summaryrefslogtreecommitdiff
path: root/tools/perf/util/cpumap.c
diff options
context:
space:
mode:
authorStephane Eranian <eranian@gmail.com>2013-02-14 16:57:29 +0400
committerArnaldo Carvalho de Melo <acme@redhat.com>2013-03-25 23:13:26 +0400
commit12c08a9f591aeda57fb3b05897169e7da5439a79 (patch)
tree4301499861ad5167139beaf6596b721badebe119 /tools/perf/util/cpumap.c
parentd4304958a25414a6e67b8a41c0f230e05cafafb6 (diff)
downloadlinux-12c08a9f591aeda57fb3b05897169e7da5439a79.tar.xz
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.c46
1 files changed, 46 insertions, 0 deletions
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 7bb8e87a5847..beb8cf9f9976 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);
+}