[Lustre-discuss] kernel: BUG: soft lockup - CPU stuck for 10s! with lustre 1.8.4
peter.x.jones at oracle.com
Mon Sep 20 06:53:16 PDT 2010
Yes, turning off statahead is a workaround. Of course it is a trade-off
and ultimately for you to decide. However, the statahead feature
(introduced in 1.6.2 I think) has been very problematic and many
previous attempts at fixing issues have caused subtle regressions. Most
sites seem to be able to run statahead ok with the latest 1.8.x releases
so I think that we are just down to edge cases. We will of course still
continue to remove the edge cases in future releases, and perhaps
FanYong's patch might land and be tested out as part of a release, but,
as things stand, this is still just a proposed fix. If you do decide to
try the patch, please post your experiences to the bz ticket - thanks!
Temple Jason wrote:
> It appears that turning off statahead does indeed avoid the soft lockup bug. But this seems to me to be a workaround, and not a solution.
> Is statahead not useful for performance gains? I am not comfortable making my user's jobs waste more cpu time because I have to implement a workaround instead of a fix.
> Is there one in the works? Nasf - does your patch solve the bug, or does it just disable statahead by default?
More information about the lustre-discuss