20114.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 16045355927, "pcnt-running" : 100.00, "metric-value" : "1.253577", "metric-unit" : "K/sec"} {"interval" : 1.001089747, "counter-value" : "4066679471.000000", "unit" : "", "event" : "instructions", "event-runtime" : 16045369123, "pcnt-running" : 100.00, "metric-value" : "1.628330", "metric-unit" : "insn per cycle"} {"interval" : 1.001089747, "counter-value" : "2497454658.000000", "unit" : "", "event" : "cycles", "event-runtime" : 16045374810, "pcnt-running" : 100.00, "metric-value" : "0.155650", "metric-unit" : "GHz"} {"interval" : 1.001089747, "counter-value" : "914974294.000000", "unit" : "", "event" : "branches", "event-runtime" : 16045379877, "pcnt-running" : 100.00, "metric-value" : "57.024509", "metric-unit" : "M/sec"} {"interval" : 1.001089747, "counter-value" : "9237201.000000", "unit" : "", "event" : "branch-misses", "event-runtime" : 16045375017, "pcnt-running" : 100.00, "metric-value" : "1.009559", "metric-unit" : "of all branches", "metric-threshold" : "good"} {"interval" : 1.001089747, "event-runtime" : 16045397172, "pcnt-running" : 100.00, "metricgroup" : "TopdownL1"} {"interval" : 1.001089747, "metric-value" : "22.036686", "metric-unit" : "% tma_backend_bound", "metric-threshold" : "bad"} {"interval" : 1.001089747, "metric-value" : "7.610161", "metric-unit" : "% tma_bad_speculation", "metric-threshold" : "good"} {"interval" : 1.001089747, "metric-value" : "36.729687", "metric-unit" : "% tma_frontend_bound", "metric-threshold" : "bad"} {"interval" : 1.001089747, "metric-value" : "33.623465", "metric-unit" : "% tma_retiring"} ... ``` Signed-off-by: Ian Rogers <irogers@google.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Cc: Weilin Wang <weilin.wang@intel.com> Cc: Will Deacon <will@kernel.org> Cc: James Clark <james.clark@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Leo Yan <leo.yan@linux.dev> Cc: Sumanth Korikkar <sumanthk@linux.ibm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: John Garry <john.g.garry@oracle.com> Link: https://lore.kernel.org/r/20241017175356.783793-7-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-17 10:53:55 -07:00
enum metric_threshold_classify thresh,
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
const char *fmt __maybe_unused,
const char *unit, double val)
{
struct outstate *os = ctx;
FILE *out = os->fh;
perf stat: Add metric-threshold to json output When the threshold isn't unknown add a value to the json like: "metric-threshold" : "good" A more complete example: ``` $ perf stat -a -j -I 1000 {"interval" : 1.001089747, "counter-value" : "16045.281449", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 16045355135, "pcnt-running" : 100.00, "metric-value" : "16.045281", "metric-unit" : "CPUs utilized"} {"interval" : 1.001089747, "counter-value" : "10003.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 16045314844, "pcnt-running" : 100.00, "metric-value" : "623.423156", "metric-unit" : "/sec"} {"interval" : 1.001089747, "counter-value" : "328.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 16045321403, "pcnt-running" : 100.00, "metric-value" : "20.442147", "metric-unit" : "/sec"} {"interval" : 1.001089747, "counter-value" : "20114.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 16045355927, "pcnt-running" : 100.00, "metric-value" : "1.253577", "metric-unit" : "K/sec"} {"interval" : 1.001089747, "counter-value" : "4066679471.000000", "unit" : "", "event" : "instructions", "event-runtime" : 16045369123, "pcnt-running" : 100.00, "metric-value" : "1.628330", "metric-unit" : "insn per cycle"} {"interval" : 1.001089747, "counter-value" : "2497454658.000000", "unit" : "", "event" : "cycles", "event-runtime" : 16045374810, "pcnt-running" : 100.00, "metric-value" : "0.155650", "metric-unit" : "GHz"} {"interval" : 1.001089747, "counter-value" : "914974294.000000", "unit" : "", "event" : "branches", "event-runtime" : 16045379877, "pcnt-running" : 100.00, "metric-value" : "57.024509", "metric-unit" : "M/sec"} {"interval" : 1.001089747, "counter-value" : "9237201.000000", "unit" : "", "event" : "branch-misses", "event-runtime" : 16045375017, "pcnt-running" : 100.00, "metric-value" : "1.009559", "metric-unit" : "of all branches", "metric-threshold" : "good"} {"interval" : 1.001089747, "event-runtime" : 16045397172, "pcnt-running" : 100.00, "metricgroup" : "TopdownL1"} {"interval" : 1.001089747, "metric-value" : "22.036686", "metric-unit" : "% tma_backend_bound", "metric-threshold" : "bad"} {"interval" : 1.001089747, "metric-value" : "7.610161", "metric-unit" : "% tma_bad_speculation", "metric-threshold" : "good"} {"interval" : 1.001089747, "metric-value" : "36.729687", "metric-unit" : "% tma_frontend_bound", "metric-threshold" : "bad"} {"interval" : 1.001089747, "metric-value" : "33.623465", "metric-unit" : "% tma_retiring"} ... ``` Signed-off-by: Ian Rogers <irogers@google.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Cc: Weilin Wang <weilin.wang@intel.com> Cc: Will Deacon <will@kernel.org> Cc: James Clark <james.clark@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Leo Yan <leo.yan@linux.dev> Cc: Sumanth Korikkar <sumanthk@linux.ibm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: John Garry <john.g.garry@oracle.com> Link: https://lore.kernel.org/r/20241017175356.783793-7-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-17 10:53:55 -07:00
if (unit) {
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
json_out(os, "\"metric-value\" : \"%f\", \"metric-unit\" : \"%s\"", val, unit);
perf stat: Add metric-threshold to json output When the threshold isn't unknown add a value to the json like: "metric-threshold" : "good" A more complete example: ``` $ perf stat -a -j -I 1000 {"interval" : 1.001089747, "counter-value" : "16045.281449", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 16045355135, "pcnt-running" : 100.00, "metric-value" : "16.045281", "metric-unit" : "CPUs utilized"} {"interval" : 1.001089747, "counter-value" : "10003.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 16045314844, "pcnt-running" : 100.00, "metric-value" : "623.423156", "metric-unit" : "/sec"} {"interval" : 1.001089747, "counter-value" : "328.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 16045321403, "pcnt-running" : 100.00, "metric-value" : "20.442147", "metric-unit" : "/sec"} {"interval" : 1.001089747, "counter-value" : "20114.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 16045355927, "pcnt-running" : 100.00, "metric-value" : "1.253577", "metric-unit" : "K/sec"} {"interval" : 1.001089747, "counter-value" : "4066679471.000000", "unit" : "", "event" : "instructions", "event-runtime" : 16045369123, "pcnt-running" : 100.00, "metric-value" : "1.628330", "metric-unit" : "insn per cycle"} {"interval" : 1.001089747, "counter-value" : "2497454658.000000", "unit" : "", "event" : "cycles", "event-runtime" : 16045374810, "pcnt-running" : 100.00, "metric-value" : "0.155650", "metric-unit" : "GHz"} {"interval" : 1.001089747, "counter-value" : "914974294.000000", "unit" : "", "event" : "branches", "event-runtime" : 16045379877, "pcnt-running" : 100.00, "metric-value" : "57.024509", "metric-unit" : "M/sec"} {"interval" : 1.001089747, "counter-value" : "9237201.000000", "unit" : "", "event" : "branch-misses", "event-runtime" : 16045375017, "pcnt-running" : 100.00, "metric-value" : "1.009559", "metric-unit" : "of all branches", "metric-threshold" : "good"} {"interval" : 1.001089747, "event-runtime" : 16045397172, "pcnt-running" : 100.00, "metricgroup" : "TopdownL1"} {"interval" : 1.001089747, "metric-value" : "22.036686", "metric-unit" : "% tma_backend_bound", "metric-threshold" : "bad"} {"interval" : 1.001089747, "metric-value" : "7.610161", "metric-unit" : "% tma_bad_speculation", "metric-threshold" : "good"} {"interval" : 1.001089747, "metric-value" : "36.729687", "metric-unit" : "% tma_frontend_bound", "metric-threshold" : "bad"} {"interval" : 1.001089747, "metric-value" : "33.623465", "metric-unit" : "% tma_retiring"} ... ``` Signed-off-by: Ian Rogers <irogers@google.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Cc: Weilin Wang <weilin.wang@intel.com> Cc: Will Deacon <will@kernel.org> Cc: James Clark <james.clark@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Leo Yan <leo.yan@linux.dev> Cc: Sumanth Korikkar <sumanthk@linux.ibm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: John Garry <john.g.garry@oracle.com> Link: https://lore.kernel.org/r/20241017175356.783793-7-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-17 10:53:55 -07:00
if (thresh != METRIC_THRESHOLD_UNKNOWN) {
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
json_out(os, "\"metric-threshold\" : \"%s\"",
perf stat: Add metric-threshold to json output When the threshold isn't unknown add a value to the json like: "metric-threshold" : "good" A more complete example: ``` $ perf stat -a -j -I 1000 {"interval" : 1.001089747, "counter-value" : "16045.281449", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 16045355135, "pcnt-running" : 100.00, "metric-value" : "16.045281", "metric-unit" : "CPUs utilized"} {"interval" : 1.001089747, "counter-value" : "10003.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 16045314844, "pcnt-running" : 100.00, "metric-value" : "623.423156", "metric-unit" : "/sec"} {"interval" : 1.001089747, "counter-value" : "328.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 16045321403, "pcnt-running" : 100.00, "metric-value" : "20.442147", "metric-unit" : "/sec"} {"interval" : 1.001089747, "counter-value" : "20114.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 16045355927, "pcnt-running" : 100.00, "metric-value" : "1.253577", "metric-unit" : "K/sec"} {"interval" : 1.001089747, "counter-value" : "4066679471.000000", "unit" : "", "event" : "instructions", "event-runtime" : 16045369123, "pcnt-running" : 100.00, "metric-value" : "1.628330", "metric-unit" : "insn per cycle"} {"interval" : 1.001089747, "counter-value" : "2497454658.000000", "unit" : "", "event" : "cycles", "event-runtime" : 16045374810, "pcnt-running" : 100.00, "metric-value" : "0.155650", "metric-unit" : "GHz"} {"interval" : 1.001089747, "counter-value" : "914974294.000000", "unit" : "", "event" : "branches", "event-runtime" : 16045379877, "pcnt-running" : 100.00, "metric-value" : "57.024509", "metric-unit" : "M/sec"} {"interval" : 1.001089747, "counter-value" : "9237201.000000", "unit" : "", "event" : "branch-misses", "event-runtime" : 16045375017, "pcnt-running" : 100.00, "metric-value" : "1.009559", "metric-unit" : "of all branches", "metric-threshold" : "good"} {"interval" : 1.001089747, "event-runtime" : 16045397172, "pcnt-running" : 100.00, "metricgroup" : "TopdownL1"} {"interval" : 1.001089747, "metric-value" : "22.036686", "metric-unit" : "% tma_backend_bound", "metric-threshold" : "bad"} {"interval" : 1.001089747, "metric-value" : "7.610161", "metric-unit" : "% tma_bad_speculation", "metric-threshold" : "good"} {"interval" : 1.001089747, "metric-value" : "36.729687", "metric-unit" : "% tma_frontend_bound", "metric-threshold" : "bad"} {"interval" : 1.001089747, "metric-value" : "33.623465", "metric-unit" : "% tma_retiring"} ... ``` Signed-off-by: Ian Rogers <irogers@google.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Cc: Weilin Wang <weilin.wang@intel.com> Cc: Will Deacon <will@kernel.org> Cc: James Clark <james.clark@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Leo Yan <leo.yan@linux.dev> Cc: Sumanth Korikkar <sumanthk@linux.ibm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: John Garry <john.g.garry@oracle.com> Link: https://lore.kernel.org/r/20241017175356.783793-7-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-10-17 10:53:55 -07:00
metric_threshold_classify__str(thresh));
}
}
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
if (!config->metric_only)
fprintf(out, "}");
}
static void new_line_json(struct perf_stat_config *config, void *ctx)
{
struct outstate *os = ctx;
fputs("\n{", os->fh);
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
os->first = true;
if (config->interval)
json_out(os, "%s", os->timestamp);
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
aggr_printout(config, os, os->evsel, os->id, os->aggr_nr);
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
}
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
static void print_metricgroup_header_json(struct perf_stat_config *config,
void *ctx,
const char *metricgroup_name)
{
if (!metricgroup_name)
return;
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
json_out((struct outstate *) ctx, "\"metricgroup\" : \"%s\"}", metricgroup_name);
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
new_line_json(config, ctx);
}
static void print_metricgroup_header_csv(struct perf_stat_config *config,
void *ctx,
const char *metricgroup_name)
{
struct outstate *os = ctx;
int i;
if (!metricgroup_name) {
/* Leave space for running and enabling */
for (i = 0; i < os->csv_col_pad - 2; i++)
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
fputs(config->csv_sep, os->fh);
return;
}
for (i = 0; i < os->csv_col_pad; i++)
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
fputs(config->csv_sep, os->fh);
fprintf(config->output, "%s", metricgroup_name);
new_line_csv(config, ctx);
}
static void print_metricgroup_header_std(struct perf_stat_config *config,
void *ctx,
const char *metricgroup_name)
{
struct outstate *os = ctx;
int n;
if (!metricgroup_name) {
__new_line_std(os);
return;
}
n = fprintf(config->output, " %*s", EVNAME_LEN, metricgroup_name);
fprintf(config->output, "%*s", MGROUP_LEN - n - 1, "");
}
/* Filter out some columns that don't work well in metrics only mode */
static bool valid_only_metric(const char *unit)
{
if (!unit)
return false;
if (strstr(unit, "/sec") ||
strstr(unit, "CPUs utilized"))
return false;
return true;
}
static const char *fixunit(char *buf, struct evsel *evsel,
const char *unit)
{
if (!strncmp(unit, "of all", 6)) {
snprintf(buf, 1024, "%s %s", evsel__name(evsel),
unit);
return buf;
}
return unit;
}
static void print_metric_only(struct perf_stat_config *config,
void *ctx, enum metric_threshold_classify thresh,
const char *fmt, const char *unit, double val)
{
struct outstate *os = ctx;
FILE *out = os->fh;
char buf[1024], str[1024];
unsigned mlen = config->metric_only_len;
const char *color = metric_threshold_classify__color(thresh);
if (!valid_only_metric(unit))
return;
unit = fixunit(buf, os->evsel, unit);
if (mlen < strlen(unit))
mlen = strlen(unit) + 1;
if (color)
mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1;
color_snprintf(str, sizeof(str), color ?: "", fmt ?: "", val);
fprintf(out, "%*s ", mlen, str);
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 10:02:06 -08:00
os->first = false;
}
static void print_metric_only_csv(struct perf_stat_config *config __maybe_unused,
void *ctx,
enum metric_threshold_classify thresh __maybe_unused,
const char *fmt,
const char *unit, double val)
{
struct outstate *os = ctx;
FILE *out = os->fh;
char buf[64], *vals, *ends;
char tbuf[1024];
if (!valid_only_metric(unit))
return;
unit = fixunit(tbuf, os->evsel, unit);
snprintf(buf, sizeof(buf), fmt ?: "", val);
ends = vals = skip_spaces(buf);
while (isdigit(*ends) || *ends == '.')
ends++;
*ends = 0;
fprintf(out, "%s%s", vals, config->csv_sep);
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 10:02:06 -08:00
os->first = false;
}
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
static void print_metric_only_json(struct perf_stat_config *config __maybe_unused,
void *ctx,
enum metric_threshold_classify thresh __maybe_unused,
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
const char *fmt,
const char *unit, double val)
{
struct outstate *os = ctx;
char buf[64], *ends;
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
char tbuf[1024];
const char *vals;
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
if (!valid_only_metric(unit))
return;
unit = fixunit(tbuf, os->evsel, unit);
if (!unit[0])
return;
snprintf(buf, sizeof(buf), fmt ?: "", val);
vals = ends = skip_spaces(buf);
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
while (isdigit(*ends) || *ends == '.')
ends++;
*ends = 0;
if (!vals[0])
vals = "none";
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
json_out(os, "\"%s\" : \"%s\"", unit, vals);
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
}
static void print_metric_header(struct perf_stat_config *config,
void *ctx,
enum metric_threshold_classify thresh __maybe_unused,
const char *fmt __maybe_unused,
const char *unit, double val __maybe_unused)
{
struct outstate *os = ctx;
char tbuf[1024];
/* In case of iostat, print metric header for first root port only */
if (config->iostat_run &&
os->evsel->priv != os->evsel->evlist->selected->priv)
return;
if (os->evsel->cgrp != os->cgrp)
return;
perf stat: Fix --metric-only --json output Currently it prints all metric headers for JSON output. But actually it skips some metrics with valid_only_metric(). So the output looks like: $ perf stat --metric-only --json true {"unit" : "CPUs utilized", "unit" : "/sec", "unit" : "/sec", "unit" : "/sec", "unit" : "GHz", "unit" : "insn per cycle", "unit" : "/sec", "unit" : "branch-misses of all branches"} {"metric-value" : "3.861"}{"metric-value" : "0.79"}{"metric-value" : "3.04"} As you can see there are 8 units in the header but only 3 metric-values are there. It should skip the unused headers as well. Also each unit should be printed as a separate object like metric values. With this patch: $ perf stat --metric-only --json true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"metric-value" : "4.166"}{"metric-value" : "0.73"}{"metric-value" : "2.96"} Fixes: df936cadfb58ba93 ("perf stat: Add JSON output option") Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Claire Jensen <cjense@google.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221107213314.3239159-6-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-07 13:33:10 -08:00
if (!valid_only_metric(unit))
return;
unit = fixunit(tbuf, os->evsel, unit);
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
if (config->json_output)
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 10:02:06 -08:00
return;
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
else if (config->csv_output)
fprintf(os->fh, "%s%s", unit, config->csv_sep);
else
fprintf(os->fh, "%*s ", config->metric_only_len, unit);
}
static void print_counter_value_std(struct perf_stat_config *config,
struct evsel *evsel, double avg, bool ok)
{
FILE *output = config->output;
double sc = evsel->scale;
const char *fmt;
const char *bad_count = evsel->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED;
if (config->big_num)
fmt = floor(sc) != sc ? "%'*.2f " : "%'*.0f ";
else
fmt = floor(sc) != sc ? "%*.2f " : "%*.0f ";
if (ok)
fprintf(output, fmt, COUNTS_LEN, avg);
else
fprintf(output, "%*s ", COUNTS_LEN, bad_count);
if (evsel->unit)
fprintf(output, "%-*s ", config->unit_width, evsel->unit);
fprintf(output, "%-*s", EVNAME_LEN, evsel__name(evsel));
}
static void print_counter_value_csv(struct perf_stat_config *config,
struct evsel *evsel, double avg, bool ok)
{
FILE *output = config->output;
double sc = evsel->scale;
const char *sep = config->csv_sep;
const char *fmt = floor(sc) != sc ? "%.2f%s" : "%.0f%s";
const char *bad_count = evsel->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED;
if (ok)
fprintf(output, fmt, avg, sep);
else
fprintf(output, "%s%s", bad_count, sep);
if (evsel->unit)
fprintf(output, "%s%s", evsel->unit, sep);
fprintf(output, "%s", evsel__name(evsel));
}
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
static void print_counter_value_json(struct outstate *os,
struct evsel *evsel, double avg, bool ok)
{
const char *bad_count = evsel->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED;
if (ok)
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
json_out(os, "\"counter-value\" : \"%f\"", avg);
else
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
json_out(os, "\"counter-value\" : \"%s\"", bad_count);
if (evsel->unit)
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
json_out(os, "\"unit\" : \"%s\"", evsel->unit);
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
json_out(os, "\"event\" : \"%s\"", evsel__name(evsel));
}
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
static void print_counter_value(struct perf_stat_config *config, struct outstate *os,
struct evsel *evsel, double avg, bool ok)
{
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
if (config->json_output)
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
print_counter_value_json(os, evsel, avg, ok);
else if (config->csv_output)
print_counter_value_csv(config, evsel, avg, ok);
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
else
print_counter_value_std(config, evsel, avg, ok);
}
static void abs_printout(struct perf_stat_config *config,
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
struct outstate *os,
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
struct aggr_cpu_id id, int aggr_nr,
struct evsel *evsel, double avg, bool ok)
{
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
aggr_printout(config, os, evsel, id, aggr_nr);
print_counter_value(config, os, evsel, avg, ok);
print_cgroup(config, os, evsel->cgrp);
}
perf stat: Better hybrid support for the NMI watchdog warning Prior to this patch evlist__has_hybrid would return false if the processor wasn't hybrid or the evlist didn't contain any core events. If the only PMU used by events was cpu_core then it would true even though there are no cpu_atom events. For example: ``` $ perf stat --cputype=cpu_core -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}' true Performance counter stats for 'true': <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) 0.001981900 seconds time elapsed 0.002311000 seconds user 0.000000000 seconds sys ``` This patch changes evlist__has_hybrid to return true only if the evlist contains events from >1 core PMU. This means the NMI watchdog warning is shown for the case above. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Dominique Martinet <asmadeus@codewreck.org> Cc: Dr. David Alan Gilbert <linux@treblig.org> Cc: Howard Chu <howardchu95@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@linaro.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Levi Yun <yeoreum.yun@arm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Weilin Wang <weilin.wang@intel.com> Link: https://lore.kernel.org/r/20250402201549.4090305-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2025-04-02 13:15:45 -07:00
static bool evlist__has_hybrid_pmus(struct evlist *evlist)
perf evlist: Reduce scope of evlist__has_hybrid Function is only used in printout, reduce scope to stat-display.c. Remove the now empty evlist-hybrid.c and evlist-hybrid.h. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Ming Wang <wangming01@loongson.cn> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230527072210.2900565-15-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-27 00:21:50 -07:00
{
struct evsel *evsel;
perf stat: Better hybrid support for the NMI watchdog warning Prior to this patch evlist__has_hybrid would return false if the processor wasn't hybrid or the evlist didn't contain any core events. If the only PMU used by events was cpu_core then it would true even though there are no cpu_atom events. For example: ``` $ perf stat --cputype=cpu_core -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}' true Performance counter stats for 'true': <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) 0.001981900 seconds time elapsed 0.002311000 seconds user 0.000000000 seconds sys ``` This patch changes evlist__has_hybrid to return true only if the evlist contains events from >1 core PMU. This means the NMI watchdog warning is shown for the case above. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Dominique Martinet <asmadeus@codewreck.org> Cc: Dr. David Alan Gilbert <linux@treblig.org> Cc: Howard Chu <howardchu95@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@linaro.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Levi Yun <yeoreum.yun@arm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Weilin Wang <weilin.wang@intel.com> Link: https://lore.kernel.org/r/20250402201549.4090305-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2025-04-02 13:15:45 -07:00
struct perf_pmu *last_core_pmu = NULL;
perf evlist: Reduce scope of evlist__has_hybrid Function is only used in printout, reduce scope to stat-display.c. Remove the now empty evlist-hybrid.c and evlist-hybrid.h. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Ming Wang <wangming01@loongson.cn> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230527072210.2900565-15-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-27 00:21:50 -07:00
perf pmus: Remove perf_pmus__has_hybrid perf_pmus__has_hybrid was used to detect when there was >1 core PMU, this can be achieved with perf_pmus__num_core_pmus that doesn't depend upon is_pmu_hybrid and PMU name comparisons. When modifying the function calls take the opportunity to improve comments, enable/simplify tests that were previously failing for hybrid but now pass and to simplify generic code. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Ming Wang <wangming01@loongson.cn> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230527072210.2900565-34-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-27 00:22:09 -07:00
if (perf_pmus__num_core_pmus() == 1)
perf stat: Avoid hybrid PMU list perf_pmu__is_hybrid implicitly uses the hybrid PMU list. Instead return false if hybrid isn't present, if it is then see if any evsel's PMUs are core. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Ming Wang <wangming01@loongson.cn> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230527072210.2900565-23-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-27 00:21:58 -07:00
return false;
perf evlist: Reduce scope of evlist__has_hybrid Function is only used in printout, reduce scope to stat-display.c. Remove the now empty evlist-hybrid.c and evlist-hybrid.h. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Ming Wang <wangming01@loongson.cn> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230527072210.2900565-15-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-27 00:21:50 -07:00
evlist__for_each_entry(evlist, evsel) {
perf stat: Better hybrid support for the NMI watchdog warning Prior to this patch evlist__has_hybrid would return false if the processor wasn't hybrid or the evlist didn't contain any core events. If the only PMU used by events was cpu_core then it would true even though there are no cpu_atom events. For example: ``` $ perf stat --cputype=cpu_core -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}' true Performance counter stats for 'true': <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) 0.001981900 seconds time elapsed 0.002311000 seconds user 0.000000000 seconds sys ``` This patch changes evlist__has_hybrid to return true only if the evlist contains events from >1 core PMU. This means the NMI watchdog warning is shown for the case above. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Dominique Martinet <asmadeus@codewreck.org> Cc: Dr. David Alan Gilbert <linux@treblig.org> Cc: Howard Chu <howardchu95@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@linaro.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Levi Yun <yeoreum.yun@arm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Weilin Wang <weilin.wang@intel.com> Link: https://lore.kernel.org/r/20250402201549.4090305-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2025-04-02 13:15:45 -07:00
if (evsel->core.is_pmu_core) {
struct perf_pmu *pmu = evsel__find_pmu(evsel);
if (pmu == last_core_pmu)
continue;
if (last_core_pmu == NULL) {
last_core_pmu = pmu;
continue;
}
/* A distinct core PMU. */
perf evlist: Reduce scope of evlist__has_hybrid Function is only used in printout, reduce scope to stat-display.c. Remove the now empty evlist-hybrid.c and evlist-hybrid.h. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Ming Wang <wangming01@loongson.cn> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230527072210.2900565-15-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-27 00:21:50 -07:00
return true;
perf stat: Better hybrid support for the NMI watchdog warning Prior to this patch evlist__has_hybrid would return false if the processor wasn't hybrid or the evlist didn't contain any core events. If the only PMU used by events was cpu_core then it would true even though there are no cpu_atom events. For example: ``` $ perf stat --cputype=cpu_core -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}' true Performance counter stats for 'true': <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) 0.001981900 seconds time elapsed 0.002311000 seconds user 0.000000000 seconds sys ``` This patch changes evlist__has_hybrid to return true only if the evlist contains events from >1 core PMU. This means the NMI watchdog warning is shown for the case above. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Dominique Martinet <asmadeus@codewreck.org> Cc: Dr. David Alan Gilbert <linux@treblig.org> Cc: Howard Chu <howardchu95@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@linaro.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Levi Yun <yeoreum.yun@arm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Weilin Wang <weilin.wang@intel.com> Link: https://lore.kernel.org/r/20250402201549.4090305-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2025-04-02 13:15:45 -07:00
}
perf evlist: Reduce scope of evlist__has_hybrid Function is only used in printout, reduce scope to stat-display.c. Remove the now empty evlist-hybrid.c and evlist-hybrid.h. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Ming Wang <wangming01@loongson.cn> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230527072210.2900565-15-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-27 00:21:50 -07:00
}
return false;
}
static void printout(struct perf_stat_config *config, struct outstate *os,
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
double uval, u64 run, u64 ena, double noise, int aggr_idx)
{
struct perf_stat_output_ctx out;
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
print_metric_t pm;
new_line_t nl;
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
print_metricgroup_header_t pmh;
bool ok = true;
struct evsel *counter = os->evsel;
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
if (config->csv_output) {
pm = config->metric_only ? print_metric_only_csv : print_metric_csv;
nl = config->metric_only ? NULL : new_line_csv;
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
pmh = print_metricgroup_header_csv;
os->csv_col_pad = 4 + (counter->cgrp ? 1 : 0);
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
} else if (config->json_output) {
pm = config->metric_only ? print_metric_only_json : print_metric_json;
nl = config->metric_only ? NULL : new_line_json;
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
pmh = print_metricgroup_header_json;
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
} else {
pm = config->metric_only ? print_metric_only : print_metric_std;
nl = config->metric_only ? NULL : new_line_std;
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
pmh = print_metricgroup_header_std;
}
perf stat: Align CSV output for summary mode The 'perf stat' subcommand supports the request for a summary of the interval counter readings. But the summary lines break the CSV output so it's hard for scripts to parse the result. Before: # perf stat -x, -I1000 --interval-count 1 --summary 1.001323097,8013.48,msec,cpu-clock,8013483384,100.00,8.013,CPUs utilized 1.001323097,270,,context-switches,8013513297,100.00,0.034,K/sec 1.001323097,13,,cpu-migrations,8013530032,100.00,0.002,K/sec 1.001323097,184,,page-faults,8013546992,100.00,0.023,K/sec 1.001323097,20574191,,cycles,8013551506,100.00,0.003,GHz 1.001323097,10562267,,instructions,8013564958,100.00,0.51,insn per cycle 1.001323097,2019244,,branches,8013575673,100.00,0.252,M/sec 1.001323097,106152,,branch-misses,8013585776,100.00,5.26,of all branches 8013.48,msec,cpu-clock,8013483384,100.00,7.984,CPUs utilized 270,,context-switches,8013513297,100.00,0.034,K/sec 13,,cpu-migrations,8013530032,100.00,0.002,K/sec 184,,page-faults,8013546992,100.00,0.023,K/sec 20574191,,cycles,8013551506,100.00,0.003,GHz 10562267,,instructions,8013564958,100.00,0.51,insn per cycle 2019244,,branches,8013575673,100.00,0.252,M/sec 106152,,branch-misses,8013585776,100.00,5.26,of all branches The summary line loses the timestamp column, which breaks the CSV output. We add a column at the original 'timestamp' position and it just says 'summary' for the summary line. After: # perf stat -x, -I1000 --interval-count 1 --summary 1.001196053,8012.72,msec,cpu-clock,8012722903,100.00,8.013,CPUs utilized 1.001196053,218,,context-switches,8012753271,100.00,0.027,K/sec 1.001196053,9,,cpu-migrations,8012769767,100.00,0.001,K/sec 1.001196053,0,,page-faults,8012786257,100.00,0.000,K/sec 1.001196053,15004518,,cycles,8012790637,100.00,0.002,GHz 1.001196053,7954691,,instructions,8012804027,100.00,0.53,insn per cycle 1.001196053,1590259,,branches,8012814766,100.00,0.198,M/sec 1.001196053,82601,,branch-misses,8012824365,100.00,5.19,of all branches summary,8012.72,msec,cpu-clock,8012722903,100.00,7.986,CPUs utilized summary,218,,context-switches,8012753271,100.00,0.027,K/sec summary,9,,cpu-migrations,8012769767,100.00,0.001,K/sec summary,0,,page-faults,8012786257,100.00,0.000,K/sec summary,15004518,,cycles,8012790637,100.00,0.002,GHz summary,7954691,,instructions,8012804027,100.00,0.53,insn per cycle summary,1590259,,branches,8012814766,100.00,0.198,M/sec summary,82601,,branch-misses,8012824365,100.00,5.19,of all branches Now it's easy for script to analyse the summary lines. Of course, we also consider not to break possible existing scripts which can continue to use the broken CSV format by using a new '--no-csv-summary.' option. # perf stat -x, -I1000 --interval-count 1 --summary --no-csv-summary 1.001213261,8012.67,msec,cpu-clock,8012672327,100.00,8.013,CPUs utilized 1.001213261,197,,context-switches,8012703742,100.00,24.586,/sec 1.001213261,9,,cpu-migrations,8012720902,100.00,1.123,/sec 1.001213261,644,,page-faults,8012738266,100.00,80.373,/sec 1.001213261,18350698,,cycles,8012744109,100.00,0.002,GHz 1.001213261,12745021,,instructions,8012759001,100.00,0.69,insn per cycle 1.001213261,2458033,,branches,8012770864,100.00,306.768,K/sec 1.001213261,102107,,branch-misses,8012781751,100.00,4.15,of all branches 8012.67,msec,cpu-clock,8012672327,100.00,7.985,CPUs utilized 197,,context-switches,8012703742,100.00,24.586,/sec 9,,cpu-migrations,8012720902,100.00,1.123,/sec 644,,page-faults,8012738266,100.00,80.373,/sec 18350698,,cycles,8012744109,100.00,0.002,GHz 12745021,,instructions,8012759001,100.00,0.69,insn per cycle 2458033,,branches,8012770864,100.00,306.768,K/sec 102107,,branch-misses,8012781751,100.00,4.15,of all branches This option can be enabled in perf config by setting the variable 'stat.no-csv-summary'. # perf config stat.no-csv-summary=true # perf config -l stat.no-csv-summary=true # perf stat -x, -I1000 --interval-count 1 --summary 1.001330198,8013.28,msec,cpu-clock,8013279201,100.00,8.013,CPUs utilized 1.001330198,205,,context-switches,8013308394,100.00,25.583,/sec 1.001330198,10,,cpu-migrations,8013324681,100.00,1.248,/sec 1.001330198,0,,page-faults,8013340926,100.00,0.000,/sec 1.001330198,8027742,,cycles,8013344503,100.00,0.001,GHz 1.001330198,2871717,,instructions,8013356501,100.00,0.36,insn per cycle 1.001330198,553564,,branches,8013366204,100.00,69.081,K/sec 1.001330198,54021,,branch-misses,8013375952,100.00,9.76,of all branches 8013.28,msec,cpu-clock,8013279201,100.00,7.985,CPUs utilized 205,,context-switches,8013308394,100.00,25.583,/sec 10,,cpu-migrations,8013324681,100.00,1.248,/sec 0,,page-faults,8013340926,100.00,0.000,/sec 8027742,,cycles,8013344503,100.00,0.001,GHz 2871717,,instructions,8013356501,100.00,0.36,insn per cycle 553564,,branches,8013366204,100.00,69.081,K/sec 54021,,branch-misses,8013375952,100.00,9.76,of all branches Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20210319070156.20394-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-03-19 15:01:55 +08:00
if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
if (config->metric_only) {
perf stat: Also hide metric-units from JSON when event didn't run We decided to hide NULL metric-units rather than showing it as "(null)" when a dependent event for a metric doesn't exist. But on hybrid systems if the process doesn't hit a PMU you get an empty string metric unit instead. To make it consistent change all empty strings to NULL. Note that metric-threshold is already hidden in this case without this change. Where a process only runs on cpu_core and never hits cpu_atom: Before: $ perf stat -j -- true ... {"counter-value" : "<not counted>", "unit" : "", "event" : "cpu_atom/branch-misses/", "event-runtime" : 0, "pcnt-running" : 0.00, "metric-value" : "0.000000", "metric-unit" : ""} {"counter-value" : "6326.000000", "unit" : "", "event" : "cpu_core/branch-misses/", "event-runtime" : 293786, "pcnt-running" : 100.00, "metric-value" : "3.553394", "metric-unit" : "of all branches", "metric-threshold" : "good"} ... After: ... {"counter-value" : "<not counted>", "unit" : "", "event" : "cpu_atom/branch-misses/", "event-runtime" : 0, "pcnt-running" : 0.00} {"counter-value" : "5778.000000", "unit" : "", "event" : "cpu_core/branch-misses/", "event-runtime" : 282240, "pcnt-running" : 100.00, "metric-value" : "3.226797", "metric-unit" : "of all branches", "metric-threshold" : "good"} ... Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-3-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:42 +00:00
pm(config, os, METRIC_THRESHOLD_UNKNOWN, /*format=*/NULL,
/*unit=*/NULL, /*val=*/0);
return;
}
ok = false;
if (counter->supported) {
perf stat: Better hybrid support for the NMI watchdog warning Prior to this patch evlist__has_hybrid would return false if the processor wasn't hybrid or the evlist didn't contain any core events. If the only PMU used by events was cpu_core then it would true even though there are no cpu_atom events. For example: ``` $ perf stat --cputype=cpu_core -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}' true Performance counter stats for 'true': <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) <not counted> cpu_core/cycles/ (0.00%) 0.001981900 seconds time elapsed 0.002311000 seconds user 0.000000000 seconds sys ``` This patch changes evlist__has_hybrid to return true only if the evlist contains events from >1 core PMU. This means the NMI watchdog warning is shown for the case above. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Dominique Martinet <asmadeus@codewreck.org> Cc: Dr. David Alan Gilbert <linux@treblig.org> Cc: Howard Chu <howardchu95@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@linaro.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Levi Yun <yeoreum.yun@arm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Weilin Wang <weilin.wang@intel.com> Link: https://lore.kernel.org/r/20250402201549.4090305-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2025-04-02 13:15:45 -07:00
if (!evlist__has_hybrid_pmus(counter->evlist)) {
perf stat: Disable the NMI watchdog message on hybrid If we run a single workload that only runs on big core, there is always a ugly message about disabling the NMI watchdog because the atom is not counted. Before: # ./perf stat true Performance counter stats for 'true': 0.43 msec task-clock # 0.396 CPUs utilized 0 context-switches # 0.000 /sec 0 cpu-migrations # 0.000 /sec 45 page-faults # 103.918 K/sec 639,634 cpu_core/cycles/ # 1.477 G/sec <not counted> cpu_atom/cycles/ (0.00%) 643,498 cpu_core/instructions/ # 1.486 G/sec <not counted> cpu_atom/instructions/ (0.00%) 123,715 cpu_core/branches/ # 285.694 M/sec <not counted> cpu_atom/branches/ (0.00%) 4,094 cpu_core/branch-misses/ # 9.454 M/sec <not counted> cpu_atom/branch-misses/ (0.00%) 0.001092407 seconds time elapsed 0.001144000 seconds user 0.000000000 seconds sys Some events weren't counted. Try disabling the NMI watchdog: echo 0 > /proc/sys/kernel/nmi_watchdog perf stat ... echo 1 > /proc/sys/kernel/nmi_watchdog # ./perf stat -e '{cpu_atom/cycles/,msr/tsc/}' true Performance counter stats for 'true': <not counted> cpu_atom/cycles/ (0.00%) <not counted> msr/tsc/ (0.00%) 0.001904106 seconds time elapsed 0.001947000 seconds user 0.000000000 seconds sys Some events weren't counted. Try disabling the NMI watchdog: echo 0 > /proc/sys/kernel/nmi_watchdog perf stat ... echo 1 > /proc/sys/kernel/nmi_watchdog The events in group usually have to be from the same PMU. Try reorganizing the group. Now we disable the NMI watchdog message on hybrid, otherwise there are too many false positives. After: # ./perf stat true Performance counter stats for 'true': 0.79 msec task-clock # 0.419 CPUs utilized 0 context-switches # 0.000 /sec 0 cpu-migrations # 0.000 /sec 48 page-faults # 60.889 K/sec 777,692 cpu_core/cycles/ # 986.519 M/sec <not counted> cpu_atom/cycles/ (0.00%) 669,147 cpu_core/instructions/ # 848.828 M/sec <not counted> cpu_atom/instructions/ (0.00%) 128,635 cpu_core/branches/ # 163.176 M/sec <not counted> cpu_atom/branches/ (0.00%) 4,089 cpu_core/branch-misses/ # 5.187 M/sec <not counted> cpu_atom/branch-misses/ (0.00%) 0.001880649 seconds time elapsed 0.001935000 seconds user 0.000000000 seconds sys # ./perf stat -e '{cpu_atom/cycles/,msr/tsc/}' true Performance counter stats for 'true': <not counted> cpu_atom/cycles/ (0.00%) <not counted> msr/tsc/ (0.00%) 0.000963319 seconds time elapsed 0.000999000 seconds user 0.000000000 seconds sys Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20210610034557.29766-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-06-10 11:45:57 +08:00
config->print_free_counters_hint = 1;
}
}
}
out.print_metric = pm;
out.new_line = nl;
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
out.print_metricgroup_header = pmh;
out.ctx = os;
out.force_header = false;
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
if (!config->metric_only && !counter->default_metricgroup) {
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
abs_printout(config, os, os->id, os->aggr_nr, counter, uval, ok);
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
print_noise(config, os, counter, noise, /*before_metric=*/true);
print_running(config, os, run, ena, /*before_metric=*/true);
}
if (ok) {
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
if (!config->metric_only && counter->default_metricgroup) {
void *from = NULL;
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
aggr_printout(config, os, os->evsel, os->id, os->aggr_nr);
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
/* Print out all the metricgroup with the same metric event. */
do {
int num = 0;
/* Print out the new line for the next new metricgroup. */
if (from) {
if (config->json_output)
new_line_json(config, (void *)os);
else
__new_line_std_csv(config, os);
}
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
print_noise(config, os, counter, noise, /*before_metric=*/true);
print_running(config, os, run, ena, /*before_metric=*/true);
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
from = perf_stat__print_shadow_stats_metricgroup(config, counter, aggr_idx,
&num, from, &out);
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
} while (from != NULL);
} else {
perf_stat__print_shadow_stats(config, counter, uval, aggr_idx, &out);
}
} else {
perf stat: Also hide metric-units from JSON when event didn't run We decided to hide NULL metric-units rather than showing it as "(null)" when a dependent event for a metric doesn't exist. But on hybrid systems if the process doesn't hit a PMU you get an empty string metric unit instead. To make it consistent change all empty strings to NULL. Note that metric-threshold is already hidden in this case without this change. Where a process only runs on cpu_core and never hits cpu_atom: Before: $ perf stat -j -- true ... {"counter-value" : "<not counted>", "unit" : "", "event" : "cpu_atom/branch-misses/", "event-runtime" : 0, "pcnt-running" : 0.00, "metric-value" : "0.000000", "metric-unit" : ""} {"counter-value" : "6326.000000", "unit" : "", "event" : "cpu_core/branch-misses/", "event-runtime" : 293786, "pcnt-running" : 100.00, "metric-value" : "3.553394", "metric-unit" : "of all branches", "metric-threshold" : "good"} ... After: ... {"counter-value" : "<not counted>", "unit" : "", "event" : "cpu_atom/branch-misses/", "event-runtime" : 0, "pcnt-running" : 0.00} {"counter-value" : "5778.000000", "unit" : "", "event" : "cpu_core/branch-misses/", "event-runtime" : 282240, "pcnt-running" : 100.00, "metric-value" : "3.226797", "metric-unit" : "of all branches", "metric-threshold" : "good"} ... Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-3-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:42 +00:00
pm(config, os, METRIC_THRESHOLD_UNKNOWN, /*format=*/NULL, /*unit=*/NULL, /*val=*/0);
}
if (!config->metric_only) {
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
print_noise(config, os, counter, noise, /*before_metric=*/false);
print_running(config, os, run, ena, /*before_metric=*/false);
}
}
perf stat: Hide invalid uncore event output for aggr mode The current display code for perf stat iterates given cpus and build the aggr map to collect the event data for the aggregation mode. But uncore events have their own cpu maps and it won't guarantee that it'd match to the aggr map. For example, per-package uncore events would generate a single value for each socket. When user asks per-core aggregation mode, the output would contain 0 values for other cores. Thus it needs to check the uncore PMU's cpumask and if it matches to the current aggregation id. Before: $ sudo ./perf stat -a --per-core -e power/energy-pkg/ sleep 1 Performance counter stats for 'system wide': S0-D0-C0 1 3.73 Joules power/energy-pkg/ S0-D0-C1 0 <not counted> Joules power/energy-pkg/ S0-D0-C2 0 <not counted> Joules power/energy-pkg/ S0-D0-C3 0 <not counted> Joules power/energy-pkg/ 1.001404046 seconds time elapsed Some events weren't counted. Try disabling the NMI watchdog: echo 0 > /proc/sys/kernel/nmi_watchdog perf stat ... echo 1 > /proc/sys/kernel/nmi_watchdog The core 1, 2 and 3 should not be printed because the event is handled in a cpu in the core 0 only. With this change, the output becomes like below. After: $ sudo ./perf stat -a --per-core -e power/energy-pkg/ sleep 1 Performance counter stats for 'system wide': S0-D0-C0 1 2.09 Joules power/energy-pkg/ Fixes: b897613510890d6e ("perf stat: Update event skip condition for system-wide per-thread mode and merged uncore and hybrid events") Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Ian Rogers <irogers@google.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20230125192431.2929677-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-01-25 11:24:31 -08:00
/**
* should_skip_zero_count() - Check if the event should print 0 values.
* @config: The perf stat configuration (including aggregation mode).
* @counter: The evsel with its associated cpumap.
* @id: The aggregation id that is being queried.
*
* Due to mismatch between the event cpumap or thread-map and the
* aggregation mode, sometimes it'd iterate the counter with the map
* which does not contain any values.
*
* For example, uncore events have dedicated CPUs to manage them,
* result for other CPUs should be zero and skipped.
*
* Return: %true if the value should NOT be printed, %false if the value
* needs to be printed like "<not counted>" or "<not supported>".
*/
static bool should_skip_zero_counter(struct perf_stat_config *config,
struct evsel *counter,
const struct aggr_cpu_id *id)
{
struct perf_cpu cpu;
int idx;
perf stat: Remove evlist__add_default_attrs use strings add_default_atttributes would add evsels by having pre-created perf_event_attr, however, this needed fixing for hybrid as the extended PMU type was necessary for each core PMU. The logic for this was in an arch specific x86 function and wasn't present for ARM, meaning that default events weren't being opened on all PMUs on ARM. Change the creation of the default events to use parse_events and strings as that will open the events on all PMUs. Rather than try to detect events on PMUs before parsing, parse the event but skip its output in stat-display. The previous order of hardware events was: cycles, stalled-cycles-frontend, stalled-cycles-backend, instructions. As instructions is a more fundamental concept the order is changed to: instructions, cycles, stalled-cycles-frontend, stalled-cycles-backend. Closes: https://lore.kernel.org/lkml/CAP-5=fVABSBZnsmtRn1uF-k-G1GWM-L5SgiinhPTfHbQsKXb_g@mail.gmail.com/ Acked-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Ian Rogers <irogers@google.com> [Don't display unsupported default events except 'cycles'] Acked-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: James Clark <james.clark@linaro.org> Cc: Yang Jihong <yangjihong@bytedance.com> Cc: Dominique Martinet <asmadeus@codewreck.org> Cc: Colin Ian King <colin.i.king@gmail.com> Cc: Howard Chu <howardchu95@gmail.com> Cc: Ze Gao <zegao2021@gmail.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Cc: Weilin Wang <weilin.wang@intel.com> Cc: Will Deacon <will@kernel.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Yang Li <yang.lee@linux.alibaba.com> Cc: Leo Yan <leo.yan@linux.dev> Cc: ak@linux.intel.com Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: linux-arm-kernel@lists.infradead.org Cc: Sun Haiyong <sunhaiyong@loongson.cn> Cc: John Garry <john.g.garry@oracle.com> Link: https://lore.kernel.org/r/20240926144851.245903-4-james.clark@linaro.org Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-09-26 15:48:34 +01:00
/*
* Skip unsupported default events when not verbose. (default events
* are all marked 'skippable').
*/
if (verbose == 0 && counter->skippable && !counter->supported)
return true;
perf stat: Hide invalid uncore event output for aggr mode The current display code for perf stat iterates given cpus and build the aggr map to collect the event data for the aggregation mode. But uncore events have their own cpu maps and it won't guarantee that it'd match to the aggr map. For example, per-package uncore events would generate a single value for each socket. When user asks per-core aggregation mode, the output would contain 0 values for other cores. Thus it needs to check the uncore PMU's cpumask and if it matches to the current aggregation id. Before: $ sudo ./perf stat -a --per-core -e power/energy-pkg/ sleep 1 Performance counter stats for 'system wide': S0-D0-C0 1 3.73 Joules power/energy-pkg/ S0-D0-C1 0 <not counted> Joules power/energy-pkg/ S0-D0-C2 0 <not counted> Joules power/energy-pkg/ S0-D0-C3 0 <not counted> Joules power/energy-pkg/ 1.001404046 seconds time elapsed Some events weren't counted. Try disabling the NMI watchdog: echo 0 > /proc/sys/kernel/nmi_watchdog perf stat ... echo 1 > /proc/sys/kernel/nmi_watchdog The core 1, 2 and 3 should not be printed because the event is handled in a cpu in the core 0 only. With this change, the output becomes like below. After: $ sudo ./perf stat -a --per-core -e power/energy-pkg/ sleep 1 Performance counter stats for 'system wide': S0-D0-C0 1 2.09 Joules power/energy-pkg/ Fixes: b897613510890d6e ("perf stat: Update event skip condition for system-wide per-thread mode and merged uncore and hybrid events") Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Ian Rogers <irogers@google.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20230125192431.2929677-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-01-25 11:24:31 -08:00
/*
* Skip value 0 when enabling --per-thread globally,
* otherwise it will have too many 0 output.
*/
if (config->aggr_mode == AGGR_THREAD && config->system_wide)
return true;
/*
perf stat: Use counter cpumask to skip zero values When a counter is 0 it may or may not be skipped. For uncore counters it is common they are only valid on 1 logical CPU and all other CPUs should be skipped. The PMU's cpumask was used for the skip calculation, but that cpumask may not reflect user overrides. Similarly a counter on a core PMU may explicitly not request a CPU be gathered. If the counter on this CPU's value is 0 then the counter should be skipped as it wasn't requested. Switch from using the PMU cpumask to that associated with the evsel to support these cases. Avoid potential crash with --per-thread mode where config->aggr_get_id is NULL. Add some examples for the tool event 0 counter skipping. Signed-off-by: Ian Rogers <irogers@google.com> Tested-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Dominique Martinet <asmadeus@codewreck.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@linaro.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Leo Yan <leo.yan@arm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Weilin Wang <weilin.wang@intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20250403194337.40202-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2025-04-03 12:43:35 -07:00
* In per-thread mode the aggr_map and aggr_get_id functions may be
* NULL, assume all 0 values should be output in that case.
*/
if (!config->aggr_map || !config->aggr_get_id)
return false;
/*
* Tool events may be gathered on all logical CPUs, for example
* system_time, but for many the first index is the only one used, for
* example num_cores. Don't skip for the first index.
*/
if (evsel__is_tool(counter)) {
struct aggr_cpu_id own_id =
config->aggr_get_id(config, (struct perf_cpu){ .cpu = 0 });
return !aggr_cpu_id__equal(id, &own_id);
}
perf stat: Hide invalid uncore event output for aggr mode The current display code for perf stat iterates given cpus and build the aggr map to collect the event data for the aggregation mode. But uncore events have their own cpu maps and it won't guarantee that it'd match to the aggr map. For example, per-package uncore events would generate a single value for each socket. When user asks per-core aggregation mode, the output would contain 0 values for other cores. Thus it needs to check the uncore PMU's cpumask and if it matches to the current aggregation id. Before: $ sudo ./perf stat -a --per-core -e power/energy-pkg/ sleep 1 Performance counter stats for 'system wide': S0-D0-C0 1 3.73 Joules power/energy-pkg/ S0-D0-C1 0 <not counted> Joules power/energy-pkg/ S0-D0-C2 0 <not counted> Joules power/energy-pkg/ S0-D0-C3 0 <not counted> Joules power/energy-pkg/ 1.001404046 seconds time elapsed Some events weren't counted. Try disabling the NMI watchdog: echo 0 > /proc/sys/kernel/nmi_watchdog perf stat ... echo 1 > /proc/sys/kernel/nmi_watchdog The core 1, 2 and 3 should not be printed because the event is handled in a cpu in the core 0 only. With this change, the output becomes like below. After: $ sudo ./perf stat -a --per-core -e power/energy-pkg/ sleep 1 Performance counter stats for 'system wide': S0-D0-C0 1 2.09 Joules power/energy-pkg/ Fixes: b897613510890d6e ("perf stat: Update event skip condition for system-wide per-thread mode and merged uncore and hybrid events") Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Ian Rogers <irogers@google.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20230125192431.2929677-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-01-25 11:24:31 -08:00
/*
perf stat: Use counter cpumask to skip zero values When a counter is 0 it may or may not be skipped. For uncore counters it is common they are only valid on 1 logical CPU and all other CPUs should be skipped. The PMU's cpumask was used for the skip calculation, but that cpumask may not reflect user overrides. Similarly a counter on a core PMU may explicitly not request a CPU be gathered. If the counter on this CPU's value is 0 then the counter should be skipped as it wasn't requested. Switch from using the PMU cpumask to that associated with the evsel to support these cases. Avoid potential crash with --per-thread mode where config->aggr_get_id is NULL. Add some examples for the tool event 0 counter skipping. Signed-off-by: Ian Rogers <irogers@google.com> Tested-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Dominique Martinet <asmadeus@codewreck.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@linaro.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Leo Yan <leo.yan@arm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Weilin Wang <weilin.wang@intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20250403194337.40202-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2025-04-03 12:43:35 -07:00
* Skip value 0 when the counter's cpumask doesn't match the given aggr
* id.
perf stat: Hide invalid uncore event output for aggr mode The current display code for perf stat iterates given cpus and build the aggr map to collect the event data for the aggregation mode. But uncore events have their own cpu maps and it won't guarantee that it'd match to the aggr map. For example, per-package uncore events would generate a single value for each socket. When user asks per-core aggregation mode, the output would contain 0 values for other cores. Thus it needs to check the uncore PMU's cpumask and if it matches to the current aggregation id. Before: $ sudo ./perf stat -a --per-core -e power/energy-pkg/ sleep 1 Performance counter stats for 'system wide': S0-D0-C0 1 3.73 Joules power/energy-pkg/ S0-D0-C1 0 <not counted> Joules power/energy-pkg/ S0-D0-C2 0 <not counted> Joules power/energy-pkg/ S0-D0-C3 0 <not counted> Joules power/energy-pkg/ 1.001404046 seconds time elapsed Some events weren't counted. Try disabling the NMI watchdog: echo 0 > /proc/sys/kernel/nmi_watchdog perf stat ... echo 1 > /proc/sys/kernel/nmi_watchdog The core 1, 2 and 3 should not be printed because the event is handled in a cpu in the core 0 only. With this change, the output becomes like below. After: $ sudo ./perf stat -a --per-core -e power/energy-pkg/ sleep 1 Performance counter stats for 'system wide': S0-D0-C0 1 2.09 Joules power/energy-pkg/ Fixes: b897613510890d6e ("perf stat: Update event skip condition for system-wide per-thread mode and merged uncore and hybrid events") Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Ian Rogers <irogers@google.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20230125192431.2929677-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-01-25 11:24:31 -08:00
*/
perf stat: Use counter cpumask to skip zero values When a counter is 0 it may or may not be skipped. For uncore counters it is common they are only valid on 1 logical CPU and all other CPUs should be skipped. The PMU's cpumask was used for the skip calculation, but that cpumask may not reflect user overrides. Similarly a counter on a core PMU may explicitly not request a CPU be gathered. If the counter on this CPU's value is 0 then the counter should be skipped as it wasn't requested. Switch from using the PMU cpumask to that associated with the evsel to support these cases. Avoid potential crash with --per-thread mode where config->aggr_get_id is NULL. Add some examples for the tool event 0 counter skipping. Signed-off-by: Ian Rogers <irogers@google.com> Tested-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Dominique Martinet <asmadeus@codewreck.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@linaro.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Leo Yan <leo.yan@arm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Weilin Wang <weilin.wang@intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20250403194337.40202-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2025-04-03 12:43:35 -07:00
perf_cpu_map__for_each_cpu(cpu, idx, counter->core.cpus) {
perf stat: Hide invalid uncore event output for aggr mode The current display code for perf stat iterates given cpus and build the aggr map to collect the event data for the aggregation mode. But uncore events have their own cpu maps and it won't guarantee that it'd match to the aggr map. For example, per-package uncore events would generate a single value for each socket. When user asks per-core aggregation mode, the output would contain 0 values for other cores. Thus it needs to check the uncore PMU's cpumask and if it matches to the current aggregation id. Before: $ sudo ./perf stat -a --per-core -e power/energy-pkg/ sleep 1 Performance counter stats for 'system wide': S0-D0-C0 1 3.73 Joules power/energy-pkg/ S0-D0-C1 0 <not counted> Joules power/energy-pkg/ S0-D0-C2 0 <not counted> Joules power/energy-pkg/ S0-D0-C3 0 <not counted> Joules power/energy-pkg/ 1.001404046 seconds time elapsed Some events weren't counted. Try disabling the NMI watchdog: echo 0 > /proc/sys/kernel/nmi_watchdog perf stat ... echo 1 > /proc/sys/kernel/nmi_watchdog The core 1, 2 and 3 should not be printed because the event is handled in a cpu in the core 0 only. With this change, the output becomes like below. After: $ sudo ./perf stat -a --per-core -e power/energy-pkg/ sleep 1 Performance counter stats for 'system wide': S0-D0-C0 1 2.09 Joules power/energy-pkg/ Fixes: b897613510890d6e ("perf stat: Update event skip condition for system-wide per-thread mode and merged uncore and hybrid events") Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Ian Rogers <irogers@google.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20230125192431.2929677-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-01-25 11:24:31 -08:00
struct aggr_cpu_id own_id = config->aggr_get_id(config, cpu);
if (aggr_cpu_id__equal(id, &own_id))
return false;
}
return true;
}
static void print_counter_aggrdata(struct perf_stat_config *config,
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
struct evsel *counter, int aggr_idx,
struct outstate *os)
{
FILE *output = config->output;
u64 ena, run, val;
double uval;
struct perf_stat_evsel *ps = counter->stats;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
struct perf_stat_aggr *aggr = &ps->aggr[aggr_idx];
struct aggr_cpu_id id = config->aggr_map->map[aggr_idx];
double avg = aggr->counts.val;
bool metric_only = config->metric_only;
os->id = id;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
os->aggr_nr = aggr->nr;
os->evsel = counter;
/* Skip already merged uncore/hybrid events */
if (config->aggr_mode != AGGR_NONE) {
if (evsel__is_hybrid(counter)) {
if (config->hybrid_merge && counter->first_wildcard_match != NULL)
return;
} else {
if (counter->first_wildcard_match != NULL)
return;
}
}
val = aggr->counts.val;
ena = aggr->counts.ena;
run = aggr->counts.run;
perf stat: Filter out unmatched aggregation for hybrid event perf-stat has supported some aggregation modes, such as --per-core, --per-socket and etc. While for hybrid event, it may only available on part of cpus. So for --per-core, we need to filter out the unavailable cores, for --per-socket, filter out the unavailable sockets, and so on. Before: # perf stat --per-core -e cpu_core/cycles/ -a -- sleep 1 Performance counter stats for 'system wide': S0-D0-C0 2 479,530 cpu_core/cycles/ S0-D0-C4 2 175,007 cpu_core/cycles/ S0-D0-C8 2 166,240 cpu_core/cycles/ S0-D0-C12 2 704,673 cpu_core/cycles/ S0-D0-C16 2 865,835 cpu_core/cycles/ S0-D0-C20 2 2,958,461 cpu_core/cycles/ S0-D0-C24 2 163,988 cpu_core/cycles/ S0-D0-C28 2 164,729 cpu_core/cycles/ S0-D0-C32 0 <not counted> cpu_core/cycles/ S0-D0-C33 0 <not counted> cpu_core/cycles/ S0-D0-C34 0 <not counted> cpu_core/cycles/ S0-D0-C35 0 <not counted> cpu_core/cycles/ S0-D0-C36 0 <not counted> cpu_core/cycles/ S0-D0-C37 0 <not counted> cpu_core/cycles/ S0-D0-C38 0 <not counted> cpu_core/cycles/ S0-D0-C39 0 <not counted> cpu_core/cycles/ 1.003597211 seconds time elapsed After: # perf stat --per-core -e cpu_core/cycles/ -a -- sleep 1 Performance counter stats for 'system wide': S0-D0-C0 2 210,428 cpu_core/cycles/ S0-D0-C4 2 444,830 cpu_core/cycles/ S0-D0-C8 2 435,241 cpu_core/cycles/ S0-D0-C12 2 423,976 cpu_core/cycles/ S0-D0-C16 2 859,350 cpu_core/cycles/ S0-D0-C20 2 1,559,589 cpu_core/cycles/ S0-D0-C24 2 163,924 cpu_core/cycles/ S0-D0-C28 2 376,610 cpu_core/cycles/ 1.003621290 seconds time elapsed Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Co-developed-by: Jiri Olsa <jolsa@redhat.com> Reviewed-by: Jiri Olsa <jolsa@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20210427070139.25256-16-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-04-27 15:01:28 +08:00
if (perf_stat__skip_metric_event(counter, ena, run))
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
return;
perf stat: Hide invalid uncore event output for aggr mode The current display code for perf stat iterates given cpus and build the aggr map to collect the event data for the aggregation mode. But uncore events have their own cpu maps and it won't guarantee that it'd match to the aggr map. For example, per-package uncore events would generate a single value for each socket. When user asks per-core aggregation mode, the output would contain 0 values for other cores. Thus it needs to check the uncore PMU's cpumask and if it matches to the current aggregation id. Before: $ sudo ./perf stat -a --per-core -e power/energy-pkg/ sleep 1 Performance counter stats for 'system wide': S0-D0-C0 1 3.73 Joules power/energy-pkg/ S0-D0-C1 0 <not counted> Joules power/energy-pkg/ S0-D0-C2 0 <not counted> Joules power/energy-pkg/ S0-D0-C3 0 <not counted> Joules power/energy-pkg/ 1.001404046 seconds time elapsed Some events weren't counted. Try disabling the NMI watchdog: echo 0 > /proc/sys/kernel/nmi_watchdog perf stat ... echo 1 > /proc/sys/kernel/nmi_watchdog The core 1, 2 and 3 should not be printed because the event is handled in a cpu in the core 0 only. With this change, the output becomes like below. After: $ sudo ./perf stat -a --per-core -e power/energy-pkg/ sleep 1 Performance counter stats for 'system wide': S0-D0-C0 1 2.09 Joules power/energy-pkg/ Fixes: b897613510890d6e ("perf stat: Update event skip condition for system-wide per-thread mode and merged uncore and hybrid events") Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Ian Rogers <irogers@google.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20230125192431.2929677-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-01-25 11:24:31 -08:00
if (val == 0 && should_skip_zero_counter(config, counter, &id))
return;
if (!metric_only) {
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
if (config->json_output) {
os->first = true;
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 10:02:06 -08:00
fputc('{', output);
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
}
if (config->interval) {
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
if (config->json_output)
json_out(os, "%s", os->timestamp);
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
else
fprintf(output, "%s", os->timestamp);
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
} else if (config->summary && config->csv_output &&
!config->no_csv_summary)
perf stat: Do not align time prefix in CSV output We don't care about the alignment in the CSV output as it's intended for machine processing. Let's get rid of it to make the output more compact. Before: # perf stat -a --summary -I 1 -x, true 0.001149309,219.20,msec,cpu-clock,219322251,100.00,219.200,CPUs utilized 0.001149309,144,,context-switches,219241902,100.00,656.935,/sec 0.001149309,38,,cpu-migrations,219173705,100.00,173.358,/sec 0.001149309,61,,page-faults,219093635,100.00,278.285,/sec 0.001149309,10679310,,cycles,218746228,100.00,0.049,GHz 0.001149309,6288296,,instructions,218589869,100.00,0.59,insn per cycle 0.001149309,1386904,,branches,218428851,100.00,6.327,M/sec 0.001149309,56863,,branch-misses,218219951,100.00,4.10,of all branches summary,219.20,msec,cpu-clock,219322251,100.00,20.025,CPUs utilized summary,144,,context-switches,219241902,100.00,656.935,/sec summary,38,,cpu-migrations,219173705,100.00,173.358,/sec summary,61,,page-faults,219093635,100.00,278.285,/sec summary,10679310,,cycles,218746228,100.00,0.049,GHz summary,6288296,,instructions,218589869,100.00,0.59,insn per cycle summary,1386904,,branches,218428851,100.00,6.327,M/sec summary,56863,,branch-misses,218219951,100.00,4.10,of all branches After: 0.001148449,224.75,msec,cpu-clock,224870589,100.00,224.747,CPUs utilized 0.001148449,176,,context-switches,224775564,100.00,783.103,/sec 0.001148449,38,,cpu-migrations,224707428,100.00,169.079,/sec 0.001148449,61,,page-faults,224629326,100.00,271.416,/sec 0.001148449,12172071,,cycles,224266368,100.00,0.054,GHz 0.001148449,6901907,,instructions,224108764,100.00,0.57,insn per cycle 0.001148449,1515655,,branches,223946693,100.00,6.744,M/sec 0.001148449,70027,,branch-misses,223735385,100.00,4.62,of all branches summary,224.75,msec,cpu-clock,224870589,100.00,21.066,CPUs utilized summary,176,,context-switches,224775564,100.00,783.103,/sec summary,38,,cpu-migrations,224707428,100.00,169.079,/sec summary,61,,page-faults,224629326,100.00,271.416,/sec summary,12172071,,cycles,224266368,100.00,0.054,GHz summary,6901907,,instructions,224108764,100.00,0.57,insn per cycle summary,1515655,,branches,223946693,100.00,6.744,M/sec summary,70027,,branch-misses,223735385,100.00,4.62,of all branches Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-4-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 10:01:56 -08:00
fprintf(output, "%s%s", "summary", config->csv_sep);
}
uval = val * counter->scale;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
printout(config, os, uval, run, ena, avg, aggr_idx);
if (!metric_only)
fputc('\n', output);
}
static void print_metric_begin(struct perf_stat_config *config,
struct evlist *evlist,
struct outstate *os, int aggr_idx)
{
struct perf_stat_aggr *aggr;
struct aggr_cpu_id id;
struct evsel *evsel;
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 10:02:06 -08:00
os->first = true;
if (!config->metric_only)
return;
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 10:02:06 -08:00
if (config->json_output)
fputc('{', config->output);
if (config->interval) {
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
if (config->json_output)
json_out(os, "%s", os->timestamp);
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
else
fprintf(config->output, "%s", os->timestamp);
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
}
evsel = evlist__first(evlist);
id = config->aggr_map->map[aggr_idx];
aggr = &evsel->stats->aggr[aggr_idx];
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
aggr_printout(config, os, evsel, id, aggr->nr);
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
print_cgroup(config, os, os->cgrp ? : evsel->cgrp);
}
static void print_metric_end(struct perf_stat_config *config, struct outstate *os)
{
FILE *output = config->output;
if (!config->metric_only)
return;
if (config->json_output) {
if (os->first)
fputs("\"metric-value\" : \"none\"", output);
fputc('}', output);
}
fputc('\n', output);
}
static void print_aggr(struct perf_stat_config *config,
struct evlist *evlist,
struct outstate *os)
{
struct evsel *counter;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
int aggr_idx;
if (!config->aggr_map || !config->aggr_get_id)
return;
/*
* With metric_only everything is on a single line.
* Without each counter has its own line.
*/
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) {
print_metric_begin(config, evlist, os, aggr_idx);
evlist__for_each_entry(evlist, counter) {
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
print_counter_aggrdata(config, counter, aggr_idx, os);
}
print_metric_end(config, os);
}
}
perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown Normally, --for-each-cgroup only works with AGGR_GLOBAL. However the --topdown on some cpu (e.g. Intel Skylake) converts it to the AGGR_CORE internally. To support those machines, add print_aggr_cgroup and handle the events like in print_cgroup_events(). $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1 nmi_watchdog enabled with topdown. May give wrong results. Disable with echo 0 > /proc/sys/kernel/nmi_watchdog Performance counter stats for 'system wide': retiring bad speculation frontend bound backend bound S0-D0-C0 2 system.slice 49.0% -46.6% 31.4% S0-D0-C1 2 system.slice 55.5% 8.0% 45.5% -9.0% S0-D0-C2 2 system.slice 87.8% 22.1% 30.3% -40.3% S0-D0-C3 2 system.slice 53.3% -11.9% 45.2% 13.4% S0-D0-C0 2 user.slice 123.5% 4.0% 48.5% -75.9% S0-D0-C1 2 user.slice 19.9% 6.5% 89.9% -16.3% S0-D0-C2 2 user.slice 29.9% 7.9% 71.3% -9.1 S0-D0-C3 2 user.slice 28.0% 7.2% 43.3% 21.5% 1.004136937 seconds time elapsed Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-14 15:02:27 -08:00
static void print_aggr_cgroup(struct perf_stat_config *config,
struct evlist *evlist,
struct outstate *os)
perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown Normally, --for-each-cgroup only works with AGGR_GLOBAL. However the --topdown on some cpu (e.g. Intel Skylake) converts it to the AGGR_CORE internally. To support those machines, add print_aggr_cgroup and handle the events like in print_cgroup_events(). $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1 nmi_watchdog enabled with topdown. May give wrong results. Disable with echo 0 > /proc/sys/kernel/nmi_watchdog Performance counter stats for 'system wide': retiring bad speculation frontend bound backend bound S0-D0-C0 2 system.slice 49.0% -46.6% 31.4% S0-D0-C1 2 system.slice 55.5% 8.0% 45.5% -9.0% S0-D0-C2 2 system.slice 87.8% 22.1% 30.3% -40.3% S0-D0-C3 2 system.slice 53.3% -11.9% 45.2% 13.4% S0-D0-C0 2 user.slice 123.5% 4.0% 48.5% -75.9% S0-D0-C1 2 user.slice 19.9% 6.5% 89.9% -16.3% S0-D0-C2 2 user.slice 29.9% 7.9% 71.3% -9.1 S0-D0-C3 2 user.slice 28.0% 7.2% 43.3% 21.5% 1.004136937 seconds time elapsed Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-14 15:02:27 -08:00
{
struct evsel *counter, *evsel;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
int aggr_idx;
perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown Normally, --for-each-cgroup only works with AGGR_GLOBAL. However the --topdown on some cpu (e.g. Intel Skylake) converts it to the AGGR_CORE internally. To support those machines, add print_aggr_cgroup and handle the events like in print_cgroup_events(). $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1 nmi_watchdog enabled with topdown. May give wrong results. Disable with echo 0 > /proc/sys/kernel/nmi_watchdog Performance counter stats for 'system wide': retiring bad speculation frontend bound backend bound S0-D0-C0 2 system.slice 49.0% -46.6% 31.4% S0-D0-C1 2 system.slice 55.5% 8.0% 45.5% -9.0% S0-D0-C2 2 system.slice 87.8% 22.1% 30.3% -40.3% S0-D0-C3 2 system.slice 53.3% -11.9% 45.2% 13.4% S0-D0-C0 2 user.slice 123.5% 4.0% 48.5% -75.9% S0-D0-C1 2 user.slice 19.9% 6.5% 89.9% -16.3% S0-D0-C2 2 user.slice 29.9% 7.9% 71.3% -9.1 S0-D0-C3 2 user.slice 28.0% 7.2% 43.3% 21.5% 1.004136937 seconds time elapsed Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-14 15:02:27 -08:00
if (!config->aggr_map || !config->aggr_get_id)
return;
evlist__for_each_entry(evlist, evsel) {
if (os->cgrp == evsel->cgrp)
perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown Normally, --for-each-cgroup only works with AGGR_GLOBAL. However the --topdown on some cpu (e.g. Intel Skylake) converts it to the AGGR_CORE internally. To support those machines, add print_aggr_cgroup and handle the events like in print_cgroup_events(). $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1 nmi_watchdog enabled with topdown. May give wrong results. Disable with echo 0 > /proc/sys/kernel/nmi_watchdog Performance counter stats for 'system wide': retiring bad speculation frontend bound backend bound S0-D0-C0 2 system.slice 49.0% -46.6% 31.4% S0-D0-C1 2 system.slice 55.5% 8.0% 45.5% -9.0% S0-D0-C2 2 system.slice 87.8% 22.1% 30.3% -40.3% S0-D0-C3 2 system.slice 53.3% -11.9% 45.2% 13.4% S0-D0-C0 2 user.slice 123.5% 4.0% 48.5% -75.9% S0-D0-C1 2 user.slice 19.9% 6.5% 89.9% -16.3% S0-D0-C2 2 user.slice 29.9% 7.9% 71.3% -9.1 S0-D0-C3 2 user.slice 28.0% 7.2% 43.3% 21.5% 1.004136937 seconds time elapsed Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-14 15:02:27 -08:00
continue;
os->cgrp = evsel->cgrp;
perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown Normally, --for-each-cgroup only works with AGGR_GLOBAL. However the --topdown on some cpu (e.g. Intel Skylake) converts it to the AGGR_CORE internally. To support those machines, add print_aggr_cgroup and handle the events like in print_cgroup_events(). $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1 nmi_watchdog enabled with topdown. May give wrong results. Disable with echo 0 > /proc/sys/kernel/nmi_watchdog Performance counter stats for 'system wide': retiring bad speculation frontend bound backend bound S0-D0-C0 2 system.slice 49.0% -46.6% 31.4% S0-D0-C1 2 system.slice 55.5% 8.0% 45.5% -9.0% S0-D0-C2 2 system.slice 87.8% 22.1% 30.3% -40.3% S0-D0-C3 2 system.slice 53.3% -11.9% 45.2% 13.4% S0-D0-C0 2 user.slice 123.5% 4.0% 48.5% -75.9% S0-D0-C1 2 user.slice 19.9% 6.5% 89.9% -16.3% S0-D0-C2 2 user.slice 29.9% 7.9% 71.3% -9.1 S0-D0-C3 2 user.slice 28.0% 7.2% 43.3% 21.5% 1.004136937 seconds time elapsed Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-14 15:02:27 -08:00
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) {
print_metric_begin(config, evlist, os, aggr_idx);
perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown Normally, --for-each-cgroup only works with AGGR_GLOBAL. However the --topdown on some cpu (e.g. Intel Skylake) converts it to the AGGR_CORE internally. To support those machines, add print_aggr_cgroup and handle the events like in print_cgroup_events(). $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1 nmi_watchdog enabled with topdown. May give wrong results. Disable with echo 0 > /proc/sys/kernel/nmi_watchdog Performance counter stats for 'system wide': retiring bad speculation frontend bound backend bound S0-D0-C0 2 system.slice 49.0% -46.6% 31.4% S0-D0-C1 2 system.slice 55.5% 8.0% 45.5% -9.0% S0-D0-C2 2 system.slice 87.8% 22.1% 30.3% -40.3% S0-D0-C3 2 system.slice 53.3% -11.9% 45.2% 13.4% S0-D0-C0 2 user.slice 123.5% 4.0% 48.5% -75.9% S0-D0-C1 2 user.slice 19.9% 6.5% 89.9% -16.3% S0-D0-C2 2 user.slice 29.9% 7.9% 71.3% -9.1 S0-D0-C3 2 user.slice 28.0% 7.2% 43.3% 21.5% 1.004136937 seconds time elapsed Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-14 15:02:27 -08:00
evlist__for_each_entry(evlist, counter) {
if (counter->cgrp != os->cgrp)
perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown Normally, --for-each-cgroup only works with AGGR_GLOBAL. However the --topdown on some cpu (e.g. Intel Skylake) converts it to the AGGR_CORE internally. To support those machines, add print_aggr_cgroup and handle the events like in print_cgroup_events(). $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1 nmi_watchdog enabled with topdown. May give wrong results. Disable with echo 0 > /proc/sys/kernel/nmi_watchdog Performance counter stats for 'system wide': retiring bad speculation frontend bound backend bound S0-D0-C0 2 system.slice 49.0% -46.6% 31.4% S0-D0-C1 2 system.slice 55.5% 8.0% 45.5% -9.0% S0-D0-C2 2 system.slice 87.8% 22.1% 30.3% -40.3% S0-D0-C3 2 system.slice 53.3% -11.9% 45.2% 13.4% S0-D0-C0 2 user.slice 123.5% 4.0% 48.5% -75.9% S0-D0-C1 2 user.slice 19.9% 6.5% 89.9% -16.3% S0-D0-C2 2 user.slice 29.9% 7.9% 71.3% -9.1 S0-D0-C3 2 user.slice 28.0% 7.2% 43.3% 21.5% 1.004136937 seconds time elapsed Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-14 15:02:27 -08:00
continue;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
print_counter_aggrdata(config, counter, aggr_idx, os);
perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown Normally, --for-each-cgroup only works with AGGR_GLOBAL. However the --topdown on some cpu (e.g. Intel Skylake) converts it to the AGGR_CORE internally. To support those machines, add print_aggr_cgroup and handle the events like in print_cgroup_events(). $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1 nmi_watchdog enabled with topdown. May give wrong results. Disable with echo 0 > /proc/sys/kernel/nmi_watchdog Performance counter stats for 'system wide': retiring bad speculation frontend bound backend bound S0-D0-C0 2 system.slice 49.0% -46.6% 31.4% S0-D0-C1 2 system.slice 55.5% 8.0% 45.5% -9.0% S0-D0-C2 2 system.slice 87.8% 22.1% 30.3% -40.3% S0-D0-C3 2 system.slice 53.3% -11.9% 45.2% 13.4% S0-D0-C0 2 user.slice 123.5% 4.0% 48.5% -75.9% S0-D0-C1 2 user.slice 19.9% 6.5% 89.9% -16.3% S0-D0-C2 2 user.slice 29.9% 7.9% 71.3% -9.1 S0-D0-C3 2 user.slice 28.0% 7.2% 43.3% 21.5% 1.004136937 seconds time elapsed Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-14 15:02:27 -08:00
}
print_metric_end(config, os);
perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown Normally, --for-each-cgroup only works with AGGR_GLOBAL. However the --topdown on some cpu (e.g. Intel Skylake) converts it to the AGGR_CORE internally. To support those machines, add print_aggr_cgroup and handle the events like in print_cgroup_events(). $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1 nmi_watchdog enabled with topdown. May give wrong results. Disable with echo 0 > /proc/sys/kernel/nmi_watchdog Performance counter stats for 'system wide': retiring bad speculation frontend bound backend bound S0-D0-C0 2 system.slice 49.0% -46.6% 31.4% S0-D0-C1 2 system.slice 55.5% 8.0% 45.5% -9.0% S0-D0-C2 2 system.slice 87.8% 22.1% 30.3% -40.3% S0-D0-C3 2 system.slice 53.3% -11.9% 45.2% 13.4% S0-D0-C0 2 user.slice 123.5% 4.0% 48.5% -75.9% S0-D0-C1 2 user.slice 19.9% 6.5% 89.9% -16.3% S0-D0-C2 2 user.slice 29.9% 7.9% 71.3% -9.1 S0-D0-C3 2 user.slice 28.0% 7.2% 43.3% 21.5% 1.004136937 seconds time elapsed Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-14 15:02:27 -08:00
}
}
}
static void print_counter(struct perf_stat_config *config,
struct evsel *counter, struct outstate *os)
{
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
int aggr_idx;
/* AGGR_THREAD doesn't have config->aggr_get_id */
if (!config->aggr_map)
return;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) {
print_counter_aggrdata(config, counter, aggr_idx, os);
}
}
static void print_no_aggr_metric(struct perf_stat_config *config,
struct evlist *evlist,
struct outstate *os)
{
perf cpumap: Give CPUs their own type A common problem is confusing CPU map indices with the CPU, by wrapping the CPU with a struct then this is avoided. This approach is similar to atomic_t. Committer notes: To make it build with BUILD_BPF_SKEL=1 these files needed the conversions to 'struct perf_cpu' usage: tools/perf/util/bpf_counter.c tools/perf/util/bpf_counter_cgroup.c tools/perf/util/bpf_ftrace.c Also perf_env__get_cpu() was removed back in "perf cpumap: Switch cpu_map__build_map to cpu function". Additionally these needed to be fixed for the ARM builds to complete: tools/perf/arch/arm/util/cs-etm.c tools/perf/arch/arm64/util/pmu.c Suggested-by: John Garry <john.garry@huawei.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Clarke <pc@us.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Riccardo Mancini <rickyman7@gmail.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Vineet Singh <vineet.singh@intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Cc: zhengjun.xing@intel.com Link: https://lore.kernel.org/r/20220105061351.120843-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-01-04 22:13:51 -08:00
int all_idx;
struct perf_cpu cpu;
perf evlist: Rename cpus to user_requested_cpus evlist contains cpus and all_cpus. all_cpus is the union of the cpu maps of all evsels. For non-task targets, cpus is set to be cpus requested from the command line, defaulting to all online cpus if no cpus are specified. For an uncore event, all_cpus may be just CPU 0 or every online CPU. This causes all_cpus to have fewer values than the cpus variable which is confusing given the 'all' in the name. To try to make the behavior clearer, rename cpus to user_requested_cpus and add comments on the two struct variables. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Antonov <alexander.antonov@linux.intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: German Gomez <german.gomez@arm.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Fastabend <john.fastabend@gmail.com> Cc: John Garry <john.garry@huawei.com> Cc: KP Singh <kpsingh@kernel.org> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Riccardo Mancini <rickyman7@gmail.com> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Will Deacon <will@kernel.org> Cc: Yonghong Song <yhs@fb.com> Cc: bpf@vger.kernel.org Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20220328232648.2127340-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-03-28 16:26:44 -07:00
perf_cpu_map__for_each_cpu(cpu, all_idx, evlist->core.user_requested_cpus) {
struct evsel *counter;
bool first = true;
evlist__for_each_entry(evlist, counter) {
u64 ena, run, val;
double uval;
struct perf_stat_evsel *ps = counter->stats;
int aggr_idx = 0;
if (!perf_cpu_map__has(evsel__cpus(counter), cpu))
continue;
cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) {
if (config->aggr_map->map[aggr_idx].cpu.cpu == cpu.cpu)
break;
}
os->evsel = counter;
os->id = aggr_cpu_id__cpu(cpu, /*data=*/NULL);
if (first) {
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
print_metric_begin(config, evlist, os, aggr_idx);
first = false;
}
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
val = ps->aggr[aggr_idx].counts.val;
ena = ps->aggr[aggr_idx].counts.ena;
run = ps->aggr[aggr_idx].counts.run;
uval = val * counter->scale;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
printout(config, os, uval, run, ena, 1.0, aggr_idx);
}
perf stat: Avoid printing cpus with no counters perf_evlist's user_requested_cpus can contain CPUs not present in any evsel's cpus, for example uncore counters. Avoid printing the prefix and trailing \n until the first valid counter is encountered. Reviewed-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Alexander Antonov <alexander.antonov@linux.intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: German Gomez <german.gomez@arm.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Fastabend <john.fastabend@gmail.com> Cc: John Garry <john.garry@huawei.com> Cc: KP Singh <kpsingh@kernel.org> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Riccardo Mancini <rickyman7@gmail.com> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Will Deacon <will@kernel.org> Cc: Yonghong Song <yhs@fb.com> Link: http://lore.kernel.org/lkml/20220503041757.2365696-4-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-05-02 21:17:54 -07:00
if (!first)
print_metric_end(config, os);
}
}
static void print_metric_headers_std(struct perf_stat_config *config,
bool no_indent)
{
fputc(' ', config->output);
if (!no_indent) {
int len = aggr_header_lens[config->aggr_mode];
if (nr_cgroups || config->cgroup_list)
len += CGROUP_LEN + 1;
fprintf(config->output, "%*s", len, "");
}
}
static void print_metric_headers_csv(struct perf_stat_config *config,
bool no_indent __maybe_unused)
{
const char *p;
if (config->interval)
fprintf(config->output, "time%s", config->csv_sep);
if (config->iostat_run)
return;
p = aggr_header_csv[config->aggr_mode];
while (*p) {
if (*p == ',')
fputs(config->csv_sep, config->output);
else
fputc(*p, config->output);
p++;
}
}
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 10:02:06 -08:00
static void print_metric_headers_json(struct perf_stat_config *config __maybe_unused,
bool no_indent __maybe_unused)
{
}
static void print_metric_headers(struct perf_stat_config *config,
struct evlist *evlist, bool no_indent)
{
struct evsel *counter;
struct outstate os = {
.fh = config->output
};
struct perf_stat_output_ctx out = {
.ctx = &os,
.print_metric = print_metric_header,
.new_line = NULL,
.force_header = true,
};
if (config->json_output)
print_metric_headers_json(config, no_indent);
else if (config->csv_output)
print_metric_headers_csv(config, no_indent);
else
print_metric_headers_std(config, no_indent);
if (config->iostat_run)
iostat_print_header_prefix(config);
if (config->cgroup_list)
os.cgrp = evlist__first(evlist)->cgrp;
/* Print metrics headers only */
evlist__for_each_entry(evlist, counter) {
if (!config->iostat_run &&
config->aggr_mode != AGGR_NONE && counter->metric_leader != counter)
perf stat: Don't display metric header for non-leader uncore events On an Intel tigerlake laptop a metric like: { "BriefDescription": "Test", "MetricExpr": "imc_free_running@data_read@ + imc_free_running@data_write@", "MetricGroup": "Test", "MetricName": "Test", "ScaleUnit": "6.103515625e-5MiB" }, Will have 4 events: uncore_imc_free_running_0/data_read/ uncore_imc_free_running_0/data_write/ uncore_imc_free_running_1/data_read/ uncore_imc_free_running_1/data_write/ If aggregration is disabled with metric-only 2 column headers are needed: $ perf stat -M test --metric-only -A -a sleep 1 Performance counter stats for 'system wide': MiB Test MiB Test CPU0 1821.0 1820.5 But when not, the counts aggregated in the metric leader and only 1 column should be shown: $ perf stat -M test --metric-only -a sleep 1 Performance counter stats for 'system wide': MiB Test 5909.4 1.001258915 seconds time elapsed Achieve this by skipping events that aren't metric leaders when printing column headers and aggregation isn't disabled. The bug is long standing, the fixes tag is set to a refactor as that is as far back as is reasonable to backport. Fixes: 088519f318be3a41 ("perf stat: Move the display functions to stat-display.c") Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kaige Ye <ye@kaige.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: K Prateek Nayak <kprateek.nayak@amd.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20240510051309.2452468-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-05-09 22:13:09 -07:00
continue;
os.evsel = counter;
perf_stat__print_shadow_stats(config, counter, 0, 0, &out);
}
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 10:02:06 -08:00
if (!config->json_output)
fputc('\n', config->output);
}
static void prepare_timestamp(struct perf_stat_config *config,
struct outstate *os, struct timespec *ts)
{
if (config->iostat_run)
return;
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 10:02:06 -08:00
if (config->json_output)
scnprintf(os->timestamp, sizeof(os->timestamp), "\"interval\" : %lu.%09lu",
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 10:02:06 -08:00
(unsigned long) ts->tv_sec, ts->tv_nsec);
else if (config->csv_output)
scnprintf(os->timestamp, sizeof(os->timestamp), "%lu.%09lu%s",
(unsigned long) ts->tv_sec, ts->tv_nsec, config->csv_sep);
else
scnprintf(os->timestamp, sizeof(os->timestamp), "%6lu.%09lu ",
(unsigned long) ts->tv_sec, ts->tv_nsec);
}
static void print_header_interval_std(struct perf_stat_config *config,
struct target *_target __maybe_unused,
struct evlist *evlist,
int argc __maybe_unused,
const char **argv __maybe_unused)
{
FILE *output = config->output;
switch (config->aggr_mode) {
case AGGR_NODE:
case AGGR_SOCKET:
case AGGR_DIE:
perf stat: Support per-cluster aggregation Some platforms have 'cluster' topology and CPUs in the cluster will share resources like L3 Cache Tag (for HiSilicon Kunpeng SoC) or L2 cache (for Intel Jacobsville). Currently parsing and building cluster topology have been supported since [1]. perf stat has already supported aggregation for other topologies like die or socket, etc. It'll be useful to aggregate per-cluster to find problems like L3T bandwidth contention. This patch add support for "--per-cluster" option for per-cluster aggregation. Also update the docs and related test. The output will be like: [root@localhost tmp]# perf stat -a -e LLC-load --per-cluster -- sleep 5 Performance counter stats for 'system wide': S56-D0-CLS158 4 1,321,521,570 LLC-load S56-D0-CLS594 4 794,211,453 LLC-load S56-D0-CLS1030 4 41,623 LLC-load S56-D0-CLS1466 4 41,646 LLC-load S56-D0-CLS1902 4 16,863 LLC-load S56-D0-CLS2338 4 15,721 LLC-load S56-D0-CLS2774 4 22,671 LLC-load [...] On a legacy system without cluster or cluster support, the output will be look like: [root@localhost perf]# perf stat -a -e cycles --per-cluster -- sleep 1 Performance counter stats for 'system wide': S56-D0-CLS0 64 18,011,485 cycles S7182-D0-CLS0 64 16,548,835 cycles Note that this patch doesn't mix the cluster information in the outputs of --per-core to avoid breaking any tools/scripts using it. Note that perf recently supports "--per-cache" aggregation, but it's not the same with the cluster although cluster CPUs may share some cache resources. For example on my machine all clusters within a die share the same L3 cache: $ cat /sys/devices/system/cpu/cpu0/cache/index3/shared_cpu_list 0-31 $ cat /sys/devices/system/cpu/cpu0/topology/cluster_cpus_list 0-3 [1] commit c5e22feffdd7 ("topology: Represent clusters of CPUs within a die") Tested-by: Jie Zhan <zhanjie9@hisilicon.com> Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yicong Yang <yangyicong@hisilicon.com> Cc: james.clark@arm.com Cc: 21cnbao@gmail.com Cc: prime.zeng@hisilicon.com Cc: Jonathan.Cameron@huawei.com Cc: fanghao11@huawei.com Cc: linuxarm@huawei.com Cc: tim.c.chen@intel.com Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/r/20240208024026.2691-1-yangyicong@huawei.com
2024-02-08 10:40:26 +08:00
case AGGR_CLUSTER:
perf stat: Setup the foundation to allow aggregation based on cache topology Processors based on chiplet architecture, such as AMD EPYC and Hygon do not expose the chiplet details in the sysfs CPU topology information. However, this information can be derived from the per CPU cache level information from the sysfs. 'perf stat' has already supported aggregation based on topology information using core ID, socket ID, etc. It'll be useful to aggregate based on the cache topology to detect problems like imbalance and cache-to-cache sharing at various cache levels. This patch lays the foundation for aggregating data in 'perf stat' based on the processor's cache topology. The cmdline option to aggregate data based on the cache topology is added in Patch 4 of the series while this patch sets up all the necessary functions and variables required to support the new aggregation option. The patch also adds support to display per-cache aggregation, or save it as a JSON or CSV, as splitting it into a separate patch would break builds when compiling with "-Werror=switch-enum" where the compiler will complain about the lack of handling for the AGGR_CACHE case in the output functions. Committer notes: Don't use perf_stat_config in tools/perf/util/cpumap.c, this would make code that is in util/, thus not really specific to a single builtin, use a specific builtin config structure. Move the functions introduced in this patch from tools/perf/util/cpumap.c since it needs access to builtin specific and is not strictly needed to live in the util/ directory. With this 'perf test python' is back building. Suggested-by: Gautham Shenoy <gautham.shenoy@amd.com> Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ananth Narayan <ananth.narayan@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Wen Pu <puwen@hygon.cn> Link: https://lore.kernel.org/r/20230517172745.5833-3-kprateek.nayak@amd.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-17 22:57:42 +05:30
case AGGR_CACHE:
case AGGR_CORE:
perf stat: Fix uncore aggregation number Follow up: lore.kernel.org/CAP-5=fVDF4-qYL1Lm7efgiHk7X=_nw_nEFMBZFMcsnOOJgX4Kg@mail.gmail.com/ The patch adds unit aggregation during evsel merge the aggregated uncore counters. Change the name of the column to `ctrs` and `counters` for json mode. Tested on a 2-socket machine with SNC3, uncore_imc_[0-11] and cpumask="0,120" Before: perf stat -e clockticks -I 1000 --per-socket # time socket cpus counts unit events 1.001085024 S0 1 9615386315 clockticks 1.001085024 S1 1 9614287448 clockticks perf stat -e clockticks -I 1000 --per-node # time node cpus counts unit events 1.001029867 N0 1 3205726984 clockticks 1.001029867 N1 1 3205444421 clockticks 1.001029867 N2 1 3205234018 clockticks 1.001029867 N3 1 3205224660 clockticks 1.001029867 N4 1 3205207213 clockticks 1.001029867 N5 1 3205528246 clockticks After: perf stat -e clockticks -I 1000 --per-socket # time socket ctrs counts unit events 1.001026071 S0 12 9619677996 clockticks 1.001026071 S1 12 9618612614 clockticks perf stat -e clockticks -I 1000 --per-node # time node ctrs counts unit events 1.001027449 N0 4 3207251859 clockticks 1.001027449 N1 4 3207315930 clockticks 1.001027449 N2 4 3206981828 clockticks 1.001027449 N3 4 3206566126 clockticks 1.001027449 N4 4 3206032609 clockticks 1.001027449 N5 4 3205651355 clockticks Tested with JSON output linter: perf test "perf stat JSON output linter" 94: perf stat JSON output linter : Ok Suggested-by: Ian Rogers <irogers@google.com> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Chun-Tse Shao <ctshao@google.com> Link: https://lore.kernel.org/r/20250627201818.479421-1-ctshao@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2025-06-27 13:16:41 -07:00
fprintf(output, "#%*s %-*s ctrs",
INTERVAL_LEN - 1, "time",
aggr_header_lens[config->aggr_mode],
aggr_header_std[config->aggr_mode]);
break;
case AGGR_NONE:
fprintf(output, "#%*s %-*s",
INTERVAL_LEN - 1, "time",
aggr_header_lens[config->aggr_mode],
aggr_header_std[config->aggr_mode]);
break;
case AGGR_THREAD:
fprintf(output, "#%*s %*s-%-*s",
INTERVAL_LEN - 1, "time",
COMM_LEN, "comm", PID_LEN, "pid");
break;
case AGGR_GLOBAL:
default:
if (!config->iostat_run)
fprintf(output, "#%*s",
INTERVAL_LEN - 1, "time");
case AGGR_UNSET:
case AGGR_MAX:
break;
}
if (config->metric_only)
print_metric_headers(config, evlist, true);
else
fprintf(output, " %*s %*s events\n",
COUNTS_LEN, "counts", config->unit_width, "unit");
}
static void print_header_std(struct perf_stat_config *config,
struct target *_target, struct evlist *evlist,
int argc, const char **argv)
{
FILE *output = config->output;
int i;
fprintf(output, "\n");
fprintf(output, " Performance counter stats for ");
if (_target->bpf_str)
fprintf(output, "\'BPF program(s) %s", _target->bpf_str);
else if (_target->system_wide)
fprintf(output, "\'system wide");
else if (_target->cpu_list)
fprintf(output, "\'CPU(s) %s", _target->cpu_list);
else if (!target__has_task(_target)) {
fprintf(output, "\'%s", argv ? argv[0] : "pipe");
for (i = 1; argv && (i < argc); i++)
fprintf(output, " %s", argv[i]);
} else if (_target->pid)
fprintf(output, "process id \'%s", _target->pid);
else
fprintf(output, "thread id \'%s", _target->tid);
fprintf(output, "\'");
if (config->run_count > 1)
fprintf(output, " (%d runs)", config->run_count);
fprintf(output, ":\n\n");
if (config->metric_only)
print_metric_headers(config, evlist, false);
}
static void print_header_csv(struct perf_stat_config *config,
struct target *_target __maybe_unused,
struct evlist *evlist,
int argc __maybe_unused,
const char **argv __maybe_unused)
{
if (config->metric_only)
print_metric_headers(config, evlist, true);
}
static void print_header_json(struct perf_stat_config *config,
struct target *_target __maybe_unused,
struct evlist *evlist,
int argc __maybe_unused,
const char **argv __maybe_unused)
{
if (config->metric_only)
print_metric_headers(config, evlist, true);
}
static void print_header(struct perf_stat_config *config,
struct target *_target,
struct evlist *evlist,
int argc, const char **argv)
{
static int num_print_iv;
fflush(stdout);
if (config->interval_clear)
puts(CONSOLE_CLEAR);
if (num_print_iv == 0 || config->interval_clear) {
if (config->json_output)
print_header_json(config, _target, evlist, argc, argv);
else if (config->csv_output)
print_header_csv(config, _target, evlist, argc, argv);
else if (config->interval)
print_header_interval_std(config, _target, evlist, argc, argv);
else
print_header_std(config, _target, evlist, argc, argv);
}
if (num_print_iv++ == 25)
num_print_iv = 0;
}
static int get_precision(double num)
{
if (num > 1)
return 0;
return lround(ceil(-log10(num)));
}
static void print_table(struct perf_stat_config *config,
FILE *output, int precision, double avg)
{
char tmp[64];
int idx, indent = 0;
scnprintf(tmp, 64, " %17.*f", precision, avg);
while (tmp[indent] == ' ')
indent++;
fprintf(output, "%*s# Table of individual measurements:\n", indent, "");
for (idx = 0; idx < config->run_count; idx++) {
double run = (double) config->walltime_run[idx] / NSEC_PER_SEC;
int h, n = 1 + abs((int) (100.0 * (run - avg)/run) / 5);
fprintf(output, " %17.*f (%+.*f) ",
precision, run, precision, run - avg);
for (h = 0; h < n; h++)
fprintf(output, "#");
fprintf(output, "\n");
}
fprintf(output, "\n%*s# Final result:\n", indent, "");
}
static double timeval2double(struct timeval *t)
{
return t->tv_sec + (double) t->tv_usec/USEC_PER_SEC;
}
static void print_footer(struct perf_stat_config *config)
{
double avg = avg_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
FILE *output = config->output;
if (config->interval || config->csv_output || config->json_output)
return;
if (!config->null_run)
fprintf(output, "\n");
if (config->run_count == 1) {
fprintf(output, " %17.9f seconds time elapsed", avg);
if (config->ru_display) {
double ru_utime = timeval2double(&config->ru_data.ru_utime);
double ru_stime = timeval2double(&config->ru_data.ru_stime);
fprintf(output, "\n\n");
fprintf(output, " %17.9f seconds user\n", ru_utime);
fprintf(output, " %17.9f seconds sys\n", ru_stime);
}
} else {
double sd = stddev_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
/*
* Display at most 2 more significant
* digits than the stddev inaccuracy.
*/
int precision = get_precision(sd) + 2;
if (config->walltime_run_table)
print_table(config, output, precision, avg);
fprintf(output, " %17.*f +- %.*f seconds time elapsed",
precision, avg, precision, sd);
perf stat: Fix trailing comma when there is no metric unit Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-11-12 16:00:41 +00:00
print_noise_pct(config, NULL, sd, avg, /*before_metric=*/false);
}
fprintf(output, "\n\n");
if (config->print_free_counters_hint && sysctl__nmi_watchdog_enabled())
fprintf(output,
"Some events weren't counted. Try disabling the NMI watchdog:\n"
" echo 0 > /proc/sys/kernel/nmi_watchdog\n"
" perf stat ...\n"
" echo 1 > /proc/sys/kernel/nmi_watchdog\n");
}
perf stat: Support 'percore' event qualifier With this patch, we can use the 'percore' event qualifier in perf-stat. root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000 1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%) 1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%) 1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%) In this example, we count the event 'ref-cycles' per-core and per-CPU in one perf stat command-line. From the output, we can see: S0-C0 = CPU0 + CPU4 S0-C1 = CPU1 + CPU5 S0-C2 = CPU2 + CPU6 S0-C3 = CPU3 + CPU7 So the result is expected (tiny difference is ignored). Note that, the 'percore' event qualifier needs to use with option '-A'. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 21:59:49 +08:00
static void print_percore(struct perf_stat_config *config,
struct evsel *counter, struct outstate *os)
perf stat: Support 'percore' event qualifier With this patch, we can use the 'percore' event qualifier in perf-stat. root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000 1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%) 1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%) 1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%) In this example, we count the event 'ref-cycles' per-core and per-CPU in one perf stat command-line. From the output, we can see: S0-C0 = CPU0 + CPU4 S0-C1 = CPU1 + CPU5 S0-C2 = CPU2 + CPU6 S0-C3 = CPU3 + CPU7 So the result is expected (tiny difference is ignored). Note that, the 'percore' event qualifier needs to use with option '-A'. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 21:59:49 +08:00
{
bool metric_only = config->metric_only;
FILE *output = config->output;
struct cpu_aggr_map *core_map;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
int aggr_idx, core_map_len = 0;
perf stat: Support 'percore' event qualifier With this patch, we can use the 'percore' event qualifier in perf-stat. root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000 1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%) 1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%) 1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%) In this example, we count the event 'ref-cycles' per-core and per-CPU in one perf stat command-line. From the output, we can see: S0-C0 = CPU0 + CPU4 S0-C1 = CPU1 + CPU5 S0-C2 = CPU2 + CPU6 S0-C3 = CPU3 + CPU7 So the result is expected (tiny difference is ignored). Note that, the 'percore' event qualifier needs to use with option '-A'. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 21:59:49 +08:00
if (!config->aggr_map || !config->aggr_get_id)
perf stat: Support 'percore' event qualifier With this patch, we can use the 'percore' event qualifier in perf-stat. root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000 1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%) 1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%) 1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%) In this example, we count the event 'ref-cycles' per-core and per-CPU in one perf stat command-line. From the output, we can see: S0-C0 = CPU0 + CPU4 S0-C1 = CPU1 + CPU5 S0-C2 = CPU2 + CPU6 S0-C3 = CPU3 + CPU7 So the result is expected (tiny difference is ignored). Note that, the 'percore' event qualifier needs to use with option '-A'. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 21:59:49 +08:00
return;
perf stat: Show percore counts in per CPU output We have supported the event modifier "percore" which sums up the event counts for all hardware threads in a core and show the counts per core. For example, # perf stat -e cpu/event=cpu-cycles,percore/ -a -A -- sleep 1 Performance counter stats for 'system wide': S0-D0-C0 395,072 cpu/event=cpu-cycles,percore/ S0-D0-C1 851,248 cpu/event=cpu-cycles,percore/ S0-D0-C2 954,226 cpu/event=cpu-cycles,percore/ S0-D0-C3 1,233,659 cpu/event=cpu-cycles,percore/ This patch provides a new option "--percore-show-thread". It is used with event modifier "percore" together to sum up the event counts for all hardware threads in a core but show the counts per hardware thread. This is essentially a replacement for the any bit (which is gone in Icelake). Per core counts are useful for some formulas, e.g. CoreIPC. The original percore version was inconvenient to post process. This variant matches the output of the any bit. With this patch, for example, # perf stat -e cpu/event=cpu-cycles,percore/ -a -A --percore-show-thread -- sleep 1 Performance counter stats for 'system wide': CPU0 2,453,061 cpu/event=cpu-cycles,percore/ CPU1 1,823,921 cpu/event=cpu-cycles,percore/ CPU2 1,383,166 cpu/event=cpu-cycles,percore/ CPU3 1,102,652 cpu/event=cpu-cycles,percore/ CPU4 2,453,061 cpu/event=cpu-cycles,percore/ CPU5 1,823,921 cpu/event=cpu-cycles,percore/ CPU6 1,383,166 cpu/event=cpu-cycles,percore/ CPU7 1,102,652 cpu/event=cpu-cycles,percore/ We can see counts are duplicated in CPU pairs (CPU0/CPU4, CPU1/CPU5, CPU2/CPU6, CPU3/CPU7). The interval mode also works. For example, # perf stat -e cpu/event=cpu-cycles,percore/ -a -A --percore-show-thread -I 1000 # time CPU counts unit events 1.000425421 CPU0 925,032 cpu/event=cpu-cycles,percore/ 1.000425421 CPU1 430,202 cpu/event=cpu-cycles,percore/ 1.000425421 CPU2 436,843 cpu/event=cpu-cycles,percore/ 1.000425421 CPU3 1,192,504 cpu/event=cpu-cycles,percore/ 1.000425421 CPU4 925,032 cpu/event=cpu-cycles,percore/ 1.000425421 CPU5 430,202 cpu/event=cpu-cycles,percore/ 1.000425421 CPU6 436,843 cpu/event=cpu-cycles,percore/ 1.000425421 CPU7 1,192,504 cpu/event=cpu-cycles,percore/ If we offline CPU5, the result is: # perf stat -e cpu/event=cpu-cycles,percore/ -a -A --percore-show-thread -- sleep 1 Performance counter stats for 'system wide': CPU0 2,752,148 cpu/event=cpu-cycles,percore/ CPU1 1,009,312 cpu/event=cpu-cycles,percore/ CPU2 2,784,072 cpu/event=cpu-cycles,percore/ CPU3 2,427,922 cpu/event=cpu-cycles,percore/ CPU4 2,752,148 cpu/event=cpu-cycles,percore/ CPU6 2,784,072 cpu/event=cpu-cycles,percore/ CPU7 2,427,922 cpu/event=cpu-cycles,percore/ 1.001416041 seconds time elapsed v4: --- Ravi Bangoria reports an issue in v3. Once we offline a CPU, the output is not correct. The issue is we should use the cpu idx in print_percore_thread rather than using the cpu value. v3: --- 1. Fix the interval mode output error 2. Use cpu value (not cpu index) in config->aggr_get_id(). 3. Refine the code according to Jiri's comments. v2: --- Add the explanation in change log. This is essentially a replacement for the any bit. No code change. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20200214080452.26402-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-14 16:04:52 +08:00
if (config->percore_show_thread)
return print_counter(config, counter, os);
perf stat: Show percore counts in per CPU output We have supported the event modifier "percore" which sums up the event counts for all hardware threads in a core and show the counts per core. For example, # perf stat -e cpu/event=cpu-cycles,percore/ -a -A -- sleep 1 Performance counter stats for 'system wide': S0-D0-C0 395,072 cpu/event=cpu-cycles,percore/ S0-D0-C1 851,248 cpu/event=cpu-cycles,percore/ S0-D0-C2 954,226 cpu/event=cpu-cycles,percore/ S0-D0-C3 1,233,659 cpu/event=cpu-cycles,percore/ This patch provides a new option "--percore-show-thread". It is used with event modifier "percore" together to sum up the event counts for all hardware threads in a core but show the counts per hardware thread. This is essentially a replacement for the any bit (which is gone in Icelake). Per core counts are useful for some formulas, e.g. CoreIPC. The original percore version was inconvenient to post process. This variant matches the output of the any bit. With this patch, for example, # perf stat -e cpu/event=cpu-cycles,percore/ -a -A --percore-show-thread -- sleep 1 Performance counter stats for 'system wide': CPU0 2,453,061 cpu/event=cpu-cycles,percore/ CPU1 1,823,921 cpu/event=cpu-cycles,percore/ CPU2 1,383,166 cpu/event=cpu-cycles,percore/ CPU3 1,102,652 cpu/event=cpu-cycles,percore/ CPU4 2,453,061 cpu/event=cpu-cycles,percore/ CPU5 1,823,921 cpu/event=cpu-cycles,percore/ CPU6 1,383,166 cpu/event=cpu-cycles,percore/ CPU7 1,102,652 cpu/event=cpu-cycles,percore/ We can see counts are duplicated in CPU pairs (CPU0/CPU4, CPU1/CPU5, CPU2/CPU6, CPU3/CPU7). The interval mode also works. For example, # perf stat -e cpu/event=cpu-cycles,percore/ -a -A --percore-show-thread -I 1000 # time CPU counts unit events 1.000425421 CPU0 925,032 cpu/event=cpu-cycles,percore/ 1.000425421 CPU1 430,202 cpu/event=cpu-cycles,percore/ 1.000425421 CPU2 436,843 cpu/event=cpu-cycles,percore/ 1.000425421 CPU3 1,192,504 cpu/event=cpu-cycles,percore/ 1.000425421 CPU4 925,032 cpu/event=cpu-cycles,percore/ 1.000425421 CPU5 430,202 cpu/event=cpu-cycles,percore/ 1.000425421 CPU6 436,843 cpu/event=cpu-cycles,percore/ 1.000425421 CPU7 1,192,504 cpu/event=cpu-cycles,percore/ If we offline CPU5, the result is: # perf stat -e cpu/event=cpu-cycles,percore/ -a -A --percore-show-thread -- sleep 1 Performance counter stats for 'system wide': CPU0 2,752,148 cpu/event=cpu-cycles,percore/ CPU1 1,009,312 cpu/event=cpu-cycles,percore/ CPU2 2,784,072 cpu/event=cpu-cycles,percore/ CPU3 2,427,922 cpu/event=cpu-cycles,percore/ CPU4 2,752,148 cpu/event=cpu-cycles,percore/ CPU6 2,784,072 cpu/event=cpu-cycles,percore/ CPU7 2,427,922 cpu/event=cpu-cycles,percore/ 1.001416041 seconds time elapsed v4: --- Ravi Bangoria reports an issue in v3. Once we offline a CPU, the output is not correct. The issue is we should use the cpu idx in print_percore_thread rather than using the cpu value. v3: --- 1. Fix the interval mode output error 2. Use cpu value (not cpu index) in config->aggr_get_id(). 3. Refine the code according to Jiri's comments. v2: --- Add the explanation in change log. This is essentially a replacement for the any bit. No code change. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20200214080452.26402-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-14 16:04:52 +08:00
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
/*
* core_map will hold the aggr_cpu_id for the cores that have been
* printed so that each core is printed just once.
*/
core_map = cpu_aggr_map__empty_new(config->aggr_map->nr);
if (core_map == NULL) {
fprintf(output, "Cannot allocate per-core aggr map for display\n");
return;
}
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) {
struct perf_cpu curr_cpu = config->aggr_map->map[aggr_idx].cpu;
struct aggr_cpu_id core_id = aggr_cpu_id__core(curr_cpu, NULL);
bool found = false;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
for (int i = 0; i < core_map_len; i++) {
if (aggr_cpu_id__equal(&core_map->map[i], &core_id)) {
found = true;
break;
}
}
if (found)
continue;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
print_counter_aggrdata(config, counter, aggr_idx, os);
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 01:28:45 -08:00
core_map->map[core_map_len++] = core_id;
perf stat: Support 'percore' event qualifier With this patch, we can use the 'percore' event qualifier in perf-stat. root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000 1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%) 1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%) 1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%) In this example, we count the event 'ref-cycles' per-core and per-CPU in one perf stat command-line. From the output, we can see: S0-C0 = CPU0 + CPU4 S0-C1 = CPU1 + CPU5 S0-C2 = CPU2 + CPU6 S0-C3 = CPU3 + CPU7 So the result is expected (tiny difference is ignored). Note that, the 'percore' event qualifier needs to use with option '-A'. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 21:59:49 +08:00
}
free(core_map);
perf stat: Support 'percore' event qualifier With this patch, we can use the 'percore' event qualifier in perf-stat. root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000 1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%) 1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%) 1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%) In this example, we count the event 'ref-cycles' per-core and per-CPU in one perf stat command-line. From the output, we can see: S0-C0 = CPU0 + CPU4 S0-C1 = CPU1 + CPU5 S0-C2 = CPU2 + CPU6 S0-C3 = CPU3 + CPU7 So the result is expected (tiny difference is ignored). Note that, the 'percore' event qualifier needs to use with option '-A'. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 21:59:49 +08:00
if (metric_only)
fputc('\n', output);
}
static void print_cgroup_counter(struct perf_stat_config *config, struct evlist *evlist,
struct outstate *os)
{
struct evsel *counter;
evlist__for_each_entry(evlist, counter) {
if (os->cgrp != counter->cgrp) {
if (os->cgrp != NULL)
print_metric_end(config, os);
os->cgrp = counter->cgrp;
print_metric_begin(config, evlist, os, /*aggr_idx=*/0);
}
print_counter(config, counter, os);
}
if (os->cgrp)
print_metric_end(config, os);
}
void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config,
struct target *_target, struct timespec *ts,
int argc, const char **argv)
{
bool metric_only = config->metric_only;
struct evsel *counter;
struct outstate os = {
.fh = config->output,
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 10:02:06 -08:00
.first = true,
};
perf evlist: Make uniquifying counter names consistent 'perf stat' has different uniquification logic to 'perf record' and perf top. In the case of perf record and 'perf top' all hybrid event names are uniquified. 'perf stat' is more disciplined respecting name config terms, libpfm4 events, etc. 'perf stat' will uniquify hybrid events and the non-core PMU cases shouldn't apply to perf record or 'perf top'. For consistency, remove the uniquification for 'perf record' and 'perf top' and reuse the 'perf stat' uniquification, making the code more globally visible for this. Fix the detection of cross-PMU for disabling uniquify by correctly setting last_pmu. When setting uniquify on an evsel, make sure the PMUs between the 2 considered events differ otherwise the uniquify isn't adding value. Signed-off-by: Ian Rogers <irogers@google.com> Tested-by: Chun-Tse Shao <ctshao@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Dr. David Alan Gilbert <linux@treblig.org> Cc: Howard Chu <howardchu95@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@linaro.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Levi Yun <yeoreum.yun@arm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Weilin Wang <weilin.wang@intel.com> Link: https://lore.kernel.org/r/20250513215401.2315949-2-ctshao@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2025-05-13 14:45:01 -07:00
evlist__uniquify_evsel_names(evlist, config);
perf stat: Uniquify event name improvements Without aggregation on Intel: ``` $ perf stat -e instructions,cycles ... ``` Will use "cycles" for the name of the legacy cycles event but as "instructions" has a sysfs name it will and a "[cpu]" PMU suffix. This often breaks things as the space between the event and the PMU name look like an extra column. The existing uniquify logic was also uniquifying in cases when all events are core and not with uncore events, it was not correctly handling modifiers, etc. Change the logic so that an initial pass that can disable uniquification is run. For individual counters, disable uniquification in more cases such as for consistency with legacy events or for libpfm4 events. Don't use the "[pmu]" style suffix in uniquification, always use "pmu/.../". Change how modifiers/terms are handled in the uniquification so that they look like parse-able events. This fixes "102: perf stat metrics (shadow stat) test:" that has been failing due to "instructions [cpu]" breaking its column/awk logic when values aren't aggregated. This started happening when instructions could match a sysfs rather than a legacy event, so the fixes tag reflects this. Fixes: 617824a7f0f7 ("perf parse-events: Prefer sysfs/JSON hardware events over legacy") Acked-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Ian Rogers <irogers@google.com> [ Fix Intel TPEBS counting mode test ] Acked-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: James Clark <james.clark@linaro.org> Cc: Yang Jihong <yangjihong@bytedance.com> Cc: Dominique Martinet <asmadeus@codewreck.org> Cc: Colin Ian King <colin.i.king@gmail.com> Cc: Howard Chu <howardchu95@gmail.com> Cc: Ze Gao <zegao2021@gmail.com> Cc: Yicong Yang <yangyicong@hisilicon.com> Cc: Weilin Wang <weilin.wang@intel.com> Cc: Will Deacon <will@kernel.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Yang Li <yang.lee@linux.alibaba.com> Cc: Leo Yan <leo.yan@linux.dev> Cc: ak@linux.intel.com Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: linux-arm-kernel@lists.infradead.org Cc: Sun Haiyong <sunhaiyong@loongson.cn> Cc: John Garry <john.g.garry@oracle.com> Link: https://lore.kernel.org/r/20240926144851.245903-3-james.clark@linaro.org Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-09-26 15:48:33 +01:00
if (config->iostat_run)
evlist->selected = evlist__first(evlist);
if (config->interval)
prepare_timestamp(config, &os, ts);
print_header(config, _target, evlist, argc, argv);
switch (config->aggr_mode) {
case AGGR_CORE:
perf stat: Setup the foundation to allow aggregation based on cache topology Processors based on chiplet architecture, such as AMD EPYC and Hygon do not expose the chiplet details in the sysfs CPU topology information. However, this information can be derived from the per CPU cache level information from the sysfs. 'perf stat' has already supported aggregation based on topology information using core ID, socket ID, etc. It'll be useful to aggregate based on the cache topology to detect problems like imbalance and cache-to-cache sharing at various cache levels. This patch lays the foundation for aggregating data in 'perf stat' based on the processor's cache topology. The cmdline option to aggregate data based on the cache topology is added in Patch 4 of the series while this patch sets up all the necessary functions and variables required to support the new aggregation option. The patch also adds support to display per-cache aggregation, or save it as a JSON or CSV, as splitting it into a separate patch would break builds when compiling with "-Werror=switch-enum" where the compiler will complain about the lack of handling for the AGGR_CACHE case in the output functions. Committer notes: Don't use perf_stat_config in tools/perf/util/cpumap.c, this would make code that is in util/, thus not really specific to a single builtin, use a specific builtin config structure. Move the functions introduced in this patch from tools/perf/util/cpumap.c since it needs access to builtin specific and is not strictly needed to live in the util/ directory. With this 'perf test python' is back building. Suggested-by: Gautham Shenoy <gautham.shenoy@amd.com> Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ananth Narayan <ananth.narayan@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Wen Pu <puwen@hygon.cn> Link: https://lore.kernel.org/r/20230517172745.5833-3-kprateek.nayak@amd.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-17 22:57:42 +05:30
case AGGR_CACHE:
perf stat: Support per-cluster aggregation Some platforms have 'cluster' topology and CPUs in the cluster will share resources like L3 Cache Tag (for HiSilicon Kunpeng SoC) or L2 cache (for Intel Jacobsville). Currently parsing and building cluster topology have been supported since [1]. perf stat has already supported aggregation for other topologies like die or socket, etc. It'll be useful to aggregate per-cluster to find problems like L3T bandwidth contention. This patch add support for "--per-cluster" option for per-cluster aggregation. Also update the docs and related test. The output will be like: [root@localhost tmp]# perf stat -a -e LLC-load --per-cluster -- sleep 5 Performance counter stats for 'system wide': S56-D0-CLS158 4 1,321,521,570 LLC-load S56-D0-CLS594 4 794,211,453 LLC-load S56-D0-CLS1030 4 41,623 LLC-load S56-D0-CLS1466 4 41,646 LLC-load S56-D0-CLS1902 4 16,863 LLC-load S56-D0-CLS2338 4 15,721 LLC-load S56-D0-CLS2774 4 22,671 LLC-load [...] On a legacy system without cluster or cluster support, the output will be look like: [root@localhost perf]# perf stat -a -e cycles --per-cluster -- sleep 1 Performance counter stats for 'system wide': S56-D0-CLS0 64 18,011,485 cycles S7182-D0-CLS0 64 16,548,835 cycles Note that this patch doesn't mix the cluster information in the outputs of --per-core to avoid breaking any tools/scripts using it. Note that perf recently supports "--per-cache" aggregation, but it's not the same with the cluster although cluster CPUs may share some cache resources. For example on my machine all clusters within a die share the same L3 cache: $ cat /sys/devices/system/cpu/cpu0/cache/index3/shared_cpu_list 0-31 $ cat /sys/devices/system/cpu/cpu0/topology/cluster_cpus_list 0-3 [1] commit c5e22feffdd7 ("topology: Represent clusters of CPUs within a die") Tested-by: Jie Zhan <zhanjie9@hisilicon.com> Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yicong Yang <yangyicong@hisilicon.com> Cc: james.clark@arm.com Cc: 21cnbao@gmail.com Cc: prime.zeng@hisilicon.com Cc: Jonathan.Cameron@huawei.com Cc: fanghao11@huawei.com Cc: linuxarm@huawei.com Cc: tim.c.chen@intel.com Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/r/20240208024026.2691-1-yangyicong@huawei.com
2024-02-08 10:40:26 +08:00
case AGGR_CLUSTER:
case AGGR_DIE:
case AGGR_SOCKET:
perf stat: Add --per-node agregation support Adding new --per-node option to aggregate counts per NUMA nodes for system-wide mode measurements. You can specify --per-node in live mode: # perf stat -a -I 1000 -e cycles --per-node # time node cpus counts unit events 1.000542550 N0 20 6,202,097 cycles 1.000542550 N1 20 639,559 cycles 2.002040063 N0 20 7,412,495 cycles 2.002040063 N1 20 2,185,577 cycles 3.003451699 N0 20 6,508,917 cycles 3.003451699 N1 20 765,607 cycles ... Or in the record/report stat session: # perf stat record -a -I 1000 -e cycles # time counts unit events 1.000536937 10,008,468 cycles 2.002090152 9,578,539 cycles 3.003625233 7,647,869 cycles 4.005135036 7,032,086 cycles ^C 4.340902364 3,923,893 cycles # perf stat report --per-node # time node cpus counts unit events 1.000536937 N0 20 9,355,086 cycles 1.000536937 N1 20 653,382 cycles 2.002090152 N0 20 7,712,838 cycles 2.002090152 N1 20 1,865,701 cycles 3.003625233 N0 20 6,604,441 cycles 3.003625233 N1 20 1,043,428 cycles 4.005135036 N0 20 6,350,522 cycles 4.005135036 N1 20 681,564 cycles 4.340902364 N0 20 3,403,188 cycles 4.340902364 N1 20 520,705 cycles Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexey Budankov <alexey.budankov@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Joe Mario <jmario@redhat.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20190904073415.723-4-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-08-28 10:17:43 +02:00
case AGGR_NODE:
perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown Normally, --for-each-cgroup only works with AGGR_GLOBAL. However the --topdown on some cpu (e.g. Intel Skylake) converts it to the AGGR_CORE internally. To support those machines, add print_aggr_cgroup and handle the events like in print_cgroup_events(). $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1 nmi_watchdog enabled with topdown. May give wrong results. Disable with echo 0 > /proc/sys/kernel/nmi_watchdog Performance counter stats for 'system wide': retiring bad speculation frontend bound backend bound S0-D0-C0 2 system.slice 49.0% -46.6% 31.4% S0-D0-C1 2 system.slice 55.5% 8.0% 45.5% -9.0% S0-D0-C2 2 system.slice 87.8% 22.1% 30.3% -40.3% S0-D0-C3 2 system.slice 53.3% -11.9% 45.2% 13.4% S0-D0-C0 2 user.slice 123.5% 4.0% 48.5% -75.9% S0-D0-C1 2 user.slice 19.9% 6.5% 89.9% -16.3% S0-D0-C2 2 user.slice 29.9% 7.9% 71.3% -9.1 S0-D0-C3 2 user.slice 28.0% 7.2% 43.3% 21.5% 1.004136937 seconds time elapsed Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-14 15:02:27 -08:00
if (config->cgroup_list)
print_aggr_cgroup(config, evlist, &os);
perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown Normally, --for-each-cgroup only works with AGGR_GLOBAL. However the --topdown on some cpu (e.g. Intel Skylake) converts it to the AGGR_CORE internally. To support those machines, add print_aggr_cgroup and handle the events like in print_cgroup_events(). $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1 nmi_watchdog enabled with topdown. May give wrong results. Disable with echo 0 > /proc/sys/kernel/nmi_watchdog Performance counter stats for 'system wide': retiring bad speculation frontend bound backend bound S0-D0-C0 2 system.slice 49.0% -46.6% 31.4% S0-D0-C1 2 system.slice 55.5% 8.0% 45.5% -9.0% S0-D0-C2 2 system.slice 87.8% 22.1% 30.3% -40.3% S0-D0-C3 2 system.slice 53.3% -11.9% 45.2% 13.4% S0-D0-C0 2 user.slice 123.5% 4.0% 48.5% -75.9% S0-D0-C1 2 user.slice 19.9% 6.5% 89.9% -16.3% S0-D0-C2 2 user.slice 29.9% 7.9% 71.3% -9.1 S0-D0-C3 2 user.slice 28.0% 7.2% 43.3% 21.5% 1.004136937 seconds time elapsed Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-14 15:02:27 -08:00
else
print_aggr(config, evlist, &os);
break;
case AGGR_THREAD:
case AGGR_GLOBAL:
if (config->iostat_run) {
iostat_print_counters(evlist, config, ts, os.timestamp,
(iostat_print_counter_t)print_counter, &os);
} else if (config->cgroup_list) {
print_cgroup_counter(config, evlist, &os);
} else {
print_metric_begin(config, evlist, &os, /*aggr_idx=*/0);
evlist__for_each_entry(evlist, counter) {
print_counter(config, counter, &os);
}
print_metric_end(config, &os);
}
break;
case AGGR_NONE:
if (metric_only)
print_no_aggr_metric(config, evlist, &os);
else {
evlist__for_each_entry(evlist, counter) {
perf stat: Support 'percore' event qualifier With this patch, we can use the 'percore' event qualifier in perf-stat. root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000 1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%) 1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%) 1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%) In this example, we count the event 'ref-cycles' per-core and per-CPU in one perf stat command-line. From the output, we can see: S0-C0 = CPU0 + CPU4 S0-C1 = CPU1 + CPU5 S0-C2 = CPU2 + CPU6 S0-C3 = CPU3 + CPU7 So the result is expected (tiny difference is ignored). Note that, the 'percore' event qualifier needs to use with option '-A'. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 21:59:49 +08:00
if (counter->percore)
print_percore(config, counter, &os);
perf stat: Support 'percore' event qualifier With this patch, we can use the 'percore' event qualifier in perf-stat. root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000 1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%) 1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%) 1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%) In this example, we count the event 'ref-cycles' per-core and per-CPU in one perf stat command-line. From the output, we can see: S0-C0 = CPU0 + CPU4 S0-C1 = CPU1 + CPU5 S0-C2 = CPU2 + CPU6 S0-C3 = CPU3 + CPU7 So the result is expected (tiny difference is ignored). Note that, the 'percore' event qualifier needs to use with option '-A'. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 21:59:49 +08:00
else
print_counter(config, counter, &os);
}
}
break;
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
case AGGR_MAX:
case AGGR_UNSET:
default:
break;
}
print_footer(config);
fflush(config->output);
}