diff options
author | Kan Liang <kan.liang@linux.intel.com> | 2023-06-16 05:14:17 +0200 |
---|---|---|
committer | Arnaldo Carvalho de Melo <acme@redhat.com> | 2023-06-16 14:57:19 +0200 |
commit | 6a80d794d796d22910c03d3e52a3bf0d885326a7 (patch) | |
tree | 9282f96e127b6a7293678d9155698c504f0e56f2 /tools/perf/util/stat-display.c | |
parent | perf metrics: Sort the Default metricgroup (diff) | |
download | linux-6a80d794d796d22910c03d3e52a3bf0d885326a7.tar.xz linux-6a80d794d796d22910c03d3e52a3bf0d885326a7.zip |
perf stat: New metricgroup output for the default mode
In the default mode, the current output of the metricgroup include both
events and metrics, which is not necessary and just makes the output
hard to read. Since different ARCHs (even different generations in the
same ARCH) may use different events. The output also vary on different
platforms.
For a metricgroup, only outputting the value of each metric is good
enough.
Add a new field default_metricgroup in evsel to indicate an event of the
default metricgroup. For those events, printout() should print the
metricgroup name rather than each event.
Add perf_stat__skip_metric_event() to skip the evsel in the Default
metricgroup, if it's not running or not the metric event.
Add print_metricgroup_header_t to pass the functions which print the
display name of each metricgroup in the Default metricgroup. Support all
three output methods.
Factor out perf_stat__print_shadow_stats_metricgroup() to print out each
metrics.
On SPR:
Before:
./perf_old stat sleep 1
Performance counter stats for 'sleep 1':
0.54 msec task-clock:u # 0.001 CPUs utilized
0 context-switches:u # 0.000 /sec
0 cpu-migrations:u # 0.000 /sec
68 page-faults:u # 125.445 K/sec
540,970 cycles:u # 0.998 GHz
556,325 instructions:u # 1.03 insn per cycle
123,602 branches:u # 228.018 M/sec
6,889 branch-misses:u # 5.57% of all branches
3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound
# 17.2 % tma_retiring
# 23.1 % tma_bad_speculation
# 41.4 % tma_frontend_bound
564,859 topdown-retiring:u
1,370,999 topdown-fe-bound:u
603,271 topdown-be-bound:u
744,874 topdown-bad-spec:u
12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec
1.001798215 seconds time elapsed
0.000193000 seconds user
0.001700000 seconds sys
After:
$ ./perf stat sleep 1
Performance counter stats for 'sleep 1':
0.51 msec task-clock:u # 0.001 CPUs utilized
0 context-switches:u # 0.000 /sec
0 cpu-migrations:u # 0.000 /sec
68 page-faults:u # 132.683 K/sec
545,228 cycles:u # 1.064 GHz
555,509 instructions:u # 1.02 insn per cycle
123,574 branches:u # 241.120 M/sec
6,957 branch-misses:u # 5.63% of all branches
TopdownL1 # 17.5 % tma_backend_bound
# 22.6 % tma_bad_speculation
# 42.7 % tma_frontend_bound
# 17.1 % tma_retiring
TopdownL2 # 21.8 % tma_branch_mispredicts
# 11.5 % tma_core_bound
# 13.4 % tma_fetch_bandwidth
# 29.3 % tma_fetch_latency
# 2.7 % tma_heavy_operations
# 14.5 % tma_light_operations
# 0.8 % tma_machine_clears
# 6.1 % tma_memory_bound
1.001712086 seconds time elapsed
0.000151000 seconds user
0.001618000 seconds sys
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ahmad Yasin <ahmad.yasin@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools/perf/util/stat-display.c')
-rw-r--r-- | tools/perf/util/stat-display.c | 108 |
1 files changed, 98 insertions, 10 deletions
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index a2bbdc25d979..7329b3340f88 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -25,6 +25,7 @@ #define CNTR_NOT_SUPPORTED "<not supported>" #define CNTR_NOT_COUNTED "<not counted>" +#define MGROUP_LEN 50 #define METRIC_LEN 38 #define EVNAME_LEN 32 #define COUNTS_LEN 18 @@ -364,16 +365,27 @@ static void new_line_std(struct perf_stat_config *config __maybe_unused, os->newline = true; } -static void do_new_line_std(struct perf_stat_config *config, - struct outstate *os) +static inline void __new_line_std_csv(struct perf_stat_config *config, + struct outstate *os) { fputc('\n', os->fh); if (os->prefix) fputs(os->prefix, os->fh); aggr_printout(config, os->evsel, os->id, os->aggr_nr); +} + +static inline void __new_line_std(struct outstate *os) +{ + fprintf(os->fh, " "); +} + +static void do_new_line_std(struct perf_stat_config *config, + struct outstate *os) +{ + __new_line_std_csv(config, os); if (config->aggr_mode == AGGR_NONE) fprintf(os->fh, " "); - fprintf(os->fh, " "); + __new_line_std(os); } static void print_metric_std(struct perf_stat_config *config, @@ -408,10 +420,7 @@ 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", os->prefix); - aggr_printout(config, os->evsel, os->id, os->aggr_nr); + __new_line_std_csv(config, os); for (i = 0; i < os->nfields; i++) fputs(config->csv_sep, os->fh); } @@ -462,6 +471,54 @@ static void new_line_json(struct perf_stat_config *config, void *ctx) aggr_printout(config, os->evsel, os->id, os->aggr_nr); } +static void print_metricgroup_header_json(struct perf_stat_config *config, + void *ctx, + const char *metricgroup_name) +{ + if (!metricgroup_name) + return; + + fprintf(config->output, "\"metricgroup\" : \"%s\"}", metricgroup_name); + new_line_json(config, ctx); +} + +static void print_metricgroup_header_csv(struct perf_stat_config *config, + void *ctx, + const char *metricgroup_name) +{ + struct outstate *os = ctx; + int i; + + if (!metricgroup_name) { + /* Leave space for running and enabling */ + for (i = 0; i < os->nfields - 2; i++) + fputs(config->csv_sep, os->fh); + return; + } + + for (i = 0; i < os->nfields; i++) + fputs(config->csv_sep, os->fh); + fprintf(config->output, "%s", metricgroup_name); + new_line_csv(config, ctx); +} + +static void print_metricgroup_header_std(struct perf_stat_config *config, + void *ctx, + const char *metricgroup_name) +{ + struct outstate *os = ctx; + int n; + + if (!metricgroup_name) { + __new_line_std(os); + return; + } + + n = fprintf(config->output, " %*s", EVNAME_LEN, metricgroup_name); + + fprintf(config->output, "%*s", MGROUP_LEN - n - 1, ""); +} + /* Filter out some columns that don't work well in metrics only mode */ static bool valid_only_metric(const char *unit) @@ -713,19 +770,23 @@ static void printout(struct perf_stat_config *config, struct outstate *os, struct perf_stat_output_ctx out; print_metric_t pm; new_line_t nl; + print_metricgroup_header_t pmh; bool ok = true; struct evsel *counter = os->evsel; if (config->csv_output) { pm = config->metric_only ? print_metric_only_csv : print_metric_csv; nl = config->metric_only ? new_line_metric : new_line_csv; + pmh = print_metricgroup_header_csv; os->nfields = 4 + (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; + pmh = print_metricgroup_header_json; } else { pm = config->metric_only ? print_metric_only : print_metric_std; nl = config->metric_only ? new_line_metric : new_line_std; + pmh = print_metricgroup_header_std; } if (run == 0 || ena == 0 || counter->counts->scaled == -1) { @@ -747,10 +808,11 @@ static void printout(struct perf_stat_config *config, struct outstate *os, out.print_metric = pm; out.new_line = nl; + out.print_metricgroup_header = pmh; out.ctx = os; out.force_header = false; - if (!config->metric_only) { + if (!config->metric_only && !counter->default_metricgroup) { abs_printout(config, os->id, os->aggr_nr, counter, uval, ok); print_noise(config, counter, noise, /*before_metric=*/true); @@ -758,8 +820,31 @@ static void printout(struct perf_stat_config *config, struct outstate *os, } if (ok) { - perf_stat__print_shadow_stats(config, counter, uval, aggr_idx, - &out, &config->metric_events); + if (!config->metric_only && counter->default_metricgroup) { + void *from = NULL; + + aggr_printout(config, os->evsel, os->id, os->aggr_nr); + /* Print out all the metricgroup with the same metric event. */ + do { + int num = 0; + + /* Print out the new line for the next new metricgroup. */ + if (from) { + if (config->json_output) + new_line_json(config, (void *)os); + else + __new_line_std_csv(config, os); + } + + print_noise(config, counter, noise, /*before_metric=*/true); + print_running(config, run, ena, /*before_metric=*/true); + from = perf_stat__print_shadow_stats_metricgroup(config, counter, aggr_idx, + &num, from, &out, + &config->metric_events); + } while (from != NULL); + } else + perf_stat__print_shadow_stats(config, counter, uval, aggr_idx, + &out, &config->metric_events); } else { pm(config, os, /*color=*/NULL, /*format=*/NULL, /*unit=*/"", /*val=*/0); } @@ -889,6 +974,9 @@ static void print_counter_aggrdata(struct perf_stat_config *config, ena = aggr->counts.ena; run = aggr->counts.run; + if (perf_stat__skip_metric_event(counter, &config->metric_events, ena, run)) + return; + if (val == 0 && should_skip_zero_counter(config, counter, &id)) return; |