lkml.org 
[lkml]   [2011]   [Apr]   [26]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: [PATCH RFC] Fix per-task profiling Re: [PATCH] perf: Allow set output buffer for tasks in the same thread group
From
Date
On Wed, 2011-04-27 at 04:44 +0800, Arnaldo Carvalho de Melo wrote:
> Em Mon, Apr 25, 2011 at 12:28:33PM -0300, Arnaldo Carvalho de Melo escreveu:
> > Em Mon, Apr 25, 2011 at 09:40:38PM +0800, Lin Ming escreveu:
> > > On Mon, 2011-04-25 at 01:05 +0800, Peter Zijlstra wrote:
> > > > On Sun, 2011-04-24 at 22:57 +0800, Lin Ming wrote:
> > > > > Currently, kernel only allows an event to redirect its output to other
> > > > > events of the same task.
>
> > > > > This causes PERF_EVENT_IOC_SET_OUTPUT ioctl fails when an event is
> > > > > trying to redirect its output to other events in the same thread group.
>
> > > > Which is exactly what it should do, you should never be allowed to
> > > > redirect your events to that of another task, since that other task
> > > > might be running on another CPU.
>
> > > > The buffer code strictly assumes no concurrency, therefore its either
> > > > one task or one CPU.
>
> > > Well, this is not the right fix, then the perf tool code need to be
> > > fixed.
>
> > Yes, I'm working on it.
>
> Lin, David, Tim, can you please try the two patches attached?
>
> 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

Tested and it works OK.

But here is one thing make me confused.
I thought that "--pid" and "--cpu" parameters are not allowed to be used
at the same time. Otherwise, is it a task event or cpu event?

Or does it mean that the event is only monitored when the "task" is
running on the specified "cpu"?

Thanks,
Lin Ming



\
 
 \ /
  Last update: 2011-04-27 04:43    [W:0.158 / U:0.076 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site