linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Andi Kleen <andi@firstfloor.org>
To: acme@kernel.org
Cc: jolsa@kernel.org, kan.liang@intel.com,
	linux-kernel@vger.kernel.org, Andi Kleen <ak@linux.intel.com>
Subject: [PATCH v1 3/4] perf stat: Fix group lookup for metric group
Date: Mon, 24 Jun 2019 12:37:10 -0700	[thread overview]
Message-ID: <20190624193711.35241-4-andi@firstfloor.org> (raw)
In-Reply-To: <20190624193711.35241-1-andi@firstfloor.org>

From: Andi Kleen <ak@linux.intel.com>

The metric group code tries to find a group it added earlier
in the evlist. Fix the lookup to handle groups with partially
overlaps correctly. When a sub string match fails and we reset
the match, we have to compare the first element again.

I also renamed the find_evsel function to find_evsel_group
to make its purpose clearer.

With the earlier changes this fixes:

Before:

% perf stat -M UPI,IPC sleep 1
...
         1,032,922      uops_retired.retire_slots #      1.1 UPI
         1,896,096      inst_retired.any
         1,896,096      inst_retired.any
         1,177,254      cpu_clk_unhalted.thread

After:

% perf stat -M UPI,IPC sleep 1
...
        1,013,193      uops_retired.retire_slots #      1.1 UPI
           932,033      inst_retired.any
           932,033      inst_retired.any          #      0.9 IPC
         1,091,245      cpu_clk_unhalted.thread

Fixes: b18f3e365019 ("perf stat: Support JSON metrics ...")
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/util/metricgroup.c | 47 ++++++++++++++++++++++++++---------
 1 file changed, 35 insertions(+), 12 deletions(-)

diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 699e020737d9..fabdb6dde88e 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -85,26 +85,49 @@ struct egroup {
 	const char *metric_expr;
 };
 
-static struct perf_evsel *find_evsel(struct perf_evlist *perf_evlist,
-				     const char **ids,
-				     int idnum,
-				     struct perf_evsel **metric_events)
+static bool record_evsel(int *ind, struct perf_evsel **start,
+			 int idnum,
+			 struct perf_evsel **metric_events,
+			 struct perf_evsel *ev)
+{
+	metric_events[*ind] = ev;
+	if (*ind == 0)
+		*start = ev;
+	if (++*ind == idnum) {
+		metric_events[*ind] = NULL;
+		return true;
+	}
+	return false;
+}
+
+static struct perf_evsel *find_evsel_group(struct perf_evlist *perf_evlist,
+					   const char **ids,
+					   int idnum,
+					   struct perf_evsel **metric_events)
 {
 	struct perf_evsel *ev, *start = NULL;
 	int ind = 0;
 
 	evlist__for_each_entry (perf_evlist, ev) {
+		if (ev->collect_stat)
+			continue;
 		if (!strcmp(ev->name, ids[ind])) {
-			metric_events[ind] = ev;
-			if (ind == 0)
-				start = ev;
-			if (++ind == idnum) {
-				metric_events[ind] = NULL;
+			if (record_evsel(&ind, &start, idnum,
+					 metric_events, ev))
 				return start;
-			}
 		} else {
+			/*
+			 * We saw some other event that is not
+			 * in our list of events. Discard
+			 * the whole match and start again.
+			 */
 			ind = 0;
 			start = NULL;
+			if (!strcmp(ev->name, ids[ind])) {
+				if (record_evsel(&ind, &start, idnum,
+						 metric_events, ev))
+					return start;
+			}
 		}
 	}
 	/*
@@ -134,8 +157,8 @@ static int metricgroup__setup_events(struct list_head *groups,
 			ret = -ENOMEM;
 			break;
 		}
-		evsel = find_evsel(perf_evlist, eg->ids, eg->idnum,
-				   metric_events);
+		evsel = find_evsel_group(perf_evlist, eg->ids, eg->idnum,
+					 metric_events);
 		if (!evsel) {
 			pr_debug("Cannot resolve %s: %s\n",
 					eg->metric_name, eg->metric_expr);
-- 
2.20.1


  parent reply	other threads:[~2019-06-24 19:37 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-24 19:37 Some bug fixes for perf stat metrics Andi Kleen
2019-06-24 19:37 ` [PATCH v1 1/4] perf stat: Make metric event lookup more robust Andi Kleen
2019-07-03 14:27   ` [tip:perf/core] " tip-bot for Andi Kleen
2019-06-24 19:37 ` [PATCH v1 2/4] perf stat: Don't merge events in the same PMU Andi Kleen
2019-07-03 14:28   ` [tip:perf/core] " tip-bot for Andi Kleen
2019-06-24 19:37 ` Andi Kleen [this message]
2019-07-03 14:29   ` [tip:perf/core] perf stat: Fix group lookup for metric group tip-bot for Andi Kleen
2019-06-24 19:37 ` [PATCH v1 4/4] perf stat: Fix metrics with --no-merge Andi Kleen
2019-07-03 14:29   ` [tip:perf/core] " tip-bot for Andi Kleen
2019-06-25  9:23 ` Some bug fixes for perf stat metrics Jiri Olsa
2019-06-26 18:43   ` Arnaldo Carvalho de Melo

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190624193711.35241-4-andi@firstfloor.org \
    --to=andi@firstfloor.org \
    --cc=acme@kernel.org \
    --cc=ak@linux.intel.com \
    --cc=jolsa@kernel.org \
    --cc=kan.liang@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).