Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1436251 > unrolled thread

Re: [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis

Started by"Hillf Danton" <hillf.zj@alibaba-inc.com>
First post2016-07-04 12:10 +0200
Last post2016-07-04 12:40 +0200
Articles 2 — 2 participants

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.


Contents

  Re: [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis "Hillf Danton" <hillf.zj@alibaba-inc.com> - 2016-07-04 12:10 +0200
    Re: [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node  basis Mel Gorman <mgorman@techsingularity.net> - 2016-07-04 12:40 +0200

#1436251 — Re: [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis

From"Hillf Danton" <hillf.zj@alibaba-inc.com>
Date2016-07-04 12:10 +0200
SubjectRe: [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis
Message-ID<rR8Zc-4jv-21@gated-at.bofh.it>
> @@ -2561,17 +2580,23 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
>  	 * highmem pages could be pinning lowmem pages storing buffer_heads
>  	 */
>  	orig_mask = sc->gfp_mask;
> -	if (buffer_heads_over_limit)
> +	if (buffer_heads_over_limit) {
>  		sc->gfp_mask |= __GFP_HIGHMEM;
> +		sc->reclaim_idx = classzone_idx = gfp_zone(sc->gfp_mask);
> +	}
> 
We need to push/pop ->reclaim_idx as ->gfp_mask handled?

thanks
Hillf

[toc] | [next] | [standalone]


#1436337 — Re: [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis

FromMel Gorman <mgorman@techsingularity.net>
Date2016-07-04 12:40 +0200
SubjectRe: [PATCH 04/31] mm, vmscan: begin reclaiming pages on a per-node basis
Message-ID<rR9sd-4tf-27@gated-at.bofh.it>
In reply to#1436251
On Mon, Jul 04, 2016 at 06:08:27PM +0800, Hillf Danton wrote:
> > @@ -2561,17 +2580,23 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
> >  	 * highmem pages could be pinning lowmem pages storing buffer_heads
> >  	 */
> >  	orig_mask = sc->gfp_mask;
> > -	if (buffer_heads_over_limit)
> > +	if (buffer_heads_over_limit) {
> >  		sc->gfp_mask |= __GFP_HIGHMEM;
> > +		sc->reclaim_idx = classzone_idx = gfp_zone(sc->gfp_mask);
> > +	}
> > 
> We need to push/pop ->reclaim_idx as ->gfp_mask handled?
> 

I saw no harm in having one full reclaim attempt reclaiming from all
zones if buffer_heads_over_limit was triggered. If it fails, the page
allocator will loop again and reset the reclaim_idx.

-- 
Mel Gorman
SUSE Labs

[toc] | [prev] | [standalone]


Back to top | Article view | linux.kernel


csiph-web