On Wed, 12 Jun 2013, Michal Hocko wrote:

quoted

quoted

quoted

quoted

quoted

quoted

Reported-by: Reported-by: azurIt <redacted>

Ok, so the key here is that azurIt was able to reliably reproduce this 
issue and now it has been resurrected after seven months of silence since 
that thread.  I also notice that azurIt isn't cc'd on this thread.  Do we 
know if this is still a problem?

I have backported the patch for his 3.2 and waiting for his feedback.

Ok, thanks.  I thought this was only going seven months back when it was 
reported, I missed that the issue this patch is trying to address goes 
back a 1 1/2 years to 3.2 and nobody else has reported it.  I think his 
feedback would be the key, specifically if he can upgrade to a later 
kernel first.