AuxXxilium/linux_dsm_epyc7002
1
0
Fork 0
mirror of https://github.com/AuxXxilium/linux_dsm_epyc7002.git synced 2024-12-05 09:46:43 +07:00
Code Issues Actions Packages Projects Releases Wiki Activity

perf record: Introduce --switch-output-event

Browse Source 
Now we can use it with --overwrite to have a flight recorder mode that
gets snapshot requests from arbitrary events that are processed in the
side band thread together with the PERF_RECORD_BPF_EVENT processing.

Example:

To collect scheduler events until a recvmmsg syscall happens, system
wide:

  [root@five a]# rm -f perf.data.2020042717*
  [root@five a]# perf record --overwrite -e sched:*switch,syscalls:*recvmmsg --switch-output-event syscalls:sys_enter_recvmmsg
  [ perf record: dump data: Woken up 1 times ]
  [ perf record: Dump perf.data.2020042717585458 ]
  [ perf record: dump data: Woken up 1 times ]
  [ perf record: Dump perf.data.2020042717590235 ]
  [ perf record: dump data: Woken up 1 times ]
  [ perf record: Dump perf.data.2020042717590398 ]
  ^C[ perf record: Woken up 1 times to write data ]
  [ perf record: Dump perf.data.2020042717590511 ]
  [ perf record: Captured and wrote 7.244 MB perf.data.<timestamp> ]

So in the above case we had 3 snapshots, the fourth was forced by
control+C:

  [root@five a]# ls -la
  total 20440
  drwxr-xr-x.  2 root root    4096 Apr 27 17:59 .
  dr-xr-x---. 12 root root    4096 Apr 27 17:46 ..
  -rw-------.  1 root root 3936125 Apr 27 17:58 perf.data.2020042717585458
  -rw-------.  1 root root 5074869 Apr 27 17:59 perf.data.2020042717590235
  -rw-------.  1 root root 4291037 Apr 27 17:59 perf.data.2020042717590398
  -rw-------.  1 root root 7617037 Apr 27 17:59 perf.data.2020042717590511
  [root@five a]#

One can make this more precise by adding the switch output event to the
main -e events list, as since this is done asynchronously, a few events
after the signal event will appear in the snapshots, as can be seen
with:

  [root@five a]# rm -f perf.data.20200427175*
  [root@five a]# perf record --overwrite -e sched:*switch,syscalls:*recvmmsg --switch-output-event syscalls:sys_enter_recvmmsg
  [ perf record: dump data: Woken up 1 times ]
  [ perf record: Dump perf.data.2020042718024203 ]
  [ perf record: dump data: Woken up 1 times ]
  [ perf record: Dump perf.data.2020042718024301 ]
  [ perf record: dump data: Woken up 1 times ]
  [ perf record: Dump perf.data.2020042718024484 ]
  ^C[ perf record: Woken up 1 times to write data ]
  [ perf record: Dump perf.data.2020042718024562 ]
  [ perf record: Captured and wrote 7.337 MB perf.data.<timestamp> ]
  [root@five a]# perf script -i perf.data.2020042718024203 | tail -15
       PacerThread 148586 [005] 122.830729: sched:sched_switch: prev_comm=PacerThread prev_pid=148586...
           swapper      0 [000] 122.833588: sched:sched_switch: prev_comm=swapper/0 prev_pid=...
    NetworkManager   1251 [000] 122.833619: syscalls:sys_enter_recvmmsg: fd: 0x0000001c, mmsg: 0x7ffe83054a1...
           swapper      0 [002] 122.833624: sched:sched_switch: prev_comm=swapper/2 prev_pid=...
           swapper      0 [003] 122.833624: sched:sched_switch: prev_comm=swapper/3 prev_pid=...
    NetworkManager   1251 [000] 122.833626: syscalls:sys_exit_recvmmsg: 0x1
   kworker/3:3-eve 158946 [003] 122.833628: sched:sched_switch: prev_comm=kworker/3:3 prev_pid=15894...
           swapper      0 [004] 122.833641: sched:sched_switch: prev_comm=swapper/4 prev_pid=...
    NetworkManager   1251 [000] 122.833642: sched:sched_switch: prev_comm=NetworkManage...
              perf 228273 [002] 122.833645: sched:sched_switch: prev_comm=perf prev_pid=22827...
           swapper      0 [011] 122.833646: sched:sched_switch: prev_comm=swapper/1...
           swapper      0 [002] 122.833648: sched:sched_switch: prev_comm=swapper/...
   kworker/0:2-eve 207387 [000] 122.833648: sched:sched_switch: prev_comm=kworker/0:2 prev_pid=20738...
   kworker/2:3-eve 232038 [002] 122.833652: sched:sched_switch: prev_comm=kworker/2:3 prev_pid=23203...
              perf 235825 [003] 122.833653: sched:sched_switch: prev_comm=perf prev_pid=23582...
  [root@five a]#

Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lore.kernel.org/lkml/20200429131106.27974-8-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
Arnaldo Carvalho de Melo 2020-04-27 17:56:37 -03:00
parent 636eb4d001
commit 899e5ffbf2
2 changed files with 50 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
tools/perf/Documentation/perf-record.txt
View File

@ -556,6 +556,19 @@ overhead. You can still switch them on with:
--switch-output --no-no-buildid --no-no-buildid-cache
--switch-output-event::
Events that will cause the switch of the perf.data file, auto-selecting
--switch-output=signal, the results are similar as internally the side band
thread will also send a SIGUSR2 to the main one.
Uses the same syntax as --event, it will just not be recorded, serving only to
switch the perf.data file as soon as the --switch-output event is processed by
a separate sideband thread.
This sideband thread is also used to other purposes, like processing the
PERF_RECORD_BPF_EVENT records as they happen, asking the kernel for extra BPF
information, etc.
--switch-max-files=N::
When rotating perf.data with --switch-output, only keep N files.

41
tools/perf/builtin-record.c
View File

@ -88,7 +88,9 @@ struct record {
struct evlist *evlist;
struct perf_session *session;
struct evlist *sb_evlist;
pthread_t thread_id;
int realtime_prio;
bool switch_output_event_set;
bool no_buildid;
bool no_buildid_set;
bool no_buildid_cache;
@ -1437,6 +1439,13 @@ static int record__synthesize(struct record *rec, bool tail)
return err;
}
static int record__process_signal_event(union perf_event *event __maybe_unused, void *data)
{
struct record *rec = data;
pthread_kill(rec->thread_id, SIGUSR2);
return 0;
}
static int __cmd_record(struct record *rec, int argc, const char **argv)
{
int err;
@ -1581,12 +1590,24 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
goto out_child;
}
if (!opts->no_bpf_event) {
rec->sb_evlist = evlist__new();
if (rec->sb_evlist != NULL) {
/*
* We get here if --switch-output-event populated the
* sb_evlist, so associate a callback that will send a SIGUSR2
* to the main thread.
*/
evlist__set_cb(rec->sb_evlist, record__process_signal_event, rec);
rec->thread_id = pthread_self();
}
if (!opts->no_bpf_event) {
if (rec->sb_evlist == NULL) {
pr_err("Couldn't create side band evlist.\n.");
goto out_child;
rec->sb_evlist = evlist__new();
if (rec->sb_evlist == NULL) {
pr_err("Couldn't create side band evlist.\n.");
goto out_child;
}
}
if (evlist__add_bpf_sb_event(rec->sb_evlist, &session->header.env)) {
@ -2180,10 +2201,19 @@ static int switch_output_setup(struct record *rec)
};
unsigned long val;
/*
* If we're using --switch-output-events, then we imply its
* --switch-output=signal, as we'll send a SIGUSR2 from the side band
* thread to its parent.
*/
if (rec->switch_output_event_set)
goto do_signal;
if (!s->set)
return 0;
if (!strcmp(s->str, "signal")) {
do_signal:
s->signal = true;
pr_debug("switch-output with SIGUSR2 signal\n");
goto enabled;
@ -2441,6 +2471,9 @@ static struct option __record_options[] = {
&record.switch_output.set, "signal or size[BKMG] or time[smhd]",
"Switch output when receiving SIGUSR2 (signal) or cross a size or time threshold",
"signal"),
OPT_CALLBACK_SET(0, "switch-output-event", &record.sb_evlist, &record.switch_output_event_set, "switch output event",
"switch output event selector. use 'perf list' to list available events",
parse_events_option_new_evlist),
OPT_INTEGER(0, "switch-max-files", &record.switch_output.num_files,
"Limit number of switch output generated files"),
OPT_BOOLEAN(0, "dry-run", &dry_run,