From bfd8f72c2778f5bd63dc9eb6d23bd7a0d99cff6d Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Fri, 17 Nov 2017 13:42:58 -0800 Subject: perf record: Synthesize unit/scale/... in event update Move the code to synthesize event updates for scale/unit/cpus to a common utility file, and use it both from stat and record. This allows to access scale and other extra qualifiers from perf script. Signed-off-by: Andi Kleen Acked-by: Jiri Olsa Link: http://lkml.kernel.org/r/20171117214300.32746-2-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 62 +++-------------------------------------------- 1 file changed, 4 insertions(+), 58 deletions(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 59af5a8419e2..a027b4712e48 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -458,19 +458,8 @@ static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *inf workload_exec_errno = info->si_value.sival_int; } -static bool has_unit(struct perf_evsel *counter) -{ - return counter->unit && *counter->unit; -} - -static bool has_scale(struct perf_evsel *counter) -{ - return counter->scale != 1; -} - static int perf_stat_synthesize_config(bool is_pipe) { - struct perf_evsel *counter; int err; if (is_pipe) { @@ -482,53 +471,10 @@ static int perf_stat_synthesize_config(bool is_pipe) } } - /* - * Synthesize other events stuff not carried within - * attr event - unit, scale, name - */ - evlist__for_each_entry(evsel_list, counter) { - if (!counter->supported) - continue; - - /* - * Synthesize unit and scale only if it's defined. - */ - if (has_unit(counter)) { - err = perf_event__synthesize_event_update_unit(NULL, counter, process_synthesized_event); - if (err < 0) { - pr_err("Couldn't synthesize evsel unit.\n"); - return err; - } - } - - if (has_scale(counter)) { - err = perf_event__synthesize_event_update_scale(NULL, counter, process_synthesized_event); - if (err < 0) { - pr_err("Couldn't synthesize evsel scale.\n"); - return err; - } - } - - if (counter->own_cpus) { - err = perf_event__synthesize_event_update_cpus(NULL, counter, process_synthesized_event); - if (err < 0) { - pr_err("Couldn't synthesize evsel scale.\n"); - return err; - } - } - - /* - * Name is needed only for pipe output, - * perf.data carries event names. - */ - if (is_pipe) { - err = perf_event__synthesize_event_update_name(NULL, counter, process_synthesized_event); - if (err < 0) { - pr_err("Couldn't synthesize evsel name.\n"); - return err; - } - } - } + err = perf_event__synthesize_extra_attr(NULL, + evsel_list, + process_synthesized_event, + is_pipe); err = perf_event__synthesize_thread_map2(NULL, evsel_list->threads, process_synthesized_event, -- cgit v1.2.3 From 1fcd03946b52b8a57a6692fedd4406b45baedfe6 Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Tue, 5 Dec 2017 22:03:04 +0800 Subject: perf stat: Update per-thread shadow stats The functions perf_stat__update_shadow_stats() is called to update the shadow stats on a set of static variables. But the static variables are the limitations to be extended to support per-thread shadow stats. This patch lets the perf_stat__update_shadow_stats() support to update the shadow stats on a input parameter 'st' and uses update_runtime_stat() to update the stats. It will not directly update the static variables as before. Signed-off-by: Jin Yao Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Kan Liang Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1512482591-4646-5-git-send-email-yao.jin@linux.intel.com [ Rename 'stat' variables to 'st' to build on centos:{5,6} and others where it shadows a global declaration ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index a027b4712e48..3f4a2c21b824 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1214,7 +1214,8 @@ static void aggr_update_shadow(void) val += perf_counts(counter->counts, cpu, 0)->val; } perf_stat__update_shadow_stats(counter, val, - first_shadow_cpu(counter, id)); + first_shadow_cpu(counter, id), + &rt_stat); } } } -- cgit v1.2.3 From e0128b30dbfb2884530251b4accdffdbf55a6b72 Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Tue, 5 Dec 2017 22:03:05 +0800 Subject: perf stat: Print per-thread shadow stats The function perf_stat__print_shadow_stats() is called to print the shadow stats on a set of static variables. But the static variables are the limitations to support per-thread shadow stats. This patch lets the perf_stat__print_shadow_stats() support to print the shadow stats from a input parameter 'st'. It will not directly get value from static variable. Instead, it now uses runtime_stat_avg() and runtime_stat_n() to get and compute the values. Signed-off-by: Jin Yao Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Kan Liang Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1512482591-4646-6-git-send-email-yao.jin@linux.intel.com [ Rename 'stat' variables to 'st' to build on centos:{5,6} and others where it shadows a global declaration ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 3f4a2c21b824..097a694d16f2 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1097,7 +1097,8 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg) } static void printout(int id, int nr, struct perf_evsel *counter, double uval, - char *prefix, u64 run, u64 ena, double noise) + char *prefix, u64 run, u64 ena, double noise, + struct runtime_stat *st) { struct perf_stat_output_ctx out; struct outstate os = { @@ -1190,7 +1191,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval, perf_stat__print_shadow_stats(counter, uval, first_shadow_cpu(counter, id), - &out, &metric_events); + &out, &metric_events, st); if (!csv_output && !metric_only) { print_noise(counter, noise); print_running(run, ena); @@ -1335,7 +1336,8 @@ static void print_aggr(char *prefix) fprintf(output, "%s", prefix); uval = val * counter->scale; - printout(id, nr, counter, uval, prefix, run, ena, 1.0); + printout(id, nr, counter, uval, prefix, run, ena, 1.0, + &rt_stat); if (!metric_only) fputc('\n', output); } @@ -1365,7 +1367,8 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix) fprintf(output, "%s", prefix); uval = val * counter->scale; - printout(thread, 0, counter, uval, prefix, run, ena, 1.0); + printout(thread, 0, counter, uval, prefix, run, ena, 1.0, + &rt_stat); fputc('\n', output); } } @@ -1402,7 +1405,8 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix) fprintf(output, "%s", prefix); uval = cd.avg * counter->scale; - printout(-1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled, cd.avg); + printout(-1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled, + cd.avg, &rt_stat); if (!metric_only) fprintf(output, "\n"); } @@ -1441,7 +1445,8 @@ static void print_counter(struct perf_evsel *counter, char *prefix) fprintf(output, "%s", prefix); uval = val * counter->scale; - printout(cpu, 0, counter, uval, prefix, run, ena, 1.0); + printout(cpu, 0, counter, uval, prefix, run, ena, 1.0, + &rt_stat); fputc('\n', output); } @@ -1473,7 +1478,8 @@ static void print_no_aggr_metric(char *prefix) run = perf_counts(counter->counts, cpu, 0)->run; uval = val * counter->scale; - printout(cpu, 0, counter, uval, prefix, run, ena, 1.0); + printout(cpu, 0, counter, uval, prefix, run, ena, 1.0, + &rt_stat); } fputc('\n', stat_config.output); } @@ -1529,7 +1535,8 @@ static void print_metric_headers(const char *prefix, bool no_indent) perf_stat__print_shadow_stats(counter, 0, 0, &out, - &metric_events); + &metric_events, + &rt_stat); } fputc('\n', stat_config.output); } -- cgit v1.2.3 From 56739444d861daa050624d40c7adff32c73e9980 Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Tue, 5 Dec 2017 22:03:07 +0800 Subject: perf stat: Allocate shadow stats buffer for threads After perf_evlist__create_maps() being executed, we can get all threads from /proc. And via thread_map__nr(), we can also get the number of threads. With the number of threads, the patch allocates a buffer which will record the shadow stats for these threads. The buffer pointer is saved in stat_config. Signed-off-by: Jin Yao Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Kan Liang Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1512482591-4646-8-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 46 +++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 45 insertions(+), 1 deletion(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 097a694d16f2..4c492ac3ac07 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -214,8 +214,13 @@ static inline void diff_timespec(struct timespec *r, struct timespec *a, static void perf_stat__reset_stats(void) { + int i; + perf_evlist__reset_stats(evsel_list); perf_stat__reset_shadow_stats(); + + for (i = 0; i < stat_config.stats_num; i++) + perf_stat__reset_shadow_per_stat(&stat_config.stats[i]); } static int create_perf_stat_counter(struct perf_evsel *evsel) @@ -2495,6 +2500,35 @@ int process_cpu_map_event(struct perf_tool *tool, return set_maps(st); } +static int runtime_stat_new(struct perf_stat_config *config, int nthreads) +{ + int i; + + config->stats = calloc(nthreads, sizeof(struct runtime_stat)); + if (!config->stats) + return -1; + + config->stats_num = nthreads; + + for (i = 0; i < nthreads; i++) + runtime_stat__init(&config->stats[i]); + + return 0; +} + +static void runtime_stat_delete(struct perf_stat_config *config) +{ + int i; + + if (!config->stats) + return; + + for (i = 0; i < config->stats_num; i++) + runtime_stat__exit(&config->stats[i]); + + free(config->stats); +} + static const char * const stat_report_usage[] = { "perf stat report []", NULL, @@ -2750,8 +2784,15 @@ int cmd_stat(int argc, const char **argv) * Initialize thread_map with comm names, * so we could print it out on output. */ - if (stat_config.aggr_mode == AGGR_THREAD) + if (stat_config.aggr_mode == AGGR_THREAD) { thread_map__read_comms(evsel_list->threads); + if (target.system_wide) { + if (runtime_stat_new(&stat_config, + thread_map__nr(evsel_list->threads))) { + goto out; + } + } + } if (interval && interval < 100) { if (interval < 10) { @@ -2841,5 +2882,8 @@ out: sysfs__write_int(FREEZE_ON_SMI_PATH, 0); perf_evlist__delete(evsel_list); + + runtime_stat_delete(&stat_config); + return status; } -- cgit v1.2.3 From 14e72a21c783654ca7b6c897b6d6508c1abccd7d Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Tue, 5 Dec 2017 22:03:08 +0800 Subject: perf stat: Update or print per-thread stats If the stats pointer in stat_config structure is not null, it will update the per-thread stats or print the per-thread stats on this buffer. Signed-off-by: Jin Yao Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Kan Liang Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1512482591-4646-9-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 4c492ac3ac07..f4129a5fbb01 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1372,8 +1372,13 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix) fprintf(output, "%s", prefix); uval = val * counter->scale; - printout(thread, 0, counter, uval, prefix, run, ena, 1.0, - &rt_stat); + + if (stat_config.stats) + printout(thread, 0, counter, uval, prefix, run, ena, + 1.0, &stat_config.stats[thread]); + else + printout(thread, 0, counter, uval, prefix, run, ena, + 1.0, &rt_stat); fputc('\n', output); } } -- cgit v1.2.3 From 1d9f8d1b824bf69cf984c1c36e5641b51eea42bb Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Tue, 5 Dec 2017 22:03:10 +0800 Subject: perf stat: Remove --per-thread pid/tid limitation Currently, if we execute 'perf stat --per-thread' without specifying pid/tid, perf will return error. root@skl:/tmp# perf stat --per-thread The --per-thread option is only available when monitoring via -p -t options. -p, --pid stat events on existing process id -t, --tid stat events on existing thread id This patch removes this limitation. If no pid/tid specified, it returns all threads (get threads from /proc). Note that it doesn't support cpu_list yet so if it's a cpu_list case, then skip. Signed-off-by: Jin Yao Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Kan Liang Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1512482591-4646-11-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index f4129a5fbb01..ee708ba6f79a 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -277,7 +277,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel) attr->enable_on_exec = 1; } - if (target__has_cpu(&target)) + if (target__has_cpu(&target) && !target__has_per_thread(&target)) return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel)); return perf_evsel__open_per_thread(evsel, evsel_list->threads); @@ -340,7 +340,7 @@ static int read_counter(struct perf_evsel *counter) int nthreads = thread_map__nr(evsel_list->threads); int ncpus, cpu, thread; - if (target__has_cpu(&target)) + if (target__has_cpu(&target) && !target__has_per_thread(&target)) ncpus = perf_evsel__nr_cpus(counter); else ncpus = 1; @@ -2743,12 +2743,16 @@ int cmd_stat(int argc, const char **argv) run_count = 1; } - if ((stat_config.aggr_mode == AGGR_THREAD) && !target__has_task(&target)) { - fprintf(stderr, "The --per-thread option is only available " - "when monitoring via -p -t options.\n"); - parse_options_usage(NULL, stat_options, "p", 1); - parse_options_usage(NULL, stat_options, "t", 1); - goto out; + if ((stat_config.aggr_mode == AGGR_THREAD) && + !target__has_task(&target)) { + if (!target.system_wide || target.cpu_list) { + fprintf(stderr, "The --per-thread option is only " + "available when monitoring via -p -t -a " + "options or only --per-thread.\n"); + parse_options_usage(NULL, stat_options, "p", 1); + parse_options_usage(NULL, stat_options, "t", 1); + goto out; + } } /* @@ -2772,6 +2776,9 @@ int cmd_stat(int argc, const char **argv) target__validate(&target); + if ((stat_config.aggr_mode == AGGR_THREAD) && (target.system_wide)) + target.per_thread = true; + if (perf_evlist__create_maps(evsel_list, &target) < 0) { if (target__has_task(&target)) { pr_err("Problems finding threads of monitor\n"); -- cgit v1.2.3 From 29734550c996c259ffa8d32198439d6fe4b51320 Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Tue, 5 Dec 2017 22:03:11 +0800 Subject: perf stat: Resort '--per-thread' result There are many threads reported if we enable '--per-thread' globally. 1. Most of the threads are not counted or counting value 0. This patch removes these threads. 2. We also resort the threads in display according to the counting value. It's useful for user to see the hottest threads easily. For example, the new results would be: root@skl:/tmp# perf stat --per-thread ^C Performance counter stats for 'system wide': perf-24165 4.302433 cpu-clock (msec) # 0.001 CPUs utilized vmstat-23127 1.562215 cpu-clock (msec) # 0.000 CPUs utilized irqbalance-2780 0.827851 cpu-clock (msec) # 0.000 CPUs utilized sshd-23111 0.278308 cpu-clock (msec) # 0.000 CPUs utilized thermald-2841 0.230880 cpu-clock (msec) # 0.000 CPUs utilized sshd-23058 0.207306 cpu-clock (msec) # 0.000 CPUs utilized kworker/0:2-19991 0.133983 cpu-clock (msec) # 0.000 CPUs utilized kworker/u16:1-18249 0.125636 cpu-clock (msec) # 0.000 CPUs utilized rcu_sched-8 0.085533 cpu-clock (msec) # 0.000 CPUs utilized kworker/u16:2-23146 0.077139 cpu-clock (msec) # 0.000 CPUs utilized gmain-2700 0.041789 cpu-clock (msec) # 0.000 CPUs utilized kworker/4:1-15354 0.028370 cpu-clock (msec) # 0.000 CPUs utilized kworker/6:0-17528 0.023895 cpu-clock (msec) # 0.000 CPUs utilized kworker/4:1H-1887 0.013209 cpu-clock (msec) # 0.000 CPUs utilized kworker/5:2-31362 0.011627 cpu-clock (msec) # 0.000 CPUs utilized watchdog/0-11 0.010892 cpu-clock (msec) # 0.000 CPUs utilized kworker/3:2-12870 0.010220 cpu-clock (msec) # 0.000 CPUs utilized ksoftirqd/0-7 0.008869 cpu-clock (msec) # 0.000 CPUs utilized watchdog/1-14 0.008476 cpu-clock (msec) # 0.000 CPUs utilized watchdog/7-50 0.002944 cpu-clock (msec) # 0.000 CPUs utilized watchdog/3-26 0.002893 cpu-clock (msec) # 0.000 CPUs utilized watchdog/4-32 0.002759 cpu-clock (msec) # 0.000 CPUs utilized watchdog/2-20 0.002429 cpu-clock (msec) # 0.000 CPUs utilized watchdog/6-44 0.001491 cpu-clock (msec) # 0.000 CPUs utilized watchdog/5-38 0.001477 cpu-clock (msec) # 0.000 CPUs utilized rcu_sched-8 10 context-switches # 0.117 M/sec kworker/u16:1-18249 7 context-switches # 0.056 M/sec sshd-23111 4 context-switches # 0.014 M/sec vmstat-23127 4 context-switches # 0.003 M/sec perf-24165 4 context-switches # 0.930 K/sec kworker/0:2-19991 3 context-switches # 0.022 M/sec kworker/u16:2-23146 3 context-switches # 0.039 M/sec kworker/4:1-15354 2 context-switches # 0.070 M/sec kworker/6:0-17528 2 context-switches # 0.084 M/sec sshd-23058 2 context-switches # 0.010 M/sec ksoftirqd/0-7 1 context-switches # 0.113 M/sec watchdog/0-11 1 context-switches # 0.092 M/sec watchdog/1-14 1 context-switches # 0.118 M/sec watchdog/2-20 1 context-switches # 0.412 M/sec watchdog/3-26 1 context-switches # 0.346 M/sec watchdog/4-32 1 context-switches # 0.362 M/sec watchdog/5-38 1 context-switches # 0.677 M/sec watchdog/6-44 1 context-switches # 0.671 M/sec watchdog/7-50 1 context-switches # 0.340 M/sec kworker/4:1H-1887 1 context-switches # 0.076 M/sec thermald-2841 1 context-switches # 0.004 M/sec gmain-2700 1 context-switches # 0.024 M/sec irqbalance-2780 1 context-switches # 0.001 M/sec kworker/3:2-12870 1 context-switches # 0.098 M/sec kworker/5:2-31362 1 context-switches # 0.086 M/sec kworker/u16:1-18249 2 cpu-migrations # 0.016 M/sec kworker/u16:2-23146 2 cpu-migrations # 0.026 M/sec rcu_sched-8 1 cpu-migrations # 0.012 M/sec sshd-23058 1 cpu-migrations # 0.005 M/sec perf-24165 8,833,385 cycles # 2.053 GHz vmstat-23127 1,702,699 cycles # 1.090 GHz irqbalance-2780 739,847 cycles # 0.894 GHz sshd-23111 269,506 cycles # 0.968 GHz thermald-2841 204,556 cycles # 0.886 GHz sshd-23058 158,780 cycles # 0.766 GHz kworker/0:2-19991 112,981 cycles # 0.843 GHz kworker/u16:1-18249 100,926 cycles # 0.803 GHz rcu_sched-8 74,024 cycles # 0.865 GHz kworker/u16:2-23146 55,984 cycles # 0.726 GHz gmain-2700 34,278 cycles # 0.820 GHz kworker/4:1-15354 20,665 cycles # 0.728 GHz kworker/6:0-17528 16,445 cycles # 0.688 GHz kworker/5:2-31362 9,492 cycles # 0.816 GHz watchdog/3-26 8,695 cycles # 3.006 GHz kworker/4:1H-1887 8,238 cycles # 0.624 GHz watchdog/4-32 7,580 cycles # 2.747 GHz kworker/3:2-12870 7,306 cycles # 0.715 GHz watchdog/2-20 7,274 cycles # 2.995 GHz watchdog/0-11 6,988 cycles # 0.642 GHz ksoftirqd/0-7 6,376 cycles # 0.719 GHz watchdog/1-14 5,340 cycles # 0.630 GHz watchdog/5-38 4,061 cycles # 2.749 GHz watchdog/6-44 3,976 cycles # 2.667 GHz watchdog/7-50 3,418 cycles # 1.161 GHz vmstat-23127 2,511,699 instructions # 1.48 insn per cycle perf-24165 1,829,908 instructions # 0.21 insn per cycle irqbalance-2780 1,190,204 instructions # 1.61 insn per cycle thermald-2841 143,544 instructions # 0.70 insn per cycle sshd-23111 128,138 instructions # 0.48 insn per cycle sshd-23058 57,654 instructions # 0.36 insn per cycle rcu_sched-8 44,063 instructions # 0.60 insn per cycle kworker/u16:1-18249 42,551 instructions # 0.42 insn per cycle kworker/0:2-19991 25,873 instructions # 0.23 insn per cycle kworker/u16:2-23146 21,407 instructions # 0.38 insn per cycle gmain-2700 13,691 instructions # 0.40 insn per cycle kworker/4:1-15354 12,964 instructions # 0.63 insn per cycle kworker/6:0-17528 10,034 instructions # 0.61 insn per cycle kworker/5:2-31362 5,203 instructions # 0.55 insn per cycle kworker/3:2-12870 4,866 instructions # 0.67 insn per cycle kworker/4:1H-1887 3,586 instructions # 0.44 insn per cycle ksoftirqd/0-7 3,463 instructions # 0.54 insn per cycle watchdog/0-11 3,135 instructions # 0.45 insn per cycle watchdog/1-14 3,135 instructions # 0.59 insn per cycle watchdog/2-20 3,135 instructions # 0.43 insn per cycle watchdog/3-26 3,135 instructions # 0.36 insn per cycle watchdog/4-32 3,135 instructions # 0.41 insn per cycle watchdog/5-38 3,135 instructions # 0.77 insn per cycle watchdog/6-44 3,135 instructions # 0.79 insn per cycle watchdog/7-50 3,135 instructions # 0.92 insn per cycle vmstat-23127 539,181 branches # 345.139 M/sec perf-24165 375,364 branches # 87.245 M/sec irqbalance-2780 262,092 branches # 316.593 M/sec thermald-2841 31,611 branches # 136.915 M/sec sshd-23111 21,874 branches # 78.596 M/sec sshd-23058 10,682 branches # 51.528 M/sec rcu_sched-8 8,693 branches # 101.633 M/sec kworker/u16:1-18249 7,891 branches # 62.808 M/sec kworker/0:2-19991 5,761 branches # 42.998 M/sec kworker/u16:2-23146 4,099 branches # 53.138 M/sec kworker/4:1-15354 2,755 branches # 97.110 M/sec gmain-2700 2,638 branches # 63.127 M/sec kworker/6:0-17528 2,216 branches # 92.739 M/sec kworker/5:2-31362 1,132 branches # 97.360 M/sec kworker/3:2-12870 1,081 branches # 105.773 M/sec kworker/4:1H-1887 725 branches # 54.887 M/sec ksoftirqd/0-7 707 branches # 79.716 M/sec watchdog/0-11 652 branches # 59.860 M/sec watchdog/1-14 652 branches # 76.923 M/sec watchdog/2-20 652 branches # 268.423 M/sec watchdog/3-26 652 branches # 225.372 M/sec watchdog/4-32 652 branches # 236.318 M/sec watchdog/5-38 652 branches # 441.435 M/sec watchdog/6-44 652 branches # 437.290 M/sec watchdog/7-50 652 branches # 221.467 M/sec vmstat-23127 8,960 branch-misses # 1.66% of all branches irqbalance-2780 3,047 branch-misses # 1.16% of all branches perf-24165 2,876 branch-misses # 0.77% of all branches sshd-23111 1,843 branch-misses # 8.43% of all branches thermald-2841 1,444 branch-misses # 4.57% of all branches sshd-23058 1,379 branch-misses # 12.91% of all branches kworker/u16:1-18249 982 branch-misses # 12.44% of all branches rcu_sched-8 893 branch-misses # 10.27% of all branches kworker/u16:2-23146 578 branch-misses # 14.10% of all branches kworker/0:2-19991 376 branch-misses # 6.53% of all branches gmain-2700 280 branch-misses # 10.61% of all branches kworker/6:0-17528 196 branch-misses # 8.84% of all branches kworker/4:1-15354 187 branch-misses # 6.79% of all branches kworker/5:2-31362 123 branch-misses # 10.87% of all branches watchdog/0-11 95 branch-misses # 14.57% of all branches watchdog/4-32 89 branch-misses # 13.65% of all branches kworker/3:2-12870 80 branch-misses # 7.40% of all branches watchdog/3-26 61 branch-misses # 9.36% of all branches kworker/4:1H-1887 60 branch-misses # 8.28% of all branches watchdog/2-20 52 branch-misses # 7.98% of all branches ksoftirqd/0-7 47 branch-misses # 6.65% of all branches watchdog/1-14 46 branch-misses # 7.06% of all branches watchdog/7-50 13 branch-misses # 1.99% of all branches watchdog/5-38 8 branch-misses # 1.23% of all branches watchdog/6-44 7 branch-misses # 1.07% of all branches 3.695150786 seconds time elapsed root@skl:/tmp# perf stat --per-thread -M IPC,CPI ^C Performance counter stats for 'system wide': vmstat-23127 2,000,783 inst_retired.any # 1.5 IPC thermald-2841 1,472,670 inst_retired.any # 1.3 IPC sshd-23111 977,374 inst_retired.any # 1.2 IPC perf-24163 483,779 inst_retired.any # 0.2 IPC gmain-2700 341,213 inst_retired.any # 0.9 IPC sshd-23058 148,891 inst_retired.any # 0.8 IPC rtkit-daemon-3288 71,210 inst_retired.any # 0.7 IPC kworker/u16:1-18249 39,562 inst_retired.any # 0.3 IPC rcu_sched-8 14,474 inst_retired.any # 0.8 IPC kworker/0:2-19991 7,659 inst_retired.any # 0.2 IPC kworker/4:1-15354 6,714 inst_retired.any # 0.8 IPC rtkit-daemon-3289 4,839 inst_retired.any # 0.3 IPC kworker/6:0-17528 3,321 inst_retired.any # 0.6 IPC kworker/5:2-31362 3,215 inst_retired.any # 0.5 IPC kworker/7:2-23145 3,173 inst_retired.any # 0.7 IPC kworker/4:1H-1887 1,719 inst_retired.any # 0.3 IPC watchdog/0-11 1,479 inst_retired.any # 0.3 IPC watchdog/1-14 1,479 inst_retired.any # 0.3 IPC watchdog/2-20 1,479 inst_retired.any # 0.4 IPC watchdog/3-26 1,479 inst_retired.any # 0.4 IPC watchdog/4-32 1,479 inst_retired.any # 0.3 IPC watchdog/5-38 1,479 inst_retired.any # 0.3 IPC watchdog/6-44 1,479 inst_retired.any # 0.7 IPC watchdog/7-50 1,479 inst_retired.any # 0.7 IPC kworker/u16:2-23146 1,408 inst_retired.any # 0.5 IPC perf-24163 2,249,872 cpu_clk_unhalted.thread vmstat-23127 1,352,455 cpu_clk_unhalted.thread thermald-2841 1,161,140 cpu_clk_unhalted.thread sshd-23111 807,827 cpu_clk_unhalted.thread gmain-2700 375,535 cpu_clk_unhalted.thread sshd-23058 194,071 cpu_clk_unhalted.thread kworker/u16:1-18249 114,306 cpu_clk_unhalted.thread rtkit-daemon-3288 103,547 cpu_clk_unhalted.thread kworker/0:2-19991 46,550 cpu_clk_unhalted.thread rcu_sched-8 18,855 cpu_clk_unhalted.thread rtkit-daemon-3289 17,549 cpu_clk_unhalted.thread kworker/4:1-15354 8,812 cpu_clk_unhalted.thread kworker/5:2-31362 6,812 cpu_clk_unhalted.thread kworker/4:1H-1887 5,270 cpu_clk_unhalted.thread kworker/6:0-17528 5,111 cpu_clk_unhalted.thread kworker/7:2-23145 4,667 cpu_clk_unhalted.thread watchdog/0-11 4,663 cpu_clk_unhalted.thread watchdog/1-14 4,663 cpu_clk_unhalted.thread watchdog/4-32 4,626 cpu_clk_unhalted.thread watchdog/5-38 4,403 cpu_clk_unhalted.thread watchdog/3-26 3,936 cpu_clk_unhalted.thread watchdog/2-20 3,850 cpu_clk_unhalted.thread kworker/u16:2-23146 2,654 cpu_clk_unhalted.thread watchdog/6-44 2,017 cpu_clk_unhalted.thread watchdog/7-50 2,017 cpu_clk_unhalted.thread vmstat-23127 2,000,783 inst_retired.any # 0.7 CPI thermald-2841 1,472,670 inst_retired.any # 0.8 CPI sshd-23111 977,374 inst_retired.any # 0.8 CPI perf-24163 495,037 inst_retired.any # 4.7 CPI gmain-2700 341,213 inst_retired.any # 1.1 CPI sshd-23058 148,891 inst_retired.any # 1.3 CPI rtkit-daemon-3288 71,210 inst_retired.any # 1.5 CPI kworker/u16:1-18249 39,562 inst_retired.any # 2.9 CPI rcu_sched-8 14,474 inst_retired.any # 1.3 CPI kworker/0:2-19991 7,659 inst_retired.any # 6.1 CPI kworker/4:1-15354 6,714 inst_retired.any # 1.3 CPI rtkit-daemon-3289 4,839 inst_retired.any # 3.6 CPI kworker/6:0-17528 3,321 inst_retired.any # 1.5 CPI kworker/5:2-31362 3,215 inst_retired.any # 2.1 CPI kworker/7:2-23145 3,173 inst_retired.any # 1.5 CPI kworker/4:1H-1887 1,719 inst_retired.any # 3.1 CPI watchdog/0-11 1,479 inst_retired.any # 3.2 CPI watchdog/1-14 1,479 inst_retired.any # 3.2 CPI watchdog/2-20 1,479 inst_retired.any # 2.6 CPI watchdog/3-26 1,479 inst_retired.any # 2.7 CPI watchdog/4-32 1,479 inst_retired.any # 3.1 CPI watchdog/5-38 1,479 inst_retired.any # 3.0 CPI watchdog/6-44 1,479 inst_retired.any # 1.4 CPI watchdog/7-50 1,479 inst_retired.any # 1.4 CPI kworker/u16:2-23146 1,408 inst_retired.any # 1.9 CPI perf-24163 2,302,323 cycles vmstat-23127 1,352,455 cycles thermald-2841 1,161,140 cycles sshd-23111 807,827 cycles gmain-2700 375,535 cycles sshd-23058 194,071 cycles kworker/u16:1-18249 114,306 cycles rtkit-daemon-3288 103,547 cycles kworker/0:2-19991 46,550 cycles rcu_sched-8 18,855 cycles rtkit-daemon-3289 17,549 cycles kworker/4:1-15354 8,812 cycles kworker/5:2-31362 6,812 cycles kworker/4:1H-1887 5,270 cycles kworker/6:0-17528 5,111 cycles kworker/7:2-23145 4,667 cycles watchdog/0-11 4,663 cycles watchdog/1-14 4,663 cycles watchdog/4-32 4,626 cycles watchdog/5-38 4,403 cycles watchdog/3-26 3,936 cycles watchdog/2-20 3,850 cycles kworker/u16:2-23146 2,654 cycles watchdog/6-44 2,017 cycles watchdog/7-50 2,017 cycles 2.175726600 seconds time elapsed Signed-off-by: Jin Yao Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Kan Liang Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1512482591-4646-12-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 77 ++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 66 insertions(+), 11 deletions(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index ee708ba6f79a..58d501d1f5fd 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1351,13 +1351,24 @@ static void print_aggr(char *prefix) } } -static void print_aggr_thread(struct perf_evsel *counter, char *prefix) +static int cmp_val(const void *a, const void *b) { - FILE *output = stat_config.output; - int nthreads = thread_map__nr(counter->threads); - int ncpus = cpu_map__nr(counter->cpus); - int cpu, thread; + 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 perf_evsel *counter, + int nthreads, int ncpus, + int *ret) +{ + int cpu, thread, i = 0; double uval; + struct perf_aggr_thread_value *buf; + + buf = calloc(nthreads, sizeof(struct perf_aggr_thread_value)); + if (!buf) + return NULL; for (thread = 0; thread < nthreads; thread++) { u64 ena = 0, run = 0, val = 0; @@ -1368,19 +1379,63 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix) run += perf_counts(counter->counts, cpu, thread)->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 = 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_evsel *counter, char *prefix) +{ + FILE *output = stat_config.output; + int nthreads = thread_map__nr(counter->threads); + int ncpus = cpu_map__nr(counter->cpus); + int thread, sorted_threads, id; + struct perf_aggr_thread_value *buf; + + buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads); + if (!buf) { + perror("cannot sort aggr thread"); + return; + } + + for (thread = 0; thread < sorted_threads; thread++) { if (prefix) fprintf(output, "%s", prefix); - uval = val * counter->scale; - + id = buf[thread].id; if (stat_config.stats) - printout(thread, 0, counter, uval, prefix, run, ena, - 1.0, &stat_config.stats[thread]); + printout(id, 0, buf[thread].counter, buf[thread].uval, + prefix, buf[thread].run, buf[thread].ena, 1.0, + &stat_config.stats[id]); else - printout(thread, 0, counter, uval, prefix, run, ena, - 1.0, &rt_stat); + printout(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 { -- cgit v1.2.3 From 3315d14f8eea27a845bd2e3a88341a35f4025866 Mon Sep 17 00:00:00 2001 From: Pravin Shedge Date: Wed, 6 Dec 2017 23:13:24 +0530 Subject: perf perf: Remove duplicate includes These duplicate includes have been found with scripts/checkincludes.pl but they have been removed manually to avoid removing false positives. Signed-off-by: Pravin Shedge Cc: David S. Miller Cc: Greg Kroah-Hartman Cc: Jiri Olsa Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1512582204-6493-1-git-send-email-pravin.shedge4linux@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 1 - 1 file changed, 1 deletion(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 58d501d1f5fd..98bf9d32f222 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -63,7 +63,6 @@ #include "util/group.h" #include "util/session.h" #include "util/tool.h" -#include "util/group.h" #include "util/string2.h" #include "util/metricgroup.h" #include "asm/bug.h" -- cgit v1.2.3