From: Namhyung Kim <namhyung@kernel.org>
To: Ian Rogers <irogers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@redhat.com>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Jiri Olsa <jolsa@kernel.org>,
Adrian Hunter <adrian.hunter@intel.com>,
James Clark <james.clark@linaro.org>, Xu Yang <xu.yang_2@nxp.com>,
Chun-Tse Shao <ctshao@google.com>,
Thomas Richter <tmricht@linux.ibm.com>,
Sumanth Korikkar <sumanthk@linux.ibm.com>,
Collin Funk <collin.funk1@gmail.com>,
Thomas Falcon <thomas.falcon@intel.com>,
Howard Chu <howardchu95@gmail.com>,
Dapeng Mi <dapeng1.mi@linux.intel.com>,
Levi Yun <yeoreum.yun@arm.com>,
Yang Li <yang.lee@linux.alibaba.com>,
linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org
Subject: Re: [PATCH v1 05/22] perf metricgroup: Add care to picking the evsel for displaying a metric
Date: Mon, 3 Nov 2025 20:52:12 -0800 [thread overview]
Message-ID: <aQmGfLVKk0UFGAyd@google.com> (raw)
In-Reply-To: <20251024175857.808401-6-irogers@google.com>
On Fri, Oct 24, 2025 at 10:58:40AM -0700, Ian Rogers wrote:
> Rather than using the first evsel in the matched events, try to find
> the least shared non-tool evsel. The aim is to pick the first evsel
> that typifies the metric within the list of metrics.
>
> This addresses an issue where Default metric group metrics may lose
> their counter value due to how the stat displaying hides counters for
> default event/metric output.
Do you have a command line example to show impact of this change?
Thanks,
Namhyung
>
> Signed-off-by: Ian Rogers <irogers@google.com>
> ---
> tools/perf/util/metricgroup.c | 48 ++++++++++++++++++++++++++++++++++-
> 1 file changed, 47 insertions(+), 1 deletion(-)
>
> diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
> index 48936e517803..76092ee26761 100644
> --- a/tools/perf/util/metricgroup.c
> +++ b/tools/perf/util/metricgroup.c
> @@ -1323,6 +1323,51 @@ static int parse_ids(bool metric_no_merge, bool fake_pmu,
> return ret;
> }
>
> +/* How many times will a given evsel be used in a set of metrics? */
> +static int count_uses(struct list_head *metric_list, struct evsel *evsel)
> +{
> + const char *metric_id = evsel__metric_id(evsel);
> + struct metric *m;
> + int uses = 0;
> +
> + list_for_each_entry(m, metric_list, nd) {
> + if (hashmap__find(m->pctx->ids, metric_id, NULL))
> + uses++;
> + }
> + return uses;
> +}
> +
> +/*
> + * Select the evsel that stat-display will use to trigger shadow/metric
> + * printing. Pick the least shared non-tool evsel, encouraging metrics to be
> + * with a hardware counter that is specific to them.
> + */
> +static struct evsel *pick_display_evsel(struct list_head *metric_list,
> + struct evsel **metric_events)
> +{
> + struct evsel *selected = metric_events[0];
> + size_t selected_uses;
> + bool selected_is_tool;
> +
> + if (!selected)
> + return NULL;
> +
> + selected_uses = count_uses(metric_list, selected);
> + selected_is_tool = evsel__is_tool(selected);
> + for (int i = 1; metric_events[i]; i++) {
> + struct evsel *candidate = metric_events[i];
> + size_t candidate_uses = count_uses(metric_list, candidate);
> +
> + if ((selected_is_tool && !evsel__is_tool(candidate)) ||
> + (candidate_uses < selected_uses)) {
> + selected = candidate;
> + selected_uses = candidate_uses;
> + selected_is_tool = evsel__is_tool(selected);
> + }
> + }
> + return selected;
> +}
> +
> static int parse_groups(struct evlist *perf_evlist,
> const char *pmu, const char *str,
> bool metric_no_group,
> @@ -1430,7 +1475,8 @@ static int parse_groups(struct evlist *perf_evlist,
> goto out;
> }
>
> - me = metricgroup__lookup(&perf_evlist->metric_events, metric_events[0],
> + me = metricgroup__lookup(&perf_evlist->metric_events,
> + pick_display_evsel(&metric_list, metric_events),
> /*create=*/true);
>
> expr = malloc(sizeof(struct metric_expr));
> --
> 2.51.1.821.gb6fe4d2222-goog
>
next prev parent reply other threads:[~2025-11-04 4:52 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-24 17:58 [PATCH v1 00/22] Switch the default perf stat metrics to json Ian Rogers
2025-10-24 17:58 ` [PATCH v1 01/22] perf evsel: Remove unused metric_events variable Ian Rogers
2025-10-24 17:58 ` [PATCH v1 02/22] perf metricgroup: Update comment on location of metric_event list Ian Rogers
2025-10-24 17:58 ` [PATCH v1 03/22] perf metricgroup: Missed free on error path Ian Rogers
2025-10-24 17:58 ` [PATCH v1 04/22] perf metricgroup: When copy metrics copy default information Ian Rogers
2025-10-24 17:58 ` [PATCH v1 05/22] perf metricgroup: Add care to picking the evsel for displaying a metric Ian Rogers
2025-11-04 4:52 ` Namhyung Kim [this message]
2025-11-04 5:28 ` Ian Rogers
2025-11-06 6:03 ` Namhyung Kim
2025-11-06 6:42 ` Ian Rogers
2025-10-24 17:58 ` [PATCH v1 06/22] perf jevents: Make all tables static Ian Rogers
2025-10-24 17:58 ` [PATCH v1 07/22] perf expr: Add #target_cpu literal Ian Rogers
2025-11-04 4:56 ` Namhyung Kim
2025-11-06 18:43 ` Ian Rogers
2025-10-24 17:58 ` [PATCH v1 08/22] perf jevents: Add set of common metrics based on default ones Ian Rogers
2025-11-06 6:22 ` Namhyung Kim
2025-11-06 18:05 ` Ian Rogers
2025-10-24 17:58 ` [PATCH v1 09/22] perf jevents: Add metric DefaultShowEvents Ian Rogers
2025-10-24 17:58 ` [PATCH v1 10/22] perf stat: Add detail -d,-dd,-ddd metrics Ian Rogers
2025-10-24 17:58 ` [PATCH v1 11/22] perf script: Change metric format to use json metrics Ian Rogers
2025-10-24 17:58 ` [PATCH v1 12/22] perf stat: Remove hard coded shadow metrics Ian Rogers
2025-10-24 17:58 ` [PATCH v1 13/22] perf stat: Fix default metricgroup display on hybrid Ian Rogers
2025-10-24 17:58 ` [PATCH v1 14/22] perf stat: Sort default events/metrics Ian Rogers
2025-10-24 17:58 ` [PATCH v1 15/22] perf stat: Remove "unit" workarounds for metric-only Ian Rogers
2025-10-24 17:58 ` [PATCH v1 16/22] perf test stat+json: Improve metric-only testing Ian Rogers
2025-10-24 17:58 ` [PATCH v1 17/22] perf test stat: Ignore failures in Default[234] metricgroups Ian Rogers
2025-10-24 17:58 ` [PATCH v1 18/22] perf test stat: Update std_output testing metric expectations Ian Rogers
2025-10-24 17:58 ` [PATCH v1 19/22] perf test metrics: Update all metrics for possibly failing default metrics Ian Rogers
2025-10-24 17:58 ` [PATCH v1 20/22] perf test stat: Update shadow test to use metrics Ian Rogers
2025-10-24 17:58 ` [PATCH v1 21/22] perf test stat: Update test expectations and events Ian Rogers
2025-10-24 17:58 ` [PATCH v1 22/22] perf test stat csv: " Ian Rogers
2025-10-30 20:51 ` [PATCH v1 00/22] Switch the default perf stat metrics to json Ian Rogers
2025-11-03 17:05 ` Ian Rogers
2025-11-04 4:47 ` Namhyung Kim
2025-11-04 5:09 ` Ian Rogers
2025-11-06 5:29 ` Namhyung Kim
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=aQmGfLVKk0UFGAyd@google.com \
--to=namhyung@kernel.org \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=collin.funk1@gmail.com \
--cc=ctshao@google.com \
--cc=dapeng1.mi@linux.intel.com \
--cc=howardchu95@gmail.com \
--cc=irogers@google.com \
--cc=james.clark@linaro.org \
--cc=jolsa@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=sumanthk@linux.ibm.com \
--cc=thomas.falcon@intel.com \
--cc=tmricht@linux.ibm.com \
--cc=xu.yang_2@nxp.com \
--cc=yang.lee@linux.alibaba.com \
--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).