linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Ian Rogers <irogers@google.com>
To: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>,
	Jiri Olsa <jolsa@redhat.com>,
	Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>,
	Namhyung Kim <namhyung@kernel.org>, Leo Yan <leo.yan@linaro.org>,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH V1 13/23] perf evlist: Add evlist__add_system_wide_dummy()
Date: Fri, 6 May 2022 01:34:13 -0700	[thread overview]
Message-ID: <CAP-5=fWF=c1Hu5JaJfz4oZLg15ZQy=gqVkNc34Xphtroenfm8g@mail.gmail.com> (raw)
In-Reply-To: <fed8d256-b214-e25f-9a5f-492442c4b849@intel.com>

On Fri, May 6, 2022 at 1:14 AM Adrian Hunter <adrian.hunter@intel.com> wrote:
>
> On 6/05/22 02:56, Ian Rogers wrote:
> > On Thu, May 5, 2022 at 9:57 AM Adrian Hunter <adrian.hunter@intel.com> wrote:
> >>
> >> Add evlist__add_system_wide_dummy() to enable creating a system-wide dummy
> >> event that sets up the system-wide maps before map propagation.
> >
> > Perhaps this should be:
> > evlist__add_dummy_on_all_online_cpus()
>
> Ok, but offline isn't an option, so I'll drop 'online' from the name.

I'm not sure I follow. There can be CPUs that are offline (echo 0 >
/sys/devices/system/cpu/cpu2/online) and then brought online while
perf is running. The output obviously won't be right as we're missing
dummy events. Losing online from the name here seems to remove a
useful clue.

Thanks,
Ian

> > my thoughts being that a system wide dummy sounds like the dummy CPU
> > map, ie {-1} whilst what happens here is opening on all online CPUs
> > {0-35} on a 36 hyperthread system. Note also that the libperf
> > cpu_map__read_all_cpu_map code doesn't discover sysfs' mount properly,
> > as done in:
> > tools/lib/api/fs/fs.h
> > Some tech debt.
> >
> >> For convenience, add evlist__add_aux_dummy() so that the logic can be used
> >> whether or not the event needs to be system-wide.
> >>
> >> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
> >> ---
> >>  tools/perf/util/evlist.c | 40 ++++++++++++++++++++++++++++++++++++++++
> >>  tools/perf/util/evlist.h |  5 +++++
> >>  2 files changed, 45 insertions(+)
> >>
> >> diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
> >> index 78c47cbafbc2..58ea562ddbd2 100644
> >> --- a/tools/perf/util/evlist.c
> >> +++ b/tools/perf/util/evlist.c
> >> @@ -264,6 +264,46 @@ int evlist__add_dummy(struct evlist *evlist)
> >>         return 0;
> >>  }
> >>
> >> +static void evlist__add_system_wide(struct evlist *evlist, struct evsel *evsel)
> >
> > This would be:
> > evlist__add_on_all_online_cpus(..)
> >
> >> +{
> >> +       evsel->core.system_wide = true;
> >> +
> >> +       /* All CPUs */
> >> +       perf_cpu_map__put(evsel->core.own_cpus);
> >> +       evsel->core.own_cpus = perf_cpu_map__new(NULL);
> >> +       perf_cpu_map__put(evsel->core.cpus);
> >> +       evsel->core.cpus = perf_cpu_map__get(evsel->core.own_cpus);
> >> +
> >> +       /* No threads */
> >> +       perf_thread_map__put(evsel->core.threads);
> >> +       evsel->core.threads = perf_thread_map__new_dummy();
> >> +
> >> +       evlist__add(evlist, evsel);
> >> +}
> >> +
> >> +struct evsel *evlist__add_aux_dummy(struct evlist *evlist, bool system_wide)
> >> +{
> >> +       struct evsel *evsel = evlist__dummy_event(evlist);
> >> +
> >> +       if (!evsel)
> >> +               return NULL;
> >> +
> >> +       evsel->core.attr.exclude_kernel = 1;
> >> +       evsel->core.attr.exclude_guest = 1;
> >> +       evsel->core.attr.exclude_hv = 1;
> >> +       evsel->core.attr.freq = 0;
> >> +       evsel->core.attr.sample_period = 1;
> >> +       evsel->no_aux_samples = true;
> >> +       evsel->name = strdup("dummy:u");
> >> +
> >> +       if (system_wide)
> >> +               evlist__add_system_wide(evlist, evsel);
> >> +       else
> >> +               evlist__add(evlist, evsel);
> >> +
> >> +       return evsel;
> >> +}
> >> +
> >>  static int evlist__add_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs)
> >>  {
> >>         struct evsel *evsel, *n;
> >> diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
> >> index 4062f5aebfc1..dd1af114e033 100644
> >> --- a/tools/perf/util/evlist.h
> >> +++ b/tools/perf/util/evlist.h
> >> @@ -114,6 +114,11 @@ int arch_evlist__add_default_attrs(struct evlist *evlist);
> >>  struct evsel *arch_evlist__leader(struct list_head *list);
> >>
> >>  int evlist__add_dummy(struct evlist *evlist);
> >> +struct evsel *evlist__add_aux_dummy(struct evlist *evlist, bool system_wide);
> >> +static inline struct evsel *evlist__add_system_wide_dummy(struct evlist *evlist)
> >> +{
> >> +       return evlist__add_aux_dummy(evlist, true);
> >> +}
> >>
> >>  int evlist__add_sb_event(struct evlist *evlist, struct perf_event_attr *attr,
> >>                          evsel__sb_cb_t cb, void *data);
> >> --
> >> 2.25.1
> >>
>

  reply	other threads:[~2022-05-06  8:34 UTC|newest]

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-05-05 16:56 [PATCH V1 00/23] perf intel-pt: Better support for perf record --cpu Adrian Hunter
2022-05-05 16:56 ` [PATCH V1 01/23] perf intel-pt: Add a test for system-wide side band Adrian Hunter
2022-05-05 22:37   ` Ian Rogers
2022-05-05 16:56 ` [PATCH V1 02/23] libperf evsel: Add perf_evsel__enable_thread() Adrian Hunter
2022-05-05 22:48   ` Ian Rogers
2022-05-06  7:18     ` Adrian Hunter
2022-05-05 16:56 ` [PATCH V1 03/23] perf evlist: Use libperf functions in evlist__enable_event_idx() Adrian Hunter
2022-05-05 22:58   ` Ian Rogers
2022-05-05 16:56 ` [PATCH V1 04/23] perf auxtrace: Move evlist__enable_event_idx() to auxtrace.c Adrian Hunter
2022-05-05 23:06   ` Ian Rogers
2022-05-05 16:56 ` [PATCH V1 05/23] perf auxtrace: Do not mix up mmap idx Adrian Hunter
2022-05-05 23:08   ` Ian Rogers
2022-05-05 16:56 ` [PATCH V1 06/23] libperf evlist: Remove ->idx() per_cpu parameter Adrian Hunter
2022-05-05 23:08   ` Ian Rogers
2022-05-05 16:56 ` [PATCH V1 07/23] libperf evlist: Move ->idx() into mmap_per_evsel() Adrian Hunter
2022-05-05 23:09   ` Ian Rogers
2022-05-05 16:56 ` [PATCH V1 08/23] libperf evlist: Add evsel as a parameter to ->idx() Adrian Hunter
2022-05-05 23:27   ` Ian Rogers
2022-05-05 16:56 ` [PATCH V1 09/23] perf auxtrace: Record whether an auxtrace mmap is needed Adrian Hunter
2022-05-05 23:28   ` Ian Rogers
2022-05-05 16:56 ` [PATCH V1 10/23] perf auxtrace: Add mmap_needed to auxtrace_mmap_params Adrian Hunter
2022-05-05 23:40   ` Ian Rogers
2022-05-05 16:56 ` [PATCH V1 11/23] perf auxtrace: Remove auxtrace_mmap_params__set_idx() per_cpu parameter Adrian Hunter
2022-05-05 22:13   ` Ian Rogers
2022-05-05 16:56 ` [PATCH V1 12/23] perf evlist: Factor out evlist__dummy_event() Adrian Hunter
2022-05-05 23:42   ` Ian Rogers
2022-05-05 16:56 ` [PATCH V1 13/23] perf evlist: Add evlist__add_system_wide_dummy() Adrian Hunter
2022-05-05 23:56   ` Ian Rogers
2022-05-06  8:14     ` Adrian Hunter
2022-05-06  8:34       ` Ian Rogers [this message]
2022-05-06  9:27         ` Adrian Hunter
2022-05-05 16:56 ` [PATCH V1 14/23] perf record: Use evlist__add_system_wide_dummy() in record__config_text_poke() Adrian Hunter
2022-05-05 23:57   ` Ian Rogers
2022-05-05 16:56 ` [PATCH V1 15/23] perf intel-pt: Use evlist__add_system_wide_dummy() for switch tracking Adrian Hunter
2022-05-05 23:58   ` Ian Rogers
2022-05-05 16:56 ` [PATCH V1 16/23] perf intel-pt: Track sideband system-wide when needed Adrian Hunter
2022-05-06  0:01   ` Ian Rogers
2022-05-05 16:56 ` [PATCH V1 17/23] perf tools: Allow all_cpus to be a superset of user_requested_cpus Adrian Hunter
2022-05-05 16:56 ` [PATCH V1 18/23] libperf evlist: Allow mixing per-thread and per-cpu mmaps Adrian Hunter
2022-05-06  0:09   ` Ian Rogers
2022-05-05 16:56 ` [PATCH V1 19/23] libperf evlist: Check nr_mmaps is correct Adrian Hunter
2022-05-06  0:13   ` Ian Rogers
2022-05-05 16:56 ` [PATCH V1 20/23] perf stat: Add requires_cpu flag for uncore Adrian Hunter
2022-05-06  0:50   ` Ian Rogers
2022-05-06  0:52     ` Ian Rogers
2022-05-05 16:56 ` [PATCH V1 21/23] libperf evsel: Add comments for booleans Adrian Hunter
2022-05-06  0:55   ` Ian Rogers
2022-05-05 16:56 ` [PATCH V1 22/23] perf tools: Allow system-wide events to keep their own CPUs Adrian Hunter
2022-05-06  1:00   ` Ian Rogers
2022-05-05 16:56 ` [PATCH V1 23/23] perf tools: Allow system-wide events to keep their own threads Adrian Hunter
2022-05-06  0:51   ` Ian Rogers
2022-05-06  1:06 ` [PATCH V1 00/23] perf intel-pt: Better support for perf record --cpu Ian Rogers

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='CAP-5=fWF=c1Hu5JaJfz4oZLg15ZQy=gqVkNc34Xphtroenfm8g@mail.gmail.com' \
    --to=irogers@google.com \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=alexey.v.bayduraev@linux.intel.com \
    --cc=jolsa@redhat.com \
    --cc=leo.yan@linaro.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=namhyung@kernel.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).