From: James Clark <james.clark@linaro.org>
To: Ian Rogers <irogers@google.com>, Andi Kleen <ak@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@redhat.com>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
Namhyung Kim <namhyung@kernel.org>,
Mark Rutland <mark.rutland@arm.com>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Jiri Olsa <jolsa@kernel.org>,
Adrian Hunter <adrian.hunter@intel.com>,
Kan Liang <kan.liang@linux.intel.com>,
linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org,
Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Subject: Re: [PATCH v1 2/2] perf script: Fix for `perf script +F metric` with leader sampling
Date: Tue, 23 Jul 2024 15:41:35 +0100 [thread overview]
Message-ID: <8c8da262-a398-41cc-9721-4e72e6b7e5fd@linaro.org> (raw)
In-Reply-To: <20240720074552.1915993-2-irogers@google.com>
On 20/07/2024 8:45 am, Ian Rogers wrote:
> Andi Kleen reported a regression where `perf script +F metric` would
> crash. With this change the output is:
>
> ```
> $ perf record -a -e '{cycles,instructions}:S' perf bench mem memcpy
>
> 21.229620 GB/sec
>
> 15.751008 GB/sec
>
> 16.009221 GB/sec
> [ perf record: Woken up 1 times to write data ]
> [ perf record: Captured and wrote 1.945 MB perf.data (294 samples) ]
> $ perf --no-pager script -F +metric
> perf 1912464 [000] 814503.473101: 6325 cycles: ffffffff8548d64a native_write_msr+0xa ([kernel.kallsyms])
> perf 1912464 [000] 814503.473101: metric: 0.06 insn per cycle
> perf 1912464 [000] 814503.473101: 351 instructions: ffffffff8548d64a native_write_msr+0xa ([kernel.kallsyms])
> perf 1912464 [000] 814503.473101: metric: 0.03 insn per cycle
> ...
> ```
For some reason I only get the metric: lines when I record with -a. I
noticed this because Andi's test doesn't use -a so it fails.
I'm not sure if that's expected or it's related to your disclaimer below?
>
> The change fixes perf script to update counts and thereby aggregate
> values which then get consumed by unchanged metric logic in the shadow
> stat output. Note, it would be preferential to switch to json metrics.
>
> Reported-by: Andi Kleen <ak@linux.intel.com>
> Closes: https://lore.kernel.org/linux-perf-users/20240713155443.1665378-1-ak@linux.intel.com/
> Fixes: 37cc8ad77cf8 ("perf metric: Directly use counts rather than saved_value")'
> Signed-off-by: Ian Rogers <irogers@google.com>
> ---
> The code isn't well tested nor does it support non-leader sampling
> reading of counts based on periods that seemed to present in the
> previous code. Sending out for the sake of discussion. Andi's changes
> added a test and that should certainly be added.
> ---
> tools/perf/builtin-script.c | 114 +++++++++++++++++++++++++++++-------
> 1 file changed, 93 insertions(+), 21 deletions(-)
>
next prev parent reply other threads:[~2024-07-23 14:41 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-07-20 7:45 [PATCH v1 1/2] libperf threadmap: Add ability to find index from pid Ian Rogers
2024-07-20 7:45 ` [PATCH v1 2/2] perf script: Fix for `perf script +F metric` with leader sampling Ian Rogers
2024-07-23 14:41 ` James Clark [this message]
2024-07-23 14:57 ` Ian Rogers
2024-07-23 15:26 ` Andi Kleen
2024-07-23 15:26 ` James Clark
2024-07-23 15:39 ` Andi Kleen
2024-07-23 15:49 ` Ian Rogers
2024-07-26 0:05 ` Namhyung Kim
2024-07-26 3:32 ` Ian Rogers
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=8c8da262-a398-41cc-9721-4e72e6b7e5fd@linaro.org \
--to=james.clark@linaro.org \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=ak@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=atrajeev@linux.vnet.ibm.com \
--cc=irogers@google.com \
--cc=jolsa@kernel.org \
--cc=kan.liang@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).