[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20220207103807.857049867@linuxfoundation.org>
Date: Mon, 7 Feb 2022 12:07:21 +0100
From: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To: linux-kernel@...r.kernel.org
Cc: Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
stable@...r.kernel.org, Andi Kleen <ak@...ux.intel.com>,
Ian Rogers <irogers@...gle.com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Alexandre Torgue <alexandre.torgue@...s.st.com>,
Asaf Yaffe <asaf.yaffe@...el.com>,
Caleb Biggers <caleb.biggers@...el.com>,
Ingo Molnar <mingo@...hat.com>,
James Clark <james.clark@....com>,
Jiri Olsa <jolsa@...hat.com>,
John Garry <john.garry@...wei.com>,
Kan Liang <kan.liang@...ux.intel.com>,
Kshipra Bopardikar <kshipra.bopardikar@...el.com>,
Mark Rutland <mark.rutland@....com>,
Maxime Coquelin <mcoquelin.stm32@...il.com>,
Namhyung Kim <namhyung@...nel.org>,
Perry Taylor <perry.taylor@...el.com>,
Peter Zijlstra <peterz@...radead.org>,
Stephane Eranian <eranian@...gle.com>,
Vineet Singh <vineet.singh@...el.com>,
Zhengjun Xing <zhengjun.xing@...ux.intel.com>,
Arnaldo Carvalho de Melo <acme@...hat.com>,
Sasha Levin <sashal@...nel.org>
Subject: [PATCH 5.16 110/126] perf stat: Fix display of grouped aliased events
From: Ian Rogers <irogers@...gle.com>
[ Upstream commit b2b1aa73ade982c175ac926a1fd34e76ad628b94 ]
An event may have a number of uncore aliases that when added to the
evlist are consecutive.
If there are multiple uncore events in a group then
parse_events__set_leader_for_uncore_aliase will reorder the evlist so
that events on the same PMU are adjacent.
The collect_all_aliases function assumes that aliases are in blocks so
that only the first counter is printed and all others are marked merged.
The reordering for groups breaks the assumption and so all counts are
printed.
This change removes the assumption from collect_all_aliases
that the events are in blocks and instead processes the entire evlist.
Before:
```
$ perf stat -e '{UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE,UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE},duration_time' -a -A -- sleep 1
Performance counter stats for 'system wide':
CPU0 256,866 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 494,413 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 967 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,738 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 285,161 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 429,920 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 955 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,443 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 310,753 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 416,657 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,231 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,573 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 416,067 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 405,966 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,481 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,447 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 312,911 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 408,154 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,086 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,380 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 333,994 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 370,349 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,287 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,335 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 188,107 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 302,423 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 701 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,070 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 307,221 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 383,642 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,036 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,158 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 318,479 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 821,545 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,028 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 2,550 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 227,618 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 372,272 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 903 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,456 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 376,783 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 419,827 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,406 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,453 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 286,583 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 429,956 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 999 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,436 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 313,867 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 370,159 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,114 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,291 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 342,083 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 409,111 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,399 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,684 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 365,828 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 376,037 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,378 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,411 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 382,456 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 621,743 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,232 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,955 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 342,316 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 385,067 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,176 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,268 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 373,588 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 386,163 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,394 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,464 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 381,206 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 546,891 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,266 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,712 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 221,176 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 392,069 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 831 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,456 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 355,401 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 705,595 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,235 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 2,216 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 371,436 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 428,103 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,306 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,442 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 384,352 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 504,200 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,468 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,860 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 228,856 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 287,976 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 832 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,060 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 215,121 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 334,162 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 681 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,026 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 296,179 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 436,083 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,084 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,525 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 262,296 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 416,573 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 986 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,533 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 285,852 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 359,842 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,073 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,326 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 303,379 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 367,222 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,008 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,156 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 273,487 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 425,449 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 932 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,367 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 297,596 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 414,793 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,140 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,601 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 342,365 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 360,422 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,291 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,342 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 327,196 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 580,858 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,122 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 2,014 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 296,564 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 452,817 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,087 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,694 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 375,002 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 389,393 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,478 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 1,540 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 365,213 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 594,685 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 1,401 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 2,222 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 1,000,749,060 ns duration_time
1.000749060 seconds time elapsed
```
After:
```
Performance counter stats for 'system wide':
CPU0 20,547,434 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU36 45,202,862 UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE
CPU0 82,001 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU36 159,688 UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE
CPU0 1,000,464,828 ns duration_time
1.000464828 seconds time elapsed
```
Fixes: 3cdc5c2cb924acb4 ("perf parse-events: Handle uncore event aliases in small groups properly")
Reviewed-by: Andi Kleen <ak@...ux.intel.com>
Signed-off-by: Ian Rogers <irogers@...gle.com>
Cc: Alexander Shishkin <alexander.shishkin@...ux.intel.com>
Cc: Alexandre Torgue <alexandre.torgue@...s.st.com>
Cc: Asaf Yaffe <asaf.yaffe@...el.com>
Cc: Caleb Biggers <caleb.biggers@...el.com>
Cc: Ingo Molnar <mingo@...hat.com>
Cc: James Clark <james.clark@....com>
Cc: Jiri Olsa <jolsa@...hat.com>
Cc: John Garry <john.garry@...wei.com>
Cc: Kan Liang <kan.liang@...ux.intel.com>
Cc: Kshipra Bopardikar <kshipra.bopardikar@...el.com>
Cc: Mark Rutland <mark.rutland@....com>
Cc: Maxime Coquelin <mcoquelin.stm32@...il.com>
Cc: Namhyung Kim <namhyung@...nel.org>
Cc: Perry Taylor <perry.taylor@...el.com>
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Stephane Eranian <eranian@...gle.com>
Cc: Vineet Singh <vineet.singh@...el.com>
Cc: Zhengjun Xing <zhengjun.xing@...ux.intel.com>
Link: https://lore.kernel.org/r/20220205010941.1065469-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@...hat.com>
Signed-off-by: Sasha Levin <sashal@...nel.org>
---
tools/perf/util/stat-display.c | 19 ++++++++++---------
1 file changed, 10 insertions(+), 9 deletions(-)
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 588601000f3f9..db00ca6a67deb 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -584,15 +584,16 @@ static void collect_all_aliases(struct perf_stat_config *config, struct evsel *c
alias = list_prepare_entry(counter, &(evlist->core.entries), core.node);
list_for_each_entry_continue (alias, &evlist->core.entries, core.node) {
- if (strcmp(evsel__name(alias), evsel__name(counter)) ||
- alias->scale != counter->scale ||
- alias->cgrp != counter->cgrp ||
- strcmp(alias->unit, counter->unit) ||
- evsel__is_clock(alias) != evsel__is_clock(counter) ||
- !strcmp(alias->pmu_name, counter->pmu_name))
- break;
- alias->merged_stat = true;
- cb(config, alias, data, false);
+ /* Merge events with the same name, etc. but on different PMUs. */
+ if (!strcmp(evsel__name(alias), evsel__name(counter)) &&
+ alias->scale == counter->scale &&
+ alias->cgrp == counter->cgrp &&
+ !strcmp(alias->unit, counter->unit) &&
+ evsel__is_clock(alias) == evsel__is_clock(counter) &&
+ strcmp(alias->pmu_name, counter->pmu_name)) {
+ alias->merged_stat = true;
+ cb(config, alias, data, false);
+ }
}
}
--
2.34.1
Powered by blists - more mailing lists