Re: [PATCH v6 3/7] perf record: Move setting dummy tracking before record__init_thread_masks()

[Yang Jihong]

Hello,

On 2023/8/25 13:10, Ian Rogers wrote:
> On Sun, Aug 20, 2023 at 6:30 PM Yang Jihong <yangjihong1@xxxxxxxxxx> wrote:
> > User space tasks can migrate between CPUs, so when tracing selected CPUs,
> > sideband for all CPUs is needed. In this case set the cpu map of the evsel
> > to all online CPUs. This may modify the original cpu map of the evlist.
> > Therefore, need to check whether the preceding scenario exists before
> > record__init_thread_masks().
> > Dummy tracking has been set in record__open(), move it before
> > record__init_thread_masks() and add a helper for unified processing.
>
> I have a hard time understanding this commit message. Let me have a go:
>
> In order to set cpu maps correctly on dummy events they need to set up
> later. Factor out the dummy event initialization from record__open and
> move it to its own function record__setup_dummy_event. Move the call
> to the record__setup_dummy to before the call to
> record__init_thread_masks in cmd_record.
Yes, as you said above, for that purpose

> > The sys_perf_event_open invoked is as follows:
> >
> >    # perf --debug verbose=3 record -e cpu-clock -D 100 true
> >    <SNIP>
> >    Opening: cpu-clock
> >    ------------------------------------------------------------
> >    perf_event_attr:
> >      type                             1 (PERF_TYPE_SOFTWARE)
> >      size                             136
> >      config                           0 (PERF_COUNT_SW_CPU_CLOCK)
> >      { sample_period, sample_freq }   4000
> >      sample_type                      IP|TID|TIME|PERIOD|IDENTIFIER
> >      read_format                      ID|LOST
> >      disabled                         1
> >      inherit                          1
> >      freq                             1
> >      sample_id_all                    1
> >      exclude_guest                    1
> >    ------------------------------------------------------------
> >    sys_perf_event_open: pid 10318  cpu 0  group_fd -1  flags 0x8 = 5
> >    sys_perf_event_open: pid 10318  cpu 1  group_fd -1  flags 0x8 = 6
> >    sys_perf_event_open: pid 10318  cpu 2  group_fd -1  flags 0x8 = 7
> >    sys_perf_event_open: pid 10318  cpu 3  group_fd -1  flags 0x8 = 9
> >    sys_perf_event_open: pid 10318  cpu 4  group_fd -1  flags 0x8 = 10
> >    sys_perf_event_open: pid 10318  cpu 5  group_fd -1  flags 0x8 = 11
> >    sys_perf_event_open: pid 10318  cpu 6  group_fd -1  flags 0x8 = 12
> >    sys_perf_event_open: pid 10318  cpu 7  group_fd -1  flags 0x8 = 13
> >    Opening: dummy:u
> >    ------------------------------------------------------------
> >    perf_event_attr:
> >      type                             1 (PERF_TYPE_SOFTWARE)
> >      size                             136
> >      config                           0x9 (PERF_COUNT_SW_DUMMY)
> >      { sample_period, sample_freq }   1
> >      sample_type                      IP|TID|TIME|IDENTIFIER
> >      read_format                      ID|LOST
> >      disabled                         1
> >      inherit                          1
> >      exclude_kernel                   1
> >      exclude_hv                       1
> >      mmap                             1
> >      comm                             1
> >      enable_on_exec                   1
> >      task                             1
> >      sample_id_all                    1
> >      exclude_guest                    1
> >      mmap2                            1
> >      comm_exec                        1
> >      ksymbol                          1
> >      bpf_event                        1
> >    ------------------------------------------------------------
> >    sys_perf_event_open: pid 10318  cpu 0  group_fd -1  flags 0x8 = 14
> >    sys_perf_event_open: pid 10318  cpu 1  group_fd -1  flags 0x8 = 15
> >    sys_perf_event_open: pid 10318  cpu 2  group_fd -1  flags 0x8 = 16
> >    sys_perf_event_open: pid 10318  cpu 3  group_fd -1  flags 0x8 = 17
> >    sys_perf_event_open: pid 10318  cpu 4  group_fd -1  flags 0x8 = 18
> >    sys_perf_event_open: pid 10318  cpu 5  group_fd -1  flags 0x8 = 19
> >    sys_perf_event_open: pid 10318  cpu 6  group_fd -1  flags 0x8 = 20
> >    sys_perf_event_open: pid 10318  cpu 7  group_fd -1  flags 0x8 = 21
> >    <SNIP>
> >
> > Signed-off-by: Yang Jihong <yangjihong1@xxxxxxxxxx>
> > Acked-by: Adrian Hunter <adrian.hunter@xxxxxxxxx>
> > ---
> >   tools/perf/builtin-record.c | 59 +++++++++++++++++++++++--------------
> >   1 file changed, 37 insertions(+), 22 deletions(-)
> >
> > diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
> > index 12edad8392cc..4ee94058028f 100644
> > --- a/tools/perf/builtin-record.c
> > +++ b/tools/perf/builtin-record.c
> > @@ -906,6 +906,37 @@ static int record__config_off_cpu(struct record *rec)
> >          return off_cpu_prepare(rec->evlist, &rec->opts.target, &rec->opts);
> >   }
> >
> > +static int record__config_tracking_events(struct record *rec)
> > +{
> > +       struct record_opts *opts = &rec->opts;
> > +       struct evlist *evlist = rec->evlist;
> > +       struct evsel *evsel;
> > +
> > +       /*
> > +        * For initial_delay, system wide or a hybrid system, we need to add a
> > +        * dummy event so that we can track PERF_RECORD_MMAP to cover the delay
>
> This code is explicitly talking about dummy events but the function is
> now renamed to call it a tracking event. I think the code should be
> consistent.
>
> > +        * of waiting or event synthesis.
> > +        */
> > +       if (opts->target.initial_delay || target__has_cpu(&opts->target) ||
> > +           perf_pmus__num_core_pmus() > 1) {
> > +               evsel = evlist__findnew_tracking_event(evlist, false);
> > +               if (!evsel)
> > +                       return -ENOMEM;
> > +
> > +               /*
> > +                * Enable the dummy event when the process is forked for
>
> Dummy again.
This comment directly copies the original content.
I can change to "tracking event" in the next version.

Thanks,
Yang