From 0abdee2bd4118366c62349a304f81537be69af33 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 13 Jan 2011 15:46:22 -0800 Subject: [PATCH] mm: kswapd: use the order that kswapd was reclaiming at for sleeping_prematurely() Before kswapd goes to sleep, it uses sleeping_prematurely() to check if there was a race pushing a zone below its watermark. If the race happened, it stays awake. However, balance_pgdat() can decide to reclaim at order-0 if it decides that high-order reclaim is not working as expected. This information is not passed back to sleeping_prematurely(). The impact is that kswapd remains awake reclaiming pages long after it should have gone to sleep. This patch passes the adjusted order to sleeping_prematurely and uses the same logic as balance_pgdat to decide if it's ok to go to sleep. Signed-off-by: Mel Gorman Reviewed-by: Minchan Kim Reviewed-by: KAMEZAWA Hiroyuki Reviewed-by: Eric B Munson Cc: Simon Kirby Cc: KOSAKI Motohiro Cc: Shaohua Li Cc: Dave Hansen Cc: Johannes Weiner Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index d3488828331a..46711f080f38 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2227,7 +2227,7 @@ static bool pgdat_balanced(pg_data_t *pgdat, unsigned long balanced_pages, } /* is kswapd sleeping prematurely? */ -static int sleeping_prematurely(pg_data_t *pgdat, int order, long remaining) +static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining) { int i; unsigned long balanced = 0; @@ -2237,7 +2237,7 @@ static int sleeping_prematurely(pg_data_t *pgdat, int order, long remaining) if (remaining) return 1; - /* If after HZ/10, a zone is below the high mark, it's premature */ + /* Check the watermark levels */ for (i = 0; i < pgdat->nr_zones; i++) { struct zone *zone = pgdat->node_zones + i; @@ -2269,7 +2269,7 @@ static int sleeping_prematurely(pg_data_t *pgdat, int order, long remaining) * For kswapd, balance_pgdat() will work across all this node's zones until * they are all at high_wmark_pages(zone). * - * Returns the number of pages which were actually freed. + * Returns the final order kswapd was reclaiming at * * There is special handling here for zones which are full of pinned pages. * This can happen if the pages are all mlocked, or if they are all used by @@ -2532,7 +2532,13 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order, } } - return sc.nr_reclaimed; + /* + * Return the order we were reclaiming at so sleeping_prematurely() + * makes a decision on the order we were last reclaiming at. However, + * if another caller entered the allocator slow path while kswapd + * was awake, order will remain at the higher level + */ + return order; } static void kswapd_try_to_sleep(pg_data_t *pgdat, int order) @@ -2659,7 +2665,7 @@ static int kswapd(void *p) */ if (!ret) { trace_mm_vmscan_kswapd_wake(pgdat->node_id, order); - balance_pgdat(pgdat, order, classzone_idx); + order = balance_pgdat(pgdat, order, classzone_idx); } } return 0; -- GitLab