| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CAP-5=fXOasXgKRSvrA1B+Yx42egfZfLO4h1OKrB4tLCCz_o8Cg@mail.gmail.com>
Date: Sat, 7 Feb 2026 07:54:05 -0800
From: Ian Rogers <irogers@...gle.com>
To: Arnaldo Carvalho de Melo <acme@...nel.org>, namhyung@...nel.org
Cc: adrian.hunter@...el.com, ak@...ux.intel.com,
alexander.shishkin@...ux.intel.com, andres@...razel.de,
dapeng1.mi@...ux.intel.com, james.clark@...aro.org, jolsa@...nel.org,
linux-kernel@...r.kernel.org, linux-perf-users@...r.kernel.org,
linux@...blig.org, mingo@...hat.com, peterz@...radead.org,
thomas.falcon@...el.com, tmricht@...ux.ibm.com, yang.lee@...ux.alibaba.com
Subject: Re: [PATCH v8 6/6] perf stat: Add no-affinity flag
On Sat, Feb 7, 2026 at 4:51 AM Arnaldo Carvalho de Melo <acme@...nel.org> wrote:
>
> On Fri, Feb 06, 2026 at 02:25:09PM -0800, Ian Rogers wrote:
> > Add flag that disables affinity behavior. Using sched_setaffinity to
> > place a perf thread on a CPU can avoid certain interprocessor
> > interrupts but may introduce a delay due to the scheduling,
> > particularly on loaded machines. Add a command line option to disable
> > the behavior. This behavior is less present in other tools like `perf
> > record`, as it uses a ring buffer and doesn't make repeated system
> > calls.
>
> This is confusing:
>
> ⬢ [acme@...lbx perf-tools-next]$ perf stat -h affinity
>
> Usage: perf stat [<options>] [<command>]
>
> --affinity don't allow affinity optimizations aimed at reducing IPIs
>
> ⬢ [acme@...lbx perf-tools-next]$
>
> The way it is presented in the -h output it looks as if one has to use:
>
> perf stat --affinity
>
> To disable affinity setting, when used that way it looks as if the user
> is asking for affinity to be used.
>
> We have things like:
>
> ⬢ [acme@...lbx perf-tools-next]$ grep -A2 OPT_.*no- tools/perf/builtin-record.c
> OPT_BOOLEAN(0, "no-buffering", &record.opts.no_buffering,
> "collect data without buffering"),
> OPT_BOOLEAN('R', "raw-samples", &record.opts.raw_samples,
> --
> OPT_BOOLEAN_SET('i', "no-inherit", &record.opts.no_inherit,
> &record.opts.no_inherit_set,
> "child tasks do not inherit counters"),
> --
> OPT_BOOLEAN(0, "no-bpf-event", &record.opts.no_bpf_event, "do not record bpf events"),
> OPT_BOOLEAN(0, "strict-freq", &record.opts.strict_freq,
> "Fail if the specified frequency can't be used"),
> --
> OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples,
> "don't sample"),
> OPT_BOOLEAN_SET('N', "no-buildid-cache", &record.no_buildid_cache,
> &record.no_buildid_cache_set,
> "do not update the buildid cache"),
> OPT_BOOLEAN_SET('B', "no-buildid", &record.no_buildid,
> &record.no_buildid_set,
> "do not collect buildids in perf.data"),
> ⬢ [acme@...lbx perf-tools-next]$
>
> Probably this needs to be that way?
So it was that way in the v4 patch set but Namhyung asked for it to be
the other way around:
https://lore.kernel.org/lkml/aRvcuMfbDRSBU87k@google.com/
The comment on the option didn't get changed and that's a mistake.
Let me know what's preferred and I can send a patch.
Thanks,
Ian
> - Arnaldo
>
> > Signed-off-by: Ian Rogers <irogers@...gle.com>
> > ---
> > tools/perf/Documentation/perf-stat.txt | 4 ++++
> > tools/perf/builtin-stat.c | 6 ++++++
> > tools/perf/util/evlist.c | 6 +-----
> > tools/perf/util/evlist.h | 1 +
> > 4 files changed, 12 insertions(+), 5 deletions(-)
> >
> > diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
> > index 1a766d4a2233..1ffb510606af 100644
> > --- a/tools/perf/Documentation/perf-stat.txt
> > +++ b/tools/perf/Documentation/perf-stat.txt
> > @@ -382,6 +382,10 @@ color the metric's computed value.
> > Don't print output, warnings or messages. This is useful with perf stat
> > record below to only write data to the perf.data file.
> >
> > +--no-affinity::
> > +Don't change scheduler affinities when iterating over CPUs. Disables
> > +an optimization aimed at minimizing interprocessor interrupts.
> > +
> > STAT RECORD
> > -----------
> > Stores stat data into perf data file.
> > diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> > index c1bb40b99176..8bbdea44c3ba 100644
> > --- a/tools/perf/builtin-stat.c
> > +++ b/tools/perf/builtin-stat.c
> > @@ -2426,6 +2426,7 @@ static int parse_tpebs_mode(const struct option *opt, const char *str,
> > int cmd_stat(int argc, const char **argv)
> > {
> > struct opt_aggr_mode opt_mode = {};
> > + bool affinity = true, affinity_set = false;
> > struct option stat_options[] = {
> > OPT_BOOLEAN('T', "transaction", &transaction_run,
> > "hardware transaction statistics"),
> > @@ -2554,6 +2555,8 @@ int cmd_stat(int argc, const char **argv)
> > "don't print 'summary' for CSV summary output"),
> > OPT_BOOLEAN(0, "quiet", &quiet,
> > "don't print any output, messages or warnings (useful with record)"),
> > + OPT_BOOLEAN_SET(0, "affinity", &affinity, &affinity_set,
> > + "don't allow affinity optimizations aimed at reducing IPIs"),
> > OPT_CALLBACK(0, "cputype", &evsel_list, "hybrid cpu type",
> > "Only enable events on applying cpu with this type "
> > "for hybrid platform (e.g. core or atom)",
> > @@ -2611,6 +2614,9 @@ int cmd_stat(int argc, const char **argv)
> > } else
> > stat_config.csv_sep = DEFAULT_SEPARATOR;
> >
> > + if (affinity_set)
> > + evsel_list->no_affinity = !affinity;
> > +
> > if (argc && strlen(argv[0]) > 2 && strstarts("record", argv[0])) {
> > argc = __cmd_record(stat_options, &opt_mode, argc, argv);
> > if (argc < 0)
> > diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
> > index 45833244daf3..591bdf0b3e2a 100644
> > --- a/tools/perf/util/evlist.c
> > +++ b/tools/perf/util/evlist.c
> > @@ -369,11 +369,7 @@ static bool evlist__use_affinity(struct evlist *evlist)
> > struct perf_cpu_map *used_cpus = NULL;
> > bool ret = false;
> >
> > - /*
> > - * With perf record core.user_requested_cpus is usually NULL.
> > - * Use the old method to handle this for now.
> > - */
> > - if (!evlist->core.user_requested_cpus ||
> > + if (evlist->no_affinity || !evlist->core.user_requested_cpus ||
> > cpu_map__is_dummy(evlist->core.user_requested_cpus))
> > return false;
> >
> > diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
> > index 30dff7484d3c..d17c3b57a409 100644
> > --- a/tools/perf/util/evlist.h
> > +++ b/tools/perf/util/evlist.h
> > @@ -59,6 +59,7 @@ struct event_enable_timer;
> > struct evlist {
> > struct perf_evlist core;
> > bool enabled;
> > + bool no_affinity;
> > int id_pos;
> > int is_pos;
> > int nr_br_cntr;
> > --
> > 2.53.0.rc2.204.g2597b5adb4-goog
> >
Powered by blists - more mailing lists