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

Groups > linux.kernel > #1656537 > unrolled thread

Re: [patch v2] mm, vmscan: avoid thrashing anon lru when free + file is low

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 v2] mm, vmscan: avoid thrashing anon lru when free +  file is low Andrew Morton <akpm@linux-foundation.org> - 2017-06-02 22:40 +0200
    Re: [patch v2] mm, vmscan: avoid thrashing anon lru when free + file  is low David Rientjes <rientjes@google.com> - 2017-06-05 00:30 +0200

#1656537 — Re: [patch v2] mm, vmscan: avoid thrashing anon lru when free + file is low

On Mon, 1 May 2017 14:34:21 -0700 (PDT) David Rientjes <rientjes@google.com> wrote:

> The purpose of the code that commit 623762517e23 ("revert 'mm: vmscan: do
> not swap anon pages just because free+file is low'") reintroduces is to
> prefer swapping anonymous memory rather than trashing the file lru.
> 
> If the anonymous inactive lru for the set of eligible zones is considered
> low, however, or the length of the list for the given reclaim priority
> does not allow for effective anonymous-only reclaiming, then avoid
> forcing SCAN_ANON.  Forcing SCAN_ANON will end up thrashing the small
> list and leave unreclaimed memory on the file lrus.
> 
> If the inactive list is insufficient, fallback to balanced reclaim so the
> file lru doesn't remain untouched.
> 

--- a/mm/vmscan.c~mm-vmscan-avoid-thrashing-anon-lru-when-free-file-is-low-fix
+++ a/mm/vmscan.c
@@ -2233,7 +2233,7 @@ static void get_scan_count(struct lruvec
 			 * anonymous pages on the LRU in eligible zones.
 			 * Otherwise, the small LRU gets thrashed.
 			 */
-			if (!inactive_list_is_low(lruvec, false, sc, false) &&
+			if (!inactive_list_is_low(lruvec, false, memcg, sc, false) &&
 			    lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, sc->reclaim_idx)
 					>> sc->priority) {
 				scan_balance = SCAN_ANON;

Worried.  Did you send the correct version?

[toc] | [next] | [standalone]

#1657179 — Re: [patch v2] mm, vmscan: avoid thrashing anon lru when free + file is low

On Fri, 2 Jun 2017, Andrew Morton wrote:

> On Mon, 1 May 2017 14:34:21 -0700 (PDT) David Rientjes <rientjes@google.com> wrote:
> 
> > The purpose of the code that commit 623762517e23 ("revert 'mm: vmscan: do
> > not swap anon pages just because free+file is low'") reintroduces is to
> > prefer swapping anonymous memory rather than trashing the file lru.
> > 
> > If the anonymous inactive lru for the set of eligible zones is considered
> > low, however, or the length of the list for the given reclaim priority
> > does not allow for effective anonymous-only reclaiming, then avoid
> > forcing SCAN_ANON.  Forcing SCAN_ANON will end up thrashing the small
> > list and leave unreclaimed memory on the file lrus.
> > 
> > If the inactive list is insufficient, fallback to balanced reclaim so the
> > file lru doesn't remain untouched.
> > 
> 
> --- a/mm/vmscan.c~mm-vmscan-avoid-thrashing-anon-lru-when-free-file-is-low-fix
> +++ a/mm/vmscan.c
> @@ -2233,7 +2233,7 @@ static void get_scan_count(struct lruvec
>  			 * anonymous pages on the LRU in eligible zones.
>  			 * Otherwise, the small LRU gets thrashed.
>  			 */
> -			if (!inactive_list_is_low(lruvec, false, sc, false) &&
> +			if (!inactive_list_is_low(lruvec, false, memcg, sc, false) &&
>  			    lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, sc->reclaim_idx)
>  					>> sc->priority) {
>  				scan_balance = SCAN_ANON;
> 
> Worried.  Did you send the correct version?
> 

The patch was written before commit 2a2e48854d70 ("mm: vmscan: fix 
IO/refault regression in cache workingset transition") was merged and 
changed inactive_list_is_low().

Your rebase looks good.  It could have used NULL instead of memcg since 
this is only for global_reclaim() and memcg will always be NULL here, but 
that's just personal preference.

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web