diff mbox series

[1/3] mm: Uncharge and keep page in pagecache on memcg reclaim

Message ID 154703642447.32690.5604527676583713589.stgit@localhost.localdomain (mailing list archive)
State New, archived
Headers show
Series mm: Reduce IO by improving algorithm of memcg pagecache pages eviction | expand

Commit Message

Kirill Tkhai Jan. 9, 2019, 12:20 p.m. UTC
This patch makes __remove_mapping() not remove a page from
pagecache on memcg reclaim. After all mappings are removed
and refcounter is freezed, we uncharge page memcg. Further
putback_lru_page() places page into root_mem_cgroup, so it
remains in pagecache till global reclaim. This gives memcg
tasks extra possibility to obtain page from pagecache
instead of launching IO.

Next patch makes pagecache_get_page() to recharge a page
in case of its memcg is NULL (i.e., on first access after
uncharging). It looks to be the only function, which is
used by filesystems to obtain a pagecache page. Here we
introduce AS_KEEP_MEMCG_RECLAIM flag to mark the filesystems,
which are reviewed, that they really follow this way. It
has a sense to keep pages in __remove_mapping() only for
them. Later, we remove this flags after all filesystems are
reviewed.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
---
 include/linux/pagemap.h |    1 +
 mm/vmscan.c             |   22 ++++++++++++++++++----
 2 files changed, 19 insertions(+), 4 deletions(-)
diff mbox series

Patch

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 1020e6f40880..1b880da85868 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -29,6 +29,7 @@  enum mapping_flags {
 	AS_EXITING	= 4, 	/* final truncate in progress */
 	/* writeback related tags are not used */
 	AS_NO_WRITEBACK_TAGS = 5,
+	AS_KEEP_MEMCG_RECLAIM = 6,
 };
 
 /**
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a714c4f800e9..7237603c8973 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -887,7 +887,7 @@  static pageout_t pageout(struct page *page, struct address_space *mapping,
  * gets returned with a refcount of 0.
  */
 static int __remove_mapping(struct address_space *mapping, struct page *page,
-			    bool reclaimed)
+			    bool reclaimed, bool memcg_reclaim)
 {
 	unsigned long flags;
 	int refcount;
@@ -963,7 +963,20 @@  static int __remove_mapping(struct address_space *mapping, struct page *page,
 		if (reclaimed && page_is_file_cache(page) &&
 		    !mapping_exiting(mapping) && !dax_mapping(mapping))
 			shadow = workingset_eviction(mapping, page);
-		__delete_from_page_cache(page, shadow);
+#ifdef CONFIG_MEMCG
+		if (memcg_reclaim &&
+		    test_bit(AS_KEEP_MEMCG_RECLAIM, &mapping->flags)) {
+			/*
+			 * Page is not dirty/writeback/mapped, so we may avoid
+			 * taking mem_cgroup::move_lock for changing its memcg.
+			 * See mem_cgroup_move_account() for details.
+			 */
+			mem_cgroup_uncharge(page);
+			page_ref_unfreeze(page, refcount);
+			goto cannot_free;
+		} else
+#endif
+			__delete_from_page_cache(page, shadow);
 		xa_unlock_irqrestore(&mapping->i_pages, flags);
 
 		if (freepage != NULL)
@@ -985,7 +998,7 @@  static int __remove_mapping(struct address_space *mapping, struct page *page,
  */
 int remove_mapping(struct address_space *mapping, struct page *page)
 {
-	if (__remove_mapping(mapping, page, false)) {
+	if (__remove_mapping(mapping, page, false, false)) {
 		/*
 		 * Unfreezing the refcount with 1 rather than 2 effectively
 		 * drops the pagecache ref for us without requiring another
@@ -1458,7 +1471,8 @@  static unsigned long shrink_page_list(struct list_head *page_list,
 
 			count_vm_event(PGLAZYFREED);
 			count_memcg_page_event(page, PGLAZYFREED);
-		} else if (!mapping || !__remove_mapping(mapping, page, true))
+		} else if (!mapping || !__remove_mapping(mapping, page, true,
+							!global_reclaim(sc)))
 			goto keep_locked;
 
 		unlock_page(page);