Received-SPF: pass (google.com: domain of linux-kernel+bounces-94966-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
Precedence: bulk
MIME-Version: 1.0
References: <20240304230815.1440583-1-namhyung@kernel.org> <ZejshUg8XiQz5YGa@x1>
In-Reply-To: <ZejshUg8XiQz5YGa@x1>
From: Namhyung Kim <namhyung@kernel.org>
Date: Wed, 6 Mar 2024 20:20:15 -0800
Message-ID: <CAM9d7cjfH7e5wiM9Zwfn_oCqL1tUvy1=c3RUuO=zvgTJVrU6oQ@mail.gmail.com>
Subject: Re: [PATCH v2 0/4] perf annotate: Improve memory usage for symbol histogram
To: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ian Rogers <irogers@google.com>, Jiri Olsa <jolsa@kernel.org>, 
	Adrian Hunter <adrian.hunter@intel.com>, Peter Zijlstra <peterz@infradead.org>, 
	Ingo Molnar <mingo@kernel.org>, LKML <linux-kernel@vger.kernel.org>, 
	linux-perf-users@vger.kernel.org, Andi Kleen <ak@linux.intel.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Wed, Mar 6, 2024 at 2:22=E2=80=AFPM Arnaldo Carvalho de Melo <acme@kerne=
l.org> wrote:
>
> On Mon, Mar 04, 2024 at 03:08:11PM -0800, Namhyung Kim wrote:
> > Hello,
> >
> > This is another series of memory optimization in perf annotate.
> >
> > v2 changes:
> >  * fix a bug when offset is bigger than 16 bits
> >
> >
> > When perf annotate (or perf report/top with TUI) processes samples, it
> > needs to save the sample period (overhead) at instruction level.  For
> > now, it allocates an array to do that for the whole symbol when it
> > hits any new symbol.  This comes with a lot of waste since samples can
> > be very few and instructions span to multiple bytes.
> >
> > For example, when a sample hits symbol 'foo' that has size of 100 and
> > that's the only sample falls into the symbol.  Then it needs to
> > allocate a symbol histogram (sym_hist) and the its size would be
> >
> >   16 (header) + 16 (sym_hist_entry) * 100 (symbol_size) =3D 1616
> >
> > But actually it just needs 32 (header + sym_hist_entry) bytes.  Things
> > get worse if the symbol size is bigger (and it doesn't have many
> > samples in different places).  Also note that it needs a separate
> > histogram for each event.
> >
> > Let's split the sym_hist_entry and have it in a hash table so that it
> > can allocate only necessary entries.
> >
> > No functional change intended.
> >
> > Thanks,
> > Namhyung
>
> No difference before/after on that 'perf annotate --stdio2' for all
> binaries in a perf record of building perf using the default binutils
> objdump disassembler, etc.
>
> Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com>
> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>

Great, thanks for testing.

Namhyung