From 3e76ac78b08479e84a3eca3fb1b3066fb8230461 Mon Sep 17 00:00:00 2001 From: Andrew Vagin Date: Tue, 20 Dec 2011 17:32:45 +0300 Subject: perf record: Add ability to record event period The problem is that when SAMPLE_PERIOD is not set, the kernel generates a number of samples in proportion to an event's period. Number of these samples may be too big and the kernel throttles all samples above a defined limit. E.g.: I want to trace when a process sleeps. I created a process which sleeps for 1ms and for 4ms. perf got 100 events in both cases. swapper 0 [000] 1141.371830: sched_stat_sleep: comm=foo pid=1801 delay=1386750 [ns] swapper 0 [000] 1141.369444: sched_stat_sleep: comm=foo pid=1801 delay=4499585 [ns] In the first case a kernel want to send 4499585 events and in the second case it wants to send 1386750 events. perf-reports shows that process sleeps in both places equal time. Instead of this we can get only one sample with an attribute period. As result we have less data transferring between kernel and user-space and we avoid throttling of samples. The patch "events: Don't divide events if it has field period" added a kernel part of this functionality. Acked-by: Arun Sharma Cc: Arun Sharma Cc: David Ahern Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Cc: devel@openvz.org Link: http://lkml.kernel.org/r/1324391565-1369947-1-git-send-email-avagin@openvz.org Signed-off-by: Andrew Vagin Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 1 + tools/perf/perf.h | 1 + tools/perf/util/evsel.c | 3 +++ 3 files changed, 5 insertions(+) (limited to 'tools') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 766fa0a91a32..f8fd14fb62ec 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -700,6 +700,7 @@ const struct option record_options[] = { OPT_BOOLEAN('d', "data", &record.opts.sample_address, "Sample addresses"), OPT_BOOLEAN('T', "timestamp", &record.opts.sample_time, "Sample timestamps"), + OPT_BOOLEAN('P', "period", &record.opts.period, "Sample period"), OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples, "don't sample"), OPT_BOOLEAN('N', "no-buildid-cache", &record.no_buildid_cache, diff --git a/tools/perf/perf.h b/tools/perf/perf.h index ea804f5a8cc2..64f8bee31ced 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -200,6 +200,7 @@ struct perf_record_opts { bool sample_time; bool sample_id_all_avail; bool system_wide; + bool period; unsigned int freq; unsigned int mmap_pages; unsigned int user_freq; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 4a8c8b02e9cc..60ad0286759e 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -108,6 +108,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts) if (opts->system_wide) attr->sample_type |= PERF_SAMPLE_CPU; + if (opts->period) + attr->sample_type |= PERF_SAMPLE_PERIOD; + if (opts->sample_id_all_avail && (opts->sample_time || opts->system_wide || !opts->no_inherit || opts->cpu_list)) -- cgit v1.2.3-58-ga151