linux/tools/perf/tests/expr.c
Ian Rogers 2a939c8695 perf metric: Change divide by zero and !support events behavior
Division by zero causes expression parsing to fail and no metric to be
generated. This can mean for short running benchmarks metrics are not
shown. Change the behavior to make the value nan, which gets shown like:

'''
$ perf stat -M TopdownL2 true

 Performance counter stats for 'true':

         1,031,492      INST_RETIRED.ANY                 #      nan %  tma_fetch_bandwidth
                                                  #      nan %  tma_heavy_operations
                                                  #      nan %  tma_light_operations
            29,304      CPU_CLK_UNHALTED.REF_XCLK        #      nan %  tma_fetch_latency
                                                  #      nan %  tma_branch_mispredicts
                                                  #      nan %  tma_machine_clears
                                                  #      nan %  tma_core_bound
                                                  #      nan %  tma_memory_bound
         2,658,319      IDQ_UOPS_NOT_DELIVERED.CORE
            11,167      EXE_ACTIVITY.BOUND_ON_STORES
           262,058      EXE_ACTIVITY.1_PORTS_UTIL
     <not counted>      BR_MISP_RETIRED.ALL_BRANCHES                                            (0.00%)
     <not counted>      INT_MISC.RECOVERY_CYCLES_ANY                                            (0.00%)
     <not counted>      CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE                                        (0.00%)
     <not counted>      CPU_CLK_UNHALTED.THREAD                                                 (0.00%)
     <not counted>      UOPS_RETIRED.RETIRE_SLOTS                                               (0.00%)
     <not counted>      CYCLE_ACTIVITY.STALLS_MEM_ANY                                           (0.00%)
     <not counted>      UOPS_RETIRED.MACRO_FUSED                                                (0.00%)
     <not counted>      IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE                                        (0.00%)
     <not counted>      EXE_ACTIVITY.2_PORTS_UTIL                                               (0.00%)
     <not counted>      CYCLE_ACTIVITY.STALLS_TOTAL                                             (0.00%)
     <not counted>      MACHINE_CLEARS.COUNT                                                    (0.00%)
     <not counted>      UOPS_ISSUED.ANY                                                         (0.00%)

       0.002864879 seconds time elapsed

       0.003012000 seconds user
       0.000000000 seconds sys
'''

When events aren't supported a count of 0 can be confusing and make
metrics look meaningful. Change these to be nan also which, with the
next change, gets shown like:

'''
$ perf stat true
 Performance counter stats for 'true':

              1.25 msec task-clock:u                     #    0.387 CPUs utilized
                 0      context-switches:u               #    0.000 /sec
                 0      cpu-migrations:u                 #    0.000 /sec
                46      page-faults:u                    #   36.702 K/sec
           255,942      cycles:u                         #    0.204 GHz                         (88.66%)
           123,046      instructions:u                   #    0.48  insn per cycle
            28,301      branches:u                       #   22.580 M/sec
             2,489      branch-misses:u                  #    8.79% of all branches
             4,719      CPU_CLK_UNHALTED.REF_XCLK:u      #    3.765 M/sec
                                                  #      nan %  tma_frontend_bound
                                                  #      nan %  tma_retiring
                                                  #      nan %  tma_backend_bound
                                                  #      nan %  tma_bad_speculation
           344,855      IDQ_UOPS_NOT_DELIVERED.CORE:u    #  275.147 M/sec
   <not supported>      INT_MISC.RECOVERY_CYCLES_ANY:u
     <not counted>      CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE:u                                        (0.00%)
     <not counted>      CPU_CLK_UNHALTED.THREAD:u                                               (0.00%)
     <not counted>      UOPS_RETIRED.RETIRE_SLOTS:u                                             (0.00%)
     <not counted>      UOPS_ISSUED.ANY:u                                                       (0.00%)

       0.003238142 seconds time elapsed

       0.000000000 seconds user
       0.003434000 seconds sys
'''

Ensure that nan metric values are quoted as nan isn't a valid number
in JSON.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ahmad Yasin <ahmad.yasin@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.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: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kang Minchul <tegongkang@gmail.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Samantha Alt <samantha.alt@intel.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Tiezhu Yang <yangtiezhu@loongson.cn>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20230502223851.2234828-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-10 12:35:02 -03:00

222 lines
7.1 KiB
C

// SPDX-License-Identifier: GPL-2.0
#include "util/cputopo.h"
#include "util/debug.h"
#include "util/expr.h"
#include "util/hashmap.h"
#include "util/header.h"
#include "util/smt.h"
#include "tests.h"
#include <math.h>
#include <stdlib.h>
#include <string.h>
#include <linux/zalloc.h>
static int test_ids_union(void)
{
struct hashmap *ids1, *ids2;
/* Empty union. */
ids1 = ids__new();
TEST_ASSERT_VAL("ids__new", ids1);
ids2 = ids__new();
TEST_ASSERT_VAL("ids__new", ids2);
ids1 = ids__union(ids1, ids2);
TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 0);
/* Union {foo, bar} against {}. */
ids2 = ids__new();
TEST_ASSERT_VAL("ids__new", ids2);
TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids1, strdup("foo")), 0);
TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids1, strdup("bar")), 0);
ids1 = ids__union(ids1, ids2);
TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 2);
/* Union {foo, bar} against {foo}. */
ids2 = ids__new();
TEST_ASSERT_VAL("ids__new", ids2);
TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids2, strdup("foo")), 0);
ids1 = ids__union(ids1, ids2);
TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 2);
/* Union {foo, bar} against {bar,baz}. */
ids2 = ids__new();
TEST_ASSERT_VAL("ids__new", ids2);
TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids2, strdup("bar")), 0);
TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids2, strdup("baz")), 0);
ids1 = ids__union(ids1, ids2);
TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 3);
ids__free(ids1);
return 0;
}
static int test(struct expr_parse_ctx *ctx, const char *e, double val2)
{
double val;
if (expr__parse(&val, ctx, e))
TEST_ASSERT_VAL("parse test failed", 0);
TEST_ASSERT_VAL("unexpected value", val == val2);
return 0;
}
static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_unused)
{
struct expr_id_data *val_ptr;
const char *p;
double val, num_cpus, num_cores, num_dies, num_packages;
int ret;
struct expr_parse_ctx *ctx;
bool is_intel = false;
char buf[128];
if (!get_cpuid(buf, sizeof(buf)))
is_intel = strstr(buf, "Intel") != NULL;
TEST_ASSERT_EQUAL("ids_union", test_ids_union(), 0);
ctx = expr__ctx_new();
TEST_ASSERT_VAL("expr__ctx_new", ctx);
expr__add_id_val(ctx, strdup("FOO"), 1);
expr__add_id_val(ctx, strdup("BAR"), 2);
ret = test(ctx, "1+1", 2);
ret |= test(ctx, "FOO+BAR", 3);
ret |= test(ctx, "(BAR/2)%2", 1);
ret |= test(ctx, "1 - -4", 5);
ret |= test(ctx, "(FOO-1)*2 + (BAR/2)%2 - -4", 5);
ret |= test(ctx, "1-1 | 1", 1);
ret |= test(ctx, "1-1 & 1", 0);
ret |= test(ctx, "min(1,2) + 1", 2);
ret |= test(ctx, "max(1,2) + 1", 3);
ret |= test(ctx, "1+1 if 3*4 else 0", 2);
ret |= test(ctx, "100 if 1 else 200 if 1 else 300", 100);
ret |= test(ctx, "100 if 0 else 200 if 1 else 300", 200);
ret |= test(ctx, "100 if 1 else 200 if 0 else 300", 100);
ret |= test(ctx, "100 if 0 else 200 if 0 else 300", 300);
ret |= test(ctx, "1.1 + 2.1", 3.2);
ret |= test(ctx, ".1 + 2.", 2.1);
ret |= test(ctx, "d_ratio(1, 2)", 0.5);
ret |= test(ctx, "d_ratio(2.5, 0)", 0);
ret |= test(ctx, "1.1 < 2.2", 1);
ret |= test(ctx, "2.2 > 1.1", 1);
ret |= test(ctx, "1.1 < 1.1", 0);
ret |= test(ctx, "2.2 > 2.2", 0);
ret |= test(ctx, "2.2 < 1.1", 0);
ret |= test(ctx, "1.1 > 2.2", 0);
ret |= test(ctx, "1.1e10 < 1.1e100", 1);
ret |= test(ctx, "1.1e2 > 1.1e-2", 1);
if (ret) {
expr__ctx_free(ctx);
return ret;
}
p = "FOO/0";
ret = expr__parse(&val, ctx, p);
TEST_ASSERT_VAL("division by zero", ret == 0);
TEST_ASSERT_VAL("division by zero", isnan(val));
p = "BAR/";
ret = expr__parse(&val, ctx, p);
TEST_ASSERT_VAL("missing operand", ret == -1);
expr__ctx_clear(ctx);
TEST_ASSERT_VAL("find ids",
expr__find_ids("FOO + BAR + BAZ + BOZO", "FOO",
ctx) == 0);
TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 3);
TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BAR", &val_ptr));
TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BAZ", &val_ptr));
TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BOZO", &val_ptr));
expr__ctx_clear(ctx);
ctx->sctx.runtime = 3;
TEST_ASSERT_VAL("find ids",
expr__find_ids("EVENT1\\,param\\=?@ + EVENT2\\,param\\=?@",
NULL, ctx) == 0);
TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 2);
TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT1,param=3@", &val_ptr));
TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT2,param=3@", &val_ptr));
expr__ctx_clear(ctx);
TEST_ASSERT_VAL("find ids",
expr__find_ids("dash\\-event1 - dash\\-event2",
NULL, ctx) == 0);
TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 2);
TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "dash-event1", &val_ptr));
TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "dash-event2", &val_ptr));
/* Only EVENT1 or EVENT2 need be measured depending on the value of smt_on. */
{
bool smton = smt_on();
bool corewide = core_wide(/*system_wide=*/false,
/*user_requested_cpus=*/false);
expr__ctx_clear(ctx);
TEST_ASSERT_VAL("find ids",
expr__find_ids("EVENT1 if #smt_on else EVENT2",
NULL, ctx) == 0);
TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 1);
TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids,
smton ? "EVENT1" : "EVENT2",
&val_ptr));
expr__ctx_clear(ctx);
TEST_ASSERT_VAL("find ids",
expr__find_ids("EVENT1 if #core_wide else EVENT2",
NULL, ctx) == 0);
TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 1);
TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids,
corewide ? "EVENT1" : "EVENT2",
&val_ptr));
}
/* The expression is a constant 1.0 without needing to evaluate EVENT1. */
expr__ctx_clear(ctx);
TEST_ASSERT_VAL("find ids",
expr__find_ids("1.0 if EVENT1 > 100.0 else 1.0",
NULL, ctx) == 0);
TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 0);
/* Test toplogy constants appear well ordered. */
expr__ctx_clear(ctx);
TEST_ASSERT_VAL("#num_cpus", expr__parse(&num_cpus, ctx, "#num_cpus") == 0);
TEST_ASSERT_VAL("#num_cores", expr__parse(&num_cores, ctx, "#num_cores") == 0);
TEST_ASSERT_VAL("#num_cpus >= #num_cores", num_cpus >= num_cores);
TEST_ASSERT_VAL("#num_dies", expr__parse(&num_dies, ctx, "#num_dies") == 0);
TEST_ASSERT_VAL("#num_cores >= #num_dies", num_cores >= num_dies);
TEST_ASSERT_VAL("#num_packages", expr__parse(&num_packages, ctx, "#num_packages") == 0);
if (num_dies) // Some platforms do not have CPU die support, for example s390
TEST_ASSERT_VAL("#num_dies >= #num_packages", num_dies >= num_packages);
TEST_ASSERT_VAL("#system_tsc_freq", expr__parse(&val, ctx, "#system_tsc_freq") == 0);
if (is_intel)
TEST_ASSERT_VAL("#system_tsc_freq > 0", val > 0);
else
TEST_ASSERT_VAL("#system_tsc_freq == 0", fpclassify(val) == FP_ZERO);
/*
* Source count returns the number of events aggregating in a leader
* event including the leader. Check parsing yields an id.
*/
expr__ctx_clear(ctx);
TEST_ASSERT_VAL("source count",
expr__find_ids("source_count(EVENT1)",
NULL, ctx) == 0);
TEST_ASSERT_VAL("source count", hashmap__size(ctx->ids) == 1);
TEST_ASSERT_VAL("source count", hashmap__find(ctx->ids, "EVENT1", &val_ptr));
expr__ctx_free(ctx);
return 0;
}
DEFINE_SUITE("Simple expression parser", expr);