Re: [PATCH v4] perf metricgroup: Fix uncore metric expressions
From: Namhyung Kim
Date: Thu Sep 17 2020 - 21:47:39 EST
Hi Arnaldo,
On Fri, Sep 18, 2020 at 5:39 AM Arnaldo Carvalho de Melo
<acme@xxxxxxxxxx> wrote:
>
> Em Thu, Sep 17, 2020 at 01:18:07PM -0700, Ian Rogers escreveu:
> > A metric like DRAM_BW_Use has on SkylakeX events uncore_imc/cas_count_read/
> > and uncore_imc/case_count_write/. These events open 6 events per socket
> > with pmu names of uncore_imc_[0-5]. The current metric setup code in
> > find_evsel_group assumes one ID will map to 1 event to be recorded in
> > metric_events. For events with multiple matches, the first event is
> > recorded in metric_events (avoiding matching >1 event with the same
> > name) and the evlist_used updated so that duplicate events aren't
> > removed when the evlist has unused events removed.
>
> Namhyung, please check if you still Acks this as you provided it for v3.
Sure,
Acked-by: Namhyung Kim <namhyung@xxxxxxxxxx>
Thanks
Namhyung
>
> > Before this change:
> > $ /tmp/perf/perf stat -M DRAM_BW_Use -a -- sleep 1
> >
> > Performance counter stats for 'system wide':
> >
> > 41.14 MiB uncore_imc/cas_count_read/
> > 1,002,614,251 ns duration_time
> >
> > 1.002614251 seconds time elapsed
> >
> > After this change:
> > $ /tmp/perf/perf stat -M DRAM_BW_Use -a -- sleep 1
> >
> > Performance counter stats for 'system wide':
> >
> > 157.47 MiB uncore_imc/cas_count_read/ # 0.00 DRAM_BW_Use
> > 126.97 MiB uncore_imc/cas_count_write/
> > 1,003,019,728 ns duration_time
> >
> > Erroneous duplication introduced in:
> > commit 2440689d62e9 ("perf metricgroup: Remove duped metric group events").
> >
> > Fixes: ded80bda8bc9 ("perf expr: Migrate expr ids table to a hashmap").
> > Reported-by: Jin Yao <yao.jin@xxxxxxxxxxxxxxx>
> > Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
> > ---
> > tools/perf/util/metricgroup.c | 75 ++++++++++++++++++++++++++---------
> > 1 file changed, 56 insertions(+), 19 deletions(-)
> >
> > diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
> > index ab5030fcfed4..d948a7f910cf 100644
> > --- a/tools/perf/util/metricgroup.c
> > +++ b/tools/perf/util/metricgroup.c
> > @@ -150,6 +150,18 @@ static void expr_ids__exit(struct expr_ids *ids)
> > free(ids->id[i].id);
> > }
> >
> > +static bool contains_event(struct evsel **metric_events, int num_events,
> > + const char *event_name)
> > +{
> > + int i;
> > +
> > + for (i = 0; i < num_events; i++) {
> > + if (!strcmp(metric_events[i]->name, event_name))
> > + return true;
> > + }
> > + return false;
> > +}
> > +
> > /**
> > * Find a group of events in perf_evlist that correpond to those from a parsed
> > * metric expression. Note, as find_evsel_group is called in the same order as
> > @@ -180,7 +192,11 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist,
> > int i = 0, matched_events = 0, events_to_match;
> > const int idnum = (int)hashmap__size(&pctx->ids);
> >
> > - /* duration_time is grouped separately. */
> > + /*
> > + * duration_time is always grouped separately, when events are grouped
> > + * (ie has_constraint is false) then ignore it in the matching loop and
> > + * add it to metric_events at the end.
> > + */
> > if (!has_constraint &&
> > hashmap__find(&pctx->ids, "duration_time", (void **)&val_ptr))
> > events_to_match = idnum - 1;
> > @@ -207,23 +223,20 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist,
> > sizeof(struct evsel *) * idnum);
> > current_leader = ev->leader;
> > }
> > - if (hashmap__find(&pctx->ids, ev->name, (void **)&val_ptr)) {
> > - if (has_constraint) {
> > - /*
> > - * Events aren't grouped, ensure the same event
> > - * isn't matched from two groups.
> > - */
> > - for (i = 0; i < matched_events; i++) {
> > - if (!strcmp(ev->name,
> > - metric_events[i]->name)) {
> > - break;
> > - }
> > - }
> > - if (i != matched_events)
> > - continue;
> > - }
> > + /*
> > + * Check for duplicate events with the same name. For example,
> > + * uncore_imc/cas_count_read/ will turn into 6 events per socket
> > + * on skylakex. Only the first such event is placed in
> > + * metric_events. If events aren't grouped then this also
> > + * ensures that the same event in different sibling groups
> > + * aren't both added to metric_events.
> > + */
> > + if (contains_event(metric_events, matched_events, ev->name))
> > + continue;
> > + /* Does this event belong to the parse context? */
> > + if (hashmap__find(&pctx->ids, ev->name, (void **)&val_ptr))
> > metric_events[matched_events++] = ev;
> > - }
> > +
> > if (matched_events == events_to_match)
> > break;
> > }
> > @@ -239,7 +252,7 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist,
> > }
> >
> > if (matched_events != idnum) {
> > - /* Not whole match */
> > + /* Not a whole match */
> > return NULL;
> > }
> >
> > @@ -247,8 +260,32 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist,
> >
> > for (i = 0; i < idnum; i++) {
> > ev = metric_events[i];
> > - ev->metric_leader = ev;
> > + /* Don't free the used events. */
> > set_bit(ev->idx, evlist_used);
> > + /*
> > + * The metric leader points to the identically named event in
> > + * metric_events.
> > + */
> > + ev->metric_leader = ev;
> > + /*
> > + * Mark two events with identical names in the same group (or
> > + * globally) as being in use as uncore events may be duplicated
> > + * for each pmu. Set the metric leader of such events to be the
> > + * event that appears in metric_events.
> > + */
> > + evlist__for_each_entry_continue(perf_evlist, ev) {
> > + /*
> > + * If events are grouped then the search can terminate
> > + * when then group is left.
> > + */
> > + if (!has_constraint &&
> > + ev->leader != metric_events[i]->leader)
> > + break;
> > + if (!strcmp(metric_events[i]->name, ev->name)) {
> > + set_bit(ev->idx, evlist_used);
> > + ev->metric_leader = metric_events[i];
> > + }
> > + }
> > }
> >
> > return metric_events[0];
> > --
> > 2.28.0.618.gf4bc123cb7-goog
> >
>
> --
>
> - Arnaldo