From 1f4056a0fa656c7647733e3cf906ad83979b4a42 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 29 Jul 2009 15:02:04 -0700 Subject: [PATCH] page-allocator: preserve PFN ordering when __GFP_COLD is set commit e084b2d95e48b31aa45f9c49ffc6cdae8bdb21d4 upstream. Fix a post-2.6.24 performace regression caused by 3dfa5721f12c3d5a441448086bee156887daa961 ("page-allocator: preserve PFN ordering when __GFP_COLD is set"). Narayanan reports "The regression is around 15%. There is no disk controller as our setup is based on Samsung OneNAND used as a memory mapped device on a OMAP2430 based board." The page allocator tries to preserve contiguous PFN ordering when returning pages such that repeated callers to the allocator have a strong chance of getting physically contiguous pages, particularly when external fragmentation is low. However, of the bulk of the allocations have __GFP_COLD set as they are due to aio_read() for example, then the PFNs are in reverse PFN order. This can cause performance degration when used with IO controllers that could have merged the requests. This patch attempts to preserve the contiguous ordering of PFNs for users of __GFP_COLD. Signed-off-by: Mel Gorman Reported-by: Narayananu Gopalakrishnan Tested-by: Narayanan Gopalakrishnan Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/page_alloc.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 480907cc28be..6bf3cc412d8e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -858,7 +858,7 @@ static struct page *__rmqueue(struct zone *zone, unsigned int order, */ static int rmqueue_bulk(struct zone *zone, unsigned int order, unsigned long count, struct list_head *list, - int migratetype) + int migratetype, int cold) { int i; @@ -877,7 +877,10 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, * merge IO requests if the physical pages are ordered * properly. */ - list_add(&page->lru, list); + if (likely(cold == 0)) + list_add(&page->lru, list); + else + list_add_tail(&page->lru, list); set_page_private(page, migratetype); list = &page->lru; } @@ -1077,7 +1080,8 @@ again: local_irq_save(flags); if (!pcp->count) { pcp->count = rmqueue_bulk(zone, 0, - pcp->batch, &pcp->list, migratetype); + pcp->batch, &pcp->list, + migratetype, cold); if (unlikely(!pcp->count)) goto failed; } @@ -1096,7 +1100,8 @@ again: /* Allocate more to the pcp list if necessary */ if (unlikely(&page->lru == &pcp->list)) { pcp->count += rmqueue_bulk(zone, 0, - pcp->batch, &pcp->list, migratetype); + pcp->batch, &pcp->list, + migratetype, cold); page = list_entry(pcp->list.next, struct page, lru); } -- 2.39.5