* [PATCH] perf parse-events: Move slots only with topdown
@ 2022-03-21 22:33 Ian Rogers
2022-03-22 11:48 ` Liang, Kan
0 siblings, 1 reply; 3+ messages in thread
From: Ian Rogers @ 2022-03-21 22:33 UTC (permalink / raw)
To: Kan Liang, Zhengjun Xing, Peter Zijlstra, Ingo Molnar,
Arnaldo Carvalho de Melo, Mark Rutland, Alexander Shishkin,
Jiri Olsa, Namhyung Kim, Maxime Coquelin, Alexandre Torgue,
Andi Kleen, James Clark, John Garry, linux-kernel,
linux-perf-users
Cc: Stephane Eranian, Ian Rogers
If slots isn't with a topdown event then moving it is unnecessary. For
example {instructions, slots} is re-ordered:
$ perf stat -e '{instructions,slots}' -a sleep 1
Performance counter stats for 'system wide':
936,600,825 slots
144,440,968 instructions
1.006061423 seconds time elapsed
Which can break tools expecting the command line order to match the
printed order. It is necessary to move the slots event first when it
appears with topdown events. Add extra checking so that the slots event
is only moved in the case of there being a topdown event like:
$ perf stat -e '{instructions,slots,topdown-fe-bound}' -a sleep 1
Performance counter stats for 'system wide':
2427568570 slots
300927614 instructions
551021649 topdown-fe-bound
1.001771803 seconds time elapsed
Fixes: 94dbfd6781a0 ("perf parse-events: Architecture specific leader override")
Reported-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/arch/x86/util/evlist.c | 18 ++++++++++++++----
1 file changed, 14 insertions(+), 4 deletions(-)
diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
index 8d9b55959256..cfc208d71f00 100644
--- a/tools/perf/arch/x86/util/evlist.c
+++ b/tools/perf/arch/x86/util/evlist.c
@@ -20,17 +20,27 @@ int arch_evlist__add_default_attrs(struct evlist *evlist)
struct evsel *arch_evlist__leader(struct list_head *list)
{
- struct evsel *evsel, *first;
+ struct evsel *evsel, *first, *slots = NULL;
+ bool has_topdown = false;
first = list_first_entry(list, struct evsel, core.node);
if (!pmu_have_event("cpu", "slots"))
return first;
+ /* If there is a slots event and a topdown event then the slots event comes first. */
__evlist__for_each_entry(list, evsel) {
- if (evsel->pmu_name && !strcmp(evsel->pmu_name, "cpu") &&
- evsel->name && strcasestr(evsel->name, "slots"))
- return evsel;
+ if (evsel->pmu_name && !strcmp(evsel->pmu_name, "cpu") && evsel->name) {
+ if (strcasestr(evsel->name, "slots")) {
+ slots = evsel;
+ if (slots == first)
+ return first;
+ }
+ if (!strncasecmp(evsel->name, "topdown", 7))
+ has_topdown = true;
+ if (slots && has_topdown)
+ return slots;
+ }
}
return first;
}
--
2.35.1.894.gb6a874cedc-goog
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [PATCH] perf parse-events: Move slots only with topdown
2022-03-21 22:33 [PATCH] perf parse-events: Move slots only with topdown Ian Rogers
@ 2022-03-22 11:48 ` Liang, Kan
2022-03-22 20:53 ` Arnaldo Carvalho de Melo
0 siblings, 1 reply; 3+ messages in thread
From: Liang, Kan @ 2022-03-22 11:48 UTC (permalink / raw)
To: Ian Rogers, Zhengjun Xing, Peter Zijlstra, Ingo Molnar,
Arnaldo Carvalho de Melo, Mark Rutland, Alexander Shishkin,
Jiri Olsa, Namhyung Kim, Maxime Coquelin, Alexandre Torgue,
Andi Kleen, James Clark, John Garry, linux-kernel,
linux-perf-users
Cc: Stephane Eranian
On 3/21/2022 6:33 PM, Ian Rogers wrote:
> If slots isn't with a topdown event then moving it is unnecessary. For
> example {instructions, slots} is re-ordered:
>
> $ perf stat -e '{instructions,slots}' -a sleep 1
>
> Performance counter stats for 'system wide':
>
> 936,600,825 slots
> 144,440,968 instructions
>
> 1.006061423 seconds time elapsed
>
> Which can break tools expecting the command line order to match the
> printed order. It is necessary to move the slots event first when it
> appears with topdown events. Add extra checking so that the slots event
> is only moved in the case of there being a topdown event like:
>
> $ perf stat -e '{instructions,slots,topdown-fe-bound}' -a sleep 1
>
> Performance counter stats for 'system wide':
>
> 2427568570 slots
> 300927614 instructions
> 551021649 topdown-fe-bound
>
> 1.001771803 seconds time elapsed
>
> Fixes: 94dbfd6781a0 ("perf parse-events: Architecture specific leader override")
> Reported-by: Kan Liang <kan.liang@linux.intel.com>
> Signed-off-by: Ian Rogers <irogers@google.com>
Thanks Ian. The patch works well.
Tested-by: Kan Liang <kan.liang@linux.intel.com>
Thanks,
Kan
> ---
> tools/perf/arch/x86/util/evlist.c | 18 ++++++++++++++----
> 1 file changed, 14 insertions(+), 4 deletions(-)
>
> diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
> index 8d9b55959256..cfc208d71f00 100644
> --- a/tools/perf/arch/x86/util/evlist.c
> +++ b/tools/perf/arch/x86/util/evlist.c
> @@ -20,17 +20,27 @@ int arch_evlist__add_default_attrs(struct evlist *evlist)
>
> struct evsel *arch_evlist__leader(struct list_head *list)
> {
> - struct evsel *evsel, *first;
> + struct evsel *evsel, *first, *slots = NULL;
> + bool has_topdown = false;
>
> first = list_first_entry(list, struct evsel, core.node);
>
> if (!pmu_have_event("cpu", "slots"))
> return first;
>
> + /* If there is a slots event and a topdown event then the slots event comes first. */
> __evlist__for_each_entry(list, evsel) {
> - if (evsel->pmu_name && !strcmp(evsel->pmu_name, "cpu") &&
> - evsel->name && strcasestr(evsel->name, "slots"))
> - return evsel;
> + if (evsel->pmu_name && !strcmp(evsel->pmu_name, "cpu") && evsel->name) {
> + if (strcasestr(evsel->name, "slots")) {
> + slots = evsel;
> + if (slots == first)
> + return first;
> + }
> + if (!strncasecmp(evsel->name, "topdown", 7))
> + has_topdown = true;
> + if (slots && has_topdown)
> + return slots;
> + }
> }
> return first;
> }
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH] perf parse-events: Move slots only with topdown
2022-03-22 11:48 ` Liang, Kan
@ 2022-03-22 20:53 ` Arnaldo Carvalho de Melo
0 siblings, 0 replies; 3+ messages in thread
From: Arnaldo Carvalho de Melo @ 2022-03-22 20:53 UTC (permalink / raw)
To: Liang, Kan
Cc: Ian Rogers, Zhengjun Xing, Peter Zijlstra, Ingo Molnar,
Mark Rutland, Alexander Shishkin, Jiri Olsa, Namhyung Kim,
Maxime Coquelin, Alexandre Torgue, Andi Kleen, James Clark,
John Garry, linux-kernel, linux-perf-users, Stephane Eranian
Em Tue, Mar 22, 2022 at 07:48:48AM -0400, Liang, Kan escreveu:
> On 3/21/2022 6:33 PM, Ian Rogers wrote:
> > If slots isn't with a topdown event then moving it is unnecessary. For
> > example {instructions, slots} is re-ordered:
> >
> > $ perf stat -e '{instructions,slots}' -a sleep 1
> >
> > Performance counter stats for 'system wide':
> >
> > 936,600,825 slots
> > 144,440,968 instructions
> >
> > 1.006061423 seconds time elapsed
> >
> > Which can break tools expecting the command line order to match the
> > printed order. It is necessary to move the slots event first when it
> > appears with topdown events. Add extra checking so that the slots event
> > is only moved in the case of there being a topdown event like:
> >
> > $ perf stat -e '{instructions,slots,topdown-fe-bound}' -a sleep 1
> >
> > Performance counter stats for 'system wide':
> >
> > 2427568570 slots
> > 300927614 instructions
> > 551021649 topdown-fe-bound
> >
> > 1.001771803 seconds time elapsed
> >
> > Fixes: 94dbfd6781a0 ("perf parse-events: Architecture specific leader override")
> > Reported-by: Kan Liang <kan.liang@linux.intel.com>
> > Signed-off-by: Ian Rogers <irogers@google.com>
>
> Thanks Ian. The patch works well.
>
> Tested-by: Kan Liang <kan.liang@linux.intel.com>
Thanks, applied.
- Arnaldo
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2022-03-22 20:54 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-03-21 22:33 [PATCH] perf parse-events: Move slots only with topdown Ian Rogers
2022-03-22 11:48 ` Liang, Kan
2022-03-22 20:53 ` Arnaldo Carvalho de Melo
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.