Re: [PATCH] vmscan: limit concurrent reclaimers in shrink_zone

[Rik van Riel <riel@redhat.com>]

On 12/10/2009 09:03 PM, Minchan Kim wrote:
> On Fri, Dec 11, 2009 at 8:56 AM, Rik van Riel<riel@redhat.com>  wrote:
>> Under very heavy multi-process workloads, like AIM7, the VM can
>> get into trouble in a variety of ways.  The trouble start when
>> there are hundreds, or even thousands of processes active in the
>> page reclaim code.

> Otherwise looks good to me.
>
> Reviewed-by: Minchan Kim<minchan.kim@gmail.com>

OK, we found three issues with my patch :)

1) there is a typo in sysctl.c

2) there is another typo in Documentation/vm/sysctl.c

3) the code in vmscan.c has a bug, where tasks without
     __GFP_IO or __GFP_FS can end up waiting for tasks
     with __GFP_IO or __GFP_FS, leading to a deadlock

I will fix these issues and send out a new patch.

-- 
All rights reversed.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>