summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorNeilBrown <neilb@suse.de>2014-06-05 01:07:42 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2014-06-05 01:54:01 +0200
commit399ba0b95670c70aaaa3f4f1623ea9e76c391681 (patch)
tree6db21b9d0b97a6015654f6806eb4101c61ea949d /mm
parentmm: numa: add migrated transhuge pages to LRU the same way as base pages (diff)
downloadlinux-399ba0b95670c70aaaa3f4f1623ea9e76c391681.tar.xz
linux-399ba0b95670c70aaaa3f4f1623ea9e76c391681.zip
mm/vmscan.c: avoid throttling reclaim for loop-back nfsd threads
When a loopback NFS mount is active and the backing device for the NFS mount becomes congested, that can impose throttling delays on the nfsd threads. These delays significantly reduce throughput and so the NFS mount remains congested. This results in a livelock and the reduced throughput persists. This livelock has been found in testing with the 'wait_iff_congested' call, and could possibly be caused by the 'congestion_wait' call. This livelock is similar to the deadlock which justified the introduction of PF_LESS_THROTTLE, and the same flag can be used to remove this livelock. To minimise the impact of the change, we still throttle nfsd when the filesystem it is writing to is congested, but not when some separate filesystem (e.g. the NFS filesystem) is congested. Signed-off-by: NeilBrown <neilb@suse.de> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/vmscan.c19
1 files changed, 17 insertions, 2 deletions
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 53e4534885ad..5a8776eb0f43 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1439,6 +1439,19 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list)
}
/*
+ * If a kernel thread (such as nfsd for loop-back mounts) services
+ * a backing device by writing to the page cache it sets PF_LESS_THROTTLE.
+ * In that case we should only throttle if the backing device it is
+ * writing to is congested. In other cases it is safe to throttle.
+ */
+static int current_may_throttle(void)
+{
+ return !(current->flags & PF_LESS_THROTTLE) ||
+ current->backing_dev_info == NULL ||
+ bdi_write_congested(current->backing_dev_info);
+}
+
+/*
* shrink_inactive_list() is a helper for shrink_zone(). It returns the number
* of reclaimed pages
*/
@@ -1566,7 +1579,8 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
* implies that pages are cycling through the LRU faster than
* they are written so also forcibly stall.
*/
- if (nr_unqueued_dirty == nr_taken || nr_immediate)
+ if ((nr_unqueued_dirty == nr_taken || nr_immediate) &&
+ current_may_throttle())
congestion_wait(BLK_RW_ASYNC, HZ/10);
}
@@ -1575,7 +1589,8 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
* 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())
+ if (!sc->hibernation_mode && !current_is_kswapd() &&
+ current_may_throttle())
wait_iff_congested(zone, BLK_RW_ASYNC, HZ/10);
trace_mm_vmscan_lru_shrink_inactive(zone->zone_pgdat->node_id,