mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Jiri Olsa <jolsa@kernel.org>
To: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: lkml <linux-kernel@vger.kernel.org>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Andi Kleen <ak@linux.intel.com>, David Ahern <dsahern@gmail.com>,
	Ingo Molnar <mingo@kernel.org>,
	Namhyung Kim <namhyung@kernel.org>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Stephane Eranian <eranian@google.com>
Subject: [PATCH 25/25] perf stat: Introduce --per-task option
Date: Wed, 10 Jun 2015 20:10:58 +0200	[thread overview]
Message-ID: <1433959858-31858-26-git-send-email-jolsa@kernel.org> (raw)
In-Reply-To: <1433959858-31858-1-git-send-email-jolsa@kernel.org>

Currently all the -p option PID arguments tasks values
get aggregated and printed as single values.

Adding --per-tasks option to print values per task.

  $ perf stat -e cycles,instructions --per-task -p 12451,16173
  ^C
   Performance counter stats for process id '12451,16173':

  TASK-12451                77,784      cycles
  TASK-16173                64,809      cycles
  TASK-12451                14,432      instructions
  TASK-16173                14,452      instructions

         3.854957122 seconds time elapsed

Also woks under interval mode:

  $ ./perf stat -e cycles,instructions --per-task -p 16431,16173 -I 1000
  #           time task                      counts unit events
       1.000085816 TASK-16173                     0      cycles
       1.000085816 TASK-16431         3,358,360,926      cycles
       1.000085816 TASK-16173                     0      instructions
       1.000085816 TASK-16431         9,062,422,086      instructions
       2.000212262 TASK-16173                65,386      cycles
       2.000212262 TASK-16431         3,349,355,309      cycles
       2.000212262 TASK-16173                12,151      instructions
       2.000212262 TASK-16431         9,039,401,422      instructions
       3.000333402 TASK-16173                62,797      cycles
       3.000333402 TASK-16431         3,357,140,183      cycles
       3.000333402 TASK-16173                12,208      instructions
       3.000333402 TASK-16431         9,058,080,762      instructions
  ^C     3.375949851 TASK-16173                     0      cycles
       3.375949851 TASK-16431         1,264,764,804      cycles
       3.375949851 TASK-16173                     0      instructions
       3.375949851 TASK-16431         3,414,532,317      instructions

Link: http://lkml.kernel.org/n/tip-0v0ixd9k7o9z1u8hqngm1coe@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-stat.c | 57 +++++++++++++++++++++++++++++++++++++++++++++--
 tools/perf/util/stat.h    |  1 +
 2 files changed, 56 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 4a7cad8debac..293d1029e2ba 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -237,6 +237,7 @@ process_counter_values(struct perf_evsel *evsel, int cpu, int thread,
 		count = &zero;
 
 	switch (aggr_mode) {
+	case AGGR_TASK:
 	case AGGR_CORE:
 	case AGGR_SOCKET:
 	case AGGR_NONE:
@@ -605,6 +606,11 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 			csv_output ? 0 : -4,
 			perf_evsel__cpus(evsel)->map[id], csv_sep);
 		break;
+	case AGGR_TASK:
+		fprintf(output, "TASK-%*d%s",
+			csv_output ? 0 : -8,
+			evsel->threads->map[id], csv_sep);
+		break;
 	case AGGR_GLOBAL:
 	default:
 		break;
@@ -753,6 +759,40 @@ static void print_aggr(char *prefix)
 	}
 }
 
+static void print_aggr_task(struct perf_evsel *counter, char *prefix)
+{
+	int nthreads = thread_map__nr(counter->threads);
+	int ncpus = cpu_map__nr(counter->cpus);
+	int cpu, thread;
+	double uval;
+
+	for (thread = 0; thread < nthreads; thread++) {
+		u64 ena = 0, run = 0, val = 0;
+
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			val += perf_counts(counter->counts, cpu, thread)->val;
+			ena += perf_counts(counter->counts, cpu, thread)->ena;
+			run += perf_counts(counter->counts, cpu, thread)->run;
+		}
+
+		if (prefix)
+			fprintf(output, "%s", prefix);
+
+		uval = val * counter->scale;
+
+		if (nsec_counter(counter))
+			nsec_printout(thread, 0, counter, uval);
+		else
+			abs_printout(thread, 0, counter, uval);
+
+		if (!csv_output)
+			print_noise(counter, 1.0);
+
+		print_running(run, ena);
+		fputc('\n', output);
+	}
+}
+
 /*
  * Print out the results of a single counter:
  * aggregated counts in system-wide mode
@@ -879,6 +919,9 @@ static void print_interval(char *prefix, struct timespec *ts)
 		case AGGR_NONE:
 			fprintf(output, "#           time CPU                counts %*s events\n", unit_width, "unit");
 			break;
+		case AGGR_TASK:
+			fprintf(output, "#           time task                      counts %*s events\n", unit_width, "unit");
+			break;
 		case AGGR_GLOBAL:
 		default:
 			fprintf(output, "#           time             counts %*s events\n", unit_width, "unit");
@@ -947,6 +990,10 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 	case AGGR_SOCKET:
 		print_aggr(prefix);
 		break;
+	case AGGR_TASK:
+		evlist__for_each(evsel_list, counter)
+			print_aggr_task(counter, prefix);
+		break;
 	case AGGR_GLOBAL:
 		evlist__for_each(evsel_list, counter)
 			print_counter_aggr(counter, prefix);
@@ -1034,6 +1081,7 @@ static int perf_stat_init_aggr_mode(void)
 		break;
 	case AGGR_NONE:
 	case AGGR_GLOBAL:
+	case AGGR_TASK:
 	default:
 		break;
 	}
@@ -1258,6 +1306,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "aggregate counts per processor socket", AGGR_SOCKET),
 	OPT_SET_UINT(0, "per-core", &aggr_mode,
 		     "aggregate counts per physical processor core", AGGR_CORE),
+	OPT_SET_UINT(0, "per-task", &aggr_mode,
+		     "aggregate counts per task", AGGR_TASK),
 	OPT_UINTEGER('D', "delay", &initial_delay,
 		     "ms to wait before starting measurement after program start"),
 	OPT_END()
@@ -1349,8 +1399,11 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		run_count = 1;
 	}
 
-	/* no_aggr, cgroup are for system-wide only */
-	if ((aggr_mode != AGGR_GLOBAL || nr_cgroups) &&
+	/*
+	 * no_aggr, cgroup are for system-wide only
+	 * --per-task is aggregated per task, we dont mix it with cpu mode
+	 */
+	if (((aggr_mode != AGGR_GLOBAL && aggr_mode != AGGR_TASK) || nr_cgroups) &&
 	    !target__has_cpu(&target)) {
 		fprintf(stderr, "both cgroup and no-aggregation "
 			"modes only available in system-wide mode\n");
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 615c779eb42a..e4c616af057d 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -29,6 +29,7 @@ enum aggr_mode {
 	AGGR_GLOBAL,
 	AGGR_SOCKET,
 	AGGR_CORE,
+	AGGR_TASK,
 };
 
 void update_stats(struct stats *stats, u64 val);
-- 
1.9.3


  parent reply	other threads:[~2015-06-10 18:15 UTC|newest]

Thread overview: 54+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-06-10 18:10 [RFC/PATCH 00/25] " Jiri Olsa
2015-06-10 18:10 ` [PATCH 01/25] perf tools: Fix python code with missing stat dependency Jiri Olsa
2015-06-10 18:55   ` Arnaldo Carvalho de Melo
2015-06-10 20:23     ` Jiri Olsa
2015-06-10 20:32       ` Arnaldo Carvalho de Melo
2015-06-13 10:10         ` Jiri Olsa
2015-06-10 18:10 ` [PATCH 02/25] perf tools: Introduce xyarray__zero function Jiri Olsa
2015-06-10 19:06   ` Arnaldo Carvalho de Melo
2015-06-10 20:01     ` Jiri Olsa
2015-06-10 20:17       ` Arnaldo Carvalho de Melo
2015-06-10 18:10 ` [PATCH 03/25] perf tools: Add reference counting for cpu_map object Jiri Olsa
2015-06-10 19:07   ` Arnaldo Carvalho de Melo
2015-06-10 20:07     ` Jiri Olsa
2015-06-10 18:10 ` [PATCH 04/25] perf tools: Add reference counting for thread_map object Jiri Olsa
2015-06-10 19:08   ` Arnaldo Carvalho de Melo
2015-06-10 20:24     ` Jiri Olsa
2015-06-10 18:10 ` [PATCH 05/25] perf tools: Propagate cpu maps through the evlist Jiri Olsa
2015-06-10 19:10   ` Arnaldo Carvalho de Melo
2015-06-10 18:10 ` [PATCH 06/25] perf tools: Propagate thread " Jiri Olsa
2015-06-10 19:09   ` Arnaldo Carvalho de Melo
2015-06-10 20:25     ` Jiri Olsa
2015-06-11 13:07       ` Namhyung Kim
2015-06-12 20:13         ` Jiri Olsa
2015-06-10 18:10 ` [PATCH 07/25] perf tools: Make perf_evsel__(nr_)cpus generic Jiri Olsa
2015-06-10 18:10 ` [PATCH 08/25] perf stat: Introduce perf_counts__(alloc|free|reset) functions Jiri Olsa
2015-06-10 18:54   ` Arnaldo Carvalho de Melo
2015-06-10 20:22     ` Jiri Olsa
2015-06-10 18:10 ` [PATCH 09/25] perf stat: Introduce perf_counts function Jiri Olsa
2015-06-10 18:10 ` [PATCH 10/25] perf stat: Use xyarray for cpu evsel counts Jiri Olsa
2015-06-10 18:10 ` [PATCH 11/25] perf stat: Make stats work over the thread dimension Jiri Olsa
2015-06-10 18:10 ` [PATCH 12/25] perf stat: Rename struct perf_counts::cpu member to values Jiri Olsa
2015-06-10 18:10 ` [PATCH 13/25] perf stat: Move perf_evsel__(alloc|free|reset)_stat_priv into evsel object Jiri Olsa
2015-06-10 18:49   ` Arnaldo Carvalho de Melo
2015-06-10 20:21     ` Jiri Olsa
2015-06-10 18:10 ` [PATCH 14/25] perf stat: Move perf_evsel__(alloc|free)_prev_raw_counts " Jiri Olsa
2015-06-10 18:10 ` [PATCH 15/25] perf stat: Move perf_evlist__(alloc|free)_stats into evlist object Jiri Olsa
2015-06-10 19:13   ` Arnaldo Carvalho de Melo
2015-06-10 20:25     ` Jiri Olsa
2015-06-10 18:10 ` [PATCH 16/25] perf stat: Introduce perf_evsel__alloc_stats function Jiri Olsa
2015-06-10 18:10 ` [PATCH 17/25] perf stat: Introduce perf_evsel__read function Jiri Olsa
2015-06-10 18:10 ` [PATCH 18/25] perf stat: Introduce read_counters function Jiri Olsa
2015-06-10 18:10 ` [PATCH 19/25] perf stat: Separate counters reading and processing Jiri Olsa
2015-06-10 18:10 ` [PATCH 20/25] perf stat: Move zero_per_pkg into counter process code Jiri Olsa
2015-06-10 18:10 ` [PATCH 21/25] perf stat: Move perf_stat initialization " Jiri Olsa
2015-06-10 18:47   ` David Ahern
2015-06-10 20:21     ` Jiri Olsa
2015-06-10 18:10 ` [PATCH 22/25] perf stat: Remove perf_evsel__read_cb function Jiri Olsa
2015-06-10 18:10 ` [PATCH 23/25] perf stat: Rename print_interval to process_interval Jiri Olsa
2015-06-10 18:10 ` [PATCH 24/25] perf stat: Introduce print_counters function Jiri Olsa
2015-06-10 18:10 ` Jiri Olsa [this message]
2015-06-10 18:44   ` [PATCH 25/25] perf stat: Introduce --per-task option David Ahern
2015-06-10 18:54     ` Jiri Olsa
2015-06-10 19:28     ` Arnaldo Carvalho de Melo
2015-06-10 18:16 ` [RFC/PATCH 00/25] " Jiri Olsa

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1433959858-31858-26-git-send-email-jolsa@kernel.org \
    --to=jolsa@kernel.org \
    --cc=a.p.zijlstra@chello.nl \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=ak@linux.intel.com \
    --cc=dsahern@gmail.com \
    --cc=eranian@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=namhyung@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

Powered by JetHome