summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorMel Gorman <mgorman@techsingularity.net>2017-05-03 14:53:41 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2017-05-03 15:52:09 -0700
commit631b6e083ec328f7203f466ba839d296aee70c36 (patch)
treee53940e93f57d569ad3b12f60f3e8c2597b6555f
parent333b0a459c0e1b4faa3127ec6209a4d984408b95 (diff)
downloadlinux-631b6e083ec328f7203f466ba839d296aee70c36.tar.bz2
mm, vmscan: only clear pgdat congested/dirty/writeback state when balanced
A pgdat tracks if recent reclaim encountered too many dirty, writeback or congested pages. The flags control whether kswapd writes pages back from reclaim context, tags pages for immediate reclaim when IO completes, whether processes block on wait_iff_congested and whether kswapd blocks when too many pages marked for immediate reclaim are encountered. The state is cleared in a check function with side-effects. With the patch "mm, vmscan: fix zone balance check in prepare_kswapd_sleep", the timing of when the bits get cleared changed. Due to the way the check works, it'll clear the bits if ZONE_DMA is balanced for a GFP_DMA allocation because it does not account for lowmem reserves properly. For the simoop workload, kswapd is not stalling when it should due to the premature clearing, writing pages from reclaim context like crazy and generally being unhelpful. This patch resets the pgdat bits related to page reclaim only when kswapd is going to sleep. The comparison with simoop is then 4.11.0-rc1 4.11.0-rc1 4.11.0-rc1 vanilla fixcheck-v2 clear-v2 Amean p50-Read 21670074.18 ( 0.00%) 20464344.18 ( 5.56%) 19786774.76 ( 8.69%) Amean p95-Read 25456267.64 ( 0.00%) 25721423.64 ( -1.04%) 24101956.27 ( 5.32%) Amean p99-Read 29369064.73 ( 0.00%) 30174230.76 ( -2.74%) 27691872.71 ( 5.71%) Amean p50-Write 1390.30 ( 0.00%) 1395.28 ( -0.36%) 1011.91 ( 27.22%) Amean p95-Write 412901.57 ( 0.00%) 37737.74 ( 90.86%) 34874.98 ( 91.55%) Amean p99-Write 6668722.09 ( 0.00%) 666489.04 ( 90.01%) 575449.60 ( 91.37%) Amean p50-Allocation 78714.31 ( 0.00%) 86286.22 ( -9.62%) 84246.26 ( -7.03%) Amean p95-Allocation 175533.51 ( 0.00%) 351812.27 (-100.42%) 400058.43 (-127.91%) Amean p99-Allocation 247003.02 ( 0.00%) 6291171.56 (-2447.00%) 10905600.00 (-4315.17%) Read latency is improved, write latency is mostly improved but allocation latency is regressed. kswapd is still reclaiming inefficiently, pages are being written back from writeback context and a host of other issues. However, given the change, it needed to be spelled out why the side-effect was moved. Link: http://lkml.kernel.org/r/20170309075657.25121-3-mgorman@techsingularity.net Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Shantanu Goel <sgoel01@yahoo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--mm/vmscan.c20
1 files changed, 11 insertions, 9 deletions
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1860bfab02c5..8c553fa0d800 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3056,17 +3056,17 @@ static bool zone_balanced(struct zone *zone, int order, int classzone_idx)
if (!zone_watermark_ok_safe(zone, order, mark, classzone_idx))
return false;
- /*
- * If any eligible zone is balanced then the node is not considered
- * to be congested or dirty
- */
- clear_bit(PGDAT_CONGESTED, &zone->zone_pgdat->flags);
- clear_bit(PGDAT_DIRTY, &zone->zone_pgdat->flags);
- clear_bit(PGDAT_WRITEBACK, &zone->zone_pgdat->flags);
-
return true;
}
+/* Clear pgdat state for congested, dirty or under writeback. */
+static void clear_pgdat_congested(pg_data_t *pgdat)
+{
+ clear_bit(PGDAT_CONGESTED, &pgdat->flags);
+ clear_bit(PGDAT_DIRTY, &pgdat->flags);
+ clear_bit(PGDAT_WRITEBACK, &pgdat->flags);
+}
+
/*
* Prepare kswapd for sleeping. This verifies that there are no processes
* waiting in throttle_direct_reclaim() and that watermarks have been met.
@@ -3103,8 +3103,10 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx)
if (!managed_zone(zone))
continue;
- if (zone_balanced(zone, order, classzone_idx))
+ if (zone_balanced(zone, order, classzone_idx)) {
+ clear_pgdat_congested(pgdat);
return true;
+ }
}
return false;