From 0610c25daa3e76e38ad5a8fae683a89ff9f71798 Mon Sep 17 00:00:00 2001 From: Greg Thelen Date: Thu, 1 Oct 2015 15:37:02 -0700 Subject: [PATCH] memcg: fix dirty page migration The problem starts with a file backed dirty page which is charged to a memcg. Then page migration is used to move oldpage to newpage. Migration: - copies the oldpage's data to newpage - clears oldpage.PG_dirty - sets newpage.PG_dirty - uncharges oldpage from memcg - charges newpage to memcg Clearing oldpage.PG_dirty decrements the charged memcg's dirty page count. However, because newpage is not yet charged, setting newpage.PG_dirty does not increment the memcg's dirty page count. After migration completes newpage.PG_dirty is eventually cleared, often in account_page_cleaned(). At this time newpage is charged to a memcg so the memcg's dirty page count is decremented which causes underflow because the count was not previously incremented by migration. This underflow causes balance_dirty_pages() to see a very large unsigned number of dirty memcg pages which leads to aggressive throttling of buffered writes by processes in non root memcg. This issue: - can harm performance of non root memcg buffered writes. - can report too small (even negative) values in memory.stat[(total_)dirty] counters of all memcg, including the root. To avoid polluting migrate.c with #ifdef CONFIG_MEMCG checks, introduce page_memcg() and set_page_memcg() helpers. Test: 0) setup and enter limited memcg mkdir /sys/fs/cgroup/test echo 1G > /sys/fs/cgroup/test/memory.limit_in_bytes echo $$ > /sys/fs/cgroup/test/cgroup.procs 1) buffered writes baseline dd if=/dev/zero of=/data/tmp/foo bs=1M count=1k sync grep ^dirty /sys/fs/cgroup/test/memory.stat 2) buffered writes with compaction antagonist to induce migration yes 1 > /proc/sys/vm/compact_memory & rm -rf /data/tmp/foo dd if=/dev/zero of=/data/tmp/foo bs=1M count=1k kill % sync grep ^dirty /sys/fs/cgroup/test/memory.stat 3) buffered writes without antagonist, should match baseline rm -rf /data/tmp/foo dd if=/dev/zero of=/data/tmp/foo bs=1M count=1k sync grep ^dirty /sys/fs/cgroup/test/memory.stat (speed, dirty residue) unpatched patched 1) 841 MB/s 0 dirty pages 886 MB/s 0 dirty pages 2) 611 MB/s -33427456 dirty pages 793 MB/s 0 dirty pages 3) 114 MB/s -33427456 dirty pages 891 MB/s 0 dirty pages Notice that unpatched baseline performance (1) fell after migration (3): 841 -> 114 MB/s. In the patched kernel, post migration performance matches baseline. Fixes: c4843a7593a9 ("memcg: add per cgroup dirty page accounting") Signed-off-by: Greg Thelen Reported-by: Dave Hansen Acked-by: Michal Hocko Acked-by: Johannes Weiner Cc: [4.2+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 21 +++++++++++++++++++++ mm/migrate.c | 12 +++++++++++- 2 files changed, 32 insertions(+), 1 deletion(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 91c08f6f0dc9..80001de019ba 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -905,6 +905,27 @@ static inline void set_page_links(struct page *page, enum zone_type zone, #endif } +#ifdef CONFIG_MEMCG +static inline struct mem_cgroup *page_memcg(struct page *page) +{ + return page->mem_cgroup; +} + +static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg) +{ + page->mem_cgroup = memcg; +} +#else +static inline struct mem_cgroup *page_memcg(struct page *page) +{ + return NULL; +} + +static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg) +{ +} +#endif + /* * Some inline functions in vmstat.h depend on page_zone() */ diff --git a/mm/migrate.c b/mm/migrate.c index 7452a00bbb50..842ecd7aaf7f 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -740,6 +740,15 @@ static int move_to_new_page(struct page *newpage, struct page *page, if (PageSwapBacked(page)) SetPageSwapBacked(newpage); + /* + * Indirectly called below, migrate_page_copy() copies PG_dirty and thus + * needs newpage's memcg set to transfer memcg dirty page accounting. + * So perform memcg migration in two steps: + * 1. set newpage->mem_cgroup (here) + * 2. clear page->mem_cgroup (below) + */ + set_page_memcg(newpage, page_memcg(page)); + mapping = page_mapping(page); if (!mapping) rc = migrate_page(mapping, newpage, page, mode); @@ -756,9 +765,10 @@ static int move_to_new_page(struct page *newpage, struct page *page, rc = fallback_migrate_page(mapping, newpage, page, mode); if (rc != MIGRATEPAGE_SUCCESS) { + set_page_memcg(newpage, NULL); newpage->mapping = NULL; } else { - mem_cgroup_migrate(page, newpage, false); + set_page_memcg(page, NULL); if (page_was_mapped) remove_migration_ptes(page, newpage); page->mapping = NULL; -- 2.39.2