From 11018201b831e19304c0d639f105ad6c27e120b1 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Sun, 18 Oct 2009 22:29:23 +1100 Subject: perf stat: Add branch performance metric When we count both branches and branch-misses it is useful to print out the percentage of branch-misses: # perf stat -e branches -e branch-misses /bin/true Performance counter stats for '/bin/true': 401684 branches # 0.000 M/sec 23301 branch-misses # 5.801 % Signed-off-by: Anton Blanchard Cc: paulus@samba.org Cc: a.p.zijlstra@chello.nl LKML-Reference: <20091018112923.GQ4808@kryten> Signed-off-by: Ingo Molnar --- tools/perf/builtin-stat.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 3db31e7bf173..c37368343fff 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -125,6 +125,7 @@ struct stats event_res_stats[MAX_COUNTERS][3]; struct stats runtime_nsecs_stats; struct stats walltime_nsecs_stats; struct stats runtime_cycles_stats; +struct stats runtime_branches_stats; #define MATCH_EVENT(t, c, counter) \ (attrs[counter].type == PERF_TYPE_##t && \ @@ -235,6 +236,8 @@ static void read_counter(int counter) update_stats(&runtime_nsecs_stats, count[0]); if (MATCH_EVENT(HARDWARE, HW_CPU_CYCLES, counter)) update_stats(&runtime_cycles_stats, count[0]); + if (MATCH_EVENT(HARDWARE, HW_BRANCH_INSTRUCTIONS, counter)) + update_stats(&runtime_branches_stats, count[0]); } static int run_perf_stat(int argc __used, const char **argv) @@ -352,6 +355,14 @@ static void abs_printout(int counter, double avg) ratio = avg / total; fprintf(stderr, " # %10.3f IPC ", ratio); + } else if (MATCH_EVENT(HARDWARE, HW_BRANCH_MISSES, counter)) { + total = avg_stats(&runtime_branches_stats); + + if (total) + ratio = avg * 100 / total; + + fprintf(stderr, " # %10.3f %% ", ratio); + } else { total = avg_stats(&runtime_nsecs_stats); -- cgit v1.2.3 From 12133afffcc7140eea915b1572189a2ea0cf7b0e Mon Sep 17 00:00:00 2001 From: Tim Blechmann Date: Mon, 19 Oct 2009 12:03:33 +0200 Subject: perf stat: Add branch performance events to default output Adds performance event information about branches and branch misses to the default output of perf stat. Signed-off-by: Tim Blechmann Cc: Paul Mackerras Cc: Peter Zijlstra LKML-Reference: <4ADC3975.8050109@klingt.org> Signed-off-by: Ingo Molnar --- tools/perf/builtin-stat.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index c37368343fff..95a55eaf72f5 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -59,6 +59,8 @@ static struct perf_event_attr default_attrs[] = { { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS }, { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES}, { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS}, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES }, }; -- cgit v1.2.3 From 56aab464ff6232bcc2f53b26576983dc83f75db7 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 19 Oct 2009 13:27:08 +0200 Subject: perf stat: Re-align the default_attrs[] array Clean up the array definition to be vertically aligned. No functional effects. Cc: Tim Blechmann Cc: Paul Mackerras Cc: Peter Zijlstra LKML-Reference: <4ADC3975.8050109@klingt.org> Signed-off-by: Ingo Molnar --- tools/perf/builtin-stat.c | 2 ++ 1 files changed, 2 insertions(+), 0 deletions(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index c373683..95a55ea 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -59,6 +59,8 @@ static struct perf_event_attr default_attrs[] = { { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS }, { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES}, { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS}, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES }, }; --- tools/perf/builtin-stat.c | 22 +++++++++++----------- 1 file changed, 11 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 95a55eaf72f5..90e0a268343d 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -50,17 +50,17 @@ static struct perf_event_attr default_attrs[] = { - { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK }, - { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES}, - { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS }, - { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS }, - - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES }, - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS }, - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES}, - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES }, - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS}, - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES }, + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK }, + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES }, + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS }, + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS }, + + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES }, }; -- cgit v1.2.3 From dd86e72abdbc4b436471af5a97927c6145f5298c Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 19 Oct 2009 13:33:03 +0200 Subject: perf stat: Count branches first Count branches first, cache-misses second. The reason is that on x86 branches are not counted by all counters on all CPUs. Before: Performance counter stats for 'ls': 0.756653 task-clock-msecs # 0.802 CPUs 0 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 250 page-faults # 0.330 M/sec 2375725 cycles # 3139.781 M/sec 1628129 instructions # 0.685 IPC 19643 cache-references # 25.960 M/sec 4608 cache-misses # 6.090 M/sec 342532 branches # 452.694 M/sec branch-misses 0.000943356 seconds time elapsed After: Performance counter stats for 'ls': 1.056734 task-clock-msecs # 0.859 CPUs 0 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 259 page-faults # 0.245 M/sec 3345932 cycles # 3166.295 M/sec 3074090 instructions # 0.919 IPC 616928 branches # 583.806 M/sec 39279 branch-misses # 6.367 % 21312 cache-references # 20.168 M/sec 3661 cache-misses # 3.464 M/sec 0.001230551 seconds time elapsed (also prettify the printout of branch misses, in case it's getting scaled.) Cc: Tim Blechmann Cc: Paul Mackerras Cc: Peter Zijlstra LKML-Reference: <4ADC3975.8050109@klingt.org> Signed-off-by: Ingo Molnar --- tools/perf/builtin-stat.c | 2 ++ 1 files changed, 2 insertions(+), 0 deletions(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index c373683..95a55ea 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -59,6 +59,8 @@ static struct perf_event_attr default_attrs[] = { { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS }, { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES}, { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS}, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES }, }; --- tools/perf/builtin-stat.c | 20 ++++++++++---------- 1 files changed, 10 insertions(+), 10 deletions(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 95a55ea..90e0a26 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -50,17 +50,17 @@ static struct perf_event_attr default_attrs[] = { - { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK }, - { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES}, - { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS }, - { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS }, - - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES }, - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS }, - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES}, - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES }, - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS}, - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES }, + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK }, + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES }, + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS }, + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS }, + + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES }, }; --- tools/perf/builtin-stat.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 90e0a268343d..c6df3770b87e 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -57,10 +57,10 @@ static struct perf_event_attr default_attrs[] = { { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES }, { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS }, - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES }, - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES }, { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES }, }; @@ -363,7 +363,7 @@ static void abs_printout(int counter, double avg) if (total) ratio = avg * 100 / total; - fprintf(stderr, " # %10.3f %% ", ratio); + fprintf(stderr, " # %10.3f %% ", ratio); } else { total = avg_stats(&runtime_nsecs_stats); -- cgit v1.2.3 From 7255fe2a42c612f2b8fe4c347f0a5f0c97d85a46 Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Sun, 15 Nov 2009 12:05:08 -0200 Subject: perf stat: Do not print ratio when task-clock event is not counted The ratio between the number of events and the time elapsed makes sense only if task-clock event is counted. Otherwise it will be simply a (confusing) # 0.000 M/sec This patch outputs the ratio only if task-clock event is counted. Some test examples of before and after: Before: [lucas@skywalker linux.trees.git]$ sudo perf stat -e branch-misses -a -- sleep 1 Performance counter stats for 'sleep 1': 1367818 branch-misses # 0.000 M/sec 1.001494325 seconds time elapsed After (without task-clock): [lucas@skywalker perf]$ sudo ./perf stat -e branch-misses -a -- sleep 1 Performance counter stats for 'sleep 1': 1135044 branch-misses 1.001370775 seconds time elapsed After (with task-clock): [lucas@skywalker perf]$ sudo ./perf stat -e branch-misses -e task-clock -a -- sleep 1 Performance counter stats for 'sleep 1': 1070111 branch-misses # 0.534 M/sec 2002.730893 task-clock-msecs # 1.999 CPUs 1.001640292 seconds time elapsed Signed-off-by: Lucas De Marchi Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo LKML-Reference: <20091115140507.GB21561@skywalker.lan> Signed-off-by: Ingo Molnar --- tools/perf/builtin-stat.c | 5 +++-- 1 file changed, 3 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 c6df3770b87e..c70d72003557 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -357,7 +357,8 @@ static void abs_printout(int counter, double avg) ratio = avg / total; fprintf(stderr, " # %10.3f IPC ", ratio); - } else if (MATCH_EVENT(HARDWARE, HW_BRANCH_MISSES, counter)) { + } else if (MATCH_EVENT(HARDWARE, HW_BRANCH_MISSES, counter) && + runtime_branches_stats.n != 0) { total = avg_stats(&runtime_branches_stats); if (total) @@ -365,7 +366,7 @@ static void abs_printout(int counter, double avg) fprintf(stderr, " # %10.3f %% ", ratio); - } else { + } else if (runtime_nsecs_stats.n != 0) { total = avg_stats(&runtime_nsecs_stats); if (total) -- cgit v1.2.3