From 20f0d30fb0b4bfc8ae288b1ae1184ab27ccebc39 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Wed, 4 Jun 2014 16:08:26 -0700 Subject: [PATCH] mm, compaction: return failed migration target pages back to freelist commit d53aea3d46d64e95da9952887969f7533b9ab25e upstream. Greg reported that he found isolated free pages were returned back to the VM rather than the compaction freelist. This will cause holes behind the free scanner and cause it to reallocate additional memory if necessary later. He detected the problem at runtime seeing that ext4 metadata pages (esp the ones read by "sbi->s_group_desc[i] = sb_bread(sb, block)") were constantly visited by compaction calls of migrate_pages(). These pages had a non-zero b_count which caused fallback_migrate_page() -> try_to_release_page() -> try_to_free_buffers() to fail. Memory compaction works by having a "freeing scanner" scan from one end of a zone which isolates pages as migration targets while another "migrating scanner" scans from the other end of the same zone which isolates pages for migration. When page migration fails for an isolated page, the target page is returned to the system rather than the freelist built by the freeing scanner. This may require the freeing scanner to continue scanning memory after suitable migration targets have already been returned to the system needlessly. This patch returns destination pages to the freeing scanner freelist when page migration fails. This prevents unnecessary work done by the freeing scanner but also encourages memory to be as compacted as possible at the end of the zone. Signed-off-by: David Rientjes Reported-by: Greg Thelen Acked-by: Mel Gorman Acked-by: Vlastimil Babka Reviewed-by: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Mel Gorman Signed-off-by: Greg Kroah-Hartman --- mm/compaction.c | 27 ++++++++++++++++++--------- 1 file changed, 18 insertions(+), 9 deletions(-) diff --git a/mm/compaction.c b/mm/compaction.c index 8dea401..22338a1 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -790,23 +790,32 @@ static struct page *compaction_alloc(struct page *migratepage, } /* - * We cannot control nr_migratepages and nr_freepages fully when migration is - * running as migrate_pages() has no knowledge of compact_control. When - * migration is complete, we count the number of pages on the lists by hand. + * This is a migrate-callback that "frees" freepages back to the isolated + * freelist. All pages on the freelist are from the same zone, so there is no + * special handling needed for NUMA. + */ +static void compaction_free(struct page *page, unsigned long data) +{ + struct compact_control *cc = (struct compact_control *)data; + + list_add(&page->lru, &cc->freepages); + cc->nr_freepages++; +} + +/* + * We cannot control nr_migratepages fully when migration is running as + * migrate_pages() has no knowledge of of compact_control. When migration is + * complete, we count the number of pages on the list by hand. */ static void update_nr_listpages(struct compact_control *cc) { int nr_migratepages = 0; - int nr_freepages = 0; struct page *page; list_for_each_entry(page, &cc->migratepages, lru) nr_migratepages++; - list_for_each_entry(page, &cc->freepages, lru) - nr_freepages++; cc->nr_migratepages = nr_migratepages; - cc->nr_freepages = nr_freepages; } /* possible outcome of isolate_migratepages */ @@ -1016,8 +1025,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) } nr_migrate = cc->nr_migratepages; - err = migrate_pages(&cc->migratepages, compaction_alloc, NULL, - (unsigned long)cc, + err = migrate_pages(&cc->migratepages, compaction_alloc, + compaction_free, (unsigned long)cc, cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC, MR_COMPACTION); update_nr_listpages(cc); -- 2.7.4