[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <CAP-5=fUEiPncL3Xe9WoDqWBTTxqw7dXxudx7-8muzppmz6JEXA@mail.gmail.com>
Date: Wed, 19 Nov 2025 08:33:27 -0800
From: Ian Rogers <irogers@...gle.com>
To: Namhyung Kim <namhyung@...nel.org>
Cc: Arnaldo Carvalho de Melo <acme@...nel.org>, James Clark <james.clark@...aro.org>,
Jiri Olsa <jolsa@...nel.org>, Adrian Hunter <adrian.hunter@...el.com>,
Peter Zijlstra <peterz@...radead.org>, Ingo Molnar <mingo@...nel.org>,
LKML <linux-kernel@...r.kernel.org>, linux-perf-users@...r.kernel.org
Subject: Re: [PATCH 1/3] perf list: Print matching PMU events for --unit
On Mon, Nov 17, 2025 at 10:36 PM Namhyung Kim <namhyung@...nel.org> wrote:
>
> When --unit option is used, pmu_glob is set to the argument. It should
> match with event PMU and display the matching ones only. But it also
> shows raw events and metrics after that.
>
> $ perf list --unit tool
> List of pre-defined events (to be used in -e or -M):
>
> tool:
> core_wide
> [1 if not SMT,if SMT are events being gathered on all SMT threads 1 otherwise 0. Unit: tool]
> duration_time
> [Wall clock interval time in nanoseconds. Unit: tool]
> has_pmem
> [1 if persistent memory installed otherwise 0. Unit: tool]
> num_cores
> [Number of cores. A core consists of 1 or more thread,with each thread being associated with a logical Linux CPU. Unit: tool]
> num_cpus
> [Number of logical Linux CPUs. There may be multiple such CPUs on a core. Unit: tool]
> ...
> rNNN [Raw event descriptor]
> cpu/event=0..255,pc,edge,.../modifier [Raw event descriptor]
> [(see 'man perf-list' or 'man perf-record' on how to encode it)]
> breakpoint//modifier [Raw event descriptor]
> cstate_core/event=0..0xffffffffffffffff/modifier [Raw event descriptor]
> cstate_pkg/event=0..0xffffffffffffffff/modifier [Raw event descriptor]
> drm_i915//modifier [Raw event descriptor]
> hwmon_acpitz//modifier [Raw event descriptor]
> hwmon_ac//modifier [Raw event descriptor]
> hwmon_bat0//modifier [Raw event descriptor]
> hwmon_coretemp//modifier [Raw event descriptor]
> ...
>
> Metric Groups:
>
> Backend: [Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet]
> tma_core_bound
> [This metric represents fraction of slots where Core non-memory issues were of a bottleneck]
> tma_info_core_ilp
> [Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)]
> tma_info_memory_l2mpki
> [L2 cache true misses per kilo instruction for retired demand loads]
> ...
>
> This change makes it print the tool PMU events only.
Perhaps this can be used to simplify tests like:
https://lore.kernel.org/lkml/20251109005959.2540616-2-irogers@google.com/
Reviewed-by: Ian Rogers <irogers@...gle.com>
Thanks,
Ian
> Signed-off-by: Namhyung Kim <namhyung@...nel.org>
> ---
> tools/perf/builtin-list.c | 8 +++++---
> 1 file changed, 5 insertions(+), 3 deletions(-)
>
> diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
> index 16400366f8276a7a..28bf1fc7f5eeff8f 100644
> --- a/tools/perf/builtin-list.c
> +++ b/tools/perf/builtin-list.c
> @@ -130,7 +130,7 @@ static void default_print_event(void *ps, const char *topic,
> if (deprecated && !print_state->deprecated)
> return;
>
> - if (print_state->pmu_glob && pmu_name && !strglobmatch(pmu_name, print_state->pmu_glob))
> + if (print_state->pmu_glob && (!pmu_name || !strglobmatch(pmu_name, print_state->pmu_glob)))
> return;
>
> if (print_state->exclude_abi && pmu_type < PERF_TYPE_MAX && pmu_type != PERF_TYPE_RAW)
> @@ -612,8 +612,10 @@ int cmd_list(int argc, const char **argv)
> print_cb.print_start(ps);
>
> if (argc == 0) {
> - default_ps.metrics = true;
> - default_ps.metricgroups = true;
> + if (!unit_name) {
> + default_ps.metrics = true;
> + default_ps.metricgroups = true;
> + }
> print_events(&print_cb, ps);
> goto out;
> }
> --
> 2.52.0.rc1.455.g30608eb744-goog
>
Powered by blists - more mailing lists