From: Christoph Lameter Add some comments to explain how zone reclaim works. And it fixes the following issues: - 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 Signed-off-by: Andrew Morton --- mm/vmscan.c | 18 ++++++++++++++---- 1 files changed, 14 insertions(+), 4 deletions(-) diff -puN mm/vmscan.c~zone_reclaim-additional-comments-and-cleanup mm/vmscan.c --- devel/mm/vmscan.c~zone_reclaim-additional-comments-and-cleanup 2006-03-08 21:35:05.000000000 -0800 +++ devel-akpm/mm/vmscan.c 2006-03-08 21:35:05.000000000 -0800 @@ -1881,6 +1881,7 @@ int zone_reclaim_interval __read_mostly */ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) { + /* Minimum pages needed in order to stay on node */ const unsigned long nr_pages = 1 << order; struct task_struct *p = current; struct reclaim_state reclaim_state; @@ -1918,9 +1919,12 @@ static int __zone_reclaim(struct zone *z if (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() does not currently allow us to determine how + * many pages were freed in this zone. So we just shake the slab + * a bit and then go off node for this particular allocation + * despite possibly having freed enough memory to allocate in + * this zone. If we freed local memory then the next + * allocations will be local again. * * shrink_slab will free memory on all zones and may take * a long time. @@ -1931,8 +1935,14 @@ static int __zone_reclaim(struct zone *z p->reclaim_state = NULL; current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE); - if (nr_reclaimed == 0) + if (nr_reclaimed == 0) { + /* + * We were unable to reclaim enough pages to stay on node. We + * now allow off node accesses for a certain time period before + * trying again to reclaim pages from the local zone. + */ zone->last_unsuccessful_zone_reclaim = jiffies; + } return nr_reclaimed >= nr_pages; } _