linux-perf-users.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Falcon, Thomas" <thomas.falcon@intel.com>
To: "alexander.shishkin@linux.intel.com"
	<alexander.shishkin@linux.intel.com>,
	"peterz@infradead.org" <peterz@infradead.org>,
	"acme@kernel.org" <acme@kernel.org>,
	"mingo@redhat.com" <mingo@redhat.com>,
	"mark.rutland@arm.com" <mark.rutland@arm.com>,
	"Hunter, Adrian" <adrian.hunter@intel.com>,
	"namhyung@kernel.org" <namhyung@kernel.org>,
	"irogers@google.com" <irogers@google.com>,
	"jolsa@kernel.org" <jolsa@kernel.org>,
	"kan.liang@linux.intel.com" <kan.liang@linux.intel.com>
Cc: "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"linux-perf-users@vger.kernel.org"
	<linux-perf-users@vger.kernel.org>,
	"ak@linux.intel.com" <ak@linux.intel.com>
Subject: Re: [RESEND][PATCH v2 0/2] perf record: ratio-to-prev event term for auto counter reload
Date: Wed, 24 Sep 2025 19:09:22 +0000	[thread overview]
Message-ID: <6478744c4c07fae4b889b252248522f81359ec77.camel@intel.com> (raw)
In-Reply-To: <20250902164047.64261-1-thomas.falcon@intel.com>

On Tue, 2025-09-02 at 11:40 -0500, Thomas Falcon wrote:
> The Auto Counter Reload (ACR)[1] feature is used to track the
> relative rates of two or more perf events, only sampling
> when a given threshold is exceeded. This helps reduce overhead
> and unnecessary samples. However, enabling this feature
> currently requires setting two parameters:

Ping.

Thanks,
Tom

> 
>  -- Event sampling period ("period")
>  -- acr_mask, which determines which events get reloaded
>     when the sample period is reached.
> 
> For example, in the following command:
> 
> perf record -e "{cpu_atom/branch-misses,period=200000,\
> acr_mask=0x2/ppu,cpu_atom/branch-instructions,period=1000000,\
> acr_mask=0x3/u}" -- ./mispredict
> 
> The goal is to limit event sampling to cases when the
> branch miss rate exceeds 20%. If the branch instructions
> sample period is exceeded first, both events are reloaded.
> If branch misses exceed their threshold first, only the
> second counter is reloaded, and a sample is taken.
> 
> To simplify this, provide a new “ratio-to-prev” event term
> that works alongside the period event option or -c option.
> This would allow users to specify the desired relative rate
> between events as a ratio, making configuration more intuitive.
> 
> With this enhancement, the equivalent command would be:
> 
> perf record -e "{cpu_atom/branch-misses/ppu,\
> cpu_atom/branch-instructions,period=1000000,ratio_to_prev=5/u}" \
> -- ./mispredict
> 
> or
> 
> perf record -e "{cpu_atom/branch-misses/ppu,\
> cpu_atom/branch-instructions,ratio-to-prev=5/u}" -c 1000000 \
> -- ./mispredict
> 
> [1]
> https://lore.kernel.org/lkml/20250327195217.2683619-1-kan.liang@linux.intel.com/
> 
> Changes in v2 (mostly suggested by Ian Rogers):
> 
> -- Add documentation explaining acr_mask bitmask used by ACR
> -- Move ACR specific implementation to arch/x86/
> -- Provide test cases for event parsing and perf record tests
> 
> Thomas Falcon (2):
>   perf record: Add ratio-to-prev term
>   perf record: add auto counter reload parse and regression tests
> 
>  tools/perf/Documentation/intel-acr.txt | 53 ++++++++++++++++++
>  tools/perf/Documentation/perf-list.txt |  2 +
>  tools/perf/arch/x86/util/evsel.c       | 53 ++++++++++++++++++
>  tools/perf/tests/parse-events.c        | 54 ++++++++++++++++++
>  tools/perf/tests/shell/record.sh       | 40 ++++++++++++++
>  tools/perf/util/evsel.c                | 76
> ++++++++++++++++++++++++++
>  tools/perf/util/evsel.h                |  1 +
>  tools/perf/util/evsel_config.h         |  1 +
>  tools/perf/util/parse-events.c         | 22 ++++++++
>  tools/perf/util/parse-events.h         |  3 +-
>  tools/perf/util/parse-events.l         |  1 +
>  tools/perf/util/pmu.c                  |  3 +-
>  12 files changed, 307 insertions(+), 2 deletions(-)
>  create mode 100644 tools/perf/Documentation/intel-acr.txt
> 


  parent reply	other threads:[~2025-09-24 19:09 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-09-02 16:40 [RESEND][PATCH v2 0/2] perf record: ratio-to-prev event term for auto counter reload Thomas Falcon
2025-09-02 16:40 ` [RESEND][PATCH v2 1/2] perf record: Add ratio-to-prev term Thomas Falcon
2025-09-24 21:34   ` Ian Rogers
2025-09-02 16:40 ` [RESEND][PATCH v2 2/2] perf record: Add auto counter reload parse and regression tests Thomas Falcon
2025-09-24 21:37   ` Ian Rogers
2025-09-24 19:09 ` Falcon, Thomas [this message]
2025-09-30  7:28 ` [RESEND][PATCH v2 0/2] perf record: ratio-to-prev event term for auto counter reload Mi, Dapeng
2025-10-02 15:38   ` Falcon, Thomas
2025-10-09  2:31     ` Mi, Dapeng
2025-10-02 19:35 ` Arnaldo Carvalho de Melo
2025-10-02 21:57   ` Falcon, Thomas

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=6478744c4c07fae4b889b252248522f81359ec77.camel@intel.com \
    --to=thomas.falcon@intel.com \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=ak@linux.intel.com \
    --cc=alexander.shishkin@linux.intel.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).