diff options
| author | Stephane Eranian <eranian@gmail.com> | 2013-02-14 13:57:29 +0100 | 
|---|---|---|
| committer | Arnaldo Carvalho de Melo <acme@redhat.com> | 2013-03-25 16:13:26 -0300 | 
| commit | 12c08a9f591aeda57fb3b05897169e7da5439a79 (patch) | |
| tree | 4301499861ad5167139beaf6596b721badebe119 /tools/perf/util/cpumap.c | |
| parent | d4304958a25414a6e67b8a41c0f230e05cafafb6 (diff) | |
| download | olio-linux-3.10-12c08a9f591aeda57fb3b05897169e7da5439a79.tar.xz olio-linux-3.10-12c08a9f591aeda57fb3b05897169e7da5439a79.zip | |
perf stat: Add per-core aggregation
This patch adds the --per-core option to perf stat.
This option is used to aggregate system-wide counts
on a per physical core basis. On processors with
hyperthreading, this means counts of all HT threads
running on a physical core are aggregated.
This mode is useful to find imblance between physical
cores running an uniform workload. Cores are identified
by socket: S0-C1, means physical core 1 on socket 0. Note
that cores are identified using their physical core id,
thus their numbering may not be continuous.
Per core aggregation can be combined with interval printing:
 # perf stat -a --per-core -I 1000 -e cycles sleep 1000
 #           time core         cpus             counts events
      1.000090030 S0-C0           1          4,765,747 cycles
      1.000090030 S0-C1           1          5,580,647 cycles
      1.000090030 S0-C2           1            221,181 cycles
      1.000090030 S0-C3           1            266,092 cycles
Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1360846649-6411-4-git-send-email-eranian@google.com
[ committer note: Remove parts already applied on 86ee6e1 to keep bisectability ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools/perf/util/cpumap.c')
| -rw-r--r-- | tools/perf/util/cpumap.c | 46 | 
1 files changed, 46 insertions, 0 deletions
| diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 7bb8e87a584..beb8cf9f997 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -267,7 +267,53 @@ static int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,  	return 0;  } +int cpu_map__get_core(struct cpu_map *map, int idx) +{ +	FILE *fp; +	const char *mnt; +	char path[PATH_MAX]; +	int cpu, ret, s; + +	if (idx > map->nr) +		return -1; + +	cpu = map->map[idx]; + +	mnt = sysfs_find_mountpoint(); +	if (!mnt) +		return -1; + +	snprintf(path, PATH_MAX, +		"%s/devices/system/cpu/cpu%d/topology/core_id", +		mnt, cpu); + +	fp = fopen(path, "r"); +	if (!fp) +		return -1; +	ret = fscanf(fp, "%d", &cpu); +	fclose(fp); +	if (ret != 1) +		return -1; + +	s = cpu_map__get_socket(map, idx); +	if (s == -1) +		return -1; + +	/* +	 * encode socket in upper 16 bits +	 * core_id is relative to socket, and +	 * we need a global id. So we combine +	 * socket+ core id +	 */ +	return (s << 16) | (cpu & 0xffff); +} +  int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp)  {  	return cpu_map__build_map(cpus, sockp, cpu_map__get_socket);  } + +int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep) +{ +	return cpu_map__build_map(cpus, corep, cpu_map__get_core); +} |