diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 4bca2a3d917..a46c10fcddf 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -137,6 +137,7 @@ This is value ORed together of 1 = Zone reclaim on 2 = Zone reclaim writes dirty pages out 4 = Zone reclaim swaps pages +8 = Also do a global slab reclaim pass zone_reclaim_mode is set during bootup to 1 if it is determined that pages from remote zones will cause a measurable performance reduction. The @@ -160,6 +161,11 @@ Allowing regular swap effectively restricts allocations to the local node unless explicitly overridden by memory policies or cpuset configurations. +It may be advisable to allow slab reclaim if the system makes heavy +use of files and builds up large slab caches. However, the slab +shrink operation is global, may take a long time and free slabs +in all nodes of the system. + ================================================================ zone_reclaim_interval: diff --git a/mm/vmscan.c b/mm/vmscan.c index 9e2ef3624d7..aa4b80dbe3a 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1596,6 +1596,7 @@ int zone_reclaim_mode __read_mostly; #define RECLAIM_ZONE (1<<0) /* Run shrink_cache on the zone */ #define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */ #define RECLAIM_SWAP (1<<2) /* Swap pages out during reclaim */ +#define RECLAIM_SLAB (1<<3) /* Do a global slab shrink if the zone is out of memory */ /* * Mininum time between zone reclaim scans @@ -1666,6 +1667,19 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) } while (sc.nr_reclaimed < nr_pages && sc.priority > 0); + if (sc.nr_reclaimed < nr_pages && (zone_reclaim_mode & RECLAIM_SLAB)) { + /* + * shrink_slab does not currently allow us to determine + * how many pages were freed in the zone. So we just + * shake the slab and then go offnode for a single allocation. + * + * shrink_slab will free memory on all zones and may take + * 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;