From ded2e511a8af9f14482b11225f73db63231fc7a4 Mon Sep 17 00:00:00 2001 From: Pierre Gondois Date: Wed, 24 Feb 2021 18:24:10 +0000 Subject: perf tools: Cast (struct timeval).tv_sec when printing The musl-libc [1] defines (struct timeval).tv_sec as a 'long long' for arm and other architectures. The default build having a '-Wformat' flag, not casting the field when printing prevents from building perf. This patch casts the (struct timeval).tv_sec fields to the expected format. [1] git://git.musl-libc.org/musl Signed-off-by: Pierre Gondois Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Douglas.raillard@arm.com Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210224182410.5366-1-Pierre.Gondois@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/stat-display.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/util/stat-display.c') diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index cce7a76d6473..7f09cdaf5b60 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -983,7 +983,7 @@ static void print_interval(struct perf_stat_config *config, if (config->interval_clear) puts(CONSOLE_CLEAR); - sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, config->csv_sep); + sprintf(prefix, "%6lu.%09lu%s", (unsigned long) ts->tv_sec, ts->tv_nsec, config->csv_sep); if ((num_print_interval == 0 && !config->csv_output) || config->interval_clear) { switch (config->aggr_mode) { -- cgit v1.2.3 From 0bdad97801af5913101179a5de3f54b0eb88deea Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Fri, 19 Mar 2021 15:01:55 +0800 Subject: 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 Acked-by: Andi Kleen Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Jin Yao Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210319070156.20394-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-stat.txt | 9 +++++++++ tools/perf/builtin-stat.c | 7 +++++++ tools/perf/util/config.c | 3 +++ tools/perf/util/stat-display.c | 6 ++++++ tools/perf/util/stat.h | 2 ++ 5 files changed, 27 insertions(+) (limited to 'tools/perf/util/stat-display.c') diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 744211fa8c18..6ec5960b08c3 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -482,6 +482,15 @@ convenient for post processing. --summary:: Print summary for interval mode (-I). +--no-csv-summary:: +Don't print 'summary' at the first column for CVS summary output. +This option must be used with -x and --summary. + +This option can be enabled in perf config by setting the variable +'stat.no-csv-summary'. + +$ perf config stat.no-csv-summary=true + EXAMPLES -------- diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 4bb48c6b6698..2a2c15cac80a 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1093,6 +1093,11 @@ void perf_stat__set_big_num(int set) stat_config.big_num = (set != 0); } +void perf_stat__set_no_csv_summary(int set) +{ + stat_config.no_csv_summary = (set != 0); +} + static int stat__set_big_num(const struct option *opt __maybe_unused, const char *s __maybe_unused, int unset) { @@ -1249,6 +1254,8 @@ static struct option stat_options[] = { "threads of same physical core"), OPT_BOOLEAN(0, "summary", &stat_config.summary, "print summary for interval mode"), + OPT_BOOLEAN(0, "no-csv-summary", &stat_config.no_csv_summary, + "don't print 'summary' for CSV summary output"), OPT_BOOLEAN(0, "quiet", &stat_config.quiet, "don't print output (useful with record)"), #ifdef HAVE_LIBPFM diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 2daeaa9a4a24..6bcb5ef221f8 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -457,6 +457,9 @@ static int perf_stat_config(const char *var, const char *value) if (!strcmp(var, "stat.big-num")) perf_stat__set_big_num(perf_config_bool(var, value)); + if (!strcmp(var, "stat.no-csv-summary")) + perf_stat__set_no_csv_summary(perf_config_bool(var, value)); + /* Add other config variables here. */ return 0; } diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 7f09cdaf5b60..d3137bc17065 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -439,6 +439,12 @@ static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int if (counter->cgrp) os.nfields++; } + + 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); diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 41107b8deac5..48e6a06233fa 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -128,6 +128,7 @@ struct perf_stat_config { bool all_user; bool percore_show_thread; bool summary; + bool no_csv_summary; bool metric_no_group; bool metric_no_merge; bool stop_read_counter; @@ -160,6 +161,7 @@ struct perf_stat_config { }; void perf_stat__set_big_num(int set); +void perf_stat__set_no_csv_summary(int set); void update_stats(struct stats *stats, u64 val); double avg_stats(struct stats *stats); -- cgit v1.2.3 From f07952b17969777196512368a216baae1ad45ea6 Mon Sep 17 00:00:00 2001 From: Alexander Antonov Date: Mon, 19 Apr 2021 12:41:44 +0300 Subject: perf stat: Basic support for iostat in perf Add basic flow for a new iostat mode in perf. Mode is intended to provide four I/O performance metrics per each PCIe root port: Inbound Read, Inbound Write, Outbound Read, Outbound Write. The actual code to compute the metrics and attribute it to root port is in follow-on patches. Signed-off-by: Alexander Antonov Acked-by: Namhyung Kim Cc: Alexander Shishkin Cc: Alexey V Bayduraev Cc: Andi Kleen Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20210419094147.15909-2-alexander.antonov@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 21 ++++++++++++++++- tools/perf/util/Build | 1 + tools/perf/util/iostat.c | 53 ++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/iostat.h | 47 +++++++++++++++++++++++++++++++++++++ tools/perf/util/stat-display.c | 40 +++++++++++++++++++++++-------- tools/perf/util/stat-shadow.c | 5 +++- tools/perf/util/stat.h | 1 + 7 files changed, 156 insertions(+), 12 deletions(-) create mode 100644 tools/perf/util/iostat.c create mode 100644 tools/perf/util/iostat.h (limited to 'tools/perf/util/stat-display.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 2a2c15cac80a..ba5b31aab86b 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -68,6 +68,7 @@ #include "util/affinity.h" #include "util/pfm.h" #include "util/bpf_counter.h" +#include "util/iostat.h" #include "asm/bug.h" #include @@ -212,7 +213,8 @@ static struct perf_stat_config stat_config = { .walltime_nsecs_stats = &walltime_nsecs_stats, .big_num = true, .ctl_fd = -1, - .ctl_fd_ack = -1 + .ctl_fd_ack = -1, + .iostat_run = false, }; static bool cpus_map_matched(struct evsel *a, struct evsel *b) @@ -1268,6 +1270,9 @@ static struct option stat_options[] = { "\t\t\t Optionally send control command completion ('ack\\n') to ack-fd descriptor.\n" "\t\t\t Alternatively, ctl-fifo / ack-fifo will be opened and used as ctl-fd / ack-fd.", parse_control_option), + OPT_CALLBACK_OPTARG(0, "iostat", &evsel_list, &stat_config, "default", + "measure I/O performance metrics provided by arch/platform", + iostat_parse), OPT_END() }; @@ -2341,6 +2346,17 @@ int cmd_stat(int argc, const char **argv) goto out; } + if (stat_config.iostat_run) { + status = iostat_prepare(evsel_list, &stat_config); + if (status) + goto out; + if (iostat_mode == IOSTAT_LIST) { + iostat_list(evsel_list, &stat_config); + goto out; + } else if (verbose) + iostat_list(evsel_list, &stat_config); + } + if (add_default_attributes()) goto out; @@ -2516,6 +2532,9 @@ int cmd_stat(int argc, const char **argv) perf_stat__exit_aggr_mode(); evlist__free_stats(evsel_list); out: + if (stat_config.iostat_run) + iostat_release(evsel_list); + zfree(&stat_config.walltime_run); if (smi_cost && smi_reset) diff --git a/tools/perf/util/Build b/tools/perf/util/Build index e3e12f9d4733..7dd815712d60 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -102,6 +102,7 @@ perf-y += rwsem.o perf-y += thread-stack.o perf-y += spark.o perf-y += topdown.o +perf-y += iostat.o perf-y += stream.o perf-$(CONFIG_AUXTRACE) += auxtrace.o perf-$(CONFIG_AUXTRACE) += intel-pt-decoder/ diff --git a/tools/perf/util/iostat.c b/tools/perf/util/iostat.c new file mode 100644 index 000000000000..57dd49da28fe --- /dev/null +++ b/tools/perf/util/iostat.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "util/iostat.h" +#include "util/debug.h" + +enum iostat_mode_t iostat_mode = IOSTAT_NONE; + +__weak int iostat_prepare(struct evlist *evlist __maybe_unused, + struct perf_stat_config *config __maybe_unused) +{ + return -1; +} + +__weak int iostat_parse(const struct option *opt __maybe_unused, + const char *str __maybe_unused, + int unset __maybe_unused) +{ + pr_err("iostat mode is not supported on current platform\n"); + return -1; +} + +__weak void iostat_list(struct evlist *evlist __maybe_unused, + struct perf_stat_config *config __maybe_unused) +{ +} + +__weak void iostat_release(struct evlist *evlist __maybe_unused) +{ +} + +__weak void iostat_print_header_prefix(struct perf_stat_config *config __maybe_unused) +{ +} + +__weak void iostat_print_metric(struct perf_stat_config *config __maybe_unused, + struct evsel *evsel __maybe_unused, + struct perf_stat_output_ctx *out __maybe_unused) +{ +} + +__weak void iostat_prefix(struct evlist *evlist __maybe_unused, + struct perf_stat_config *config __maybe_unused, + char *prefix __maybe_unused, + struct timespec *ts __maybe_unused) +{ +} + +__weak void iostat_print_counters(struct evlist *evlist __maybe_unused, + struct perf_stat_config *config __maybe_unused, + struct timespec *ts __maybe_unused, + char *prefix __maybe_unused, + iostat_print_counter_t print_cnt_cb __maybe_unused) +{ +} diff --git a/tools/perf/util/iostat.h b/tools/perf/util/iostat.h new file mode 100644 index 000000000000..23c1c46a331a --- /dev/null +++ b/tools/perf/util/iostat.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * perf iostat + * + * Copyright (C) 2020, Intel Corporation + * + * Authors: Alexander Antonov + */ + +#ifndef _IOSTAT_H +#define _IOSTAT_H + +#include +#include "util/stat.h" +#include "util/parse-events.h" +#include "util/evlist.h" + +struct option; +struct perf_stat_config; +struct evlist; +struct timespec; + +enum iostat_mode_t { + IOSTAT_NONE = -1, + IOSTAT_RUN = 0, + IOSTAT_LIST = 1 +}; + +extern enum iostat_mode_t iostat_mode; + +typedef void (*iostat_print_counter_t)(struct perf_stat_config *, struct evsel *, char *); + +int iostat_prepare(struct evlist *evlist, struct perf_stat_config *config); +int iostat_parse(const struct option *opt, const char *str, + int unset __maybe_unused); +void iostat_list(struct evlist *evlist, struct perf_stat_config *config); +void iostat_release(struct evlist *evlist); +void iostat_prefix(struct evlist *evlist, struct perf_stat_config *config, + char *prefix, struct timespec *ts); +void iostat_print_header_prefix(struct perf_stat_config *config); +void iostat_print_metric(struct perf_stat_config *config, struct evsel *evsel, + struct perf_stat_output_ctx *out); +void iostat_print_counters(struct evlist *evlist, + struct perf_stat_config *config, struct timespec *ts, + char *prefix, iostat_print_counter_t print_cnt_cb); + +#endif /* _IOSTAT_H */ diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index d3137bc17065..98664caef6af 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -17,6 +17,7 @@ #include "cgroup.h" #include #include "util.h" +#include "iostat.h" #define CNTR_NOT_SUPPORTED "" #define CNTR_NOT_COUNTED "" @@ -310,6 +311,11 @@ static void print_metric_header(struct perf_stat_config *config, struct outstate *os = ctx; char tbuf[1024]; + /* In case of iostat, print metric header for first root port only */ + if (config->iostat_run && + os->evsel->priv != os->evsel->evlist->selected->priv) + return; + if (!valid_only_metric(unit)) return; unit = fixunit(tbuf, os->evsel, unit); @@ -958,8 +964,11 @@ static void print_metric_headers(struct perf_stat_config *config, if (config->csv_output) { if (config->interval) fputs("time,", config->output); - fputs(aggr_header_csv[config->aggr_mode], 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) { @@ -989,7 +998,8 @@ static void print_interval(struct perf_stat_config *config, if (config->interval_clear) puts(CONSOLE_CLEAR); - sprintf(prefix, "%6lu.%09lu%s", (unsigned long) ts->tv_sec, ts->tv_nsec, config->csv_sep); + if (!config->iostat_run) + sprintf(prefix, "%6lu.%09lu%s", (unsigned long) ts->tv_sec, ts->tv_nsec, config->csv_sep); if ((num_print_interval == 0 && !config->csv_output) || config->interval_clear) { switch (config->aggr_mode) { @@ -1025,9 +1035,11 @@ static void print_interval(struct perf_stat_config *config, break; case AGGR_GLOBAL: default: - fprintf(output, "# time"); - if (!metric_only) - fprintf(output, " counts %*s events\n", unit_width, "unit"); + if (!config->iostat_run) { + fprintf(output, "# time"); + if (!metric_only) + fprintf(output, " counts %*s events\n", unit_width, "unit"); + } case AGGR_UNSET: break; } @@ -1220,6 +1232,9 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf 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 @@ -1232,7 +1247,7 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf print_metric_headers(config, evlist, prefix, false); if (num_print_iv++ == 25) num_print_iv = 0; - if (config->aggr_mode == AGGR_GLOBAL && prefix) + if (config->aggr_mode == AGGR_GLOBAL && prefix && !config->iostat_run) fprintf(config->output, "%s", prefix); } @@ -1249,11 +1264,16 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf } break; case AGGR_GLOBAL: - evlist__for_each_entry(evlist, counter) { - print_counter_aggr(config, counter, prefix); + 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); } - if (metric_only) - fputc('\n', config->output); break; case AGGR_NONE: if (metric_only) diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 3f800e71126f..39967a45f55b 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -11,6 +11,7 @@ #include "cgroup.h" #include "units.h" #include +#include "iostat.h" /* * AGGR_GLOBAL: Use CPU 0 @@ -962,7 +963,9 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, struct metric_event *me; int num = 1; - if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) { + if (config->iostat_run) { + iostat_print_metric(config, evsel, out); + } else if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) { total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd); if (total) { diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 48e6a06233fa..32c8527de347 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -133,6 +133,7 @@ struct perf_stat_config { bool metric_no_merge; bool stop_read_counter; bool quiet; + bool iostat_run; FILE *output; unsigned int interval; unsigned int timeout; -- cgit v1.2.3 From 12279429d8620fe0cb2cdc0ba68cae3cc2c826f9 Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Tue, 27 Apr 2021 15:01:20 +0800 Subject: perf stat: Uniquify hybrid event name It would be useful to let user know the pmu which the event belongs to. perf-stat has supported '--no-merge' option and it can print the pmu name after the event name, such as: "cycles [cpu_core]" Now this option is enabled by default for hybrid platform but change the format to: "cpu_core/cycles/" If user configs the name, we still use the user specified name. Signed-off-by: Jin Yao Reviewed-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ingo Molnar Cc: Kan Liang Cc: Peter Zijlstra ink: https://lore.kernel.org/r/20210427070139.25256-8-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 4 ++++ tools/perf/util/evsel.h | 1 + tools/perf/util/parse-events.c | 3 +++ tools/perf/util/stat-display.c | 15 +++++++++++++-- 4 files changed, 21 insertions(+), 2 deletions(-) (limited to 'tools/perf/util/stat-display.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 5ec2190e45cd..835e3696b9ce 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -69,6 +69,7 @@ #include "util/pfm.h" #include "util/bpf_counter.h" #include "util/iostat.h" +#include "util/pmu-hybrid.h" #include "asm/bug.h" #include @@ -2402,6 +2403,9 @@ int cmd_stat(int argc, const char **argv) evlist__check_cpu_maps(evsel_list); + if (perf_pmu__has_hybrid()) + stat_config.no_merge = true; + /* * Initialize thread_map with comm names, * so we could print it out on output. diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 8f66cdcb338d..ad74c83bd35b 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -116,6 +116,7 @@ struct evsel { bool merged_stat; bool reset_group; bool errored; + bool use_config_name; struct hashmap *per_pkg_mask; struct evsel *leader; struct list_head config_terms; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 46ebd269a98d..f4628c886e30 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1567,6 +1567,9 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, if (!evsel) return -ENOMEM; + if (evsel->name) + evsel->use_config_name = true; + evsel->pmu_name = name ? strdup(name) : NULL; evsel->use_uncore_alias = use_uncore_alias; evsel->percore = config_term_percore(&evsel->config_terms); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 98664caef6af..0679129ad05e 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -18,6 +18,7 @@ #include #include "util.h" #include "iostat.h" +#include "pmu-hybrid.h" #define CNTR_NOT_SUPPORTED "" #define CNTR_NOT_COUNTED "" @@ -538,6 +539,7 @@ static void uniquify_event_name(struct evsel *counter) { char *new_name; char *config; + int ret = 0; if (counter->uniquified_name || !counter->pmu_name || !strncmp(counter->name, counter->pmu_name, @@ -552,8 +554,17 @@ static void uniquify_event_name(struct evsel *counter) counter->name = new_name; } } else { - if (asprintf(&new_name, - "%s [%s]", counter->name, counter->pmu_name) > 0) { + if (perf_pmu__has_hybrid()) { + if (!counter->use_config_name) { + 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; } -- cgit v1.2.3 From 92637cc7295510f4b3cb945cafcaec97c82e42f2 Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Tue, 27 Apr 2021 15:01:28 +0800 Subject: 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 cpu_core/cycles/ S0-D0-C33 0 cpu_core/cycles/ S0-D0-C34 0 cpu_core/cycles/ S0-D0-C35 0 cpu_core/cycles/ S0-D0-C36 0 cpu_core/cycles/ S0-D0-C37 0 cpu_core/cycles/ S0-D0-C38 0 cpu_core/cycles/ S0-D0-C39 0 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 Co-developed-by: Jiri Olsa Reviewed-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ingo Molnar Cc: Kan Liang Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20210427070139.25256-16-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/stat-display.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools/perf/util/stat-display.c') diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 0679129ad05e..a76fff5e7d83 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -667,6 +667,9 @@ static void print_counter_aggrdata(struct perf_stat_config *config, if (!collect_data(config, counter, aggr_cb, &ad)) return; + if (perf_pmu__has_hybrid() && ad.ena == 0) + return; + nr = ad.nr; ena = ad.ena; run = ad.run; -- cgit v1.2.3