Linux-mm Archive on lore.kernel.org
 help / color / Atom feed
* [patch 108/158] mm: vmscan: replace shrink_node() loop with a retry jump
@ 2019-12-01  1:55 akpm
  0 siblings, 0 replies; only message in thread
From: akpm @ 2019-12-01  1:55 UTC (permalink / raw)
  To: akpm, guro, hannes, linux-mm, mhocko, mm-commits, shakeelb, torvalds

From: Johannes Weiner <hannes@cmpxchg.org>
Subject: mm: vmscan: replace shrink_node() loop with a retry jump

Most of the function body is inside a loop, which imposes an additional
indentation and scoping level that makes the code a bit hard to follow and
modify.

The looping only happens in case of reclaim-compaction, which isn't the
common case.  So rather than adding yet another function level to the
reclaim path and have every reclaim invocation go through a level that
only exists for one specific cornercase, use a retry goto.

Link: http://lkml.kernel.org/r/20191022144803.302233-6-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/vmscan.c |  237 ++++++++++++++++++++++++--------------------------
 1 file changed, 118 insertions(+), 119 deletions(-)

--- a/mm/vmscan.c~mm-vmscan-replace-shrink_node-loop-with-a-retry-jump
+++ a/mm/vmscan.c
@@ -2729,144 +2729,143 @@ static bool pgdat_memcg_congested(pg_dat
 static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 {
 	struct reclaim_state *reclaim_state = current->reclaim_state;
+	struct mem_cgroup *root = sc->target_mem_cgroup;
 	unsigned long nr_reclaimed, nr_scanned;
 	bool reclaimable = false;
+	struct mem_cgroup *memcg;
+again:
+	memset(&sc->nr, 0, sizeof(sc->nr));
 
-	do {
-		struct mem_cgroup *root = sc->target_mem_cgroup;
-		struct mem_cgroup *memcg;
-
-		memset(&sc->nr, 0, sizeof(sc->nr));
-
-		nr_reclaimed = sc->nr_reclaimed;
-		nr_scanned = sc->nr_scanned;
-
-		memcg = mem_cgroup_iter(root, NULL, NULL);
-		do {
-			unsigned long reclaimed;
-			unsigned long scanned;
-
-			switch (mem_cgroup_protected(root, memcg)) {
-			case MEMCG_PROT_MIN:
-				/*
-				 * Hard protection.
-				 * If there is no reclaimable memory, OOM.
-				 */
-				continue;
-			case MEMCG_PROT_LOW:
-				/*
-				 * Soft protection.
-				 * Respect the protection only as long as
-				 * there is an unprotected supply
-				 * of reclaimable memory from other cgroups.
-				 */
-				if (!sc->memcg_low_reclaim) {
-					sc->memcg_low_skipped = 1;
-					continue;
-				}
-				memcg_memory_event(memcg, MEMCG_LOW);
-				break;
-			case MEMCG_PROT_NONE:
-				/*
-				 * All protection thresholds breached. We may
-				 * still choose to vary the scan pressure
-				 * applied based on by how much the cgroup in
-				 * question has exceeded its protection
-				 * thresholds (see get_scan_count).
-				 */
-				break;
-			}
+	nr_reclaimed = sc->nr_reclaimed;
+	nr_scanned = sc->nr_scanned;
 
-			reclaimed = sc->nr_reclaimed;
-			scanned = sc->nr_scanned;
-			shrink_node_memcg(pgdat, memcg, sc);
-
-			shrink_slab(sc->gfp_mask, pgdat->node_id, memcg,
-					sc->priority);
-
-			/* Record the group's reclaim efficiency */
-			vmpressure(sc->gfp_mask, memcg, false,
-				   sc->nr_scanned - scanned,
-				   sc->nr_reclaimed - reclaimed);
-
-		} while ((memcg = mem_cgroup_iter(root, memcg, NULL)));
-
-		if (reclaim_state) {
-			sc->nr_reclaimed += reclaim_state->reclaimed_slab;
-			reclaim_state->reclaimed_slab = 0;
-		}
-
-		/* Record the subtree's reclaim efficiency */
-		vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true,
-			   sc->nr_scanned - nr_scanned,
-			   sc->nr_reclaimed - nr_reclaimed);
-
-		if (sc->nr_reclaimed - nr_reclaimed)
-			reclaimable = true;
+	memcg = mem_cgroup_iter(root, NULL, NULL);
+	do {
+		unsigned long reclaimed;
+		unsigned long scanned;
 
-		if (current_is_kswapd()) {
+		switch (mem_cgroup_protected(root, memcg)) {
+		case MEMCG_PROT_MIN:
 			/*
-			 * If reclaim is isolating dirty pages under writeback,
-			 * it implies that the long-lived page allocation rate
-			 * is exceeding the page laundering rate. Either the
-			 * global limits are not being effective at throttling
-			 * processes due to the page distribution throughout
-			 * zones or there is heavy usage of a slow backing
-			 * device. The only option is to throttle from reclaim
-			 * context which is not ideal as there is no guarantee
-			 * the dirtying process is throttled in the same way
-			 * balance_dirty_pages() manages.
-			 *
-			 * Once a node is flagged PGDAT_WRITEBACK, kswapd will
-			 * count the number of pages under pages flagged for
-			 * immediate reclaim and stall if any are encountered
-			 * in the nr_immediate check below.
+			 * Hard protection.
+			 * If there is no reclaimable memory, OOM.
 			 */
-			if (sc->nr.writeback && sc->nr.writeback == sc->nr.taken)
-				set_bit(PGDAT_WRITEBACK, &pgdat->flags);
-
+			continue;
+		case MEMCG_PROT_LOW:
 			/*
-			 * Tag a node as congested if all the dirty pages
-			 * scanned were backed by a congested BDI and
-			 * wait_iff_congested will stall.
+			 * Soft protection.
+			 * Respect the protection only as long as
+			 * there is an unprotected supply
+			 * of reclaimable memory from other cgroups.
 			 */
-			if (sc->nr.dirty && sc->nr.dirty == sc->nr.congested)
-				set_bit(PGDAT_CONGESTED, &pgdat->flags);
-
-			/* Allow kswapd to start writing pages during reclaim.*/
-			if (sc->nr.unqueued_dirty == sc->nr.file_taken)
-				set_bit(PGDAT_DIRTY, &pgdat->flags);
-
+			if (!sc->memcg_low_reclaim) {
+				sc->memcg_low_skipped = 1;
+				continue;
+			}
+			memcg_memory_event(memcg, MEMCG_LOW);
+			break;
+		case MEMCG_PROT_NONE:
 			/*
-			 * If kswapd scans pages marked marked for immediate
-			 * reclaim and under writeback (nr_immediate), it
-			 * implies that pages are cycling through the LRU
-			 * faster than they are written so also forcibly stall.
+			 * All protection thresholds breached. We may
+			 * still choose to vary the scan pressure
+			 * applied based on by how much the cgroup in
+			 * question has exceeded its protection
+			 * thresholds (see get_scan_count).
 			 */
-			if (sc->nr.immediate)
-				congestion_wait(BLK_RW_ASYNC, HZ/10);
+			break;
 		}
 
+		reclaimed = sc->nr_reclaimed;
+		scanned = sc->nr_scanned;
+		shrink_node_memcg(pgdat, memcg, sc);
+
+		shrink_slab(sc->gfp_mask, pgdat->node_id, memcg,
+			    sc->priority);
+
+		/* Record the group's reclaim efficiency */
+		vmpressure(sc->gfp_mask, memcg, false,
+			   sc->nr_scanned - scanned,
+			   sc->nr_reclaimed - reclaimed);
+
+	} while ((memcg = mem_cgroup_iter(root, memcg, NULL)));
+
+	if (reclaim_state) {
+		sc->nr_reclaimed += reclaim_state->reclaimed_slab;
+		reclaim_state->reclaimed_slab = 0;
+	}
+
+	/* Record the subtree's reclaim efficiency */
+	vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true,
+		   sc->nr_scanned - nr_scanned,
+		   sc->nr_reclaimed - nr_reclaimed);
+
+	if (sc->nr_reclaimed - nr_reclaimed)
+		reclaimable = true;
+
+	if (current_is_kswapd()) {
+		/*
+		 * If reclaim is isolating dirty pages under writeback,
+		 * it implies that the long-lived page allocation rate
+		 * is exceeding the page laundering rate. Either the
+		 * global limits are not being effective at throttling
+		 * processes due to the page distribution throughout
+		 * zones or there is heavy usage of a slow backing
+		 * device. The only option is to throttle from reclaim
+		 * context which is not ideal as there is no guarantee
+		 * the dirtying process is throttled in the same way
+		 * balance_dirty_pages() manages.
+		 *
+		 * Once a node is flagged PGDAT_WRITEBACK, kswapd will
+		 * count the number of pages under pages flagged for
+		 * immediate reclaim and stall if any are encountered
+		 * in the nr_immediate check below.
+		 */
+		if (sc->nr.writeback && sc->nr.writeback == sc->nr.taken)
+			set_bit(PGDAT_WRITEBACK, &pgdat->flags);
+
 		/*
-		 * Legacy memcg will stall in page writeback so avoid forcibly
-		 * stalling in wait_iff_congested().
+		 * Tag a node as congested if all the dirty pages
+		 * scanned were backed by a congested BDI and
+		 * wait_iff_congested will stall.
 		 */
-		if (cgroup_reclaim(sc) && writeback_throttling_sane(sc) &&
-		    sc->nr.dirty && sc->nr.dirty == sc->nr.congested)
-			set_memcg_congestion(pgdat, root, true);
+		if (sc->nr.dirty && sc->nr.dirty == sc->nr.congested)
+			set_bit(PGDAT_CONGESTED, &pgdat->flags);
+
+		/* Allow kswapd to start writing pages during reclaim.*/
+		if (sc->nr.unqueued_dirty == sc->nr.file_taken)
+			set_bit(PGDAT_DIRTY, &pgdat->flags);
 
 		/*
-		 * Stall direct reclaim for IO completions if underlying BDIs
-		 * and node is congested. Allow kswapd to continue until it
-		 * starts encountering unqueued dirty pages or cycling through
-		 * the LRU too quickly.
+		 * If kswapd scans pages marked marked for immediate
+		 * reclaim and under writeback (nr_immediate), it
+		 * implies that pages are cycling through the LRU
+		 * faster than they are written so also forcibly stall.
 		 */
-		if (!sc->hibernation_mode && !current_is_kswapd() &&
-		   current_may_throttle() && pgdat_memcg_congested(pgdat, root))
-			wait_iff_congested(BLK_RW_ASYNC, HZ/10);
+		if (sc->nr.immediate)
+			congestion_wait(BLK_RW_ASYNC, HZ/10);
+	}
 
-	} while (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed,
-					 sc));
+	/*
+	 * Legacy memcg will stall in page writeback so avoid forcibly
+	 * stalling in wait_iff_congested().
+	 */
+	if (cgroup_reclaim(sc) && writeback_throttling_sane(sc) &&
+	    sc->nr.dirty && sc->nr.dirty == sc->nr.congested)
+		set_memcg_congestion(pgdat, root, true);
+
+	/*
+	 * Stall direct reclaim for IO completions if underlying BDIs
+	 * and node is congested. Allow kswapd to continue until it
+	 * starts encountering unqueued dirty pages or cycling through
+	 * the LRU too quickly.
+	 */
+	if (!sc->hibernation_mode && !current_is_kswapd() &&
+	    current_may_throttle() && pgdat_memcg_congested(pgdat, root))
+		wait_iff_congested(BLK_RW_ASYNC, HZ/10);
+
+	if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed,
+				    sc))
+		goto again;
 
 	/*
 	 * Kswapd gives up on balancing particular nodes after too
_


^ permalink raw reply	[flat|nested] only message in thread

only message in thread, back to index

Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-12-01  1:55 [patch 108/158] mm: vmscan: replace shrink_node() loop with a retry jump akpm

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