lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:	Wed, 23 Feb 2011 17:47:57 +0100
From:	Andrea Arcangeli <aarcange@...hat.com>
To:	Arthur Marsh <arthur.marsh@...ernode.on.net>
Cc:	Clemens Ladisch <cladisch@...glemail.com>,
	alsa-user@...ts.sourceforge.net, linux-kernel@...r.kernel.org,
	Mel Gorman <mel@....ul.ie>
Subject: Re: [Alsa-user] new source of MIDI playback slow-down identified -
 5a03b051ed87e72b959f32a86054e1142ac4cf55 thp: use compaction in kswapd for
 GFP_ATOMIC order > 0

On Wed, Feb 23, 2011 at 05:40:01PM +0100, Andrea Arcangeli wrote:
> I noticed a buglet in this break... need to repost sorry. compaction-no-kswapd-2.

and one part of the diff went missing during quilt ref...  no luck. Try
#3. So here a compaction-no-kswapd-3. Apologies for the flood.

===
Subject: compaction: fix high compaction latencies and remove compaction-kswapd

From: Andrea Arcangeli <aarcange@...hat.com>

We need to proper spin_unlock_irq/cond_resched in the compaction loop to avoid
hurting latencies. We must also stop calling compaction from kswapd as that
creates too high load during memory pressure that can't be offseted by the
improved performance of hugepage allocations. NOTE: this is not related to THP
as all THP allocations uses __GFP_NO_KSWAPD, this is only related to usually
small order allocations like the kernel stack that make kswapd go wild with
compaction.

Signed-off-by: Andrea Arcangeli <aarcange@...hat.com>
---
 mm/compaction.c |   40 +++++++++++++++++++++-------------------
 1 file changed, 21 insertions(+), 19 deletions(-)

--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -271,9 +271,27 @@ static unsigned long isolate_migratepage
 	}
 
 	/* Time to isolate some pages for migration */
+	cond_resched();
 	spin_lock_irq(&zone->lru_lock);
 	for (; low_pfn < end_pfn; low_pfn++) {
 		struct page *page;
+		int unlocked = 0;
+
+		/* give a chance to irqs before checking need_resched() */
+		if (!((low_pfn+1) % SWAP_CLUSTER_MAX)) {
+			spin_unlock_irq(&zone->lru_lock);
+			unlocked = 1;
+		}
+		if (need_resched() || spin_is_contended(&zone->lru_lock)) {
+			if (!unlocked)
+				spin_unlock_irq(&zone->lru_lock);
+			cond_resched();
+			spin_lock_irq(&zone->lru_lock);
+			if (fatal_signal_pending(current))
+				break;
+		} else if (unlocked)
+			spin_lock_irq(&zone->lru_lock);
+
 		if (!pfn_valid_within(low_pfn))
 			continue;
 		nr_scanned++;
@@ -397,10 +415,7 @@ static int compact_finished(struct zone 
 		return COMPACT_COMPLETE;
 
 	/* Compaction run is not finished if the watermark is not met */
-	if (cc->compact_mode != COMPACT_MODE_KSWAPD)
-		watermark = low_wmark_pages(zone);
-	else
-		watermark = high_wmark_pages(zone);
+	watermark = low_wmark_pages(zone);
 	watermark += (1 << cc->order);
 
 	if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0))
@@ -413,15 +428,6 @@ static int compact_finished(struct zone 
 	if (cc->order == -1)
 		return COMPACT_CONTINUE;
 
-	/*
-	 * Generating only one page of the right order is not enough
-	 * for kswapd, we must continue until we're above the high
-	 * watermark as a pool for high order GFP_ATOMIC allocations
-	 * too.
-	 */
-	if (cc->compact_mode == COMPACT_MODE_KSWAPD)
-		return COMPACT_CONTINUE;
-
 	/* Direct compactor: Is a suitable page free? */
 	for (order = cc->order; order < MAX_ORDER; order++) {
 		/* Job done if page is free of the right migratetype */
@@ -543,8 +549,7 @@ static int compact_zone(struct zone *zon
 
 unsigned long compact_zone_order(struct zone *zone,
 				 int order, gfp_t gfp_mask,
-				 bool sync,
-				 int compact_mode)
+				 bool sync)
 {
 	struct compact_control cc = {
 		.nr_freepages = 0,
@@ -553,7 +558,6 @@ unsigned long compact_zone_order(struct 
 		.migratetype = allocflags_to_migratetype(gfp_mask),
 		.zone = zone,
 		.sync = sync,
-		.compact_mode = compact_mode,
 	};
 	INIT_LIST_HEAD(&cc.freepages);
 	INIT_LIST_HEAD(&cc.migratepages);
@@ -599,8 +603,7 @@ unsigned long try_to_compact_pages(struc
 								nodemask) {
 		int status;
 
-		status = compact_zone_order(zone, order, gfp_mask, sync,
-					    COMPACT_MODE_DIRECT_RECLAIM);
+		status = compact_zone_order(zone, order, gfp_mask, sync);
 		rc = max(status, rc);
 
 		/* If a normal allocation would succeed, stop compacting */
@@ -631,7 +634,6 @@ static int compact_node(int nid)
 			.nr_freepages = 0,
 			.nr_migratepages = 0,
 			.order = -1,
-			.compact_mode = COMPACT_MODE_DIRECT_RECLAIM,
 		};
 
 		zone = &pgdat->node_zones[zoneid];
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index dfa2ed4..cc9f7a4 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -11,9 +11,6 @@
 /* The full zone was compacted */
 #define COMPACT_COMPLETE	3
 
-#define COMPACT_MODE_DIRECT_RECLAIM	0
-#define COMPACT_MODE_KSWAPD		1
-
 #ifdef CONFIG_COMPACTION
 extern int sysctl_compact_memory;
 extern int sysctl_compaction_handler(struct ctl_table *table, int write,
@@ -28,8 +25,7 @@ extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			bool sync);
 extern unsigned long compaction_suitable(struct zone *zone, int order);
 extern unsigned long compact_zone_order(struct zone *zone, int order,
-					gfp_t gfp_mask, bool sync,
-					int compact_mode);
+					gfp_t gfp_mask, bool sync);
 
 /* Do not skip compaction more than 64 times */
 #define COMPACT_MAX_DEFER_SHIFT 6
@@ -74,8 +70,7 @@ static inline unsigned long compaction_suitable(struct zone *zone, int order)
 }
 
 static inline unsigned long compact_zone_order(struct zone *zone, int order,
-					       gfp_t gfp_mask, bool sync,
-					       int compact_mode)
+					       gfp_t gfp_mask, bool sync)
 {
 	return COMPACT_CONTINUE;
 }
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 17497d0..0e7121d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2385,7 +2385,6 @@ loop_again:
 		 * cause too much scanning of the lower zones.
 		 */
 		for (i = 0; i <= end_zone; i++) {
-			int compaction;
 			struct zone *zone = pgdat->node_zones + i;
 			int nr_slab;
 
@@ -2416,24 +2415,9 @@ loop_again:
 			sc.nr_reclaimed += reclaim_state->reclaimed_slab;
 			total_scanned += sc.nr_scanned;
 
-			compaction = 0;
-			if (order &&
-			    zone_watermark_ok(zone, 0,
-					       high_wmark_pages(zone),
-					      end_zone, 0) &&
-			    !zone_watermark_ok(zone, order,
-					       high_wmark_pages(zone),
-					       end_zone, 0)) {
-				compact_zone_order(zone,
-						   order,
-						   sc.gfp_mask, false,
-						   COMPACT_MODE_KSWAPD);
-				compaction = 1;
-			}
-
 			if (zone->all_unreclaimable)
 				continue;
-			if (!compaction && nr_slab == 0 &&
+			if (nr_slab == 0 &&
 			    !zone_reclaimable(zone))
 				zone->all_unreclaimable = 1;
 			/*
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ