lkml.org 
[lkml]   [2011]   [Jul]   [31]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: [PATCH] kswapd: avoid unnecessary rebalance after an unsuccessful balancing
From
Date
On Fri, 2011-07-29 at 23:40 +0800, Mel Gorman wrote:
> On Fri, Jul 29, 2011 at 11:23:10PM +0800, Alex Shi wrote:
> > In commit 215ddd66, Mel Gorman said kswapd is better to sleep after a
> > unsuccessful balancing if there is tighter reclaim request pending in
> > the balancing. In this scenario, the 'order' and 'classzone_idx'
> > that are checked for tighter request judgment is incorrect, since they
> > aren't the one kswapd should read from new pgdat, but the last time pgdat
> > value for just now balancing. Then kswapd will skip try_to_sleep func
> > and rebalance the last pgdat request. It's not our expected behavior.
> >
> > So, I added new variables to distinguish the returned order/classzone_idx
> > from last balancing, that can resolved above issue in that scenario.
> >
>
> I'm afraid this changelog is very difficult to read and I do not see
> what problem you are trying to solve and I do not see what this patch
> might solve.
>
> When balance_pgdat() returns with a lower classzone or order, the values
> stored in pgdat are not re-read and instead it tries to go to sleep
> based on the starting request. Something like;

Thanks for your comments, I will use this comments style next time, list
request A, B etc.

>
> 1. Read pgdat request A (classzone_idx, order)

Assume the order of A > 0, like is 3.

> 2. balance_pgdat()
> 3. During pgdat, a new pgdat request B (classzone_idx, order) is placed
> 4. balance_pgdat() returns but failed so classzone_idx is lower

Another balance_pgdat() failure indicate is returned order == 0, am I
right? If so, the next step of kswapd is not trying to sleep, but do
request A balance again. And I thought this behavior doesn't match the
comments in kswapd.

> 5. Try to sleep based on pgdat request A

>
> i.e. pgdat request B is not read and there is a comment explaining
> why pgdat request B is not read after balance_pgdat() fails.
>
> This patch adds some variables that might improve the readability
> for some people but otherwise I can't see what problem is being
> fixed. What did I miss?
>




\
 
 \ /
  Last update: 2011-08-01 02:45    [W:0.054 / U:0.128 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site