packages/kernel
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
kernel/patches/0200-perf-metricgroup-Remove-duped-metric-group-events.patch
hongrongxuan a7fbfa09c7 Perf tool: perf tool add Hip09 json support
2023-11-10 14:47:39 +08:00

255 lines
9.2 KiB
Diff
Raw Blame History

From 44f2d339d18d722e5afd9beccb4474fc0ed60412 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 20 May 2020 11:20:09 -0700
Subject: [PATCH 083/201] perf metricgroup: Remove duped metric group events
mainline inclusion
from mainline-v5.8-rc1
commit 2440689d62e93574ca71c87129f7d523ddff7679
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/I8C0CX
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=2440689d62e93574ca71c87129f7d523ddff7679
----------------------------------------------------------------------
A metric group contains multiple metrics. These metrics may use the same
events. If metrics use separate events then it leads to more
multiplexing and overall metric counts fail to sum to 100%.
Modify how metrics are associated with events so that if the events in
an earlier group satisfy the current metric, the same events are used.
A record of used events is kept and at the end of processing unnecessary
events are eliminated.
Before:
$ perf stat -a -M TopDownL1 sleep 1
Performance counter stats for 'system wide':
920,211,343 uops_issued.any # 0.5 Backend_Bound (16.56%)
1,977,733,128 idq_uops_not_delivered.core (16.56%)
51,668,510 int_misc.recovery_cycles (16.56%)
732,305,692 uops_retired.retire_slots (16.56%)
1,497,621,849 cycles (16.56%)
721,098,274 uops_issued.any # 0.1 Bad_Speculation (16.79%)
1,332,681,791 cycles (16.79%)
552,475,482 uops_retired.retire_slots (16.79%)
47,708,340 int_misc.recovery_cycles (16.79%)
1,383,713,292 cycles
# 0.4 Frontend_Bound (16.76%)
2,013,757,701 idq_uops_not_delivered.core (16.76%)
1,373,363,790 cycles
# 0.1 Retiring (33.54%)
577,302,589 uops_retired.retire_slots (33.54%)
392,766,987 inst_retired.any # 0.3 IPC (50.24%)
1,351,873,350 cpu_clk_unhalted.thread (50.24%)
1,332,510,318 cycles
# 5330041272.0 SLOTS (49.90%)
1.006336145 seconds time elapsed
After:
$ perf stat -a -M TopDownL1 sleep 1
Performance counter stats for 'system wide':
765,949,145 uops_issued.any # 0.1 Bad_Speculation
# 0.5 Backend_Bound (50.09%)
1,883,830,591 idq_uops_not_delivered.core # 0.3 Frontend_Bound (50.09%)
48,237,080 int_misc.recovery_cycles (50.09%)
581,798,385 uops_retired.retire_slots # 0.1 Retiring (50.09%)
1,361,628,527 cycles
# 5446514108.0 SLOTS (50.09%)
391,415,714 inst_retired.any # 0.3 IPC (49.91%)
1,336,486,781 cpu_clk_unhalted.thread (49.91%)
1.005469298 seconds time elapsed
Note: Bad_Speculation + Backend_Bound + Frontend_Bound + Retiring = 100%
after, where as before it is 110%. After there are 2 groups, whereas
before there are 6. After the cycles event appears once, before it
appeared 5 times.
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrii Nakryiko <andriin@fb.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Kim Phillips <kim.phillips@amd.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Clarke <pc@us.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: bpf@vger.kernel.org
Cc: netdev@vger.kernel.org
Link: http://lore.kernel.org/lkml/20200520182011.32236-6-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
Conflicts:
tools/perf/util/metricgroup.c
---
tools/perf/util/metricgroup.c | 91 ++++++++++++++++++++++++-----------
1 file changed, 62 insertions(+), 29 deletions(-)
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index c9ff1be3a992..65f96cfa4183 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -99,36 +99,72 @@ struct egroup {
bool has_constraint;
};
+/**
+ * Find a group of events in perf_evlist that correpond to those from a parsed
+ * metric expression.
+ * @perf_evlist: a list of events something like: {metric1 leader, metric1
+ * sibling, metric1 sibling}:W,duration_time,{metric2 leader, metric2 sibling,
+ * metric2 sibling}:W,duration_time
+ * @pctx: the parse context for the metric expression.
+ * @has_constraint: is there a contraint on the group of events? In which case
+ * the events won't be grouped.
+ * @metric_events: out argument, null terminated array of evsel's associated
+ * with the metric.
+ * @evlist_used: in/out argument, bitmap tracking which evlist events are used.
+ * @return the first metric event or NULL on failure.
+ */
static struct perf_evsel *find_evsel_group(struct perf_evlist *perf_evlist,
struct expr_parse_ctx *pctx,
+ bool has_constraint,
struct perf_evsel **metric_events,
unsigned long *evlist_used)
{
- struct perf_evsel *ev;
- bool leader_found;
- const size_t idnum = hashmap__size(&pctx->ids);
- size_t i = 0;
- int j = 0;
+ struct perf_evsel *ev, *current_leader = NULL;
double *val_ptr;
+ int i = 0, matched_events = 0, events_to_match;
+ const int idnum = (int)hashmap__size(&pctx->ids);
+
+ /* duration_time is grouped separately. */
+ if (!has_constraint &&
+ hashmap__find(&pctx->ids, "duration_time", (void **)&val_ptr))
+ events_to_match = idnum - 1;
+ else
+ events_to_match = idnum;
evlist__for_each_entry (perf_evlist, ev) {
- if (test_bit(j++, evlist_used))
+ /*
+ * Events with a constraint aren't grouped and match the first
+ * events available.
+ */
+ if (has_constraint && ev->weak_group)
continue;
- if (hashmap__find(&pctx->ids, ev->name, (void **)&val_ptr)) {
- if (!metric_events[i])
- metric_events[i] = ev;
- i++;
- if (i == idnum)
- break;
- } else {
- /* Discard the whole match and start again */
- i = 0;
+ if (!has_constraint && ev->leader != current_leader) {
+ /*
+ * Start of a new group, discard the whole match and
+ * start again.
+ */
+ matched_events = 0;
memset(metric_events, 0,
sizeof(struct perf_evsel *) * idnum);
+ current_leader = ev->leader;
}
+ if (hashmap__find(&pctx->ids, ev->name, (void **)&val_ptr))
+ metric_events[matched_events++] = ev;
+ if (matched_events == events_to_match)
+ break;
}
- if (i != idnum) {
+ if (events_to_match != idnum) {
+ /* Add the first duration_time. */
+ evlist__for_each_entry(perf_evlist, ev) {
+ if (!strcmp(ev->name, "duration_time")) {
+ metric_events[matched_events++] = ev;
+ break;
+ }
+ }
+ }
+
+ if (matched_events != idnum) {
/* Not whole match */
return NULL;
}
@@ -136,18 +172,8 @@ static struct perf_evsel *find_evsel_group(struct perf_evlist *perf_evlist,
metric_events[idnum] = NULL;
for (i = 0; i < idnum; i++) {
- leader_found = false;
- evlist__for_each_entry(perf_evlist, ev) {
- if (!leader_found && (ev == metric_events[i]))
- leader_found = true;
-
- if (leader_found &&
- !strcmp(ev->name, metric_events[i]->name)) {
- ev->metric_leader = metric_events[i];
- }
- j++;
- }
ev = metric_events[i];
+ ev->metric_leader = ev;
set_bit(ev->idx, evlist_used);
}
@@ -163,7 +189,7 @@ static int metricgroup__setup_events(struct list_head *groups,
int i = 0;
int ret = 0;
struct egroup *eg;
- struct perf_evsel *evsel;
+ struct perf_evsel *evsel, *tmp;
unsigned long *evlist_used;
evlist_used = bitmap_alloc(perf_evlist->nr_entries);
@@ -179,7 +205,8 @@ static int metricgroup__setup_events(struct list_head *groups,
ret = -ENOMEM;
break;
}
- evsel = find_evsel_group(perf_evlist, &eg->pctx, metric_events,
+ evsel = find_evsel_group(perf_evlist, &eg->pctx,
+ eg->has_constraint, metric_events,
evlist_used);
if (!evsel) {
pr_debug("Cannot resolve %s: %s\n",
@@ -209,6 +236,12 @@ static int metricgroup__setup_events(struct list_head *groups,
list_add(&expr->nd, &me->head);
}
+ evlist__for_each_entry_safe(perf_evlist, tmp, evsel) {
+ if (!test_bit(evsel->idx, evlist_used)) {
+ perf_evlist__remove(perf_evlist, evsel);
+ perf_evsel__delete(evsel);
+ }
+ }
bitmap_free(evlist_used);
return ret;
--
2.27.0
Reference in New Issue View Git Blame Copy Permalink