From b0404be8d6186f9f3c23e2b5ff247e667be90652 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 13 May 2016 15:01:01 +0900 Subject: perf stat: Fix indentation of stalled backend cycle The commit 140aeadc1fb5 ("perf stat: Abstract stat metrics printing") changed how shadow metrics are printed, but it missed to update the width of the stalled backend cycles event to 7.2% like others. This resulted in misaligned output like below: Performance counter stats for 'pwd': 0.638313 task-clock (msec) # 0.567 CPUs utilized 0 context-switches # 0.000 K/sec 0 cpu-migrations # 0.000 K/sec 54 page-faults # 0.085 M/sec 885,600 cycles # 1.387 GHz 558,438 stalled-cycles-frontend # 63.06% frontend cycles idle 431,355 stalled-cycles-backend # 48.71% backend cycles idle 674,956 instructions # 0.76 insn per cycle # 0.83 stalled cycles per insn 130,380 branches # 204.257 M/sec branch-misses 0.001125426 seconds time elapsed Signed-off-by: Namhyung Kim Cc: Andi Kleen Cc: Jiri Olsa Cc: Peter Zijlstra Fixes: 140aeadc1fb5 ("perf stat: Abstract stat metrics printing") Link: http://lkml.kernel.org/r/1463119263-5569-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/stat-shadow.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/util/stat-shadow.c') diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index fdb71961143e..61200fcac5ef 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -188,7 +188,7 @@ static void print_stalled_cycles_backend(int cpu, color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio); - out->print_metric(out->ctx, color, "%6.2f%%", "backend cycles idle", ratio); + out->print_metric(out->ctx, color, "%7.2f%%", "backend cycles idle", ratio); } static void print_branch_misses(int cpu, -- cgit v1.2.3-70-g09d2 From daf4f4786e8af371048e72cb37ac05190e89198a Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 13 May 2016 15:01:02 +0900 Subject: perf stat: Update runtime using cpu-clock event Currently only the task-clock event updates the runtime_nsec so it cannot show the metric when using cpu-clock events. However cpu clock works basically same as task-clock, so no need to not update the runtime IMHO. Before: # perf stat -a -e cpu-clock,context-switches,page-faults,cycles sleep 0.1 Performance counter stats for 'system wide': 1217.759506 cpu-clock (msec) 93 context-switches 61 page-faults 18,958,022 cycles 0.101393794 seconds time elapsed After: Performance counter stats for 'system wide': 1220.471884 cpu-clock (msec) # 12.013 CPUs utilized 118 context-switches # 0.097 K/sec 59 page-faults # 0.048 K/sec 17,941,247 cycles # 0.015 GHz 0.101594777 seconds time elapsed Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: Jiri Olsa Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1463119263-5569-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/stat-shadow.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'tools/perf/util/stat-shadow.c') diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 61200fcac5ef..aa9efe08762b 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -94,7 +94,8 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count, { int ctx = evsel_context(counter); - if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK)) + if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK) || + perf_evsel__match(counter, SOFTWARE, SW_CPU_CLOCK)) update_stats(&runtime_nsecs_stats[cpu], count[0]); else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES)) update_stats(&runtime_cycles_stats[ctx][cpu], count[0]); @@ -444,7 +445,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, ratio = total / avg; print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio); - } else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) { + } else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK) || + perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK)) { if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0) print_metric(ctxp, NULL, "%8.3f", "CPUs utilized", avg / ratio); -- cgit v1.2.3-70-g09d2