lkml.org 
[lkml]   [2010]   [Jun]   [15]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH 12/12] vmscan: Do not writeback pages in direct reclaim
On 06/15/2010 09:37 AM, Christoph Hellwig wrote:
> On Tue, Jun 15, 2010 at 09:34:18AM -0400, Rik van Riel wrote:
>> If direct reclaim can overflow the stack, so can direct
>> memcg reclaim. That means this patch does not solve the
>> stack overflow, while admitting that we do need the
>> ability to get specific pages flushed to disk from the
>> pageout code.
>
> Can you explain what the hell memcg reclaim is and why it needs
> to reclaim from random contexts?

The page fault code will call the cgroup accounting code.

When a cgroup goes over its memory limit, __mem_cgroup_try_charge
will call mem_cgroup_hierarchical_reclaim, which will then go
into the page reclaim code.

> It seems everything that has a cg in it's name that I stumbled over
> lately seems to be some ugly wart..

No argument there. It took me a few minutes to find the code
path above :)

--
All rights reversed


\
 
 \ /
  Last update: 2010-06-15 16:41    [from the cache]
©2003-2011 Jasper Spaans