MIME-Version: 1.0
References: <20230207002403.63590-1-namhyung@kernel.org> <20230207002403.63590-3-namhyung@kernel.org>
 <Y+JqNuGA5tavdPce@kernel.org>
In-Reply-To: <Y+JqNuGA5tavdPce@kernel.org>
From:   Namhyung Kim <namhyung@kernel.org>
Date:   Tue, 7 Feb 2023 14:20:26 -0800
Message-ID: <CAM9d7ciLYdbH=K78cwy9L7Ppo0rhAsqKuJkpzfYExpNMk6FQwA@mail.gmail.com>
Subject: Re: [PATCH 2/3] perf lock contention: Add -o/--lock-owner option
To:     Arnaldo Carvalho de Melo <acme@kernel.org>
Cc:     Jiri Olsa <jolsa@kernel.org>, Ingo Molnar <mingo@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>,
        LKML <linux-kernel@vger.kernel.org>,
        Ian Rogers <irogers@google.com>,
        Adrian Hunter <adrian.hunter@intel.com>,
        linux-perf-users@vger.kernel.org, Will Deacon <will@kernel.org>,
        Waiman Long <longman@redhat.com>,
        Boqun Feng <boqun.feng@gmail.com>,
        Davidlohr Bueso <dave@stgolabs.net>,
        Song Liu <song@kernel.org>, Hao Luo <haoluo@google.com>,
        bpf@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

Hi Arnaldo,

On Tue, Feb 7, 2023 at 7:11 AM Arnaldo Carvalho de Melo <acme@kernel.org> wrote:
>
> Em Mon, Feb 06, 2023 at 04:24:02PM -0800, Namhyung Kim escreveu:
> > When there're many lock contentions in the system, people sometimes
> > want to know who caused the contention, IOW who's the owner of the
> > locks.
> >
> > The -o/--lock-owner option tries to follow the lock owners for the
> > contended mutexes and rwsems from BPF, and then attributes the
> > contention time to the owner instead of the waiter.  It's a best
> > effort approach to get the owner info at the time of the contention
> > and doesn't guarantee to have the precise tracking of owners if it's
> > changing over time.
>
> Having this in the documentation as limitations of the approach helps,
> but I'm not seeing this on this specific patch, where I think it should
> be.
>
> Furthermore probably its a good idea to have this as a warning on the
> actual output of the tool, no?
>
> Generally having cool commit log messages, as this one has, is great,
> but people have difficulty looking at docs, imagine expecting them to
> read commit log messages... :-)

I see.  I'll add this limitation to the doc and tool output.

Thanks,
Namhyung