Messages in this thread | | | From | Ian Rogers <> | Date | Thu, 6 Oct 2022 11:52:05 -0700 | Subject | Re: [PATCH 2/5] libperf: Propagate maps only if necessary |
| |
On Mon, Oct 3, 2022 at 1:46 PM Namhyung Kim <namhyung@kernel.org> wrote: > > The current code propagate evsel's cpu map settings to evlist when it's > added to an evlist. But the evlist->all_cpus and each evsel's cpus will > be updated in perf_evlist__set_maps() later. No need to do it before > evlist's cpus are set actually. > > In fact it discards this intermediate all_cpus maps at the beginning > of perf_evlist__set_maps(). Let's not do this. It's only needed when > an evsel is added after the evlist cpu/thread maps are set. > > Signed-off-by: Namhyung Kim <namhyung@kernel.org> > --- > tools/lib/perf/evlist.c | 11 ++++------- > tools/lib/perf/include/internal/evlist.h | 1 + > 2 files changed, 5 insertions(+), 7 deletions(-) > > diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c > index 187129652ab6..8ce92070086c 100644 > --- a/tools/lib/perf/evlist.c > +++ b/tools/lib/perf/evlist.c > @@ -67,9 +67,7 @@ static void perf_evlist__propagate_maps(struct perf_evlist *evlist) > { > struct perf_evsel *evsel; > > - /* Recomputing all_cpus, so start with a blank slate. */ > - perf_cpu_map__put(evlist->all_cpus); > - evlist->all_cpus = NULL; > + evlist->needs_map_propagation = true;
Might be nice to also clear this in perf_evlist__init.
> > perf_evlist__for_each_evsel(evlist, evsel) > __perf_evlist__propagate_maps(evlist, evsel); > @@ -81,7 +79,9 @@ void perf_evlist__add(struct perf_evlist *evlist, > evsel->idx = evlist->nr_entries; > list_add_tail(&evsel->node, &evlist->entries); > evlist->nr_entries += 1; > - __perf_evlist__propagate_maps(evlist, evsel); > + > + if (evlist->needs_map_propagation) > + __perf_evlist__propagate_maps(evlist, evsel);
I think a comment here would be useful. Something like: Adding events won't set the CPU maps in the evlist until set_maps/propogate_maps is called. Catch the case that an evsel is added after this and propagate the map.
Thanks, Ian
> } > > void perf_evlist__remove(struct perf_evlist *evlist, > @@ -177,9 +177,6 @@ void perf_evlist__set_maps(struct perf_evlist *evlist, > evlist->threads = perf_thread_map__get(threads); > } > > - if (!evlist->all_cpus && cpus) > - evlist->all_cpus = perf_cpu_map__get(cpus); > - > perf_evlist__propagate_maps(evlist); > } > > diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h > index 6f89aec3e608..850f07070036 100644 > --- a/tools/lib/perf/include/internal/evlist.h > +++ b/tools/lib/perf/include/internal/evlist.h > @@ -19,6 +19,7 @@ struct perf_evlist { > int nr_entries; > int nr_groups; > bool has_user_cpus; > + bool needs_map_propagation; > /** > * The cpus passed from the command line or all online CPUs by > * default. > -- > 2.38.0.rc1.362.ged0d419d3c-goog >
| |