perf stat: Fix --no-scale

tip:perf/urgent tip-bot for Andi Kleen 1 participant 1 message Mar 22, 2019 perf events

Share & tools

tip-bot for Andi Kleen

author merge bot

2019-03-22 22:24 UTC #0 lore raw

Commit-ID:  75998bb263bf48c1c85d78cd2d2f3a97d3747cab
Gitweb:     https://git.kernel.org/tip/75998bb263bf48c1c85d78cd2d2f3a97d3747cab
Author:     Andi Kleen <[email protected]>
AuthorDate: Thu, 14 Mar 2019 15:50:01 -0700
Committer:  Arnaldo Carvalho de Melo <[email protected]>
CommitDate: Tue, 19 Mar 2019 16:52:03 -0300

perf stat: Fix --no-scale

The -c option to enable multiplex scaling has been useless for quite some time because scaling is default.

It's only useful as --no-scale to disable scaling. But the non scaling code path has bitrotted and doesn't print anything because perf output code relies on value run/ena information.

Also even when we don't want to scale a value it's still useful to show its multiplex percentage.

This patch:
- Fixes help and documentation to show --no-scale instead of -c
- Removes -c, only keeps the long option because -c doesn't support negatives.
- Enables running/enabled even with --no-scale
- And fixes some other problems in the no-scale output.

Before:

  $ perf stat --no-scale -e cycles true

Performance counter stats for 'true':

<not counted> cycles

0.000984154 seconds time elapsed

After:

  $ ./perf stat --no-scale -e cycles true

Performance counter stats for 'true':

             706,070      cycles

         0.001219821 seconds time elapsed

Signed-off-by Andi Kleen <[email protected]>

Acked-by Jiri Olsa <[email protected]>

Tested-by Arnaldo Carvalho de Melo <[email protected]>

LPU-Reference: [email protected]

Link https://lkml.kernel.org/n/[email protected] open here

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

---
 tools/perf/Documentation/perf-stat.txt |  5 ++---
 tools/perf/builtin-stat.c              |  3 ++-
 tools/perf/util/evsel.c                |  3 +--
 tools/perf/util/stat.c                 | 12 ++++--------
 4 files changed, 9 insertions(+), 14 deletions(-)

tools/perf/Documentation/perf-stat.txt +2 -3

index 4bc2085e5197..39c05f89104e 100644
@@ -72,9 +72,8 @@ report::
 --all-cpus::
         system-wide collection from all CPUs (default if no target is specified)
 
--c::
---scale::
-	scale/normalize counter values
+--no-scale::
+	Don't scale/normalize counter values
 
 -d::
 --detailed::

tools/perf/builtin-stat.c +2 -1

index 7b8f09b0b8bf..49ee3c2033ec 100644
@@ -718,7 +718,8 @@ static struct option stat_options[] = {
 		    "system-wide collection from all CPUs"),
 	OPT_BOOLEAN('g', "group", &group,
 		    "put the counters into a counter group"),
-	OPT_BOOLEAN('c', "scale", &stat_config.scale, "scale/normalize counters"),
+	OPT_BOOLEAN(0, "scale", &stat_config.scale,
+		    "Use --no-scale to disable counter scaling for multiplexing"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show counter open errors, etc)"),
 	OPT_INTEGER('r', "repeat", &stat_config.run_count,

tools/perf/util/evsel.c +1 -2

index 3bbf73e979c0..53ec40cacd4b 100644
@@ -1344,8 +1344,7 @@ void perf_counts_values__scale(struct perf_counts_values *count,
 			scaled = 1;
 			count->val = (u64)((double) count->val * count->ena / count->run + 0.5);
 		}
-	} else
-		count->ena = count->run = 0;
+	}
 
 	if (pscaled)
 		*pscaled = scaled;

tools/perf/util/stat.c +4 -8

index 4d40515307b8..2856cc9d5a31 100644
@@ -291,10 +291,8 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel
 		break;
 	case AGGR_GLOBAL:
 		aggr->val += count->val;
-		if (config->scale) {
-			aggr->ena += count->ena;
-			aggr->run += count->run;
-		}
+		aggr->ena += count->ena;
+		aggr->run += count->run;
 	case AGGR_UNSET:
 	default:
 		break;

@@ -442,10 +440,8 @@ int create_perf_stat_counter(struct perf_evsel *evsel,
 	struct perf_event_attr *attr = &evsel->attr;
 	struct perf_evsel *leader = evsel->leader;
 
-	if (config->scale) {
-		attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
-				    PERF_FORMAT_TOTAL_TIME_RUNNING;
-	}
+	attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
+			    PERF_FORMAT_TOTAL_TIME_RUNNING;
 
 	/*
 	 * The event is part of non trivial group, let's enable