Linux-mm Archive on lore.kernel.org
 help / color / Atom feed
From: Dave Hansen <dave.hansen@linux.intel.com>
To: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org,Dave Hansen
	<dave.hansen@linux.intel.com>,yang.shi@linux.alibaba.com,rientjes@google.com,ying.huang@intel.com,dan.j.williams@intel.com
Subject: [RFC][PATCH 7/8] mm/vmscan: never demote for memcg reclaim
Date: Mon, 29 Jun 2020 16:45:15 -0700
Message-ID: <20200629234515.B11A021E@viggo.jf.intel.com> (raw)
In-Reply-To: <20200629234503.749E5340@viggo.jf.intel.com>


From: Dave Hansen <dave.hansen@linux.intel.com>

Global reclaim aims to reduce the amount of memory used on
a given node or set of nodes.  Migrating pages to another
node serves this purpose.

memcg reclaim is different.  Its goal is to reduce the
total memory consumption of the entire memcg, across all
nodes.  Migration does not assist memcg reclaim because
it just moves page contents between nodes rather than
actually reducing memory consumption.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Suggested-by: Yang Shi <yang.shi@linux.alibaba.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
---

 b/mm/vmscan.c |   61 +++++++++++++++++++++++++++++++++++++++-------------------
 1 file changed, 42 insertions(+), 19 deletions(-)

diff -puN mm/vmscan.c~never-demote-for-memcg-reclaim mm/vmscan.c
--- a/mm/vmscan.c~never-demote-for-memcg-reclaim	2020-06-29 16:34:44.018312591 -0700
+++ b/mm/vmscan.c	2020-06-29 16:34:44.023312591 -0700
@@ -289,7 +289,8 @@ static bool writeback_throttling_sane(st
 #endif
 
 static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg,
-					  int node_id)
+					  int node_id,
+					  struct scan_control *sc)
 {
 	/* Always age anon pages when we have swap */
 	if (memcg == NULL) {
@@ -300,8 +301,14 @@ static inline bool can_reclaim_anon_page
 			return true;
 	}
 
-	/* Also age anon pages if we can auto-migrate them */
-	if (next_demotion_node(node_id) >= 0)
+	/*
+	 * Also age anon pages if we can auto-migrate them.
+	 *
+	 * Migrating a page does not reduce comsumption of a
+	 * memcg so should not be performed when in memcg
+	 * reclaim.
+	 */
+	if ((sc && cgroup_reclaim(sc)) && (next_demotion_node(node_id) >= 0))
 		return true;
 
 	/* No way to reclaim anon pages */
@@ -319,7 +326,7 @@ unsigned long zone_reclaimable_pages(str
 
 	nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) +
 		zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE);
-	if (can_reclaim_anon_pages(NULL, zone_to_nid(zone)))
+	if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL))
 		nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) +
 			zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON);
 
@@ -1084,6 +1091,32 @@ static void page_check_dirty_writeback(s
 		mapping->a_ops->is_dirty_writeback(page, dirty, writeback);
 }
 
+
+static int shrink_do_demote_mapping(struct page *page,
+				    struct list_head *page_list,
+				    struct scan_control *sc)
+{
+	int rc;
+
+	/* It is pointless to do demotion in memcg reclaim */
+	if (cgroup_reclaim(sc))
+		return -ENOTSUPP;
+
+	rc = migrate_demote_mapping(page);
+	/*
+	 * -ENOMEM on a THP may indicate either migration is
+	 * unsupported or there was not enough contiguous
+	 * space. Split the THP into base pages and retry the
+	 * head immediately. The tail pages will be considered
+	 * individually within the current loop's page list.
+	 */
+	if (rc == -ENOMEM && PageTransHuge(page) &&
+	    !split_huge_page_to_list(page, page_list))
+		rc = migrate_demote_mapping(page);
+
+	return rc;
+}
+
 /*
  * shrink_page_list() returns the number of reclaimed pages
  */
@@ -1251,17 +1284,7 @@ static unsigned long shrink_page_list(st
 			; /* try to reclaim the page below */
 		}
 
-		rc = migrate_demote_mapping(page);
-		/*
-		 * -ENOMEM on a THP may indicate either migration is
-		 * unsupported or there was not enough contiguous
-		 * space. Split the THP into base pages and retry the
-		 * head immediately. The tail pages will be considered
-		 * individually within the current loop's page list.
-		 */
-		if (rc == -ENOMEM && PageTransHuge(page) &&
-		    !split_huge_page_to_list(page, page_list))
-			rc = migrate_demote_mapping(page);
+		rc = shrink_do_demote_mapping(page, page_list, sc);
 
 		if (rc == MIGRATEPAGE_SUCCESS) {
 			unlock_page(page);
@@ -2287,7 +2310,7 @@ static void get_scan_count(struct lruvec
 	enum lru_list lru;
 
 	/* If we have no swap space, do not bother scanning anon pages. */
-	if (!sc->may_swap || !can_reclaim_anon_pages(memcg, pgdat->node_id)) {
+	if (!sc->may_swap || !can_reclaim_anon_pages(memcg, pgdat->node_id, sc)) {
 		scan_balance = SCAN_FILE;
 		goto out;
 	}
@@ -2593,7 +2616,7 @@ static void shrink_lruvec(struct lruvec
 	 * rebalance the anon lru active/inactive ratio.
 	 */
 	if (can_reclaim_anon_pages(lruvec_memcg(lruvec),
-			       lruvec_pgdat(lruvec)->node_id) &&
+			       lruvec_pgdat(lruvec)->node_id, sc) &&
 	    inactive_is_low(lruvec, LRU_INACTIVE_ANON))
 		shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
 				   sc, LRU_ACTIVE_ANON);
@@ -2664,7 +2687,7 @@ static inline bool should_continue_recla
 	 */
 	pages_for_compaction = compact_gap(sc->order);
 	inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE);
-	if (can_reclaim_anon_pages(NULL, pgdat->node_id))
+	if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc))
 		inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON);
 
 	return inactive_lru_pages > pages_for_compaction;
@@ -3417,7 +3440,7 @@ static void age_active_anon(struct pglis
 	struct mem_cgroup *memcg;
 	struct lruvec *lruvec;
 
-	if (!can_reclaim_anon_pages(NULL, pgdat->node_id))
+	if (!can_reclaim_anon_pages(NULL, pgdat->node_id, sc))
 		return;
 
 	lruvec = mem_cgroup_lruvec(NULL, pgdat);
_


  parent reply index

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-29 23:45 [RFC][PATCH 0/8] Migrate Pages in lieu of discard Dave Hansen
2020-06-29 23:45 ` [RFC][PATCH 1/8] mm/numa: node demotion data structure and lookup Dave Hansen
2020-06-29 23:45 ` [RFC][PATCH 2/8] mm/migrate: Defer allocating new page until needed Dave Hansen
2020-07-01  8:47   ` Greg Thelen
2020-07-01 14:46     ` Dave Hansen
2020-07-01 18:32       ` Yang Shi
2020-06-29 23:45 ` [RFC][PATCH 3/8] mm/vmscan: Attempt to migrate page in lieu of discard Dave Hansen
2020-07-01  0:47   ` David Rientjes
2020-07-01  1:29     ` Yang Shi
2020-07-01  5:41       ` David Rientjes
2020-07-01  8:54         ` Huang, Ying
2020-07-01 18:20           ` Dave Hansen
2020-07-01 19:50             ` David Rientjes
2020-07-02  1:50               ` Huang, Ying
2020-07-01 15:15         ` Dave Hansen
2020-07-01 17:21         ` Yang Shi
2020-07-01 19:45           ` David Rientjes
2020-07-02 10:02             ` Jonathan Cameron
2020-07-01  1:40     ` Huang, Ying
2020-07-01 16:48     ` Dave Hansen
2020-07-01 19:25       ` David Rientjes
2020-07-02  5:02         ` Huang, Ying
2020-06-29 23:45 ` [RFC][PATCH 4/8] mm/vmscan: add page demotion counter Dave Hansen
2020-06-29 23:45 ` [RFC][PATCH 5/8] mm/numa: automatically generate node migration order Dave Hansen
2020-06-30  8:22   ` Huang, Ying
2020-07-01 18:23     ` Dave Hansen
2020-07-02  1:20       ` Huang, Ying
2020-06-29 23:45 ` [RFC][PATCH 6/8] mm/vmscan: Consider anonymous pages without swap Dave Hansen
2020-06-29 23:45 ` Dave Hansen [this message]
2020-06-29 23:45 ` [RFC][PATCH 8/8] mm/numa: new reclaim mode to enable reclaim-based migration Dave Hansen
2020-06-30  7:23   ` Huang, Ying
2020-06-30 17:50     ` Yang Shi
2020-07-01  0:48       ` Huang, Ying
2020-07-01  1:12         ` Yang Shi
2020-07-01  1:28           ` Huang, Ying
2020-07-01 16:02       ` Dave Hansen
2020-07-03  9:30   ` Huang, Ying
2020-06-30 18:36 ` [RFC][PATCH 0/8] Migrate Pages in lieu of discard Shakeel Butt
2020-06-30 18:51   ` Dave Hansen
2020-06-30 19:25     ` Shakeel Butt
2020-06-30 19:31       ` Dave Hansen
2020-07-01 14:24         ` [RFC] [PATCH " Zi Yan
2020-07-01 14:32           ` Dave Hansen

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200629234515.B11A021E@viggo.jf.intel.com \
    --to=dave.hansen@linux.intel.com \
    --cc=dan.j.williams@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=rientjes@google.com \
    --cc=yang.shi@linux.alibaba.com \
    --cc=ying.huang@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-mm Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-mm/0 linux-mm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-mm linux-mm/ https://lore.kernel.org/linux-mm \
		linux-mm@kvack.org
	public-inbox-index linux-mm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kvack.linux-mm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git