[Bug 42895] jbd2 makes all system unresponsive

[bugzilla-daemon@bugzilla.kernel.org]

https://bugzilla.kernel.org/show_bug.cgi?id=42895


Jan Kara <jack@suse.cz> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |jack@suse.cz




--- Comment #10 from Jan Kara <jack@suse.cz>  2012-05-14 21:43:40 ---
(In reply to comment #8)
> Is there a way to find a cause of flush and jbd2 writes? Like apllication name
> or PID?
> Preferably without need to patch/compile new kernel, so that as many people as
> possible can use it.
  If you have tracepoints enabled in your kernel (they usually are) and you
have relatively recent kernel, then you can enable tracepoint in
ext4_mark_inode_dirty() by:
echo 1 >/sys/kernel/debug/tracing/events/ext4/ext4_mark_inode_dirty/enable

Then you can run:
cat /sys/kernel/debug/tracing/trace_pipe
and watch how inodes are dirtied. That should catch practically all cases where
JBD2 eventually ends up doing some IO.

-- 
Configure bugmail: https://bugzilla.kernel.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are watching the assignee of the bug.