[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAH0uvogYaqjutK3WuH0+Xw0q0fGwnXQqQP7=qCd302N8S2NiLw@mail.gmail.com>
Date: Thu, 22 May 2025 17:48:42 -0700
From: Howard Chu <howardchu95@...il.com>
To: Arnaldo Carvalho de Melo <acme@...nel.org>
Cc: Namhyung Kim <namhyung@...nel.org>, Ian Rogers <irogers@...gle.com>,
Kan Liang <kan.liang@...ux.intel.com>, Jiri Olsa <jolsa@...nel.org>,
Adrian Hunter <adrian.hunter@...el.com>, Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...nel.org>, LKML <linux-kernel@...r.kernel.org>,
linux-perf-users@...r.kernel.org
Subject: Re: [PATCH] perf test: Add cgroup summary test case for perf trace
Hello Arnaldo,
On Thu, May 22, 2025 at 3:11 PM Arnaldo Carvalho de Melo
<acme@...nel.org> wrote:
>
> On Thu, May 22, 2025 at 01:49:37PM -0300, Arnaldo Carvalho de Melo wrote:
> > On Thu, May 22, 2025 at 08:33:16AM -0700, Howard Chu wrote:
> > > $ sudo /tmp/perf/perf test -vv 112
> > > 112: perf trace summary:
> > > 112: perf trace summary
> > > --- start ---
> > > test child forked, pid 1574993
> > > testing: perf trace -s -- true
> > > testing: perf trace -S -- true
> > > testing: perf trace -s --summary-mode=thread -- true
> > > testing: perf trace -S --summary-mode=total -- true
> > > testing: perf trace -as --summary-mode=thread --no-bpf-summary -- true
> > > testing: perf trace -as --summary-mode=total --no-bpf-summary -- true
> > > testing: perf trace -as --summary-mode=thread --bpf-summary -- true
> > > testing: perf trace -as --summary-mode=total --bpf-summary -- true
> > > testing: perf trace -aS --summary-mode=total --bpf-summary -- true
> > > testing: perf trace -as --summary-mode=cgroup --bpf-summary -- true
> > > testing: perf trace -aS --summary-mode=cgroup --bpf-summary -- true
> > > ---- end(0) ----
> > > 112: perf trace summary : Ok
>
> > Thanks, tested and applied to perf-tools-next,
>
> But then when running all the tests, since this does system wide
> tracing, it fails:
>
> 112: perf trace summary : FAILED!
Yeah I've been trying to diagnose the parallel problem for days... I
just can't find documentation about why 'returning 1' (in
syscall_unaugmented) can emit a sample in
tp/raw_syscalls/sys_(exit|enter)...
Thanks,
Howard
Powered by blists - more mailing lists