Revert "perf sched: Handle PERF_RECORD_EXIT events"
authorArnaldo Carvalho de Melo <acme@redhat.com>
Wed, 27 Mar 2013 13:34:49 +0000 (10:34 -0300)
committerArnaldo Carvalho de Melo <acme@redhat.com>
Mon, 1 Apr 2013 15:22:34 +0000 (12:22 -0300)
commit1c6763cb9962d6d83a8470934c20ed525ef62355
tree51e70bc73488fdfd53a115545e8f74583b8b8a85
parent62667746a6ded2a1fc8dac2e6258f46150b5e46c
Revert "perf sched: Handle PERF_RECORD_EXIT events"

This reverts commit 0439539f72ea222fbfe511b47318b9c1815a7108.

This caused this segfault:

[root@sandy linux]# perf sched rec
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.306 MB perf.data (~57062 samples) ]
perf
[root@sandy linux]# perf sched lat
perf: builtin-sched.c:781: thread_atoms_search: Assertion `!(thread != atoms->thread)' failed.
Aborted (core dumped)
[root@sandy linux]#

Further investigation is needed to check that even with machine__remove_thread()
not really deleting the thread referenced in the PERF_RECORD_EXIT (it goes to
machine->dead_threads, because references may still exist to them in things like
 hist, etc) some event later comes for this dead thread and then
machine__findnew_thread() will create a new thead instance that will not be the
same as the one referenced by work_atoms->thread in thread_atoms_search().

For now just revert this patch to get the 'perf sched lat' back working.

Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
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-`ranpwd
Link: http://lkml.kernel.org/n/tip-hg4s6e5txiwqe00h8rdg1sin@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
tools/perf/builtin-sched.c