linux-perf-users.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: James Clark <james.clark@linaro.org>
To: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: coresight@lists.linaro.org, linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
	Leo Yan <leo.yan@arm.com>,
	Suzuki K Poulose <suzuki.poulose@arm.com>,
	Mike Leach <mike.leach@linaro.org>,
	Yeoreum Yun <yeoreum.yun@arm.com>, Will Deacon <will@kernel.org>,
	Mark Rutland <mark.rutland@arm.com>,
	Tamas Petz <tamas.petz@arm.com>,
	Tamas Zsoldos <tamas.zsoldos@arm.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Namhyung Kim <namhyung@kernel.org>, Jiri Olsa <jolsa@kernel.org>,
	Ian Rogers <irogers@google.com>,
	Adrian Hunter <adrian.hunter@intel.com>
Subject: Re: [PATCH 19/19] perf: cs-etm: Set watermark for AUX trace
Date: Tue, 9 Dec 2025 14:54:19 +0000	[thread overview]
Message-ID: <5ebf1743-b01c-4664-961c-9e1e2aa7ffce@linaro.org> (raw)
In-Reply-To: <c22b084b-3853-405d-8b43-397786af7be9@arm.com>



On 05/12/2025 4:48 am, Anshuman Khandual wrote:
> On 01/12/25 4:52 PM, Leo Yan wrote:
>> The default watermark is half of the total buffer size. In many cases,
>> the tool can not be notified with sufficient free space, especially when
>> profiling with small AUX buffer (e.g., 64KiB).
> 
> Could not smaller AUX buffer be prevented for TRBE instead ?
> 

It's not really about the size of the buffer but where the wakeup points 
are. With only two wakeup points (middle and end) once you pass the 
first one you are immediately into the last chance end section.

Now the driver is writing into the end section, but Perf is still 
reading from the first one. Once the end one fills up, you end up with 
no space left without Perf having a chance to say it's finished reading.

To guarantee free space, there needs to be at least one additional 
section as a buffer zone. Ideally we'd set the wakeup point at thirds so 
there were fewer wakeups and still have one free section, but it might 
not always divide by 3, so 4 is also fine.

The commit message could probably explain it a bit better though.

The reason this is different now is because we want to be able to enable 
wrap mode as much as possible. If you imagine the scenario where a half 
way watermark is hit, you can't enable wrap mode without wrapping into 
Perf's part of the buffer (the beginning) as it's all that's left after 
the second half.

>>> Setting watermark to quarter of the buffer to notifies the tool to read
>> data earlier and prevents the data loss.
>>
>> Signed-off-by: Leo Yan <leo.yan@arm.com>
>> ---
>>   tools/perf/arch/arm/util/cs-etm.c | 7 +++++++
>>   1 file changed, 7 insertions(+)
>>
>> diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
>> index ea891d12f8f40beebf8dee1d3db71cad701f5666..649b8b0d0f92b4af45fb97db9da3c5ccf24a978b 100644
>> --- a/tools/perf/arch/arm/util/cs-etm.c
>> +++ b/tools/perf/arch/arm/util/cs-etm.c
>> @@ -424,6 +424,13 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
>>   		pr_debug2("%s snapshot size: %zu\n", CORESIGHT_ETM_PMU_NAME,
>>   			  opts->auxtrace_snapshot_size);
>>   
>> +	if (!opts->auxtrace_snapshot_mode && !opts->auxtrace_sample_mode) {
>> +		size_t aw = opts->auxtrace_mmap_pages * (size_t)page_size / 4;
>> +		u32 aux_watermark = aw > UINT_MAX ? UINT_MAX : aw;
>> +
>> +		cs_etm_evsel->core.attr.aux_watermark = aux_watermark;
>> +	}
>> +
>>   	/*
>>   	 * To obtain the auxtrace buffer file descriptor, the auxtrace
>>   	 * event must come first.
>>
> 


  reply	other threads:[~2025-12-09 14:54 UTC|newest]

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-12-01 11:21 [PATCH 00/19] coresight: trbe: Support trigger and circle buffer modes Leo Yan
2025-12-01 11:21 ` [PATCH 01/19] coresight: trbe: Use helpers for checking errata Leo Yan
2025-12-04 12:08   ` Anshuman Khandual
2025-12-01 11:21 ` [PATCH 02/19] coresight: trbe: Remove redundant disable operation Leo Yan
2025-12-04 12:25   ` Anshuman Khandual
2025-12-01 11:21 ` [PATCH 03/19] coresight: trbe: Remove buffer disabling in trbe_handle_overflow() Leo Yan
2025-12-04 12:31   ` Anshuman Khandual
2025-12-01 11:21 ` [PATCH 04/19] coresight: trbe: Remove set_trbe_disabled() from the enable flow Leo Yan
2025-12-04 12:43   ` Anshuman Khandual
2025-12-04 13:25     ` Leo Yan
2025-12-01 11:21 ` [PATCH 05/19] coresight: trbe: Refactor status clearing Leo Yan
2025-12-04 12:57   ` Anshuman Khandual
2025-12-09 15:29     ` Leo Yan
2025-12-01 11:21 ` [PATCH 06/19] coresight: trbe: Refactor syndrome decoding Leo Yan
2025-12-02 11:06   ` Suzuki K Poulose
2025-12-02 14:24     ` Leo Yan
2025-12-09 13:17     ` James Clark
2025-12-09 16:06       ` Leo Yan
2025-12-05  4:10   ` Anshuman Khandual
2025-12-09 15:57     ` Leo Yan
2025-12-01 11:21 ` [PATCH 07/19] coresight: trbe: Refactor AUX flag setting Leo Yan
2025-12-02 11:15   ` Suzuki K Poulose
2025-12-02 14:21     ` Leo Yan
2025-12-09 13:37   ` James Clark
2025-12-10 15:43     ` Leo Yan
2025-12-12 14:50       ` James Clark
2025-12-12 15:27         ` Leo Yan
2025-12-12 15:52           ` James Clark
2025-12-01 11:21 ` [PATCH 08/19] coresight: trbe: Use PERF_AUX_FLAG_PARTIAL instead of PERF_AUX_FLAG_COLLISION Leo Yan
2025-12-05  4:28   ` Anshuman Khandual
2025-12-09 13:40     ` James Clark
2025-12-10 16:19       ` Leo Yan
2025-12-01 11:21 ` [PATCH 09/19] coresight: trbe: Add fault action argument to trbe_handle_overflow() Leo Yan
2025-12-01 11:22 ` [PATCH 10/19] coresight: trbe: Always check fault action when updating buffer Leo Yan
2025-12-02 12:00   ` Suzuki K Poulose
2025-12-01 11:22 ` [PATCH 11/19] coresight: trbe: Apply overwrite erratum for only wrap event Leo Yan
2025-12-02 12:05   ` Suzuki K Poulose
2025-12-02 16:56     ` Leo Yan
2025-12-02 17:12       ` Leo Yan
2025-12-01 11:22 ` [PATCH 12/19] coresight: trbe: Calculate size for buffer wrapping Leo Yan
2025-12-01 11:22 ` [PATCH 13/19] coresight: trbe: Remove misleading comment Leo Yan
2025-12-01 11:22 ` [PATCH 14/19] coresight: trbe: Refactor compute_trbe_buffer_limit() Leo Yan
2025-12-01 11:22 ` [PATCH 15/19] coresight: trbe: Add static key for bypassing trigger mode Leo Yan
2025-12-02 12:10   ` Suzuki K Poulose
2025-12-01 11:22 ` [PATCH 16/19] coresight: trbe: Support " Leo Yan
2025-12-01 11:22 ` [PATCH 17/19] coresight: trbe: Enable circle mode for snapshot Leo Yan
2025-12-01 11:22 ` [PATCH 18/19] coresight: trbe: Add kunit tests Leo Yan
2025-12-01 11:22 ` [PATCH 19/19] perf: cs-etm: Set watermark for AUX trace Leo Yan
2025-12-05  4:48   ` Anshuman Khandual
2025-12-09 14:54     ` James Clark [this message]
2025-12-10  2:22       ` Anshuman Khandual
2025-12-05  4:53 ` [PATCH 00/19] coresight: trbe: Support trigger and circle buffer modes Anshuman Khandual

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=5ebf1743-b01c-4664-961c-9e1e2aa7ffce@linaro.org \
    --to=james.clark@linaro.org \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=anshuman.khandual@arm.com \
    --cc=coresight@lists.linaro.org \
    --cc=irogers@google.com \
    --cc=jolsa@kernel.org \
    --cc=leo.yan@arm.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mike.leach@linaro.org \
    --cc=namhyung@kernel.org \
    --cc=suzuki.poulose@arm.com \
    --cc=tamas.petz@arm.com \
    --cc=tamas.zsoldos@arm.com \
    --cc=will@kernel.org \
    --cc=yeoreum.yun@arm.com \
    /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).