Thread (25 messages) 25 messages, 2 authors, 2011-03-14

[Bug 29402] kernel panics while running ffsb scalability workloads on 2.6.38-rc1 through -rc5

From: <hidden>
Date: 2011-02-26 03:50:17

https://bugzilla.kernel.org/show_bug.cgi?id=29402




--- Comment #10 from Eric Whitney <eric.whitney@hp.com>  2011-02-26 03:50:09 ---
Created an attachment (id=49172)
 --> (https://bugzilla.kernel.org/attachment.cgi?id=49172)
Possible fix - patch simplifies completion counting and avoids races

Hi Lukas:

This patch has successfully passed an initial round of tests which 2.6.38-rc*
kernels have never passed.  It seemed appropriate to simplify the way
outstanding completions were being accounted for to avoid the races, and the
code ought to be just a little more efficient on a SMP/NUMA box as well.  At
any rate, it's a stab at it - I'd appreciate any comments you might have.  I'll
put it through a weekend's worth of test runs next.

Thanks!
Eric

-- 
Configure bugmail: https://bugzilla.kernel.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are watching the assignee of the bug.
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help