[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <87dad53f-a9a5-cd36-7348-ee10f4edd8fb@arm.com>
Date: Mon, 11 Oct 2021 14:58:40 +0100
From: German Gomez <german.gomez@....com>
To: Namhyung Kim <namhyung@...nel.org>
Cc: Leo Yan <leo.yan@...aro.org>, James Clark <james.clark@....com>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Jiri Olsa <jolsa@...hat.com>, Ingo Molnar <mingo@...nel.org>,
Peter Zijlstra <peterz@...radead.org>,
LKML <linux-kernel@...r.kernel.org>,
Andi Kleen <ak@...ux.intel.com>,
Ian Rogers <irogers@...gle.com>,
Stephane Eranian <eranian@...gle.com>,
Adrian Hunter <adrian.hunter@...el.com>
Subject: Re: [RFC] perf arm-spe: Track task context switch for cpu-mode events
Hi Namhyung,
On 09/10/2021 01:12, Namhyung Kim wrote:
> Hi German,
>
> On Fri, Oct 8, 2021 at 4:08 AM German Gomez <german.gomez@....com> wrote:
>
> [...]
>
> I think we should use context-switch even for kernel samples, but
> only if the context packets are not available.
>
> Thanks,
> Namhyung
I think I agree with that you say. If --switch-events is not enabled by
default like you mention, an user could opt-in to using the fallback if
there's no better option for kernel tracing yet.
@Leo, what are your thoughts on this? Perhaps adding a warning message
to tell the user to please enable context packets, otherwise the results
will have workload-dependant inaccuracies, could be a good enough
compromise?
Thanks,
German
Powered by blists - more mailing lists