Re: [PATCH 27/34] mm, vmscan: Have kswapd reclaim from all zones if reclaiming and buffer_heads_over_limit

From	Johannes Weiner <hannes@cmpxchg.org>
Newsgroups	linux.kernel
Subject	Re: [PATCH 27/34] mm, vmscan: Have kswapd reclaim from all zones if reclaiming and buffer_heads_over_limit
Date	2016-07-12 20:20 +0200
Message-ID	<rUarM-7W-13@gated-at.bofh.it> (permalink)
References	<rSAqm-2Tv-3@gated-at.bofh.it> <rSAA2-2Xn-31@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On Fri, Jul 08, 2016 at 10:35:03AM +0100, Mel Gorman wrote:
> The buffer_heads_over_limit limit in kswapd is inconsistent with direct
> reclaim behaviour. It may force an an attempt to reclaim from all zones and
> then not reclaim at all because higher zones were balanced than required
> by the original request.
> 
> This patch will causes kswapd to consider reclaiming from all zones if
> buffer_heads_over_limit.  However, if there are eligible zones for the
> allocation request that woke kswapd then no reclaim will occur even if
> buffer_heads_over_limit. This avoids kswapd over-reclaiming just because
> buffer_heads_over_limit.
> 
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>

Acked-by: Johannes Weiner <hannes@cmpxchg.org>

Back to linux.kernel | Previous | Next | Find similar | Unroll thread

Thread

Re: [PATCH 27/34] mm, vmscan: Have kswapd reclaim from all zones if  reclaiming and buffer_heads_over_limit Johannes Weiner <hannes@cmpxchg.org> - 2016-07-12 20:20 +0200

csiph-web