From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1946658AbbHHAwi (ORCPT ); Fri, 7 Aug 2015 20:52:38 -0400 Received: from mga14.intel.com ([192.55.52.115]:5055 "EHLO mga14.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1946550AbbHHAwJ (ORCPT ); Fri, 7 Aug 2015 20:52:09 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.15,632,1432623600"; d="scan'208";a="744476238" From: Andi Kleen To: acme@kernel.org Cc: jolsa@kernel.org, linux-kernel@vger.kernel.org, eranian@google.com, namhyung@kernel.org, Andi Kleen Subject: [PATCH 7/7] perf, tools: Support metrics in --per-core/socket mode Date: Fri, 7 Aug 2015 17:51:59 -0700 Message-Id: <1438995119-10531-8-git-send-email-andi@firstfloor.org> X-Mailer: git-send-email 2.4.3 In-Reply-To: <1438995119-10531-1-git-send-email-andi@firstfloor.org> References: <1438995119-10531-1-git-send-email-andi@firstfloor.org> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Andi Kleen Enable metrics printing in --per-core / --per-socket mode. We need to save the shadow metrics in a unique place. Always use the first CPU in the aggregation. Then use the same CPU to retrieve the shadow value later. Example output: % perf stat --per-core -a ./BC1s Performance counter stats for 'system wide': S0-C0 2 2966.020381 task-clock (msec) # 2.004 CPUs utilized (100.00%) S0-C0 2 49 context-switches # 0.017 K/sec (100.00%) S0-C0 2 4 cpu-migrations # 0.001 K/sec (100.00%) S0-C0 2 467 page-faults # 0.157 K/sec S0-C0 2 4,599,061,773 cycles # 1.551 GHz (100.00%) S0-C0 2 9,755,886,883 instructions # 2.12 insn per cycle (100.00%) S0-C0 2 1,906,272,125 branches # 642.704 M/sec (100.00%) S0-C0 2 81,180,867 branch-misses # 4.26% of all branches S0-C1 2 2965.995373 task-clock (msec) # 2.003 CPUs utilized (100.00%) S0-C1 2 62 context-switches # 0.021 K/sec (100.00%) S0-C1 2 8 cpu-migrations # 0.003 K/sec (100.00%) S0-C1 2 281 page-faults # 0.095 K/sec S0-C1 2 6,347,290 cycles # 0.002 GHz (100.00%) S0-C1 2 4,654,156 instructions # 0.73 insn per cycle (100.00%) S0-C1 2 947,121 branches # 0.319 M/sec (100.00%) S0-C1 2 37,322 branch-misses # 3.94% of all branches 1.480409747 seconds time elapsed Signed-off-by: Andi Kleen --- tools/perf/builtin-stat.c | 62 ++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 58 insertions(+), 4 deletions(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index d777bb6..ea5298a 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -488,6 +488,8 @@ struct outstate { const char *prefix; int nfields; u64 run, ena; + int id, nr; + struct perf_evsel *evsel; }; #define BASE_INDENT 41 @@ -498,13 +500,19 @@ struct outstate { static void new_line_no_aggr_std(void *ctx) { struct outstate *os = ctx; - fprintf(os->fh, "\n%s%-*s", os->prefix, BASE_INDENT + NA_INDENT, ""); + + fprintf(os->fh, "\n%s", os->prefix); + aggr_printout(os->evsel, os->id, os->nr); + fprintf(os->fh, "%-*s", BASE_INDENT + NA_INDENT, ""); } static void new_line_std(void *ctx) { struct outstate *os = ctx; - fprintf(os->fh, "\n%s%-*s", os->prefix, BASE_INDENT + AGGR_INDENT, ""); + + fprintf(os->fh, "\n%s", os->prefix); + aggr_printout(os->evsel, os->id, os->nr); + fprintf(os->fh, "%-*s", BASE_INDENT + AGGR_INDENT, ""); } static void print_metric_std(void *ctx, const char *color, const char *fmt, @@ -535,6 +543,7 @@ static void new_line_csv(void *ctx) fputc('\n', os->fh); if (os->prefix) fprintf(os->fh, "%s%s", os->prefix, csv_sep); + aggr_printout(os->evsel, os->id, os->nr); for (i = 0; i < os->nfields; i++) fputs(csv_sep, os->fh); } @@ -598,6 +607,22 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg) fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); } +static int first_shadow_cpu(struct perf_evsel *evsel, int id) +{ + int i; + + if (aggr_get_id == NULL) + return 0; + + for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) { + int cpu2 = perf_evsel__cpus(evsel)->map[i]; + + if (aggr_get_id(evsel_list->cpus, cpu2) == id) + return cpu2; + } + return 0; +} + static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg) { FILE *output = stat_config.output; @@ -633,7 +658,10 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval, { struct outstate os = { .fh = stat_config.output, - .prefix = prefix ? prefix : "" + .prefix = prefix ? prefix : "", + .id = id, + .nr = nr, + .evsel = counter, }; print_metric_t pm = print_metric_std; void (*nl)(void *); @@ -693,7 +721,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval, perf_stat__print_shadow_stats(counter, uval, stat_config.aggr_mode == AGGR_GLOBAL ? 0 : - cpu_map__id_to_cpu(id), + first_shadow_cpu(counter, id), pm, nl, &os); @@ -705,6 +733,30 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval, } } +static void aggr_update_shadow(void) +{ + int cpu, cpu2, s2, id, s; + u64 val; + struct perf_evsel *counter; + + for (s = 0; s < aggr_map->nr; s++) { + id = aggr_map->map[s]; + evlist__for_each(evsel_list, counter) { + val = 0; + for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { + cpu2 = perf_evsel__cpus(counter)->map[cpu]; + s2 = aggr_get_id(evsel_list->cpus, cpu2); + if (s2 != id) + continue; + val += perf_counts(counter->counts, cpu, 0)->val; + } + val = val * counter->scale; + perf_stat__update_shadow_stats(counter, &val, + first_shadow_cpu(counter, id)); + } + } +} + static void print_aggr(char *prefix) { FILE *output = stat_config.output; @@ -716,6 +768,8 @@ static void print_aggr(char *prefix) if (!(aggr_map || aggr_get_id)) return; + aggr_update_shadow(); + for (s = 0; s < aggr_map->nr; s++) { id = aggr_map->map[s]; evlist__for_each(evsel_list, counter) { -- 2.4.3