From: Mathieu Poirier <mathieu.poirier@linaro.org>
To: Leo Yan <leo.yan@linaro.org>
Cc: Denis Nikitin <denik@google.com>,
Mike Leach <mike.leach@linaro.org>,
"coresight@lists.linaro.org" <coresight@lists.linaro.org>,
"linux-arm-kernel@lists.infradead.org"
<linux-arm-kernel@lists.infradead.org>,
Daniel Kiss <Daniel.Kiss@arm.com>
Subject: Re: [PATCH 0/4] coresight: Add ETR-PERF polling.
Date: Tue, 18 May 2021 09:41:11 -0600 [thread overview]
Message-ID: <20210518154111.GA776252@xps15> (raw)
In-Reply-To: <20210518140040.GC942578@leoy-ThinkPad-X240s>
On Tue, May 18, 2021 at 10:00:40PM +0800, Leo Yan wrote:
> Hi Denis,
>
> On Fri, May 14, 2021 at 02:02:25AM -0700, Denis Nikitin wrote:
>
> [...]
>
> > Hi Mattieu and Leo,
> >
> > I did some evaluation of the snapshot mode.
>
> Thanks a lot for the evaluation and share back the result.
>
> > Performance overhead is indeed higher than with ETR polling patch.
> > Here are some numbers for comparison (measured on browser
> > Speedometer2 benchmark):
> > Runtime overhead of ETM tracing with ETR poll period 100ms is less than
> > 0.5%. Snapshot mode gives 2.1%.
> > With 10ms period I see 4.6% with ETR polling and 22% in snapshot mode.
>
> It's not expected that the snapshot mode causes so big overload.
> In my head, two factors might cause the overload:
>
> - The perf interaction between the user space and kernel space;
> - The data copying from the ETR's buffer to the AUX ring buffer.
>
> Check one thing: what's the buffer size for ETR polling mode and for
> snapshot mode in your experiments?
>
> If I remember correctly, by default the snapshot mode uses 4MB for ETR
> buffer, if copying 4MB per 10ms, then it's likely to cause big
> overload. So at the first glance, the overhead difference might be
> caused by the by the different buffer size between ETR poll mode and
> snapshot mode.
>
> > We could probably utilize the ETM strobing feature and reduce frequency
> > of data collection but I see a problem when I'm using both.
> > Within a minute of profiling the ETM generates a reasonable profile size
> > (with strobing autofdo,preset=9 with period 0x1000 it is up to 20MB).
> > But then the size grows unproportionally.
> > With a 4 minute run I got a 6.3GB profile.
>
> Just check, as Mathieu has suggested, have you applied the patch [1]
> on your local code base for fixing the data copying for snapshot mode?
>
> After applied this patch, one possibility for unproportional issue is
> perf tool itself introduces many activities in snapshot mode (especially
> for 10ms period), so the perf tool contributes much extra trace data.
>
> Another potential issue is: after setting strobing mode, the snapshot
> mode will disable the complete paths for tracers and ETR, so if the
> strobing configuration is lost after re-enable tracers, then it might
> cause the huge trace data in the later phase. For this case, we
> definitely should fix it.
>
> > I don't see such a problem with the ETR polling patch.
> >
> > Leo, could you please take a look at this problem?
>
> Sure. For easier reproducing the issue, could you share me the
> detailed commands (and source code)?
>
> P.s. I saw Mike suggests to continue the ETR polling development, this
> is not conflict with snapshot mode. At my side, I will investigate the
> snapshot mode, but don't want to disturb the process for ETR polling
> mode, so when the ETR polling patch series is get ready, please go
> ahead for upstreaming the patch series.
Just to clarify my position - I would definitely like to see a solution that
extends or re-use the current snapshot mode rather than introducing a new
mechanism to collect data.
>
> Thanks,
> Leo
>
> [1]. https://lists.linaro.org/pipermail/coresight/2021-April/006254.html
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
next prev parent reply other threads:[~2021-05-18 15:43 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-04-21 12:04 [PATCH 0/4] coresight: Add ETR-PERF polling Daniel Kiss
2021-04-21 12:04 ` [PATCH 1/4] coresight: tmc-etr: Advance buffer pointer in sync buffer Daniel Kiss
2021-04-23 8:23 ` Leo Yan
2021-04-26 10:40 ` Suzuki K Poulose
2021-04-27 3:45 ` Leo Yan
2021-04-27 10:00 ` Suzuki K Poulose
2021-04-28 2:34 ` Leo Yan
2021-04-21 12:04 ` [PATCH 2/4] coresight: tmc-etr: Track perf handler Daniel Kiss
2021-04-23 9:20 ` Leo Yan
2021-04-26 0:25 ` Leo Yan
2021-04-21 12:04 ` [PATCH 3/4] coresight: etm-perf: Export etm_event_cpu_path Daniel Kiss
2021-04-21 12:04 ` [PATCH 4/4] coresight: Add ETR-PERF polling Daniel Kiss
2021-04-26 1:18 ` Leo Yan
2021-05-05 7:21 ` Denis Nikitin
2021-04-26 17:54 ` [PATCH 0/4] " Mathieu Poirier
2021-04-27 10:43 ` Al Grant
2021-04-27 14:41 ` Mike Leach
2021-04-27 15:47 ` Mathieu Poirier
2021-04-27 16:04 ` Leo Yan
2021-05-05 6:46 ` Denis Nikitin
2021-05-05 15:29 ` Mathieu Poirier
2021-05-14 9:02 ` Denis Nikitin
2021-05-14 16:16 ` Mike Leach
2021-05-18 14:00 ` Leo Yan
2021-05-18 14:14 ` Leo Yan
2021-05-18 15:41 ` Mathieu Poirier [this message]
2021-05-26 6:47 ` Denis Nikitin
2021-05-23 8:45 ` Leo Yan
2021-05-27 7:50 ` Denis Nikitin
2021-05-27 15:07 ` Leo Yan
2021-05-27 16:22 ` Denis Nikitin
2021-05-28 16:37 ` Leo Yan
2021-04-27 16:24 ` James Clark
2021-04-28 11:30 ` James Clark
2021-04-28 11:52 ` Daniel Kiss
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=20210518154111.GA776252@xps15 \
--to=mathieu.poirier@linaro.org \
--cc=Daniel.Kiss@arm.com \
--cc=coresight@lists.linaro.org \
--cc=denik@google.com \
--cc=leo.yan@linaro.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=mike.leach@linaro.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).