From 4804e0111662d7d89edf4e767a64c6f7e4778bb1 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 20 Nov 2019 16:15:19 -0800 Subject: perf stat: Use affinity for opening events Restructure the event opening in perf stat to cycle through the events by CPU after setting affinity to that CPU. This eliminates IPI overhead in the perf API. We have to loop through the CPU in the outter builtin-stat code instead of leaving that to low level functions. It has to change the weak group fallback strategy slightly. Since we cannot easily undo the opens for other CPUs move the weak group retry to a separate loop. Before with a large test case with 94 CPUs: % time seconds usecs/call calls errors syscall ------ ----------- ----------- --------- --------- ---------------- 42.75 4.050910 67 60046 110 perf_event_open After: 26.86 0.944396 16 58069 110 perf_event_open (the number changes slightly because the weak group retries work differently and the test case relies on weak groups) Committer notes: Added one of the hunks in a patch provided by Andi after I noticed that the "event times" 'perf test' entry was segfaulting. Signed-off-by: Andi Kleen Acked-by: Jiri Olsa Link: http://lore.kernel.org/lkml/20191121001522.180827-10-andi@firstfloor.org Link: http://lore.kernel.org/lkml/20191127232657.GL84886@tassilo.jf.intel.com # Fix Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) (limited to 'tools/perf/util/evsel.c') diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index f4dea055b080..aa180d1df50f 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1587,8 +1587,9 @@ static int perf_event_open(struct evsel *evsel, return fd; } -int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, - struct perf_thread_map *threads) +static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, + struct perf_thread_map *threads, + int start_cpu, int end_cpu) { int cpu, thread, nthreads; unsigned long flags = PERF_FLAG_FD_CLOEXEC; @@ -1665,7 +1666,7 @@ retry_sample_id: display_attr(&evsel->core.attr); - for (cpu = 0; cpu < cpus->nr; cpu++) { + for (cpu = start_cpu; cpu < end_cpu; cpu++) { for (thread = 0; thread < nthreads; thread++) { int fd, group_fd; @@ -1843,6 +1844,12 @@ out_close: return err; } +int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, + struct perf_thread_map *threads) +{ + return evsel__open_cpu(evsel, cpus, threads, 0, cpus ? cpus->nr : 1); +} + void evsel__close(struct evsel *evsel) { perf_evsel__close(&evsel->core); @@ -1850,9 +1857,14 @@ void evsel__close(struct evsel *evsel) } int perf_evsel__open_per_cpu(struct evsel *evsel, - struct perf_cpu_map *cpus) + struct perf_cpu_map *cpus, + int cpu) { - return evsel__open(evsel, cpus, NULL); + if (cpu == -1) + return evsel__open_cpu(evsel, cpus, NULL, 0, + cpus ? cpus->nr : 1); + + return evsel__open_cpu(evsel, cpus, NULL, cpu, cpu + 1); } int perf_evsel__open_per_thread(struct evsel *evsel, -- cgit v1.2.3-59-g8ed1b