[PATCH] vmscan: fix zone_reclaim (d4f7796e) · Commits · 戴 / test

- PF_SWAPWRITE needs to be set for RECLAIM_SWAP to be able to write out pages to swap. Currently RECLAIM_SWAP may not do that. - remove setting nr_reclaimed pages after slab reclaim since the slab shrinking code does not use that and the nr_reclaimed pages is just right for the intended follow up action. Signed-off-by:

Christoph Lameter <clameter@sgi.com> Signed-off-by:

Andrew Morton <akpm@osdl.org> Signed-off-by:

Linus Torvalds <torvalds@osdl.org>

mm/vmscan.c

+7 −3

Original line number	Diff line number	Diff line
		@@ -1908,7 +1908,12 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
		sc.swap_cluster_max = SWAP_CLUSTER_MAX;

		cond_resched();
		p->flags \|= PF_MEMALLOC;
		/*
		* We need to be able to allocate from the reserves for RECLAIM_SWAP
		* and we also need to be able to write out pages for RECLAIM_WRITE
		* and RECLAIM_SWAP.
		*/
		p->flags \|= PF_MEMALLOC \| PF_SWAPWRITE;
		reclaim_state.reclaimed_slab = 0;
		p->reclaim_state = &reclaim_state;

		@@ -1932,11 +1937,10 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
		* a long time.
		*/
		shrink_slab(sc.nr_scanned, gfp_mask, order);
		sc.nr_reclaimed = 1; /* Avoid getting the off node timeout */
		}

		p->reclaim_state = NULL;
		current->flags &= ~PF_MEMALLOC;
		current->flags &= ~(PF_MEMALLOC \| PF_SWAPWRITE);

		if (sc.nr_reclaimed == 0)
		zone->last_unsuccessful_zone_reclaim = jiffies;

Admin message