Commit 5d67be97 authored by Anton Blanchard's avatar Anton Blanchard Committed by Ingo Molnar
Browse files

perf report/annotate/script: Add option to specify a CPU range 



Add an option to perf report/annotate/script to specify which
CPUs to operate on. This enables us to take a single system wide
profile and analyse each CPU (or group of CPUs) in isolation.

This was useful when profiling a multiprocess workload where the
bottleneck was on one CPU but this was hidden in the overall
profile. Per process and per thread breakdowns didn't help
because multiple processes were running on each CPU and no
single process consumed an entire CPU.

The patch converts the list of CPUs returned by cpu_map__new
into a bitmap for fast lookup. I wanted to use -C to be
consistent with perf top/record/stat, but unfortunately perf
report already uses -C <comms>.

 v2: Incorporate suggestions from David Ahern:
	- Added -c to perf script
	- Check that SAMPLE_CPU is set when -c is used
	- Update documentation

 v3: Create perf_session__cpu_bitmap()

Signed-off-by: default avatarAnton Blanchard <anton@samba.org>
Acked-by: default avatarDavid Ahern <dsahern@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Link: http://lkml.kernel.org/r/20110704215750.11647eb9@kryten


Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
parent 9f8b6a6c

tools/perf/Documentation/perf-annotate.txt

+6 −0
Original line number Diff line number Diff line
@@ -66,6 +66,12 @@ OPTIONS 
	used. This interfaces starts by centering on the line with more

	samples, TAB/UNTAB cycles through the lines with more samples.



-c::

--cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can

	be provided as a comma-separated list with no space: 0,1. Ranges of

	CPUs are specified with -: 0-2. Default is to report samples on all

	CPUs.



SEE ALSO

--------

linkperf:perf-record[1], linkperf:perf-report[1]

tools/perf/Documentation/perf-report.txt

+6 −0
Original line number Diff line number Diff line
@@ -128,6 +128,12 @@ OPTIONS 
--symfs=<directory>::

        Look for files with symbols relative to this directory.



-c::

--cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can

	be provided as a comma-separated list with no space: 0,1. Ranges of

	CPUs are specified with -: 0-2. Default is to report samples on all

	CPUs.



SEE ALSO

--------

linkperf:perf-stat[1]

tools/perf/Documentation/perf-script.txt

+6 −0
Original line number Diff line number Diff line
@@ -182,6 +182,12 @@ OPTIONS 
--hide-call-graph::

        When printing symbols do not display call chain.



-c::

--cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can

	be provided as a comma-separated list with no space: 0,1. Ranges of

	CPUs are specified with -: 0-2. Default is to report samples on all

	CPUs.



SEE ALSO

--------

linkperf:perf-record[1], linkperf:perf-script-perl[1],

tools/perf/builtin-annotate.c

+15 −0
Original line number Diff line number Diff line
@@ -28,6 +28,8 @@ 
#include "util/hist.h"

#include "util/session.h"



#include <linux/bitmap.h>



static char		const *input_name = "perf.data";



static bool		force, use_tui, use_stdio;
@@ -38,6 +40,9 @@ static bool print_line; 


static const char *sym_hist_filter;



static const char	*cpu_list;

static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);



static int perf_evlist__add_sample(struct perf_evlist *evlist,

				   struct perf_sample *sample,

				   struct perf_evsel *evsel,
@@ -90,6 +95,9 @@ static int process_sample_event(union perf_event *event, 
		return -1;

	}



	if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))

		return 0;



	if (!al.filtered &&

	    perf_evlist__add_sample(session->evlist, sample, evsel, &al)) {

		pr_warning("problem incrementing symbol count, "
@@ -177,6 +185,12 @@ static int __cmd_annotate(void) 
	if (session == NULL)

		return -ENOMEM;



	if (cpu_list) {

		ret = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap);

		if (ret)

			goto out_delete;

	}



	ret = perf_session__process_events(session, &event_ops);

	if (ret)

		goto out_delete;
@@ -252,6 +266,7 @@ static const struct option options[] = { 
		    "print matching source lines (may be slow)"),

	OPT_BOOLEAN('P', "full-paths", &full_paths,

		    "Don't shorten the displayed pathnames"),

	OPT_STRING('c', "cpu", &cpu_list, "cpu", "list of cpus to profile"),

	OPT_END()

};

tools/perf/builtin-report.c

+15 −0
Original line number Diff line number Diff line
@@ -33,6 +33,8 @@ 
#include "util/sort.h"

#include "util/hist.h"



#include <linux/bitmap.h>



static char		const *input_name = "perf.data";



static bool		force, use_tui, use_stdio;
@@ -49,6 +51,9 @@ static char callchain_default_opt[] = "fractal,0.5,callee"; 
static bool		inverted_callchain;

static symbol_filter_t	annotate_init;



static const char	*cpu_list;

static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);



static int perf_session__add_hist_entry(struct perf_session *session,

					struct addr_location *al,

					struct perf_sample *sample,
@@ -117,6 +122,9 @@ static int process_sample_event(union perf_event *event, 
	if (al.filtered || (hide_unresolved && al.sym == NULL))

		return 0;



	if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))

		return 0;



	if (al.map != NULL)

		al.map->dso->hit = 1;
@@ -263,6 +271,12 @@ static int __cmd_report(void) 
	if (session == NULL)

		return -ENOMEM;



	if (cpu_list) {

		ret = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap);

		if (ret)

			goto out_delete;

	}



	if (show_threads)

		perf_read_values_init(&show_threads_values);
@@ -473,6 +487,7 @@ static const struct option options[] = { 
		    "Only display entries resolved to a symbol"),

	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",

		    "Look for files with symbols relative to this directory"),

	OPT_STRING('c', "cpu", &cpu_list, "cpu", "list of cpus to profile"),

	OPT_END()

};

CRA Git | Maintained and supported by SUSTech CRA and CCSE