Re: [PATCH v2 2/2] perf tools: add attr->mmap2 support

[Arnaldo Carvalho de Melo]

Em Tue, Sep 10, 2013 at 03:05:03PM +0200, Stephane Eranian escreveu:
> On Tue, Sep 10, 2013 at 3:00 PM, Arnaldo Carvalho de Melo <acme@xxxxxxxxxxxxxxxxxx> wrote:
> > Em Mon, Sep 09, 2013 at 04:48:44PM -0300, Arnaldo Carvalho de Melo escreveu:
> > > Em Mon, Sep 09, 2013 at 04:47:45PM -0300, Arnaldo Carvalho de Melo escreveu:
> > > > I noticed the kernel part is in, and I'm going to use MMAP2 on that new
> > > > tool, so tried merging it, but:
> > > >
> > > > I fixed it up wrt another patch that makes machine__find_thread receive pid/tid
> > > > but then 'perf test' complains about it, see below, trying to fix...
> > >
> > > Following patch makes it progress a bit, still checking why it is not
> > > enough...
> >
> > Without your patch:
> >
> > [root@sandy ~]# perf test -v 7
> >  7: Validate PERF_RECORD_* events & perf_sample fields     :
> > --- start ---
> > 61118374953766 0 PERF_RECORD_SAMPLE
> > 61118374958840 0 PERF_RECORD_SAMPLE
> > 61118374961420 0 PERF_RECORD_SAMPLE
> > 61118374964293 0 PERF_RECORD_SAMPLE
> > 61118376117716 0 PERF_RECORD_COMM: sleep:5096
> > 61118376153724 0 PERF_RECORD_MMAP 5096/5096: [0x400000(0x7000) @ 0]: /usr/bin/sleep
> > 61118376190304 0 PERF_RECORD_MMAP 5096/5096: [0x3b7e000000(0x223000) @ 0]: /usr/lib64/ld-2.16.so
> > 61118376229562 0 PERF_RECORD_MMAP 5096/5096: [0x7fff2f9ff000(0x1000) @ 0x7fff2f9ff000]: [vdso]
> > 61118376526654 0 PERF_RECORD_MMAP 5096/5096: [0x3b7e400000(0x3b8000) @ 0]: /usr/lib64/libc-2.16.so
> > 61119377689687 0 PERF_RECORD_EXIT(5096:5096):(5096:5096)
> > ---- end ----
> > Validate PERF_RECORD_* events & perf_sample fields: Ok
> > [root@sandy ~]#
> >
> > So the tstamp grows monotonically, then, after your patch + the patch at the
> > end of this message:
> >
> > [root@sandy ~]# perf test -v 7
> >  7: Validate PERF_RECORD_* events & perf_sample fields     :
> > --- start ---
> > 61315294449606 0 PERF_RECORD_SAMPLE
> > 61315294453161 0 PERF_RECORD_SAMPLE
> > 61315294454441 0 PERF_RECORD_SAMPLE
> > 61315294455709 0 PERF_RECORD_SAMPLE
> > 61315295600899 0 PERF_RECORD_COMM: sleep:6500
> > 27917287430500 342521613 PERF_RECORD_MMAP2 6500/6500: [0x400000(0x7000) @ 0 00:1d 311442 9016]: /usr/bin/sleep
> > MMAP2 going backwards in time, prev=61315295600899, curr=27917287430500
> > MMAP2 with unexpected cpu, expected 0, got 342521613
> > MMAP2 with unexpected pid, expected 6500, got 1701606191
> > MMAP2 with unexpected tid, expected 6500, got 28773
> > 27917287430500 342561333 PERF_RECORD_MMAP2 6500/6500: [0x3b7e000000(0x223000) @ 0 00:1d 309186 9016]: /usr/lib64/ld-2.16.so
> > MMAP2 with unexpected cpu, expected 0, got 342561333
> > MMAP2 with unexpected pid, expected 6500, got 1932408369
> > MMAP2 with unexpected tid, expected 6500, got 111
> > 27917287430500 342600095 PERF_RECORD_MMAP2 6500/6500: [0x7fffbd7dc000(0x1000) @ 0x7fffbd7dc000 00:00 0 0]: [vdso]
> > MMAP2 with unexpected cpu, expected 0, got 342600095
> > MMAP2 with unexpected pid, expected 6500, got 1935963739
> > MMAP2 with unexpected tid, expected 6500, got 23919
> > 27917287430500 342882834 PERF_RECORD_MMAP2 6500/6500: [0x3b7e400000(0x3b8000) @ 0 00:1d 309187 9016]: /usr/lib64/libc-2.16.so
> > MMAP2 with unexpected cpu, expected 0, got 342882834
> > MMAP2 with unexpected pid, expected 6500, got 909192754
> > MMAP2 with unexpected tid, expected 6500, got 7303982
> > 61316297195411 0 PERF_RECORD_EXIT(6500:6500):(6500:6500)
> > ---- end ----
> > Validate PERF_RECORD_* events & perf_sample fields: FAILED!
> > [root@sandy ~]#
> >
> > So everything that is in perf_sample, i.e. in the variable area, selected via
> > sample_type, is invalid for PERF_RECORD_MMAP2.
> >
> > This is on:
> >
> > [root@sandy ~]# uname -a
> > Linux sandy.ghostprotocols.net.home 3.11.0+ #1 SMP Wed Sep 4 16:47:14 BRT 2013 x86_64 x86_64 x86_64 GNU/Linux
> > [root@sandy ~]#
> >
> > Humm, looking at perf_event_mmap_output it seems this was missed, will rebuild
> > a kernel and retest...
> >
> > diff --git a/kernel/events/core.c b/kernel/events/core.c
> > index 2207efc..dd236b6 100644
> > --- a/kernel/events/core.c
> > +++ b/kernel/events/core.c
> > @@ -5039,6 +5039,7 @@ static void perf_event_mmap_output(struct perf_event *event,
> >                 mmap_event->event_id.header.size += sizeof(mmap_event->maj);
> >                 mmap_event->event_id.header.size += sizeof(mmap_event->min);
> >                 mmap_event->event_id.header.size += sizeof(mmap_event->ino);
> > +               mmap_event->event_id.header.size += sizeof(mmap_event->ino_generation);
> >         }
> >
> >         perf_event_header__init_id(&mmap_event->event_id.header, &sample, event);
> >
> Arg, yes, this is missing.
> Do you want to submit the patch?

I will, in some jiffies, just rebooting with the patched kernel to
re-run tperf test.

> Thanks for tracking it down.

np :-)

- Arnaldo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/