12c08a9f59
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>
49 lines
1.1 KiB
C
49 lines
1.1 KiB
C
#ifndef __PERF_CPUMAP_H
|
|
#define __PERF_CPUMAP_H
|
|
|
|
#include <stdio.h>
|
|
#include <stdbool.h>
|
|
|
|
struct cpu_map {
|
|
int nr;
|
|
int map[];
|
|
};
|
|
|
|
struct cpu_map *cpu_map__new(const char *cpu_list);
|
|
struct cpu_map *cpu_map__dummy_new(void);
|
|
void cpu_map__delete(struct cpu_map *map);
|
|
struct cpu_map *cpu_map__read(FILE *file);
|
|
size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
|
|
int cpu_map__get_socket(struct cpu_map *map, int idx);
|
|
int cpu_map__get_core(struct cpu_map *map, int idx);
|
|
int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp);
|
|
int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep);
|
|
|
|
static inline int cpu_map__socket(struct cpu_map *sock, int s)
|
|
{
|
|
if (!sock || s > sock->nr || s < 0)
|
|
return 0;
|
|
return sock->map[s];
|
|
}
|
|
|
|
static inline int cpu_map__id_to_socket(int id)
|
|
{
|
|
return id >> 16;
|
|
}
|
|
|
|
static inline int cpu_map__id_to_cpu(int id)
|
|
{
|
|
return id & 0xffff;
|
|
}
|
|
|
|
static inline int cpu_map__nr(const struct cpu_map *map)
|
|
{
|
|
return map ? map->nr : 1;
|
|
}
|
|
|
|
static inline bool cpu_map__all(const struct cpu_map *map)
|
|
{
|
|
return map ? map->map[0] == -1 : true;
|
|
}
|
|
|
|
#endif /* __PERF_CPUMAP_H */
|