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

1525 lines
38 KiB
C
Raw 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"
#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"
#include "pmu-hybrid.h"
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
#include "evlist-hybrid.h"
#define CNTR_NOT_SUPPORTED "<not supported>"
#define CNTR_NOT_COUNTED "<not counted>"
static void print_running(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;
if (config->json_output)
fprintf(config->output,
"\"event-runtime\" : %" PRIu64 ", \"pcnt-running\" : %.2f, ",
run, enabled_percent);
else if (config->csv_output)
fprintf(config->output,
"%s%" PRIu64 "%s%.2f", config->csv_sep,
run, config->csv_sep, enabled_percent);
else if (run != ena)
fprintf(config->output, " (%.2f%%)", 100.0 * run / ena);
}
static void print_noise_pct(struct perf_stat_config *config,
double total, double avg)
{
double pct = rel_stddev_stats(total, avg);
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)
fprintf(config->output, "\"variance\" : %.2f, ", pct);
else if (config->csv_output)
fprintf(config->output, "%s%.2f%%", config->csv_sep, pct);
else if (pct)
fprintf(config->output, " ( +-%6.2f%% )", pct);
}
static void print_noise(struct perf_stat_config *config,
struct evsel *evsel, double avg)
{
struct perf_stat_evsel *ps;
if (config->run_count == 1)
return;
ps = evsel->stats;
print_noise_pct(config, stddev_stats(&ps->res_stats[0]), avg);
}
static void print_cgroup(struct perf_stat_config *config, struct evsel *evsel)
{
if (nr_cgroups) {
const char *cgrp_name = evsel->cgrp ? evsel->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)
fprintf(config->output, "\"cgroup\" : \"%s\", ", cgrp_name);
else
fprintf(config->output, "%s%s", config->csv_sep, cgrp_name);
}
}
static void aggr_printout(struct perf_stat_config *config,
struct evsel *evsel, struct aggr_cpu_id id, int 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
if (config->json_output && !config->interval)
fprintf(config->output, "{");
switch (config->aggr_mode) {
case AGGR_CORE:
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) {
fprintf(config->output,
"\"core\" : \"S%d-D%d-C%d\", \"aggregate-number\" : %d, ",
id.socket,
id.die,
id.core,
nr);
} else {
fprintf(config->output, "S%d-D%d-C%*d%s%*d%s",
id.socket,
id.die,
config->csv_output ? 0 : -8,
id.core,
config->csv_sep,
config->csv_output ? 0 : 4,
nr,
config->csv_sep);
}
break;
case AGGR_DIE:
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) {
fprintf(config->output,
"\"die\" : \"S%d-D%d\", \"aggregate-number\" : %d, ",
id.socket,
id.die,
nr);
} else {
fprintf(config->output, "S%d-D%*d%s%*d%s",
id.socket,
config->csv_output ? 0 : -8,
id.die,
config->csv_sep,
config->csv_output ? 0 : 4,
nr,
config->csv_sep);
}
break;
case AGGR_SOCKET:
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) {
fprintf(config->output,
"\"socket\" : \"S%d\", \"aggregate-number\" : %d, ",
id.socket,
nr);
} else {
fprintf(config->output, "S%*d%s%*d%s",
config->csv_output ? 0 : -5,
id.socket,
config->csv_sep,
config->csv_output ? 0 : 4,
nr,
config->csv_sep);
}
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:
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) {
fprintf(config->output, "\"node\" : \"N%d\", \"aggregate-number\" : %d, ",
id.node,
nr);
} else {
fprintf(config->output, "N%*d%s%*d%s",
config->csv_output ? 0 : -5,
id.node,
config->csv_sep,
config->csv_output ? 0 : 4,
nr,
config->csv_sep);
}
break;
case AGGR_NONE:
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) {
if (evsel->percore && !config->percore_show_thread) {
fprintf(config->output, "\"core\" : \"S%d-D%d-C%d\"",
id.socket,
id.die,
id.core);
} else if (id.core > -1) {
fprintf(config->output, "\"cpu\" : \"%d\", ",
id.cpu.cpu);
}
} else {
if (evsel->percore && !config->percore_show_thread) {
fprintf(config->output, "S%d-D%d-C%*d%s",
id.socket,
id.die,
config->csv_output ? 0 : -3,
id.core, config->csv_sep);
} else if (id.core > -1) {
fprintf(config->output, "CPU%*d%s",
config->csv_output ? 0 : -7,
id.cpu.cpu, config->csv_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:
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) {
fprintf(config->output, "\"thread\" : \"%s-%d\", ",
perf_thread_map__comm(evsel->core.threads, id.thread),
perf_thread_map__pid(evsel->core.threads, id.thread));
} else {
fprintf(config->output, "%*s-%*d%s",
config->csv_output ? 0 : 16,
perf_thread_map__comm(evsel->core.threads, id.thread),
config->csv_output ? 0 : -8,
perf_thread_map__pid(evsel->core.threads, id.thread),
config->csv_sep);
}
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;
}
}
struct outstate {
FILE *fh;
bool newline;
const char *prefix;
int nfields;
int nr;
struct aggr_cpu_id id;
struct evsel *evsel;
};
#define METRIC_LEN 35
static void new_line_std(struct perf_stat_config *config __maybe_unused,
void *ctx)
{
struct outstate *os = ctx;
os->newline = true;
}
static void do_new_line_std(struct perf_stat_config *config,
struct outstate *os)
{
fputc('\n', os->fh);
fputs(os->prefix, os->fh);
aggr_printout(config, os->evsel, os->id, os->nr);
if (config->aggr_mode == AGGR_NONE)
fprintf(os->fh, " ");
fprintf(os->fh, " ");
}
static void print_metric_std(struct perf_stat_config *config,
void *ctx, const char *color, const char *fmt,
const char *unit, double val)
{
struct outstate *os = ctx;
FILE *out = os->fh;
int n;
bool newline = os->newline;
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;
fputc('\n', os->fh);
if (os->prefix)
fprintf(os->fh, "%s%s", os->prefix, config->csv_sep);
aggr_printout(config, os->evsel, os->id, os->nr);
for (i = 0; i < os->nfields; i++)
fputs(config->csv_sep, os->fh);
}
static void print_metric_csv(struct perf_stat_config *config __maybe_unused,
void *ctx,
const char *color __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,
const char *color __maybe_unused,
const char *fmt __maybe_unused,
const char *unit, double val)
{
struct outstate *os = ctx;
FILE *out = os->fh;
fprintf(out, "\"metric-value\" : %f, ", val);
fprintf(out, "\"metric-unit\" : \"%s\"", unit);
if (!config->metric_only)
fprintf(out, "}");
}
static void new_line_json(struct perf_stat_config *config, void *ctx)
{
struct outstate *os = ctx;
fputc('\n', os->fh);
if (os->prefix)
fprintf(os->fh, "%s", os->prefix);
aggr_printout(config, os->evsel, os->id, os->nr);
}
/* 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, const char *color, 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;
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);
}
static void print_metric_only_csv(struct perf_stat_config *config __maybe_unused,
void *ctx, const char *color __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: 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, const char *color __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, "{\"metric-value\" : \"%s\"}", vals);
}
static void new_line_metric(struct perf_stat_config *config __maybe_unused,
void *ctx __maybe_unused)
{
}
static void print_metric_header(struct perf_stat_config *config,
void *ctx, const char *color __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;
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) && !config->json_output)
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)
fprintf(os->fh, "\"unit\" : \"%s\"", unit);
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 int first_shadow_cpu_map_idx(struct perf_stat_config *config,
struct evsel *evsel, const struct aggr_cpu_id *id)
{
struct perf_cpu_map *cpus = evsel__cpus(evsel);
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
struct perf_cpu cpu;
int idx;
if (config->aggr_mode == AGGR_NONE)
return perf_cpu_map__idx(cpus, id->cpu);
perf stat: Use proper cpu for shadow stats Currently perf stat shows some metrics (like IPC) for defined events. But when no aggregation mode is used (-A option), it shows incorrect values since it used a value from a different cpu. Before: $ perf stat -aA -e cycles,instructions sleep 1 Performance counter stats for 'system wide': CPU0 116,057,380 cycles CPU1 86,084,722 cycles CPU2 99,423,125 cycles CPU3 98,272,994 cycles CPU0 53,369,217 instructions # 0.46 insn per cycle CPU1 33,378,058 instructions # 0.29 insn per cycle CPU2 58,150,086 instructions # 0.50 insn per cycle CPU3 40,029,703 instructions # 0.34 insn per cycle 1.001816971 seconds time elapsed So the IPC for CPU1 should be 0.38 (= 33,378,058 / 86,084,722) but it was 0.29 (= 33,378,058 / 116,057,380) and so on. After: $ perf stat -aA -e cycles,instructions sleep 1 Performance counter stats for 'system wide': CPU0 109,621,384 cycles CPU1 159,026,454 cycles CPU2 99,460,366 cycles CPU3 124,144,142 cycles CPU0 44,396,706 instructions # 0.41 insn per cycle CPU1 120,195,425 instructions # 0.76 insn per cycle CPU2 44,763,978 instructions # 0.45 insn per cycle CPU3 69,049,079 instructions # 0.56 insn per cycle 1.001910444 seconds time elapsed Fixes: 44d49a600259 ("perf stat: Support metrics in --per-core/socket mode") Reported-by: Sam Xi <xyzsam@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Reviewed-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lore.kernel.org/lkml/20201127041404.390276-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-11-27 13:14:03 +09:00
if (!config->aggr_get_id)
return 0;
perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
struct aggr_cpu_id cpu_id = config->aggr_get_id(config, cpu);
if (aggr_cpu_id__equal(&cpu_id, id))
return idx;
}
return 0;
}
static void abs_printout(struct perf_stat_config *config,
struct aggr_cpu_id id, int nr, struct evsel *evsel, double avg)
{
FILE *output = config->output;
double sc = evsel->scale;
const char *fmt;
if (config->csv_output) {
fmt = floor(sc) != sc ? "%.2f%s" : "%.0f%s";
} else {
if (config->big_num)
fmt = floor(sc) != sc ? "%'18.2f%s" : "%'18.0f%s";
else
fmt = floor(sc) != sc ? "%18.2f%s" : "%18.0f%s";
}
aggr_printout(config, evsel, id, 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
if (config->json_output)
fprintf(output, "\"counter-value\" : \"%f\", ", avg);
else
fprintf(output, fmt, avg, 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
if (config->json_output) {
if (evsel->unit) {
fprintf(output, "\"unit\" : \"%s\", ",
evsel->unit);
}
} else {
if (evsel->unit)
fprintf(output, "%-*s%s",
config->csv_output ? 0 : config->unit_width,
evsel->unit, 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
if (config->json_output)
fprintf(output, "\"event\" : \"%s\", ", evsel__name(evsel));
else
fprintf(output, "%-*s", config->csv_output ? 0 : 32, evsel__name(evsel));
print_cgroup(config, evsel);
}
static bool is_mixed_hw_group(struct evsel *counter)
{
struct evlist *evlist = counter->evlist;
libperf: Move perf_event_attr field from perf's evsel to libperf's perf_evsel Move the perf_event_attr struct fron 'struct evsel' to 'struct perf_evsel'. Committer notes: Fixed up these: tools/perf/arch/arm/util/auxtrace.c tools/perf/arch/arm/util/cs-etm.c tools/perf/arch/arm64/util/arm-spe.c tools/perf/arch/s390/util/auxtrace.c tools/perf/util/cs-etm.c Also cc1: warnings being treated as errors tests/sample-parsing.c: In function 'do_test': tests/sample-parsing.c:162: error: missing initializer tests/sample-parsing.c:162: error: (near initialization for 'evsel.core.cpus') struct evsel evsel = { .needs_swap = false, - .core.attr = { - .sample_type = sample_type, - .read_format = read_format, + .core = { + . attr = { + .sample_type = sample_type, + .read_format = read_format, + }, [perfbuilder@a70e4eeb5549 /]$ gcc --version |& head -1 gcc (GCC) 4.4.7 Also we don't need to include perf_event.h in tools/perf/lib/include/perf/evsel.h, forward declaring 'struct perf_event_attr' is enough. And this even fixes the build in some systems where things are used somewhere down the include path from perf_event.h without defining __always_inline. 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: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20190721112506.12306-43-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-07-21 13:24:29 +02:00
u32 pmu_type = counter->core.attr.type;
struct evsel *pos;
if (counter->core.nr_members < 2)
return false;
evlist__for_each_entry(evlist, pos) {
/* software events can be part of any hardware group */
libperf: Move perf_event_attr field from perf's evsel to libperf's perf_evsel Move the perf_event_attr struct fron 'struct evsel' to 'struct perf_evsel'. Committer notes: Fixed up these: tools/perf/arch/arm/util/auxtrace.c tools/perf/arch/arm/util/cs-etm.c tools/perf/arch/arm64/util/arm-spe.c tools/perf/arch/s390/util/auxtrace.c tools/perf/util/cs-etm.c Also cc1: warnings being treated as errors tests/sample-parsing.c: In function 'do_test': tests/sample-parsing.c:162: error: missing initializer tests/sample-parsing.c:162: error: (near initialization for 'evsel.core.cpus') struct evsel evsel = { .needs_swap = false, - .core.attr = { - .sample_type = sample_type, - .read_format = read_format, + .core = { + . attr = { + .sample_type = sample_type, + .read_format = read_format, + }, [perfbuilder@a70e4eeb5549 /]$ gcc --version |& head -1 gcc (GCC) 4.4.7 Also we don't need to include perf_event.h in tools/perf/lib/include/perf/evsel.h, forward declaring 'struct perf_event_attr' is enough. And this even fixes the build in some systems where things are used somewhere down the include path from perf_event.h without defining __always_inline. 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: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20190721112506.12306-43-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-07-21 13:24:29 +02:00
if (pos->core.attr.type == PERF_TYPE_SOFTWARE)
continue;
if (pmu_type == PERF_TYPE_SOFTWARE) {
libperf: Move perf_event_attr field from perf's evsel to libperf's perf_evsel Move the perf_event_attr struct fron 'struct evsel' to 'struct perf_evsel'. Committer notes: Fixed up these: tools/perf/arch/arm/util/auxtrace.c tools/perf/arch/arm/util/cs-etm.c tools/perf/arch/arm64/util/arm-spe.c tools/perf/arch/s390/util/auxtrace.c tools/perf/util/cs-etm.c Also cc1: warnings being treated as errors tests/sample-parsing.c: In function 'do_test': tests/sample-parsing.c:162: error: missing initializer tests/sample-parsing.c:162: error: (near initialization for 'evsel.core.cpus') struct evsel evsel = { .needs_swap = false, - .core.attr = { - .sample_type = sample_type, - .read_format = read_format, + .core = { + . attr = { + .sample_type = sample_type, + .read_format = read_format, + }, [perfbuilder@a70e4eeb5549 /]$ gcc --version |& head -1 gcc (GCC) 4.4.7 Also we don't need to include perf_event.h in tools/perf/lib/include/perf/evsel.h, forward declaring 'struct perf_event_attr' is enough. And this even fixes the build in some systems where things are used somewhere down the include path from perf_event.h without defining __always_inline. 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: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20190721112506.12306-43-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-07-21 13:24:29 +02:00
pmu_type = pos->core.attr.type;
continue;
}
libperf: Move perf_event_attr field from perf's evsel to libperf's perf_evsel Move the perf_event_attr struct fron 'struct evsel' to 'struct perf_evsel'. Committer notes: Fixed up these: tools/perf/arch/arm/util/auxtrace.c tools/perf/arch/arm/util/cs-etm.c tools/perf/arch/arm64/util/arm-spe.c tools/perf/arch/s390/util/auxtrace.c tools/perf/util/cs-etm.c Also cc1: warnings being treated as errors tests/sample-parsing.c: In function 'do_test': tests/sample-parsing.c:162: error: missing initializer tests/sample-parsing.c:162: error: (near initialization for 'evsel.core.cpus') struct evsel evsel = { .needs_swap = false, - .core.attr = { - .sample_type = sample_type, - .read_format = read_format, + .core = { + . attr = { + .sample_type = sample_type, + .read_format = read_format, + }, [perfbuilder@a70e4eeb5549 /]$ gcc --version |& head -1 gcc (GCC) 4.4.7 Also we don't need to include perf_event.h in tools/perf/lib/include/perf/evsel.h, forward declaring 'struct perf_event_attr' is enough. And this even fixes the build in some systems where things are used somewhere down the include path from perf_event.h without defining __always_inline. 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: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20190721112506.12306-43-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-07-21 13:24:29 +02:00
if (pmu_type != pos->core.attr.type)
return true;
}
return false;
}
static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int nr,
struct evsel *counter, double uval,
char *prefix, u64 run, u64 ena, double noise,
struct runtime_stat *st)
{
struct perf_stat_output_ctx out;
struct outstate os = {
.fh = config->output,
.prefix = prefix ? prefix : "",
.id = id,
.nr = nr,
.evsel = counter,
};
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: 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) {
static const int aggr_fields[AGGR_MAX] = {
[AGGR_NONE] = 1,
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
[AGGR_GLOBAL] = 0,
[AGGR_SOCKET] = 2,
[AGGR_DIE] = 2,
[AGGR_CORE] = 2,
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
[AGGR_THREAD] = 1,
[AGGR_UNSET] = 0,
[AGGR_NODE] = 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
pm = config->metric_only ? print_metric_only_csv : print_metric_csv;
nl = config->metric_only ? new_line_metric : new_line_csv;
os.nfields = 3 + aggr_fields[config->aggr_mode] + (counter->cgrp ? 1 : 0);
} else if (config->json_output) {
pm = config->metric_only ? print_metric_only_json : print_metric_json;
nl = config->metric_only ? new_line_metric : new_line_json;
} else {
pm = config->metric_only ? print_metric_only : print_metric_std;
nl = config->metric_only ? new_line_metric : new_line_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 (!config->no_csv_summary && config->csv_output &&
config->summary && !config->interval) {
fprintf(config->output, "%16s%s", "summary", config->csv_sep);
}
if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
if (config->metric_only) {
pm(config, &os, NULL, "", "", 0);
return;
}
aggr_printout(config, counter, id, 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
if (config->json_output) {
fprintf(config->output, "\"counter-value\" : \"%s\", ",
counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED);
} else {
fprintf(config->output, "%*s%s",
config->csv_output ? 0 : 18,
counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
config->csv_sep);
}
if (counter->supported) {
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
if (!evlist__has_hybrid(counter->evlist)) {
config->print_free_counters_hint = 1;
if (is_mixed_hw_group(counter))
config->print_mixed_hw_group_error = 1;
}
}
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) {
fprintf(config->output, "\"unit\" : \"%s\", ", counter->unit);
} else {
fprintf(config->output, "%-*s%s",
config->csv_output ? 0 : config->unit_width,
counter->unit, 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
if (config->json_output) {
fprintf(config->output, "\"event\" : \"%s\", ",
evsel__name(counter));
} else {
fprintf(config->output, "%*s",
config->csv_output ? 0 : -25, evsel__name(counter));
}
print_cgroup(config, counter);
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 && !config->json_output)
pm(config, &os, NULL, NULL, "", 0);
print_noise(config, counter, noise);
print_running(config, run, ena);
if (config->csv_output)
pm(config, &os, NULL, NULL, "", 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, &os, NULL, NULL, "", 0);
return;
}
if (!config->metric_only)
abs_printout(config, id, nr, counter, uval);
out.print_metric = pm;
out.new_line = nl;
out.ctx = &os;
out.force_header = false;
if (config->csv_output && !config->metric_only) {
print_noise(config, counter, noise);
print_running(config, 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
} else if (config->json_output && !config->metric_only) {
print_noise(config, counter, noise);
print_running(config, run, ena);
}
perf_stat__print_shadow_stats(config, counter, uval,
first_shadow_cpu_map_idx(config, counter, &id),
&out, &config->metric_events, st);
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 && !config->metric_only && !config->json_output) {
print_noise(config, counter, noise);
print_running(config, run, ena);
}
}
static void aggr_update_shadow(struct perf_stat_config *config,
struct evlist *evlist)
{
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 idx, s;
struct perf_cpu cpu;
struct aggr_cpu_id s2, id;
u64 val;
struct evsel *counter;
struct perf_cpu_map *cpus;
for (s = 0; s < config->aggr_map->nr; s++) {
id = config->aggr_map->map[s];
evlist__for_each_entry(evlist, counter) {
cpus = evsel__cpus(counter);
val = 0;
perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
s2 = config->aggr_get_id(config, cpu);
if (!aggr_cpu_id__equal(&s2, &id))
continue;
val += perf_counts(counter->counts, idx, 0)->val;
}
perf_stat__update_shadow_stats(counter, val,
first_shadow_cpu_map_idx(config, counter, &id),
&rt_stat);
}
}
}
static void uniquify_event_name(struct evsel *counter)
{
char *new_name;
char *config;
int ret = 0;
if (counter->uniquified_name || counter->use_config_name ||
!counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
strlen(counter->pmu_name)))
return;
config = strchr(counter->name, '/');
if (config) {
if (asprintf(&new_name,
"%s%s", counter->pmu_name, config) > 0) {
free(counter->name);
counter->name = new_name;
}
} else {
if (perf_pmu__has_hybrid()) {
ret = asprintf(&new_name, "%s/%s/",
counter->pmu_name, counter->name);
} else {
ret = asprintf(&new_name, "%s [%s]",
counter->name, counter->pmu_name);
}
if (ret) {
free(counter->name);
counter->name = new_name;
}
}
counter->uniquified_name = true;
}
static void collect_all_aliases(struct perf_stat_config *config, struct evsel *counter,
void (*cb)(struct perf_stat_config *config, struct evsel *counter, void *data,
bool first),
void *data)
{
struct evlist *evlist = counter->evlist;
struct evsel *alias;
alias = list_prepare_entry(counter, &(evlist->core.entries), core.node);
list_for_each_entry_continue (alias, &evlist->core.entries, core.node) {
perf stat: Fix display of grouped aliased events An event may have a number of uncore aliases that when added to the evlist are consecutive. If there are multiple uncore events in a group then parse_events__set_leader_for_uncore_aliase will reorder the evlist so that events on the same PMU are adjacent. The collect_all_aliases function assumes that aliases are in blocks so that only the first counter is printed and all others are marked merged. The reordering for groups breaks the assumption and so all counts are printed. This change removes the assumption from collect_all_aliases that the events are in blocks and instead processes the entire evlist. Before: ``` $ perf stat -e '{UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE,UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE},duration_time' -a -A -- sleep 1 Performance counter stats for 'system wide': CPU0 256,866 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 494,413 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 967 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,738 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 285,161 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 429,920 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 955 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,443 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 310,753 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 416,657 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,231 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,573 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 416,067 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 405,966 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,481 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,447 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 312,911 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 408,154 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,086 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,380 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 333,994 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 370,349 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,287 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,335 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 188,107 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 302,423 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 701 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,070 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 307,221 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 383,642 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,036 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,158 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 318,479 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 821,545 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,028 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 2,550 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 227,618 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 372,272 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 903 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,456 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 376,783 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 419,827 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,406 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,453 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 286,583 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 429,956 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 999 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,436 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 313,867 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 370,159 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,114 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,291 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 342,083 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 409,111 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,399 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,684 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 365,828 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 376,037 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,378 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,411 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 382,456 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 621,743 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,232 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,955 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 342,316 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 385,067 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,176 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,268 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 373,588 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 386,163 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,394 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,464 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 381,206 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 546,891 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,266 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,712 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 221,176 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 392,069 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 831 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,456 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 355,401 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 705,595 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,235 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 2,216 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 371,436 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 428,103 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,306 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,442 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 384,352 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 504,200 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,468 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,860 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 228,856 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 287,976 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 832 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,060 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 215,121 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 334,162 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 681 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,026 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 296,179 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 436,083 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,084 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,525 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 262,296 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 416,573 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 986 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,533 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 285,852 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 359,842 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,073 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,326 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 303,379 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 367,222 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,008 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,156 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 273,487 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 425,449 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 932 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,367 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 297,596 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 414,793 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,140 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,601 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 342,365 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 360,422 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,291 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,342 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 327,196 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 580,858 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,122 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 2,014 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 296,564 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 452,817 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,087 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,694 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 375,002 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 389,393 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,478 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 1,540 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 365,213 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 594,685 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 1,401 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 2,222 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 1,000,749,060 ns duration_time 1.000749060 seconds time elapsed ``` After: ``` Performance counter stats for 'system wide': CPU0 20,547,434 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU36 45,202,862 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE CPU0 82,001 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU36 159,688 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE CPU0 1,000,464,828 ns duration_time 1.000464828 seconds time elapsed ``` Fixes: 3cdc5c2cb924acb4 ("perf parse-events: Handle uncore event aliases in small groups properly") Reviewed-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Asaf Yaffe <asaf.yaffe@intel.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: John Garry <john.garry@huawei.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kshipra Bopardikar <kshipra.bopardikar@intel.com> 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: Stephane Eranian <eranian@google.com> Cc: Vineet Singh <vineet.singh@intel.com> Cc: Zhengjun Xing <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220205010941.1065469-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-02-04 17:09:41 -08:00
/* Merge events with the same name, etc. but on different PMUs. */
if (!strcmp(evsel__name(alias), evsel__name(counter)) &&
alias->scale == counter->scale &&
alias->cgrp == counter->cgrp &&
!strcmp(alias->unit, counter->unit) &&
evsel__is_clock(alias) == evsel__is_clock(counter) &&
strcmp(alias->pmu_name, counter->pmu_name)) {
alias->merged_stat = true;
cb(config, alias, data, false);
}
}
}
perf stat: Merge uncore events by default for hybrid platform On a hybrid platform, by default 'perf stat' aggregates and reports the event counts per PMU. For example, # perf stat -e cycles -a true Performance counter stats for 'system wide': 1,400,445 cpu_core/cycles/ 680,881 cpu_atom/cycles/ 0.001770773 seconds time elapsed But for uncore events that's not a suitable method. Uncore has nothing to do with hybrid. So for uncore events, we aggregate event counts from all PMUs and report the counts without PMUs. Before: # perf stat -e arb/event=0x81,umask=0x1/,arb/event=0x84,umask=0x1/ -a true Performance counter stats for 'system wide': 2,058 uncore_arb_0/event=0x81,umask=0x1/ 2,028 uncore_arb_1/event=0x81,umask=0x1/ 0 uncore_arb_0/event=0x84,umask=0x1/ 0 uncore_arb_1/event=0x84,umask=0x1/ 0.000614498 seconds time elapsed After: # perf stat -e arb/event=0x81,umask=0x1/,arb/event=0x84,umask=0x1/ -a true Performance counter stats for 'system wide': 3,996 arb/event=0x81,umask=0x1/ 0 arb/event=0x84,umask=0x1/ 0.000630046 seconds time elapsed Of course, we also keep the '--no-merge' working for uncore events. # perf stat -e arb/event=0x81,umask=0x1/,arb/event=0x84,umask=0x1/ --no-merge true Performance counter stats for 'system wide': 1,952 uncore_arb_0/event=0x81,umask=0x1/ 1,921 uncore_arb_1/event=0x81,umask=0x1/ 0 uncore_arb_0/event=0x84,umask=0x1/ 0 uncore_arb_1/event=0x84,umask=0x1/ 0.000575536 seconds time elapsed Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-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/20210707055652.962-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-07-07 13:56:52 +08:00
static bool is_uncore(struct evsel *evsel)
{
struct perf_pmu *pmu = evsel__find_pmu(evsel);
return pmu && pmu->is_uncore;
}
static bool hybrid_uniquify(struct evsel *evsel)
{
return perf_pmu__has_hybrid() && !is_uncore(evsel);
}
static bool hybrid_merge(struct evsel *counter, struct perf_stat_config *config,
bool check)
{
if (hybrid_uniquify(counter)) {
if (check)
return config && config->hybrid_merge;
else
return config && !config->hybrid_merge;
}
return false;
}
static bool collect_data(struct perf_stat_config *config, struct evsel *counter,
void (*cb)(struct perf_stat_config *config, struct evsel *counter, void *data,
bool first),
void *data)
{
if (counter->merged_stat)
return false;
cb(config, counter, data, true);
if (config->no_merge || hybrid_merge(counter, config, false))
uniquify_event_name(counter);
else if (counter->auto_merge_stats || hybrid_merge(counter, config, true))
collect_all_aliases(config, counter, cb, data);
return true;
}
struct aggr_data {
u64 ena, run, val;
struct aggr_cpu_id id;
int nr;
int cpu_map_idx;
};
static void aggr_cb(struct perf_stat_config *config,
struct evsel *counter, void *data, bool first)
{
struct aggr_data *ad = data;
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 idx;
struct perf_cpu cpu;
struct perf_cpu_map *cpus;
struct aggr_cpu_id s2;
cpus = evsel__cpus(counter);
perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
struct perf_counts_values *counts;
s2 = config->aggr_get_id(config, cpu);
if (!aggr_cpu_id__equal(&s2, &ad->id))
continue;
if (first)
ad->nr++;
counts = perf_counts(counter->counts, idx, 0);
/*
* When any result is bad, make them all to give
* consistent output in interval mode.
*/
if (counts->ena == 0 || counts->run == 0 ||
counter->counts->scaled == -1) {
ad->ena = 0;
ad->run = 0;
break;
}
ad->val += counts->val;
ad->ena += counts->ena;
ad->run += counts->run;
}
}
static void print_counter_aggrdata(struct perf_stat_config *config,
struct evsel *counter, int s,
char *prefix, bool metric_only,
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
bool *first, struct perf_cpu cpu)
{
struct aggr_data ad;
FILE *output = config->output;
u64 ena, run, val;
int nr;
struct aggr_cpu_id id;
double uval;
ad.id = id = config->aggr_map->map[s];
ad.val = ad.ena = ad.run = 0;
ad.nr = 0;
if (!collect_data(config, counter, aggr_cb, &ad))
return;
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_pmu__has_hybrid() && ad.ena == 0)
return;
nr = ad.nr;
ena = ad.ena;
run = ad.run;
val = ad.val;
if (*first && metric_only) {
*first = false;
aggr_printout(config, counter, id, nr);
}
if (prefix && !metric_only)
fprintf(output, "%s", prefix);
uval = val * counter->scale;
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
if (cpu.cpu != -1)
id = aggr_cpu_id__cpu(cpu, /*data=*/NULL);
printout(config, id, nr, counter, uval,
prefix, run, ena, 1.0, &rt_stat);
if (!metric_only)
fputc('\n', output);
}
static void print_aggr(struct perf_stat_config *config,
struct evlist *evlist,
char *prefix)
{
bool metric_only = config->metric_only;
FILE *output = config->output;
struct evsel *counter;
int s;
bool first;
if (!config->aggr_map || !config->aggr_get_id)
return;
aggr_update_shadow(config, evlist);
/*
* With metric_only everything is on a single line.
* Without each counter has its own line.
*/
for (s = 0; s < config->aggr_map->nr; s++) {
if (prefix && metric_only)
fprintf(output, "%s", prefix);
first = true;
evlist__for_each_entry(evlist, counter) {
print_counter_aggrdata(config, counter, s,
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
prefix, metric_only,
&first, (struct perf_cpu){ .cpu = -1 });
}
if (metric_only)
fputc('\n', output);
}
}
static int cmp_val(const void *a, const void *b)
{
return ((struct perf_aggr_thread_value *)b)->val -
((struct perf_aggr_thread_value *)a)->val;
}
static struct perf_aggr_thread_value *sort_aggr_thread(
struct evsel *counter,
int *ret,
struct target *_target)
{
int nthreads = perf_thread_map__nr(counter->core.threads);
int i = 0;
double uval;
struct perf_aggr_thread_value *buf;
buf = calloc(nthreads, sizeof(struct perf_aggr_thread_value));
if (!buf)
return NULL;
for (int thread = 0; thread < nthreads; thread++) {
int idx;
u64 ena = 0, run = 0, val = 0;
perf_cpu_map__for_each_idx(idx, evsel__cpus(counter)) {
struct perf_counts_values *counts =
perf_counts(counter->counts, idx, thread);
val += counts->val;
ena += counts->ena;
run += counts->run;
}
uval = val * counter->scale;
/*
* Skip value 0 when enabling --per-thread globally,
* otherwise too many 0 output.
*/
if (uval == 0.0 && target__has_per_thread(_target))
continue;
buf[i].counter = counter;
buf[i].id = aggr_cpu_id__empty();
buf[i].id.thread = thread;
buf[i].uval = uval;
buf[i].val = val;
buf[i].run = run;
buf[i].ena = ena;
i++;
}
qsort(buf, i, sizeof(struct perf_aggr_thread_value), cmp_val);
if (ret)
*ret = i;
return buf;
}
static void print_aggr_thread(struct perf_stat_config *config,
struct target *_target,
struct evsel *counter, char *prefix)
{
FILE *output = config->output;
int thread, sorted_threads;
struct aggr_cpu_id id;
struct perf_aggr_thread_value *buf;
buf = sort_aggr_thread(counter, &sorted_threads, _target);
if (!buf) {
perror("cannot sort aggr thread");
return;
}
for (thread = 0; thread < sorted_threads; thread++) {
if (prefix)
fprintf(output, "%s", prefix);
id = buf[thread].id;
if (config->stats)
printout(config, id, 0, buf[thread].counter, buf[thread].uval,
prefix, buf[thread].run, buf[thread].ena, 1.0,
&config->stats[id.thread]);
else
printout(config, id, 0, buf[thread].counter, buf[thread].uval,
prefix, buf[thread].run, buf[thread].ena, 1.0,
&rt_stat);
fputc('\n', output);
}
free(buf);
}
struct caggr_data {
double avg, avg_enabled, avg_running;
};
static void counter_aggr_cb(struct perf_stat_config *config __maybe_unused,
struct evsel *counter, void *data,
bool first __maybe_unused)
{
struct caggr_data *cd = data;
struct perf_counts_values *aggr = &counter->counts->aggr;
cd->avg += aggr->val;
cd->avg_enabled += aggr->ena;
cd->avg_running += aggr->run;
}
/*
* Print out the results of a single counter:
* aggregated counts in system-wide mode
*/
static void print_counter_aggr(struct perf_stat_config *config,
struct evsel *counter, char *prefix)
{
bool metric_only = config->metric_only;
FILE *output = config->output;
double uval;
struct caggr_data cd = { .avg = 0.0 };
if (!collect_data(config, counter, counter_aggr_cb, &cd))
return;
if (prefix && !metric_only)
fprintf(output, "%s", prefix);
uval = cd.avg * counter->scale;
printout(config, aggr_cpu_id__empty(), 0, counter, uval, prefix, cd.avg_running,
cd.avg_enabled, cd.avg, &rt_stat);
if (!metric_only)
fprintf(output, "\n");
}
static void counter_cb(struct perf_stat_config *config __maybe_unused,
struct evsel *counter, void *data,
bool first __maybe_unused)
{
struct aggr_data *ad = data;
ad->val += perf_counts(counter->counts, ad->cpu_map_idx, 0)->val;
ad->ena += perf_counts(counter->counts, ad->cpu_map_idx, 0)->ena;
ad->run += perf_counts(counter->counts, ad->cpu_map_idx, 0)->run;
}
/*
* Print out the results of a single counter:
* does not use aggregated count in system-wide
*/
static void print_counter(struct perf_stat_config *config,
struct evsel *counter, char *prefix)
{
FILE *output = config->output;
u64 ena, run, val;
double uval;
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 idx;
struct perf_cpu cpu;
struct aggr_cpu_id id;
perf_cpu_map__for_each_cpu(cpu, idx, evsel__cpus(counter)) {
struct aggr_data ad = { .cpu_map_idx = idx };
if (!collect_data(config, counter, counter_cb, &ad))
return;
val = ad.val;
ena = ad.ena;
run = ad.run;
if (prefix)
fprintf(output, "%s", prefix);
uval = val * counter->scale;
id = aggr_cpu_id__cpu(cpu, /*data=*/NULL);
printout(config, id, 0, counter, uval, prefix,
run, ena, 1.0, &rt_stat);
fputc('\n', output);
}
}
static void print_no_aggr_metric(struct perf_stat_config *config,
struct evlist *evlist,
char *prefix)
{
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 aggr_cpu_id id;
int counter_idx = perf_cpu_map__idx(evsel__cpus(counter), cpu);
if (counter_idx < 0)
continue;
id = aggr_cpu_id__cpu(cpu, /*data=*/NULL);
if (first) {
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 (prefix)
fputs(prefix, config->output);
aggr_printout(config, counter, id, 0);
first = false;
}
val = perf_counts(counter->counts, counter_idx, 0)->val;
ena = perf_counts(counter->counts, counter_idx, 0)->ena;
run = perf_counts(counter->counts, counter_idx, 0)->run;
uval = val * counter->scale;
printout(config, id, 0, counter, uval, prefix,
run, ena, 1.0, &rt_stat);
}
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)
fputc('\n', config->output);
}
}
static int aggr_header_lens[] = {
[AGGR_CORE] = 24,
[AGGR_DIE] = 18,
[AGGR_SOCKET] = 12,
[AGGR_NONE] = 6,
[AGGR_THREAD] = 24,
[AGGR_GLOBAL] = 0,
};
static const char *aggr_header_csv[] = {
[AGGR_CORE] = "core,cpus,",
[AGGR_DIE] = "die,cpus",
[AGGR_SOCKET] = "socket,cpus",
[AGGR_NONE] = "cpu,",
[AGGR_THREAD] = "comm-pid,",
[AGGR_GLOBAL] = ""
};
static void print_metric_headers(struct perf_stat_config *config,
struct evlist *evlist,
const char *prefix, bool no_indent)
{
struct perf_stat_output_ctx out;
struct evsel *counter;
struct outstate os = {
.fh = config->output
};
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
bool first = true;
if (config->json_output && !config->interval)
fprintf(config->output, "{");
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 (prefix && !config->json_output)
fprintf(config->output, "%s", prefix);
if (!config->csv_output && !no_indent)
fprintf(config->output, "%*s",
aggr_header_lens[config->aggr_mode], "");
if (config->csv_output) {
if (config->interval)
fputs("time,", config->output);
if (!config->iostat_run)
fputs(aggr_header_csv[config->aggr_mode], config->output);
}
if (config->iostat_run)
iostat_print_header_prefix(config);
/* Print metrics headers only */
evlist__for_each_entry(evlist, counter) {
os.evsel = counter;
out.ctx = &os;
out.print_metric = print_metric_header;
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 (!first && config->json_output)
fprintf(config->output, ", ");
first = false;
out.new_line = new_line_metric;
out.force_header = true;
perf_stat__print_shadow_stats(config, counter, 0,
0,
&out,
&config->metric_events,
&rt_stat);
}
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)
fprintf(config->output, "}");
fputc('\n', config->output);
}
static void print_interval(struct perf_stat_config *config,
struct evlist *evlist,
char *prefix, struct timespec *ts)
{
bool metric_only = config->metric_only;
unsigned int unit_width = config->unit_width;
FILE *output = config->output;
static int num_print_interval;
if (config->interval_clear)
puts(CONSOLE_CLEAR);
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->iostat_run && !config->json_output)
sprintf(prefix, "%6lu.%09lu%s", (unsigned long) ts->tv_sec,
ts->tv_nsec, config->csv_sep);
if (!config->iostat_run && config->json_output && !config->metric_only)
sprintf(prefix, "{\"interval\" : %lu.%09lu, ", (unsigned long)
ts->tv_sec, ts->tv_nsec);
if (!config->iostat_run && config->json_output && config->metric_only)
sprintf(prefix, "{\"interval\" : %lu.%09lu}", (unsigned long)
ts->tv_sec, ts->tv_nsec);
if ((num_print_interval == 0 && !config->csv_output && !config->json_output)
|| config->interval_clear) {
switch (config->aggr_mode) {
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, "# time node cpus");
if (!metric_only)
fprintf(output, " counts %*s events\n", unit_width, "unit");
break;
case AGGR_SOCKET:
fprintf(output, "# time socket cpus");
if (!metric_only)
fprintf(output, " counts %*s events\n", unit_width, "unit");
break;
case AGGR_DIE:
fprintf(output, "# time die cpus");
if (!metric_only)
fprintf(output, " counts %*s events\n", unit_width, "unit");
break;
case AGGR_CORE:
fprintf(output, "# time core cpus");
if (!metric_only)
fprintf(output, " counts %*s events\n", unit_width, "unit");
break;
case AGGR_NONE:
fprintf(output, "# time CPU ");
if (!metric_only)
fprintf(output, " counts %*s events\n", unit_width, "unit");
break;
case AGGR_THREAD:
fprintf(output, "# time comm-pid");
if (!metric_only)
fprintf(output, " counts %*s events\n", unit_width, "unit");
break;
case AGGR_GLOBAL:
default:
if (!config->iostat_run) {
fprintf(output, "# time");
if (!metric_only)
fprintf(output, " counts %*s events\n", unit_width, "unit");
}
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:
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
if ((num_print_interval == 0 || config->interval_clear)
&& metric_only && !config->json_output)
print_metric_headers(config, evlist, " ", true);
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 ((num_print_interval == 0 || config->interval_clear)
&& metric_only && config->json_output) {
fprintf(output, "{");
print_metric_headers(config, evlist, " ", true);
}
if (++num_print_interval == 25)
num_print_interval = 0;
}
static void print_header(struct perf_stat_config *config,
struct target *_target,
int argc, const char **argv)
{
FILE *output = config->output;
int i;
fflush(stdout);
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 && !config->json_output) {
fprintf(output, "\n");
fprintf(output, " Performance counter stats for ");
perf stat: Enable counting events for BPF programs Introduce 'perf stat -b' option, which counts events for BPF programs, like: [root@localhost ~]# ~/perf stat -e ref-cycles,cycles -b 254 -I 1000 1.487903822 115,200 ref-cycles 1.487903822 86,012 cycles 2.489147029 80,560 ref-cycles 2.489147029 73,784 cycles 3.490341825 60,720 ref-cycles 3.490341825 37,797 cycles 4.491540887 37,120 ref-cycles 4.491540887 31,963 cycles The example above counts 'cycles' and 'ref-cycles' of BPF program of id 254. This is similar to bpftool-prog-profile command, but more flexible. 'perf stat -b' creates per-cpu perf_event and loads fentry/fexit BPF programs (monitor-progs) to the target BPF program (target-prog). The monitor-progs read perf_event before and after the target-prog, and aggregate the difference in a BPF map. Then the user space reads data from these maps. A new 'struct bpf_counter' is introduced to provide a common interface that uses BPF programs/maps to count perf events. Committer notes: Removed all but bpf_counter.h includes from evsel.h, not needed at all. Also BPF map lookups for PERCPU_ARRAYs need to have as its value receive buffer passed to the kernel libbpf_num_possible_cpus() entries, not evsel__nr_cpus(evsel), as the former uses /sys/devices/system/cpu/possible while the later uses /sys/devices/system/cpu/online, which may be less than the 'possible' number making the bpf map lookup overwrite memory and cause hard to debug memory corruption. We need to continue using evsel__nr_cpus(evsel) when accessing the perf_counts array tho, not to overwrite another are of memory :-) Signed-off-by: Song Liu <songliubraving@fb.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Link: https://lore.kernel.org/lkml/20210120163031.GU12699@kernel.org/ Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: kernel-team@fb.com Link: http://lore.kernel.org/lkml/20201229214214.3413833-4-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-12-29 13:42:14 -08:00
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");
}
}
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->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);
print_noise_pct(config, sd, avg);
}
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");
if (config->print_mixed_hw_group_error)
fprintf(output,
"The events in group usually have to be from "
"the same PMU. Try reorganizing the group.\n");
}
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
static void print_percore_thread(struct perf_stat_config *config,
struct evsel *counter, char *prefix)
{
int s;
struct aggr_cpu_id s2, id;
struct perf_cpu_map *cpus;
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
bool first = true;
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 idx;
struct perf_cpu cpu;
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
cpus = evsel__cpus(counter);
perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
s2 = config->aggr_get_id(config, cpu);
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
for (s = 0; s < config->aggr_map->nr; s++) {
id = config->aggr_map->map[s];
if (aggr_cpu_id__equal(&s2, &id))
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
break;
}
print_counter_aggrdata(config, counter, s,
prefix, false,
&first, cpu);
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: 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, char *prefix)
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;
int s;
bool first = true;
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_percore_thread(config, counter, prefix);
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
for (s = 0; s < config->aggr_map->nr; s++) {
if (prefix && metric_only)
fprintf(output, "%s", prefix);
print_counter_aggrdata(config, counter, s,
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
prefix, metric_only,
&first, (struct perf_cpu){ .cpu = -1 });
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);
}
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;
int interval = config->interval;
struct evsel *counter;
char buf[64], *prefix = NULL;
if (config->iostat_run)
evlist->selected = evlist__first(evlist);
if (interval)
print_interval(config, evlist, prefix = buf, ts);
else
print_header(config, _target, argc, argv);
if (metric_only) {
static int num_print_iv;
if (num_print_iv == 0 && !interval)
print_metric_headers(config, evlist, prefix, false);
if (num_print_iv++ == 25)
num_print_iv = 0;
if (config->aggr_mode == AGGR_GLOBAL && prefix && !config->iostat_run)
fprintf(config->output, "%s", prefix);
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 && !config->metric_only)
fprintf(config->output, "}");
}
switch (config->aggr_mode) {
case AGGR_CORE:
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:
print_aggr(config, evlist, prefix);
break;
case AGGR_THREAD:
evlist__for_each_entry(evlist, counter) {
print_aggr_thread(config, _target, counter, prefix);
}
break;
case AGGR_GLOBAL:
if (config->iostat_run)
iostat_print_counters(evlist, config, ts, prefix = buf,
print_counter_aggr);
else {
evlist__for_each_entry(evlist, counter) {
print_counter_aggr(config, counter, prefix);
}
if (metric_only)
fputc('\n', config->output);
}
break;
case AGGR_NONE:
if (metric_only)
print_no_aggr_metric(config, evlist, prefix);
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, prefix);
else
print_counter(config, counter, prefix);
}
}
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;
}
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 (!interval && !config->csv_output && !config->json_output)
print_footer(config);
fflush(config->output);
}