summaryrefslogtreecommitdiff
path: root/tools/perf/builtin-stat.c
diff options
context:
space:
mode:
authorIngo Molnar <mingo@elte.hu>2011-04-27 05:20:22 +0200
committerIngo Molnar <mingo@elte.hu>2011-04-26 20:04:57 +0200
commit1fc570ad89e55dc32dfa4dda1311948b38f26524 (patch)
tree5e775a1f2627301110bd11246dd68cf727961c94 /tools/perf/builtin-stat.c
parent481f988a016f7a0327a5537bde4794349fc4625c (diff)
perf stat: Add stalled cycles to the default output
The new default output looks like this: Performance counter stats for './loop_1b_instructions': 236.010686 task-clock # 0.996 CPUs utilized 0 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 99 page-faults # 0.000 M/sec 756,487,646 cycles # 3.205 GHz 354,938,996 stalled-cycles # 46.92% of all cycles are idle 1,001,403,797 instructions # 1.32 insns per cycle # 0.35 stalled cycles per insn 100,279,773 branches # 424.895 M/sec 12,646 branch-misses # 0.013 % of all branches 0.236902540 seconds time elapsed We dropped cache-refs and cache-misses and added stalled-cycles - this is a more generic "how well utilized is the CPU" metric. If the stalled-cycles ratio is too high then more specific measurements can be taken to figure out the source of the inefficiency. Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Link: http://lkml.kernel.org/n/tip-pbpl2l4mn797s69bclfpwkwn@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'tools/perf/builtin-stat.c')
-rw-r--r--tools/perf/builtin-stat.c5
1 files changed, 2 insertions, 3 deletions
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e881c2061381..924d18c407b8 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -65,11 +65,10 @@ static struct perf_event_attr default_attrs[] = {
{ .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_STALLED_CYCLES },
{ .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS },
{ .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 },
};
@@ -468,7 +467,7 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
if (total)
ratio = avg * 100 / total;
- fprintf(stderr, " # %8.3f %% of all branches", ratio);
+ fprintf(stderr, " # %5.2f %% of all branches ", ratio);
} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
runtime_cacherefs_stats[cpu].n != 0) {