Re: [PATCH v3 20/50] perf record: Be lazier in allocating lost samples buffer

[Namhyung Kim]

On Wed, Oct 25, 2023 at 10:01 AM Ian Rogers <irogers@xxxxxxxxxx> wrote:
>
> On Tue, Oct 24, 2023 at 8:44 PM Yang Jihong <yangjihong1@xxxxxxxxxx> wrote:
> >
> > Hello,
> >
> > On 2023/10/25 6:23, Ian Rogers wrote:
> > > Wait until a lost sample occurs to allocate the lost samples buffer,
> > > often the buffer isn't necessary. This saves a 64kb allocation and
> > > 5.3kb of peak memory consumption.
> > >
> > > Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
> > > ---
> > >   tools/perf/builtin-record.c | 29 +++++++++++++++++++----------
> > >   1 file changed, 19 insertions(+), 10 deletions(-)
> > >
> > > diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
> > > index 9b4f3805ca92..b6c8c1371b39 100644
> > > --- a/tools/perf/builtin-record.c
> > > +++ b/tools/perf/builtin-record.c
> > > @@ -1924,21 +1924,13 @@ static void __record__save_lost_samples(struct record *rec, struct evsel *evsel,
> > >   static void record__read_lost_samples(struct record *rec)
> > >   {
> > >       struct perf_session *session = rec->session;
> > > -     struct perf_record_lost_samples *lost;
> > > +     struct perf_record_lost_samples *lost = NULL;
> > >       struct evsel *evsel;
> > >
> > >       /* there was an error during record__open */
> > >       if (session->evlist == NULL)
> > >               return;
> > >
> > > -     lost = zalloc(PERF_SAMPLE_MAX_SIZE);
> > > -     if (lost == NULL) {
> > > -             pr_debug("Memory allocation failed\n");
> > > -             return;
> > > -     }
> > > -
> > > -     lost->header.type = PERF_RECORD_LOST_SAMPLES;
> > > -
> > >       evlist__for_each_entry(session->evlist, evsel) {
> > >               struct xyarray *xy = evsel->core.sample_id;
> > >               u64 lost_count;
> > > @@ -1961,6 +1953,14 @@ static void record__read_lost_samples(struct record *rec)
> > >                               }
> > >
> > >                               if (count.lost) {
> > > +                                     if (!lost) {
> > > +                                             lost = zalloc(PERF_SAMPLE_MAX_SIZE);
> > > +                                             if (!lost) {
> > > +                                                     pr_debug("Memory allocation failed\n");
> > > +                                                     return;
> > > +                                             }
> > > +                                             lost->header.type = PERF_RECORD_LOST_SAMPLES;
> > > +                                     }
> > >                                       __record__save_lost_samples(rec, evsel, lost,
> > >                                                                   x, y, count.lost, 0);
> > >                               }
> > > @@ -1968,9 +1968,18 @@ static void record__read_lost_samples(struct record *rec)
> > >               }
> > >
> > >               lost_count = perf_bpf_filter__lost_count(evsel);
> > > -             if (lost_count)
> > > +             if (lost_count) {
> > > +                     if (!lost) {
> > > +                             lost = zalloc(PERF_SAMPLE_MAX_SIZE);
> > > +                             if (!lost) {
> > > +                                     pr_debug("Memory allocation failed\n");
> > > +                                     return;
> > > +                             }
> > > +                             lost->header.type = PERF_RECORD_LOST_SAMPLES;
> > > +                     }
> > >                       __record__save_lost_samples(rec, evsel, lost, 0, 0, lost_count,
> > >                                                   PERF_RECORD_MISC_LOST_SAMPLES_BPF);
> > > +             }
> > >       }
> >
> > Can zalloc for `lost` be moved to __record__save_lost_samples?
> > This simplifies the code.
>
> Hmm.. seems marginal. This change makes the code not return in
> record__read_lost_samples when the memory allocation fails, so I'm
> 50/50 on it.

Maybe you can make it return the failure.

> >
> >
> > diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
> > index dcf288a4fb9a..8d2eb746031a 100644
> > --- a/tools/perf/builtin-record.c
> > +++ b/tools/perf/builtin-record.c
[SNIP]
> >   out:
> > -       free(lost);
> > +       if (lost)
> > +               free(lost);

This is unnecessary as free() can handle NULL pointers.

Thanks,
Namhyung


> >   }
> >
> >   static volatile sig_atomic_t workload_exec_errno;
> >
> >
> > Thanks,
> > Yang
> >