Re: [PATCH RESEND] perf record: Add --buildid-all option
From: Arnaldo Carvalho de Melo
Date: Tue Jan 12 2016 - 09:36:10 EST
Em Tue, Jan 12, 2016 at 02:28:22PM +0200, Adrian Hunter escreveu:
> On 11/01/16 15:38, Namhyung Kim wrote:
> > The --buildid-all option is to record build-id of all DSOs in the file.
> > It might be very costly to postprocess samples to find which DSO hits.
> >
> > Cc: Adrian Hunter <adrian.hunter@xxxxxxxxx>
> > Cc: Andi Kleen <andi@xxxxxxxxxxxxxx>
> > Cc: Stephane Eranian <eranian@xxxxxxxxxx>
> > Signed-off-by: Namhyung Kim <namhyung@xxxxxxxxxx>
> > ---
> > tools/perf/Documentation/perf-record.txt | 3 +++
> > tools/perf/builtin-record.c | 32 ++++++++++++++++++++++++++------
> > 2 files changed, 29 insertions(+), 6 deletions(-)
> >
> > diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
> > index 3a1a32f5479f..fbceb631387c 100644
> > --- a/tools/perf/Documentation/perf-record.txt
> > +++ b/tools/perf/Documentation/perf-record.txt
> > @@ -338,6 +338,9 @@ Options passed to clang when compiling BPF scriptlets.
> > Specify vmlinux path which has debuginfo.
> > (enabled when BPF prologue is on)
> >
> > +--buildid-all::
> > +Record build-id of all DSOs regardless whether it's actually hit or not.
> > +
> > SEE ALSO
> > --------
> > linkperf:perf-stat[1], linkperf:perf-list[1]
> > diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
> > index dc4e0adf5c5b..a42cb2955697 100644
> > --- a/tools/perf/builtin-record.c
> > +++ b/tools/perf/builtin-record.c
> > @@ -50,6 +50,7 @@ struct record {
> > int realtime_prio;
> > bool no_buildid;
> > bool no_buildid_cache;
> > + bool buildid_all;
> > unsigned long long samples;
> > };
> >
> > @@ -362,6 +363,13 @@ static int process_buildids(struct record *rec)
> > */
> > symbol_conf.ignore_vmlinux_buildid = true;
> >
> > + /*
> > + * If --buildid-all is given, it marks all DSO regardless of hits,
> > + * so no need to process samples.
> > + */
> > + if (rec->buildid_all)
> > + rec->tool.sample = NULL;
>
> I wonder, if we are not processing samples, could the processing could be
> much simpler?
> All we need to do is read all the MMAP events, in any order, and create DSOs
> - no need to
> create threads or map-groups etc etc.
Right, if that was the overhead, have you ever measured this?
- Arnaldo