summaryrefslogtreecommitdiffstats
path: root/mm/vmscan.c
diff options
context:
space:
mode:
authorShakeel Butt <shakeelb@google.com>2019-07-05 00:14:42 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2019-07-05 04:12:07 +0200
commitdffcac2cb88e4ec5906235d64a83d802580b119e (patch)
tree7d01bcf1accc132eb338f2a107d00ff74156c134 /mm/vmscan.c
parentfs/userfaultfd.c: disable irqs for fault_pending and event locks (diff)
downloadlinux-dffcac2cb88e4ec5906235d64a83d802580b119e.tar.xz
linux-dffcac2cb88e4ec5906235d64a83d802580b119e.zip
mm/vmscan.c: prevent useless kswapd loops
In production we have noticed hard lockups on large machines running large jobs due to kswaps hoarding lru lock within isolate_lru_pages when sc->reclaim_idx is 0 which is a small zone. The lru was couple hundred GiBs and the condition (page_zonenum(page) > sc->reclaim_idx) in isolate_lru_pages() was basically skipping GiBs of pages while holding the LRU spinlock with interrupt disabled. On further inspection, it seems like there are two issues: (1) If kswapd on the return from balance_pgdat() could not sleep (i.e. node is still unbalanced), the classzone_idx is unintentionally set to 0 and the whole reclaim cycle of kswapd will try to reclaim only the lowest and smallest zone while traversing the whole memory. (2) Fundamentally isolate_lru_pages() is really bad when the allocation has woken kswapd for a smaller zone on a very large machine running very large jobs. It can hoard the LRU spinlock while skipping over 100s of GiBs of pages. This patch only fixes (1). (2) needs a more fundamental solution. To fix (1), in the kswapd context, if pgdat->kswapd_classzone_idx is invalid use the classzone_idx of the previous kswapd loop otherwise use the one the waker has requested. Link: http://lkml.kernel.org/r/20190701201847.251028-1-shakeelb@google.com Fixes: e716f2eb24de ("mm, vmscan: prevent kswapd sleeping prematurely due to mismatched classzone_idx") Signed-off-by: Shakeel Butt <shakeelb@google.com> Reviewed-by: Yang Shi <yang.shi@linux.alibaba.com> Acked-by: Mel Gorman <mgorman@techsingularity.net> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Hillf Danton <hdanton@sina.com> Cc: Roman Gushchin <guro@fb.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/vmscan.c')
-rw-r--r--mm/vmscan.c27
1 files changed, 15 insertions, 12 deletions
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7889f583ced9..910e02c793ff 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3644,19 +3644,18 @@ out:
}
/*
- * pgdat->kswapd_classzone_idx is the highest zone index that a recent
- * allocation request woke kswapd for. When kswapd has not woken recently,
- * the value is MAX_NR_ZONES which is not a valid index. This compares a
- * given classzone and returns it or the highest classzone index kswapd
- * was recently woke for.
+ * The pgdat->kswapd_classzone_idx is used to pass the highest zone index to be
+ * reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is not
+ * a valid index then either kswapd runs for first time or kswapd couldn't sleep
+ * after previous reclaim attempt (node is still unbalanced). In that case
+ * return the zone index of the previous kswapd reclaim cycle.
*/
static enum zone_type kswapd_classzone_idx(pg_data_t *pgdat,
- enum zone_type classzone_idx)
+ enum zone_type prev_classzone_idx)
{
if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES)
- return classzone_idx;
-
- return max(pgdat->kswapd_classzone_idx, classzone_idx);
+ return prev_classzone_idx;
+ return pgdat->kswapd_classzone_idx;
}
static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
@@ -3797,7 +3796,7 @@ kswapd_try_sleep:
/* Read the new order and classzone_idx */
alloc_order = reclaim_order = pgdat->kswapd_order;
- classzone_idx = kswapd_classzone_idx(pgdat, 0);
+ classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
pgdat->kswapd_order = 0;
pgdat->kswapd_classzone_idx = MAX_NR_ZONES;
@@ -3851,8 +3850,12 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order,
if (!cpuset_zone_allowed(zone, gfp_flags))
return;
pgdat = zone->zone_pgdat;
- pgdat->kswapd_classzone_idx = kswapd_classzone_idx(pgdat,
- classzone_idx);
+
+ if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES)
+ pgdat->kswapd_classzone_idx = classzone_idx;
+ else
+ 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;