diff options
author | Arnaldo Carvalho de Melo <acme@redhat.com> | 2011-05-15 08:39:00 -0400 |
---|---|---|
committer | Arnaldo Carvalho de Melo <acme@redhat.com> | 2011-05-15 09:02:14 -0400 |
commit | aece948f5ddd70d70df2f35855c706ef9a4f62e2 (patch) | |
tree | ea2611cea32c492d7b3f4f49ec26df05132d5607 /tools/perf/builtin-top.c | |
parent | b90194181988063266f3da0b7bf3e57268c627c8 (diff) |
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>
Diffstat (limited to 'tools/perf/builtin-top.c')
-rw-r--r-- | tools/perf/builtin-top.c | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 7e3d6e310bf8..ebfc7cf5f63b 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c | |||
@@ -801,12 +801,12 @@ static void perf_event__process_sample(const union perf_event *event, | |||
801 | } | 801 | } |
802 | } | 802 | } |
803 | 803 | ||
804 | static void perf_session__mmap_read_cpu(struct perf_session *self, int cpu) | 804 | static void perf_session__mmap_read_idx(struct perf_session *self, int idx) |
805 | { | 805 | { |
806 | struct perf_sample sample; | 806 | struct perf_sample sample; |
807 | union perf_event *event; | 807 | union perf_event *event; |
808 | 808 | ||
809 | while ((event = perf_evlist__read_on_cpu(top.evlist, cpu)) != NULL) { | 809 | while ((event = perf_evlist__mmap_read(top.evlist, idx)) != NULL) { |
810 | perf_session__parse_sample(self, event, &sample); | 810 | perf_session__parse_sample(self, event, &sample); |
811 | 811 | ||
812 | if (event->header.type == PERF_RECORD_SAMPLE) | 812 | if (event->header.type == PERF_RECORD_SAMPLE) |
@@ -820,8 +820,8 @@ static void perf_session__mmap_read(struct perf_session *self) | |||
820 | { | 820 | { |
821 | int i; | 821 | int i; |
822 | 822 | ||
823 | for (i = 0; i < top.evlist->cpus->nr; i++) | 823 | for (i = 0; i < top.evlist->nr_mmaps; i++) |
824 | perf_session__mmap_read_cpu(self, i); | 824 | perf_session__mmap_read_idx(self, i); |
825 | } | 825 | } |
826 | 826 | ||
827 | static void start_counters(struct perf_evlist *evlist) | 827 | static void start_counters(struct perf_evlist *evlist) |