xfs
[Top] [All Lists]

Re: [PATCH 5/7] mm: vmscan: Do not writeback filesystem pages in kswapd

To: Rik van Riel <riel@xxxxxxxxxx>
Subject: Re: [PATCH 5/7] mm: vmscan: Do not writeback filesystem pages in kswapd except in high priority
From: Mel Gorman <mgorman@xxxxxxx>
Date: Thu, 11 Aug 2011 21:38:05 +0100
Cc: Linux-MM <linux-mm@xxxxxxxxx>, LKML <linux-kernel@xxxxxxxxxxxxxxx>, XFS <xfs@xxxxxxxxxxx>, Dave Chinner <david@xxxxxxxxxxxxx>, Christoph Hellwig <hch@xxxxxxxxxxxxx>, Johannes Weiner <jweiner@xxxxxxxxxx>, Wu Fengguang <fengguang.wu@xxxxxxxxx>, Jan Kara <jack@xxxxxxx>, Minchan Kim <minchan.kim@xxxxxxxxx>
In-reply-to: <4E441D0E.6020602@xxxxxxxxxx>
References: <1312973240-32576-1-git-send-email-mgorman@xxxxxxx> <1312973240-32576-6-git-send-email-mgorman@xxxxxxx> <4E441D0E.6020602@xxxxxxxxxx>
User-agent: Mutt/1.5.21 (2010-09-15)
On Thu, Aug 11, 2011 at 02:18:54PM -0400, Rik van Riel wrote:
> On 08/10/2011 06:47 AM, Mel Gorman wrote:
> >It is preferable that no dirty pages are dispatched for cleaning from
> >the page reclaim path. At normal priorities, this patch prevents kswapd
> >writing pages.
> >
> >However, page reclaim does have a requirement that pages be freed
> >in a particular zone. If it is failing to make sufficient progress
> >(reclaiming<  SWAP_CLUSTER_MAX at any priority priority), the priority
> >is raised to scan more pages. A priority of DEF_PRIORITY - 3 is
> >considered to be the point where kswapd is getting into trouble
> >reclaiming pages. If this priority is reached, kswapd will dispatch
> >pages for writing.
> >
> >Signed-off-by: Mel Gorman<mgorman@xxxxxxx>
> >Reviewed-by: Minchan Kim<minchan.kim@xxxxxxxxx>
> 
> My only worry with this patch is that maybe we'll burn too
> much CPU time freeing pages from a zone. 

The throttling patch prevents too much CPU being used if pages under
writeback are being encountered during scanning. That said, I shared
your concern and recorded kswapd CPU usage over time.

> However, chances
> are we'll have freed pages from other zones when scanning
> one zone multiple times (the page cache dirty limit is global,
> the clean pages have to be _somewhere_).
> 
> Since the bulk of the allocators are not too picky about
> which zone they get their pages from, I suspect this patch
> will be an overall improvement pretty much all the time.
> 

This is roughly similar to my own reasoning.

I uploaded all the kswapd CPU usage charts to
http://www.csn.ul.ie/~mel/postings/riel-20110811

These are smoothened as the raw figures are barely readable. If you
go through them, you'll see that kswapd CPU usage is sometimes higher
but generally within 2-3%.

> Acked-by: Rik van Riel <riel@xxxxxxxxxx>

Thanks.

-- 
Mel Gorman
SUSE Labs

<Prev in Thread] Current Thread [Next in Thread>