linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Mel Gorman <mgorman@techsingularity.net>
To: Andrew Morton <akpm@linux-foundation.org>, Linux-MM <linux-mm@kvack.org>
Cc: Rik van Riel <riel@surriel.com>, Vlastimil Babka <vbabka@suse.cz>,
	Johannes Weiner <hannes@cmpxchg.org>,
	LKML <linux-kernel@vger.kernel.org>,
	Mel Gorman <mgorman@techsingularity.net>
Subject: [PATCH 08/27] mm, vmscan: Simplify the logic deciding whether kswapd sleeps
Date: Thu,  9 Jun 2016 19:04:24 +0100	[thread overview]
Message-ID: <1465495483-11855-9-git-send-email-mgorman@techsingularity.net> (raw)
In-Reply-To: <1465495483-11855-1-git-send-email-mgorman@techsingularity.net>

kswapd goes through some complex steps trying to figure out if it
should stay awake based on the classzone_idx and the requested order.
It is unnecessarily complex and passes in an invalid classzone_idx to
balance_pgdat().  What matters most of all is whether a larger order has
been requsted and whether kswapd successfully reclaimed at the previous
order. This patch irons out the logic to check just that and the end result
is less headache inducing.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
---
 include/linux/mmzone.h |  5 ++--
 mm/memory_hotplug.c    |  5 ++--
 mm/page_alloc.c        |  2 +-
 mm/vmscan.c            | 79 +++++++++++++++++++++++++-------------------------
 4 files changed, 46 insertions(+), 45 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index aff621fcc6af..15ce454d0d59 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -663,8 +663,9 @@ typedef struct pglist_data {
 	wait_queue_head_t pfmemalloc_wait;
 	struct task_struct *kswapd;	/* Protected by
 					   mem_hotplug_begin/end() */
-	int kswapd_max_order;
-	enum zone_type classzone_idx;
+	int kswapd_order;
+	enum zone_type kswapd_classzone_idx;
+
 #ifdef CONFIG_COMPACTION
 	int kcompactd_max_order;
 	enum zone_type kcompactd_classzone_idx;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c5278360ca66..42d758bffd0a 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1209,9 +1209,10 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
 
 		arch_refresh_nodedata(nid, pgdat);
 	} else {
-		/* Reset the nr_zones and classzone_idx to 0 before reuse */
+		/* Reset the nr_zones, order and classzone_idx before reuse */
 		pgdat->nr_zones = 0;
-		pgdat->classzone_idx = 0;
+		pgdat->kswapd_order = 0;
+		pgdat->kswapd_classzone_idx = -1;
 	}
 
 	/* we can use NODE_DATA(nid) from here */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4ce578b969da..d8cb483d5cad 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6036,7 +6036,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 	unsigned long end_pfn = 0;
 
 	/* pg_data_t should be reset to zero when it's allocated */
-	WARN_ON(pgdat->nr_zones || pgdat->classzone_idx);
+	WARN_ON(pgdat->nr_zones || pgdat->kswapd_classzone_idx);
 
 	reset_deferred_meminit(pgdat);
 	pgdat->node_id = nid;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 96bf841f9352..14b34eebedff 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2727,7 +2727,7 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 
 	/* kswapd must be awake if processes are being throttled */
 	if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
-		pgdat->classzone_idx = min(pgdat->classzone_idx,
+		pgdat->kswapd_classzone_idx = min(pgdat->kswapd_classzone_idx,
 						(enum zone_type)ZONE_NORMAL);
 		wake_up_interruptible(&pgdat->kswapd_wait);
 	}
@@ -3211,6 +3211,12 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
 
 	prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
 
+	/* If kswapd has not been woken recently, then full sleep */
+	if (classzone_idx == -1) {
+		classzone_idx = balanced_classzone_idx = MAX_NR_ZONES - 1;
+		goto full_sleep;
+	}
+
 	/* Try to sleep for a short interval */
 	if (prepare_kswapd_sleep(pgdat, order, remaining,
 						balanced_classzone_idx)) {
@@ -3233,6 +3239,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
 		prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
 	}
 
+full_sleep:
 	/*
 	 * After a short sleep, check if it was a premature sleep. If not, then
 	 * go fully to sleep until explicitly woken up.
@@ -3279,9 +3286,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order,
  */
 static int kswapd(void *p)
 {
-	unsigned long order, new_order;
-	int classzone_idx, new_classzone_idx;
-	int balanced_classzone_idx;
+	unsigned int order, classzone_idx;
 	pg_data_t *pgdat = (pg_data_t*)p;
 	struct task_struct *tsk = current;
 
@@ -3311,38 +3316,25 @@ static int kswapd(void *p)
 	tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
 	set_freezable();
 
-	order = new_order = 0;
-	classzone_idx = new_classzone_idx = pgdat->nr_zones - 1;
-	balanced_classzone_idx = classzone_idx;
+	pgdat->kswapd_order = order = 0;
+	pgdat->kswapd_classzone_idx = classzone_idx = -1;
 	for ( ; ; ) {
 		bool ret;
 
+kswapd_try_sleep:
+		kswapd_try_to_sleep(pgdat, order, classzone_idx, classzone_idx);
+
 		/*
-		 * While we were reclaiming, there might have been another
-		 * wakeup, so check the values.
+		 * Read the new order and classzone_idx which may be -1 if
+		 * kswapd_try_to_sleep() woke up after a short timeout instead
+		 * of being woken by the page allocator.
 		 */
-		new_order = pgdat->kswapd_max_order;
-		new_classzone_idx = pgdat->classzone_idx;
-		pgdat->kswapd_max_order =  0;
-		pgdat->classzone_idx = pgdat->nr_zones - 1;
-
-		if (order < new_order || classzone_idx > new_classzone_idx) {
-			/*
-			 * Don't sleep if someone wants a larger 'order'
-			 * allocation or has tigher zone constraints
-			 */
-			order = new_order;
-			classzone_idx = new_classzone_idx;
-		} else {
-			kswapd_try_to_sleep(pgdat, order, classzone_idx,
-						balanced_classzone_idx);
-			order = pgdat->kswapd_max_order;
-			classzone_idx = pgdat->classzone_idx;
-			new_order = order;
-			new_classzone_idx = classzone_idx;
-			pgdat->kswapd_max_order = 0;
-			pgdat->classzone_idx = pgdat->nr_zones - 1;
-		}
+		order = pgdat->kswapd_order;
+		classzone_idx = pgdat->kswapd_classzone_idx;
+		if (classzone_idx == -1)
+			classzone_idx = MAX_NR_ZONES - 1;
+		pgdat->kswapd_order = 0;
+		pgdat->kswapd_classzone_idx = -1;
 
 		ret = try_to_freeze();
 		if (kthread_should_stop())
@@ -3352,12 +3344,19 @@ static int kswapd(void *p)
 		 * We can speed up thawing tasks if we don't call balance_pgdat
 		 * after returning from the refrigerator
 		 */
-		if (!ret) {
-			trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
+		if (ret)
+			continue;
 
-			/* return value ignored until next patch */
-			balance_pgdat(pgdat, order, classzone_idx);
-		}
+		/*
+		 * Try reclaim the requested order but if that fails
+		 * then try sleeping on the basis of the order reclaimed.
+		 */
+		trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
+		if (balance_pgdat(pgdat, order, classzone_idx) < order)
+			goto kswapd_try_sleep;
+
+		order = pgdat->kswapd_order;
+		classzone_idx = pgdat->kswapd_classzone_idx;
 	}
 
 	tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
@@ -3380,10 +3379,10 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 	if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
 		return;
 	pgdat = zone->zone_pgdat;
-	if (pgdat->kswapd_max_order < order) {
-		pgdat->kswapd_max_order = order;
-		pgdat->classzone_idx = min(pgdat->classzone_idx, classzone_idx);
-	}
+	if (pgdat->kswapd_classzone_idx == -1)
+		pgdat->kswapd_classzone_idx = classzone_idx;
+	pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx);
+	pgdat->kswapd_order = max(pgdat->kswapd_order, order);
 	if (!waitqueue_active(&pgdat->kswapd_wait))
 		return;
 	if (zone_balanced(zone, order, 0))
-- 
2.6.4

  parent reply	other threads:[~2016-06-09 18:07 UTC|newest]

Thread overview: 74+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-06-09 18:04 [PATCH 00/27] Move LRU page reclaim from zones to nodes v6 Mel Gorman
2016-06-09 18:04 ` [PATCH 01/27] mm, vmstat: Add infrastructure for per-node vmstats Mel Gorman
2016-06-10 13:31   ` Vlastimil Babka
2016-06-10 13:47     ` Mel Gorman
2016-06-13 17:26   ` Christoph Lameter
2016-06-14 14:25     ` Mel Gorman
2016-06-09 18:04 ` [PATCH 02/27] mm, vmscan: Move lru_lock to the node Mel Gorman
2016-06-10 16:39   ` Vlastimil Babka
2016-06-10 17:48     ` Peter Zijlstra
2016-06-14 14:41     ` Mel Gorman
2016-06-09 18:04 ` [PATCH 03/27] mm, vmscan: Move LRU lists to node Mel Gorman
2016-06-10 18:00   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 04/27] mm, vmscan: Begin reclaiming pages on a per-node basis Mel Gorman
2016-06-15 12:52   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 05/27] mm, vmscan: Have kswapd only scan based on the highest requested zone Mel Gorman
2016-06-15 13:13   ` Vlastimil Babka
2016-06-16  7:44     ` Mel Gorman
2016-06-09 18:04 ` [PATCH 06/27] mm, vmscan: Make kswapd reclaim in terms of nodes Mel Gorman
2016-06-15 14:23   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 07/27] mm, vmscan: Remove balance gap Mel Gorman
2016-06-15 14:28   ` Vlastimil Babka
2016-06-09 18:04 ` Mel Gorman [this message]
2016-06-15 15:18   ` [PATCH 08/27] mm, vmscan: Simplify the logic deciding whether kswapd sleeps Vlastimil Babka
2016-06-16  8:30     ` Mel Gorman
2016-06-16  9:16       ` Mel Gorman
2016-06-09 18:04 ` [PATCH 09/27] mm, vmscan: By default have direct reclaim only shrink once per node Mel Gorman
2016-06-16  8:59   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 10/27] mm, vmscan: Clear congestion, dirty and need for compaction on a per-node basis Mel Gorman
2016-06-16  9:29   ` Vlastimil Babka
2016-06-16 10:29     ` Mel Gorman
2016-06-09 18:04 ` [PATCH 11/27] mm: vmscan: Do not reclaim from kswapd if there is any eligible zone Mel Gorman
2016-06-16 10:08   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 12/27] mm, vmscan: Make shrink_node decisions more node-centric Mel Gorman
2016-06-16 13:35   ` Vlastimil Babka
2016-06-16 14:47     ` Mel Gorman
2016-06-09 18:04 ` [PATCH 13/27] mm, memcg: Move memcg limit enforcement from zones to nodes Mel Gorman
2016-06-16 15:06   ` Vlastimil Babka
2016-06-16 15:53     ` Mel Gorman
2016-06-09 18:04 ` [PATCH 14/27] mm, workingset: Make working set detection node-aware Mel Gorman
2016-06-16 15:13   ` Vlastimil Babka
2016-06-16 15:56     ` Mel Gorman
2016-06-09 18:04 ` [PATCH 15/27] mm, page_alloc: Consider dirtyable memory in terms of nodes Mel Gorman
2016-06-16 15:45   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 16/27] mm: Move page mapped accounting to the node Mel Gorman
2016-06-16 15:52   ` Vlastimil Babka
2016-06-16 16:04     ` Mel Gorman
2016-06-09 18:04 ` [PATCH 17/27] mm: Rename NR_ANON_PAGES to NR_ANON_MAPPED Mel Gorman
2016-06-17  8:28   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 18/27] mm: Move most file-based accounting to the node Mel Gorman
2016-06-17  8:35   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 19/27] mm: Move vmscan writes and file write " Mel Gorman
2016-06-17  8:51   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 20/27] mm, vmscan: Update classzone_idx if buffer_heads_over_limit Mel Gorman
2016-06-17  8:53   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 21/27] mm, vmscan: Only wakeup kswapd once per node for the requested classzone Mel Gorman
2016-06-17 10:46   ` Vlastimil Babka
2016-06-17 12:03     ` Mel Gorman
2016-06-09 18:04 ` [PATCH 22/27] mm: Convert zone_reclaim to node_reclaim Mel Gorman
2016-06-17 10:55   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 23/27] mm, vmscan: Add classzone information to tracepoints Mel Gorman
2016-06-17 10:57   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 24/27] mm, page_alloc: Remove fair zone allocation policy Mel Gorman
2016-06-17 11:27   ` Vlastimil Babka
2016-06-17 12:07     ` Mel Gorman
2016-06-09 18:04 ` [PATCH 25/27] mm: page_alloc: Cache the last node whose dirty limit is reached Mel Gorman
2016-06-17 11:31   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 26/27] mm: vmstat: Replace __count_zone_vm_events with a zone id equivalent Mel Gorman
2016-06-17 11:36   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 27/27] mm: vmstat: Account per-zone stalls and pages skipped during reclaim Mel Gorman
2016-06-17 12:39   ` Vlastimil Babka
  -- strict thread matches above, loose matches on Subject: below --
2016-06-21 14:15 [PATCH 00/27] Move LRU page reclaim from zones to nodes v7 Mel Gorman
2016-06-21 14:15 ` [PATCH 08/27] mm, vmscan: Simplify the logic deciding whether kswapd sleeps Mel Gorman
2016-06-22 15:30   ` Vlastimil Babka
2016-04-15  9:13 [PATCH 00/27] Move LRU page reclaim from zones to nodes v5 Mel Gorman
2016-04-15  9:13 ` [PATCH 08/27] mm, vmscan: Simplify the logic deciding whether kswapd sleeps Mel Gorman
2016-04-06 11:19 [RFC PATCH 00/27] Move LRU page reclaim from zones to nodes v3 Mel Gorman
2016-04-06 11:20 ` [PATCH 08/27] mm, vmscan: Simplify the logic deciding whether kswapd sleeps Mel Gorman

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=1465495483-11855-9-git-send-email-mgorman@techsingularity.net \
    --to=mgorman@techsingularity.net \
    --cc=akpm@linux-foundation.org \
    --cc=hannes@cmpxchg.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=riel@surriel.com \
    --cc=vbabka@suse.cz \
    --subject='Re: [PATCH 08/27] mm, vmscan: Simplify the logic deciding whether kswapd sleeps' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).