perf stat: Cache aggregated map entries in extra cpumap
Currently any time we need to access socket or core id for given cpu, we
access the sysfs topology file.
Adding a cpus_aggr_map cpu_map to cache those entries.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Kan Liang <kan.liang@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1445784728-21732-3-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 91e793a..2f438f7 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -100,6 +100,8 @@
.uid = UINT_MAX,
};
+typedef int (*aggr_get_id_t)(struct cpu_map *m, int cpu);
+
static int run_count = 1;
static bool no_inherit = false;
static volatile pid_t child_pid = -1;
@@ -119,7 +121,7 @@
static bool forever = false;
static struct timespec ref_time;
static struct cpu_map *aggr_map;
-static int (*aggr_get_id)(struct cpu_map *m, int cpu);
+static aggr_get_id_t aggr_get_id;
static volatile int done = 0;
@@ -954,22 +956,63 @@
return cpu_map__get_core(map, cpu, NULL);
}
+static int cpu_map__get_max(struct cpu_map *map)
+{
+ int i, max = -1;
+
+ for (i = 0; i < map->nr; i++) {
+ if (map->map[i] > max)
+ max = map->map[i];
+ }
+
+ return max;
+}
+
+static struct cpu_map *cpus_aggr_map;
+
+static int perf_stat__get_aggr(aggr_get_id_t get_id, struct cpu_map *map, int idx)
+{
+ int cpu;
+
+ if (idx >= map->nr)
+ return -1;
+
+ cpu = map->map[idx];
+
+ if (cpus_aggr_map->map[cpu] == -1)
+ cpus_aggr_map->map[cpu] = get_id(map, idx);
+
+ return cpus_aggr_map->map[cpu];
+}
+
+static int perf_stat__get_socket_cached(struct cpu_map *map, int idx)
+{
+ return perf_stat__get_aggr(perf_stat__get_socket, map, idx);
+}
+
+static int perf_stat__get_core_cached(struct cpu_map *map, int idx)
+{
+ return perf_stat__get_aggr(perf_stat__get_core, map, idx);
+}
+
static int perf_stat_init_aggr_mode(void)
{
+ int nr;
+
switch (stat_config.aggr_mode) {
case AGGR_SOCKET:
if (cpu_map__build_socket_map(evsel_list->cpus, &aggr_map)) {
perror("cannot build socket map");
return -1;
}
- aggr_get_id = perf_stat__get_socket;
+ aggr_get_id = perf_stat__get_socket_cached;
break;
case AGGR_CORE:
if (cpu_map__build_core_map(evsel_list->cpus, &aggr_map)) {
perror("cannot build core map");
return -1;
}
- aggr_get_id = perf_stat__get_core;
+ aggr_get_id = perf_stat__get_core_cached;
break;
case AGGR_NONE:
case AGGR_GLOBAL:
@@ -978,7 +1021,15 @@
default:
break;
}
- return 0;
+
+ /*
+ * The evsel_list->cpus is the base we operate on,
+ * taking the highest cpu number to be the size of
+ * the aggregation translate cpumap.
+ */
+ nr = cpu_map__get_max(evsel_list->cpus);
+ cpus_aggr_map = cpu_map__empty_new(nr + 1);
+ return cpus_aggr_map ? 0 : -ENOMEM;
}
/*