mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-27 14:28:55 +07:00
1b46cddfcc
Threads can have many and kernel modules will be represented as a tree of maps as well. Ah, and for a perf.data with 146607 samples: Before: [root@doppio ~]# perf stat -r 5 perf report > /dev/null Performance counter stats for 'perf report' (5 runs): 699.823680 task-clock-msecs # 0.991 CPUs ( +- 0.454% ) 74 context-switches # 0.000 M/sec ( +- 1.709% ) 2 CPU-migrations # 0.000 M/sec ( +- 17.008% ) 23114 page-faults # 0.033 M/sec ( +- 0.000% ) 1381257019 cycles # 1973.721 M/sec ( +- 0.290% ) 1456894438 instructions # 1.055 IPC ( +- 0.007% ) 18779818 cache-references # 26.835 M/sec ( +- 0.380% ) 641799 cache-misses # 0.917 M/sec ( +- 1.200% ) 0.705972729 seconds time elapsed ( +- 0.501% ) [root@doppio ~]# After Performance counter stats for 'perf report' (5 runs): 691.261451 task-clock-msecs # 0.993 CPUs ( +- 0.307% ) 72 context-switches # 0.000 M/sec ( +- 0.829% ) 6 CPU-migrations # 0.000 M/sec ( +- 18.409% ) 23127 page-faults # 0.033 M/sec ( +- 0.000% ) 1366395876 cycles # 1976.670 M/sec ( +- 0.153% ) 1443136016 instructions # 1.056 IPC ( +- 0.012% ) 17956402 cache-references # 25.976 M/sec ( +- 0.325% ) 661924 cache-misses # 0.958 M/sec ( +- 1.335% ) 0.696127275 seconds time elapsed ( +- 0.377% ) I.e. we see some speedup too. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> Cc: "H. Peter Anvin" <hpa@zytor.com> LKML-Reference: <20090928174846.GA3361@ghostprotocols.net> Signed-off-by: Ingo Molnar <mingo@elte.hu>
106 lines
1.8 KiB
C
106 lines
1.8 KiB
C
#ifndef __PERF_RECORD_H
|
|
#define __PERF_RECORD_H
|
|
|
|
#include "../perf.h"
|
|
#include "util.h"
|
|
#include <linux/rbtree.h>
|
|
|
|
enum {
|
|
SHOW_KERNEL = 1,
|
|
SHOW_USER = 2,
|
|
SHOW_HV = 4,
|
|
};
|
|
|
|
/*
|
|
* PERF_SAMPLE_IP | PERF_SAMPLE_TID | *
|
|
*/
|
|
struct ip_event {
|
|
struct perf_event_header header;
|
|
u64 ip;
|
|
u32 pid, tid;
|
|
unsigned char __more_data[];
|
|
};
|
|
|
|
struct mmap_event {
|
|
struct perf_event_header header;
|
|
u32 pid, tid;
|
|
u64 start;
|
|
u64 len;
|
|
u64 pgoff;
|
|
char filename[PATH_MAX];
|
|
};
|
|
|
|
struct comm_event {
|
|
struct perf_event_header header;
|
|
u32 pid, tid;
|
|
char comm[16];
|
|
};
|
|
|
|
struct fork_event {
|
|
struct perf_event_header header;
|
|
u32 pid, ppid;
|
|
u32 tid, ptid;
|
|
u64 time;
|
|
};
|
|
|
|
struct lost_event {
|
|
struct perf_event_header header;
|
|
u64 id;
|
|
u64 lost;
|
|
};
|
|
|
|
/*
|
|
* PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID
|
|
*/
|
|
struct read_event {
|
|
struct perf_event_header header;
|
|
u32 pid, tid;
|
|
u64 value;
|
|
u64 time_enabled;
|
|
u64 time_running;
|
|
u64 id;
|
|
};
|
|
|
|
struct sample_event{
|
|
struct perf_event_header header;
|
|
u64 array[];
|
|
};
|
|
|
|
|
|
typedef union event_union {
|
|
struct perf_event_header header;
|
|
struct ip_event ip;
|
|
struct mmap_event mmap;
|
|
struct comm_event comm;
|
|
struct fork_event fork;
|
|
struct lost_event lost;
|
|
struct read_event read;
|
|
struct sample_event sample;
|
|
} event_t;
|
|
|
|
struct map {
|
|
struct rb_node rb_node;
|
|
u64 start;
|
|
u64 end;
|
|
u64 pgoff;
|
|
u64 (*map_ip)(struct map *, u64);
|
|
struct dso *dso;
|
|
};
|
|
|
|
static inline u64 map__map_ip(struct map *map, u64 ip)
|
|
{
|
|
return ip - map->start + map->pgoff;
|
|
}
|
|
|
|
static inline u64 vdso__map_ip(struct map *map __used, u64 ip)
|
|
{
|
|
return ip;
|
|
}
|
|
|
|
struct map *map__new(struct mmap_event *event, char *cwd, int cwdlen);
|
|
struct map *map__clone(struct map *self);
|
|
int map__overlap(struct map *l, struct map *r);
|
|
size_t map__fprintf(struct map *self, FILE *fp);
|
|
|
|
#endif /* __PERF_RECORD_H */
|