kernel-fxtec-pro1x/tools/perf/util/evlist.h

126 lines
3.9 KiB
C
Raw Normal View History

#ifndef __PERF_EVLIST_H
#define __PERF_EVLIST_H 1
#include <linux/list.h>
#include <stdio.h>
#include "../perf.h"
#include "event.h"
#include "util.h"
#include <unistd.h>
struct pollfd;
struct thread_map;
struct cpu_map;
struct perf_record_opts;
#define PERF_EVLIST__HLIST_BITS 8
#define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS)
struct perf_evlist {
struct list_head entries;
struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
int nr_entries;
int nr_fds;
perf evlist: Fix per thread mmap setup The PERF_EVENT_IOC_SET_OUTPUT ioctl was returning -EINVAL when using --pid when monitoring multithreaded apps, as we can only share a ring buffer for events on the same thread if not doing per cpu. Fix it by using per thread ring buffers. Tested with: [root@felicio ~]# tuna -t 26131 -CP | nl 1 thread ctxt_switches 2 pid SCHED_ rtpri affinity voluntary nonvoluntary cmd 3 26131 OTHER 0 0,1 10814276 2397830 chromium-browse 4 642 OTHER 0 0,1 14688 0 chromium-browse 5 26148 OTHER 0 0,1 713602 115479 chromium-browse 6 26149 OTHER 0 0,1 801958 2262 chromium-browse 7 26150 OTHER 0 0,1 1271128 248 chromium-browse 8 26151 OTHER 0 0,1 3 0 chromium-browse 9 27049 OTHER 0 0,1 36796 9 chromium-browse 10 618 OTHER 0 0,1 14711 0 chromium-browse 11 661 OTHER 0 0,1 14593 0 chromium-browse 12 29048 OTHER 0 0,1 28125 0 chromium-browse 13 26143 OTHER 0 0,1 2202789 781 chromium-browse [root@felicio ~]# So 11 threads under pid 26131, then: [root@felicio ~]# perf record -F 50000 --pid 26131 [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7fa4a2538000-7fa4a25b9000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 2 7fa4a25b9000-7fa4a263a000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 3 7fa4a263a000-7fa4a26bb000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 4 7fa4a26bb000-7fa4a273c000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 5 7fa4a273c000-7fa4a27bd000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 6 7fa4a27bd000-7fa4a283e000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 7 7fa4a283e000-7fa4a28bf000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 8 7fa4a28bf000-7fa4a2940000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 9 7fa4a2940000-7fa4a29c1000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 10 7fa4a29c1000-7fa4a2a42000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 11 7fa4a2a42000-7fa4a2ac3000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# 11 mmaps, one per thread since we didn't specify any CPU list, so we need one mmap per thread and: [root@felicio ~]# perf record -F 50000 --pid 26131 ^M ^C[ perf record: Woken up 79 times to write data ] [ perf record: Captured and wrote 20.614 MB perf.data (~900639 samples) ] [root@felicio ~]# perf report -D | grep PERF_RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort -n | uniq -c | sort -nr | nl 1 371310 26131 2 96516 26148 3 95694 26149 4 95203 26150 5 7291 26143 6 87 27049 7 76 661 8 60 29048 9 47 618 10 43 642 [root@felicio ~]# Ok, one of the threads, 26151 was quiescent, so no samples there, but all the others are there. Then, if I specify one CPU: [root@felicio ~]# perf record -F 50000 --pid 26131 --cpu 1 ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.680 MB perf.data (~29730 samples) ] [root@felicio ~]# perf report -D | grep PERF_RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort -n | uniq -c | sort -nr | nl 1 8444 26131 2 2584 26149 3 2518 26148 4 2324 26150 5 123 26143 6 9 661 7 9 29048 [root@felicio ~]# This machine has two cores, so fewer threads appeared on the radar, and: [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7f484b922000-7f484b9a3000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# Just one mmap, as now we can use just one per-cpu buffer instead of the per-thread needed in the previous case. For global profiling: [root@felicio ~]# perf record -F 50000 -a ^C[ perf record: Woken up 26 times to write data ] [ perf record: Captured and wrote 7.128 MB perf.data (~311412 samples) ] [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7fb49b435000-7fb49b4b6000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 2 7fb49b4b6000-7fb49b537000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# It uses per-cpu buffers. For just one thread: [root@felicio ~]# perf record -F 50000 --tid 26148 ^C[ perf record: Woken up 2 times to write data ] [ perf record: Captured and wrote 0.330 MB perf.data (~14426 samples) ] [root@felicio ~]# perf report -D | grep PERF_RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort -n | uniq -c | sort -nr | nl 1 9969 26148 [root@felicio ~]# [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7f286a51b000-7f286a59c000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# Tested-by: David Ahern <dsahern@gmail.com> Tested-by: Lin Ming <ming.m.lin@intel.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> Link: http://lkml.kernel.org/r/20110426204401.GB1746@ghostprotocols.net Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-05-15 06:39:00 -06:00
int nr_mmaps;
int mmap_len;
struct {
int cork_fd;
pid_t pid;
} workload;
bool overwrite;
union perf_event event_copy;
struct perf_mmap *mmap;
struct pollfd *pollfd;
struct thread_map *threads;
struct cpu_map *cpus;
struct perf_evsel *selected;
};
perf tools: Save some loops using perf_evlist__id2evsel Since we already ask for PERF_SAMPLE_ID and use it to quickly find the associated evsel, add handler func + data to struct perf_evsel to avoid using chains of if(strcmp(event_name)) and also to avoid all the linear list searches via trace_event_find. To demonstrate the technique convert 'perf sched' to it: # perf sched record sleep 5m And then: Performance counter stats for '/tmp/oldperf sched lat': 646.929438 task-clock # 0.999 CPUs utilized 9 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 20,901 page-faults # 0.032 M/sec 1,290,144,450 cycles # 1.994 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 1,606,158,439 instructions # 1.24 insns per cycle 339,088,395 branches # 524.151 M/sec 4,550,735 branch-misses # 1.34% of all branches 0.647524759 seconds time elapsed Versus: Performance counter stats for 'perf sched lat': 473.564691 task-clock # 0.999 CPUs utilized 9 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 20,903 page-faults # 0.044 M/sec 944,367,984 cycles # 1.994 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 1,442,385,571 instructions # 1.53 insns per cycle 308,383,106 branches # 651.195 M/sec 4,481,784 branch-misses # 1.45% of all branches 0.474215751 seconds time elapsed [root@emilia ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-1kbzpl74lwi6lavpqke2u2p3@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-11-28 12:57:40 -07:00
struct perf_evsel_str_handler {
const char *name;
void *handler;
};
struct perf_evsel;
struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
struct thread_map *threads);
void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
struct thread_map *threads);
void perf_evlist__exit(struct perf_evlist *evlist);
void perf_evlist__delete(struct perf_evlist *evlist);
void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry);
int perf_evlist__add_default(struct perf_evlist *evlist);
int perf_evlist__add_attrs(struct perf_evlist *evlist,
struct perf_event_attr *attrs, size_t nr_attrs);
int perf_evlist__add_tracepoints(struct perf_evlist *evlist,
const char *tracepoints[], size_t nr_tracepoints);
perf tools: Save some loops using perf_evlist__id2evsel Since we already ask for PERF_SAMPLE_ID and use it to quickly find the associated evsel, add handler func + data to struct perf_evsel to avoid using chains of if(strcmp(event_name)) and also to avoid all the linear list searches via trace_event_find. To demonstrate the technique convert 'perf sched' to it: # perf sched record sleep 5m And then: Performance counter stats for '/tmp/oldperf sched lat': 646.929438 task-clock # 0.999 CPUs utilized 9 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 20,901 page-faults # 0.032 M/sec 1,290,144,450 cycles # 1.994 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 1,606,158,439 instructions # 1.24 insns per cycle 339,088,395 branches # 524.151 M/sec 4,550,735 branch-misses # 1.34% of all branches 0.647524759 seconds time elapsed Versus: Performance counter stats for 'perf sched lat': 473.564691 task-clock # 0.999 CPUs utilized 9 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 20,903 page-faults # 0.044 M/sec 944,367,984 cycles # 1.994 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 1,442,385,571 instructions # 1.53 insns per cycle 308,383,106 branches # 651.195 M/sec 4,481,784 branch-misses # 1.45% of all branches 0.474215751 seconds time elapsed [root@emilia ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-1kbzpl74lwi6lavpqke2u2p3@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-11-28 12:57:40 -07:00
int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist,
const struct perf_evsel_str_handler *assocs,
size_t nr_assocs);
#define perf_evlist__add_attrs_array(evlist, array) \
perf_evlist__add_attrs(evlist, array, ARRAY_SIZE(array))
#define perf_evlist__add_tracepoints_array(evlist, array) \
perf_evlist__add_tracepoints(evlist, array, ARRAY_SIZE(array))
perf tools: Save some loops using perf_evlist__id2evsel Since we already ask for PERF_SAMPLE_ID and use it to quickly find the associated evsel, add handler func + data to struct perf_evsel to avoid using chains of if(strcmp(event_name)) and also to avoid all the linear list searches via trace_event_find. To demonstrate the technique convert 'perf sched' to it: # perf sched record sleep 5m And then: Performance counter stats for '/tmp/oldperf sched lat': 646.929438 task-clock # 0.999 CPUs utilized 9 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 20,901 page-faults # 0.032 M/sec 1,290,144,450 cycles # 1.994 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 1,606,158,439 instructions # 1.24 insns per cycle 339,088,395 branches # 524.151 M/sec 4,550,735 branch-misses # 1.34% of all branches 0.647524759 seconds time elapsed Versus: Performance counter stats for 'perf sched lat': 473.564691 task-clock # 0.999 CPUs utilized 9 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 20,903 page-faults # 0.044 M/sec 944,367,984 cycles # 1.994 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 1,442,385,571 instructions # 1.53 insns per cycle 308,383,106 branches # 651.195 M/sec 4,481,784 branch-misses # 1.45% of all branches 0.474215751 seconds time elapsed [root@emilia ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-1kbzpl74lwi6lavpqke2u2p3@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-11-28 12:57:40 -07:00
#define perf_evlist__set_tracepoints_handlers_array(evlist, array) \
perf_evlist__set_tracepoints_handlers(evlist, array, ARRAY_SIZE(array))
void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
int cpu, int thread, u64 id);
void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
perf evlist: Fix per thread mmap setup The PERF_EVENT_IOC_SET_OUTPUT ioctl was returning -EINVAL when using --pid when monitoring multithreaded apps, as we can only share a ring buffer for events on the same thread if not doing per cpu. Fix it by using per thread ring buffers. Tested with: [root@felicio ~]# tuna -t 26131 -CP | nl 1 thread ctxt_switches 2 pid SCHED_ rtpri affinity voluntary nonvoluntary cmd 3 26131 OTHER 0 0,1 10814276 2397830 chromium-browse 4 642 OTHER 0 0,1 14688 0 chromium-browse 5 26148 OTHER 0 0,1 713602 115479 chromium-browse 6 26149 OTHER 0 0,1 801958 2262 chromium-browse 7 26150 OTHER 0 0,1 1271128 248 chromium-browse 8 26151 OTHER 0 0,1 3 0 chromium-browse 9 27049 OTHER 0 0,1 36796 9 chromium-browse 10 618 OTHER 0 0,1 14711 0 chromium-browse 11 661 OTHER 0 0,1 14593 0 chromium-browse 12 29048 OTHER 0 0,1 28125 0 chromium-browse 13 26143 OTHER 0 0,1 2202789 781 chromium-browse [root@felicio ~]# So 11 threads under pid 26131, then: [root@felicio ~]# perf record -F 50000 --pid 26131 [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7fa4a2538000-7fa4a25b9000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 2 7fa4a25b9000-7fa4a263a000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 3 7fa4a263a000-7fa4a26bb000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 4 7fa4a26bb000-7fa4a273c000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 5 7fa4a273c000-7fa4a27bd000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 6 7fa4a27bd000-7fa4a283e000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 7 7fa4a283e000-7fa4a28bf000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 8 7fa4a28bf000-7fa4a2940000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 9 7fa4a2940000-7fa4a29c1000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 10 7fa4a29c1000-7fa4a2a42000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 11 7fa4a2a42000-7fa4a2ac3000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# 11 mmaps, one per thread since we didn't specify any CPU list, so we need one mmap per thread and: [root@felicio ~]# perf record -F 50000 --pid 26131 ^M ^C[ perf record: Woken up 79 times to write data ] [ perf record: Captured and wrote 20.614 MB perf.data (~900639 samples) ] [root@felicio ~]# perf report -D | grep PERF_RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort -n | uniq -c | sort -nr | nl 1 371310 26131 2 96516 26148 3 95694 26149 4 95203 26150 5 7291 26143 6 87 27049 7 76 661 8 60 29048 9 47 618 10 43 642 [root@felicio ~]# Ok, one of the threads, 26151 was quiescent, so no samples there, but all the others are there. Then, if I specify one CPU: [root@felicio ~]# perf record -F 50000 --pid 26131 --cpu 1 ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.680 MB perf.data (~29730 samples) ] [root@felicio ~]# perf report -D | grep PERF_RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort -n | uniq -c | sort -nr | nl 1 8444 26131 2 2584 26149 3 2518 26148 4 2324 26150 5 123 26143 6 9 661 7 9 29048 [root@felicio ~]# This machine has two cores, so fewer threads appeared on the radar, and: [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7f484b922000-7f484b9a3000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# Just one mmap, as now we can use just one per-cpu buffer instead of the per-thread needed in the previous case. For global profiling: [root@felicio ~]# perf record -F 50000 -a ^C[ perf record: Woken up 26 times to write data ] [ perf record: Captured and wrote 7.128 MB perf.data (~311412 samples) ] [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7fb49b435000-7fb49b4b6000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 2 7fb49b4b6000-7fb49b537000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# It uses per-cpu buffers. For just one thread: [root@felicio ~]# perf record -F 50000 --tid 26148 ^C[ perf record: Woken up 2 times to write data ] [ perf record: Captured and wrote 0.330 MB perf.data (~14426 samples) ] [root@felicio ~]# perf report -D | grep PERF_RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort -n | uniq -c | sort -nr | nl 1 9969 26148 [root@felicio ~]# [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7f286a51b000-7f286a59c000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# Tested-by: David Ahern <dsahern@gmail.com> Tested-by: Lin Ming <ming.m.lin@intel.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> Link: http://lkml.kernel.org/r/20110426204401.GB1746@ghostprotocols.net Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-05-15 06:39:00 -06:00
union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
int perf_evlist__open(struct perf_evlist *evlist, bool group);
void perf_evlist__config_attrs(struct perf_evlist *evlist,
struct perf_record_opts *opts);
int perf_evlist__prepare_workload(struct perf_evlist *evlist,
struct perf_record_opts *opts,
const char *argv[]);
int perf_evlist__start_workload(struct perf_evlist *evlist);
int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
bool overwrite);
void perf_evlist__munmap(struct perf_evlist *evlist);
void perf_evlist__disable(struct perf_evlist *evlist);
void perf_evlist__enable(struct perf_evlist *evlist);
void perf_evlist__set_selected(struct perf_evlist *evlist,
struct perf_evsel *evsel);
static inline void perf_evlist__set_maps(struct perf_evlist *evlist,
struct cpu_map *cpus,
struct thread_map *threads)
{
evlist->cpus = cpus;
evlist->threads = threads;
}
int perf_evlist__create_maps(struct perf_evlist *evlist, const char *target_pid,
const char *tid, uid_t uid, const char *cpu_list);
void perf_evlist__delete_maps(struct perf_evlist *evlist);
int perf_evlist__set_filters(struct perf_evlist *evlist);
u64 perf_evlist__sample_type(const struct perf_evlist *evlist);
bool perf_evlist__sample_id_all(const const struct perf_evlist *evlist);
u16 perf_evlist__id_hdr_size(const struct perf_evlist *evlist);
bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist);
bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist);
void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
struct list_head *list,
int nr_entries);
#endif /* __PERF_EVLIST_H */