All of lore.kernel.org
 help / color / mirror / Atom feed
From: Mel Gorman <mgorman@suse.de>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Linux Kernel <linux-kernel@vger.kernel.org>,
	Linux-MM <linux-mm@kvack.org>,
	Linux-FSDevel <linux-fsdevel@vger.kernel.org>
Subject: [PATCH] mm: page_alloc: Fix setting of ZONE_FAIR_DEPLETED on UP
Date: Fri, 5 Sep 2014 11:14:51 +0100	[thread overview]
Message-ID: <20140905101451.GF17501@suse.de> (raw)
In-Reply-To: <20140902140116.GD29501@cmpxchg.org>

Commit 4ffeaf35 (mm: page_alloc: reduce cost of the fair zone allocation policy)
broke the fair zone allocation policy on UP with these hunks.

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6e5e8f7..fb99081 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1612,6 +1612,9 @@ again:
        }

        __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
+       if (zone_page_state(zone, NR_ALLOC_BATCH) == 0 &&
+           !zone_is_fair_depleted(zone))
+               zone_set_flag(zone, ZONE_FAIR_DEPLETED);

        __count_zone_vm_events(PGALLOC, zone, 1 << order);
        zone_statistics(preferred_zone, zone, gfp_flags);
@@ -1966,8 +1985,10 @@ zonelist_scan:
                if (alloc_flags & ALLOC_FAIR) {
                        if (!zone_local(preferred_zone, zone))
                                break;
-                       if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
+                       if (zone_is_fair_depleted(zone)) {
+                               nr_fair_skipped++;
                                continue;
+                       }
                }

The problem is that a <= check was replaced with a ==. On SMP it doesn't
matter because negative values are returned as zero due to per-CPU drift
which is not possible in the UP case. Vlastimil Babka correctly pointed
out that this can be negative due to high-order allocations. This patch
fixes the problem.

Reported-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/page_alloc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 18cee0d..cd4c05c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1612,7 +1612,7 @@ again:
 	}
 
 	__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
-	if (zone_page_state(zone, NR_ALLOC_BATCH) == 0 &&
+	if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0 &&
 	    !zone_is_fair_depleted(zone))
 		zone_set_flag(zone, ZONE_FAIR_DEPLETED);
 

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

WARNING: multiple messages have this Message-ID (diff)
From: Mel Gorman <mgorman@suse.de>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Linux Kernel <linux-kernel@vger.kernel.org>,
	Linux-MM <linux-mm@kvack.org>,
	Linux-FSDevel <linux-fsdevel@vger.kernel.org>
Subject: [PATCH] mm: page_alloc: Fix setting of ZONE_FAIR_DEPLETED on UP
Date: Fri, 5 Sep 2014 11:14:51 +0100	[thread overview]
Message-ID: <20140905101451.GF17501@suse.de> (raw)
In-Reply-To: <20140902140116.GD29501@cmpxchg.org>

Commit 4ffeaf35 (mm: page_alloc: reduce cost of the fair zone allocation policy)
broke the fair zone allocation policy on UP with these hunks.

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6e5e8f7..fb99081 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1612,6 +1612,9 @@ again:
        }

        __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
+       if (zone_page_state(zone, NR_ALLOC_BATCH) == 0 &&
+           !zone_is_fair_depleted(zone))
+               zone_set_flag(zone, ZONE_FAIR_DEPLETED);

        __count_zone_vm_events(PGALLOC, zone, 1 << order);
        zone_statistics(preferred_zone, zone, gfp_flags);
@@ -1966,8 +1985,10 @@ zonelist_scan:
                if (alloc_flags & ALLOC_FAIR) {
                        if (!zone_local(preferred_zone, zone))
                                break;
-                       if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
+                       if (zone_is_fair_depleted(zone)) {
+                               nr_fair_skipped++;
                                continue;
+                       }
                }

The problem is that a <= check was replaced with a ==. On SMP it doesn't
matter because negative values are returned as zero due to per-CPU drift
which is not possible in the UP case. Vlastimil Babka correctly pointed
out that this can be negative due to high-order allocations. This patch
fixes the problem.

Reported-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/page_alloc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 18cee0d..cd4c05c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1612,7 +1612,7 @@ again:
 	}
 
 	__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
-	if (zone_page_state(zone, NR_ALLOC_BATCH) == 0 &&
+	if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0 &&
 	    !zone_is_fair_depleted(zone))
 		zone_set_flag(zone, ZONE_FAIR_DEPLETED);
 

  reply	other threads:[~2014-09-05 10:14 UTC|newest]

Thread overview: 49+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-07-09  8:13 [PATCH 0/5] Reduce sequential read overhead Mel Gorman
2014-07-09  8:13 ` Mel Gorman
2014-07-09  8:13 ` [PATCH 1/6] mm: pagemap: Avoid unnecessary overhead when tracepoints are deactivated Mel Gorman
2014-07-09  8:13   ` Mel Gorman
2014-07-10 12:01   ` Johannes Weiner
2014-07-10 12:01     ` Johannes Weiner
2014-07-09  8:13 ` [PATCH 2/6] mm: Rearrange zone fields into read-only, page alloc, statistics and page reclaim lines Mel Gorman
2014-07-09  8:13   ` Mel Gorman
2014-07-10 12:06   ` Johannes Weiner
2014-07-10 12:06     ` Johannes Weiner
2014-07-09  8:13 ` [PATCH 3/6] mm: Move zone->pages_scanned into a vmstat counter Mel Gorman
2014-07-09  8:13   ` Mel Gorman
2014-07-10 12:08   ` Johannes Weiner
2014-07-10 12:08     ` Johannes Weiner
2014-07-09  8:13 ` [PATCH 4/6] mm: vmscan: Only update per-cpu thresholds for online CPU Mel Gorman
2014-07-09  8:13   ` Mel Gorman
2014-07-10 12:09   ` Johannes Weiner
2014-07-10 12:09     ` Johannes Weiner
2014-07-09  8:13 ` [PATCH 5/6] mm: page_alloc: Abort fair zone allocation policy when remotes nodes are encountered Mel Gorman
2014-07-09  8:13   ` Mel Gorman
2014-07-10 12:14   ` Johannes Weiner
2014-07-10 12:14     ` Johannes Weiner
2014-07-10 12:44     ` Mel Gorman
2014-07-10 12:44       ` Mel Gorman
2014-07-09  8:13 ` [PATCH 6/6] mm: page_alloc: Reduce cost of the fair zone allocation policy Mel Gorman
2014-07-09  8:13   ` Mel Gorman
2014-07-10 12:18   ` Johannes Weiner
2014-07-10 12:18     ` Johannes Weiner
2014-08-08 15:27   ` Vlastimil Babka
2014-08-08 15:27     ` Vlastimil Babka
2014-08-11 12:12     ` Mel Gorman
2014-08-11 12:12       ` Mel Gorman
2014-08-11 12:34       ` Vlastimil Babka
2014-08-11 12:34         ` Vlastimil Babka
2014-09-02 14:01         ` Johannes Weiner
2014-09-02 14:01           ` Johannes Weiner
2014-09-05 10:14           ` Mel Gorman [this message]
2014-09-05 10:14             ` [PATCH] mm: page_alloc: Fix setting of ZONE_FAIR_DEPLETED on UP Mel Gorman
2014-09-07  6:32             ` Leon Romanovsky
2014-09-07  6:32               ` Leon Romanovsky
2014-09-08 11:57               ` [PATCH] mm: page_alloc: Fix setting of ZONE_FAIR_DEPLETED on UP v2 Mel Gorman
2014-09-08 11:57                 ` Mel Gorman
2014-09-09  8:17                 ` Leon Romanovsky
2014-09-09 19:53                 ` Andrew Morton
2014-09-09 19:53                   ` Andrew Morton
2014-09-10  9:16                   ` Mel Gorman
2014-09-10  9:16                     ` Mel Gorman
2014-09-10 20:32                     ` Johannes Weiner
2014-09-10 20:32                       ` Johannes Weiner

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=20140905101451.GF17501@suse.de \
    --to=mgorman@suse.de \
    --cc=akpm@linux-foundation.org \
    --cc=hannes@cmpxchg.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=vbabka@suse.cz \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.