diff options
| author | Andrew Morton <akpm@digeo.com> | 2002-09-07 22:21:55 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@home.transmeta.com> | 2002-09-07 22:21:55 -0700 |
| commit | 5f607d6ecf03d5fc3512d2c0a2fc3d447ccd4174 (patch) | |
| tree | 5104f861c8d59d9fe31181ca4642ca4b10d8b6f3 | |
| parent | 9fdbd959bfec877913d4eab793e813cc7d447b3f (diff) | |
[PATCH] refill the inactive list more quickly
Fix a problem noticed by Ed Tomlinson: under shifting workloads the
shrink_zone() logic will refill the inactive load too slowly.
Bale out of the zone scan when we've reclaimed enough pages. Fixes a
rarely-occurring problem wherein refill_inactive_zone() ends up
shuffling 100,000 pages and generally goes silly.
This needs to be revisited - we should go on and rebalance the lower
zones even if we reclaimed enough pages from highmem.
| -rw-r--r-- | mm/vmscan.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/mm/vmscan.c b/mm/vmscan.c index a00fe27159d9..5ed1ec3eda52 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -483,7 +483,7 @@ shrink_zone(struct zone *zone, int priority, ratio = (unsigned long)nr_pages * zone->nr_active / ((zone->nr_inactive | 1) * 2); atomic_add(ratio+1, &zone->refill_counter); - if (atomic_read(&zone->refill_counter) > SWAP_CLUSTER_MAX) { + while (atomic_read(&zone->refill_counter) > SWAP_CLUSTER_MAX) { atomic_sub(SWAP_CLUSTER_MAX, &zone->refill_counter); refill_inactive_zone(zone, SWAP_CLUSTER_MAX); } @@ -517,7 +517,7 @@ shrink_caches(struct zone *classzone, int priority, first_classzone = classzone->zone_pgdat->node_zones; zone = classzone; - while (zone >= first_classzone) { + while (zone >= first_classzone && nr_pages > 0) { if (zone->free_pages <= zone->pages_high) { nr_pages = shrink_zone(zone, priority, gfp_mask, nr_pages); |