diff options
author | Andi Kleen <ak@linux.intel.com> | 2016-03-28 10:45:38 -0700 |
---|---|---|
committer | Arnaldo Carvalho de Melo <acme@redhat.com> | 2016-03-30 11:14:09 -0300 |
commit | d1706b39f0af6901ab2a5e2ebb210b53c1a5bdc7 (patch) | |
tree | 4bee0f637581706387688651a57fb867c7f6e559 /tools/perf/util/intel-pt.c | |
parent | f7380c12ec6cfd69f274ba6181cd01c764f877bb (diff) |
perf tools: Add support for skipping itrace instructions
When using 'perf script' to look at PT traces it is often useful to
ignore the initialization code at the beginning.
On larger traces which may have many millions of instructions in
initialization code doing that in a pipeline can be very slow, with perf
script spending a lot of CPU time calling printf and writing data.
This patch adds an extension to the --itrace argument that skips 'n'
events (instructions, branches or transactions) at the beginning. This
is much more efficient.
v2:
Add support for BTS (Adrian Hunter)
Document in itrace.txt
Fix branch check
Check transactions and instructions too
Committer note:
To test intel_pt one needs to make sure VT-x isn't active, i.e.
stopping KVM guests on the test machine, as described by Andi Kleen
at http://lkml.kernel.org/r/20160301234953.GD23621@tassilo.jf.intel.com
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1459187142-20035-1-git-send-email-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools/perf/util/intel-pt.c')
-rw-r--r-- | tools/perf/util/intel-pt.c | 22 |
1 files changed, 20 insertions, 2 deletions
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 407f11b97c8d..ddec87f6e616 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -100,6 +100,8 @@ struct intel_pt { u64 cyc_bit; u64 noretcomp_bit; unsigned max_non_turbo_ratio; + + unsigned long num_events; }; enum switch_state { @@ -972,6 +974,10 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) if (pt->branches_filter && !(pt->branches_filter & ptq->flags)) return 0; + if (pt->synth_opts.initial_skip && + pt->num_events++ < pt->synth_opts.initial_skip) + return 0; + event->sample.header.type = PERF_RECORD_SAMPLE; event->sample.header.misc = PERF_RECORD_MISC_USER; event->sample.header.size = sizeof(struct perf_event_header); @@ -1029,6 +1035,10 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq) union perf_event *event = ptq->event_buf; struct perf_sample sample = { .ip = 0, }; + if (pt->synth_opts.initial_skip && + pt->num_events++ < pt->synth_opts.initial_skip) + return 0; + event->sample.header.type = PERF_RECORD_SAMPLE; event->sample.header.misc = PERF_RECORD_MISC_USER; event->sample.header.size = sizeof(struct perf_event_header); @@ -1087,6 +1097,10 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq) union perf_event *event = ptq->event_buf; struct perf_sample sample = { .ip = 0, }; + if (pt->synth_opts.initial_skip && + pt->num_events++ < pt->synth_opts.initial_skip) + return 0; + event->sample.header.type = PERF_RECORD_SAMPLE; event->sample.header.misc = PERF_RECORD_MISC_USER; event->sample.header.size = sizeof(struct perf_event_header); @@ -1199,14 +1213,18 @@ static int intel_pt_sample(struct intel_pt_queue *ptq) ptq->have_sample = false; if (pt->sample_instructions && - (state->type & INTEL_PT_INSTRUCTION)) { + (state->type & INTEL_PT_INSTRUCTION) && + (!pt->synth_opts.initial_skip || + pt->num_events++ >= pt->synth_opts.initial_skip)) { err = intel_pt_synth_instruction_sample(ptq); if (err) return err; } if (pt->sample_transactions && - (state->type & INTEL_PT_TRANSACTION)) { + (state->type & INTEL_PT_TRANSACTION) && + (!pt->synth_opts.initial_skip || + pt->num_events++ >= pt->synth_opts.initial_skip)) { err = intel_pt_synth_transaction_sample(ptq); if (err) return err; |