summaryrefslogtreecommitdiffstats
path: root/mm/vmscan.c
diff options
context:
space:
mode:
authorMinchan Kim <minchan@kernel.org>2016-07-28 15:47:40 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-07-28 16:07:41 -0700
commit91dcade47a3d0e7c31464ef05f56c08e92a0e9c2 (patch)
tree2a8e2875018e9e13452f9f49edcd60c90ed5e818 /mm/vmscan.c
parentd7f05528eedb047efe2288cff777676b028747b6 (diff)
downloadlinux-stable-91dcade47a3d0e7c31464ef05f56c08e92a0e9c2.tar.gz
linux-stable-91dcade47a3d0e7c31464ef05f56c08e92a0e9c2.tar.bz2
linux-stable-91dcade47a3d0e7c31464ef05f56c08e92a0e9c2.zip
mm: bail out in shrink_inactive_list()
With node-lru, if there are enough reclaimable pages in highmem but nothing in lowmem, VM can try to shrink inactive list although the requested zone is lowmem. The problem is that if the inactive list is full of highmem pages then a direct reclaimer searching for a lowmem page waste CPU scanning uselessly. It just burns out CPU. Even, many direct reclaimers are stalled by too_many_isolated if lots of parallel reclaimer are going on although there are no reclaimable memory in inactive list. I tried the experiment 4 times in 32bit 2G 8 CPU KVM machine to get elapsed time. hackbench 500 process 2 = Old = 1st: 289s 2nd: 310s 3rd: 112s 4th: 272s = Now = 1st: 31s 2nd: 132s 3rd: 162s 4th: 50s. [akpm@linux-foundation.org: fixes per Mel] Link: http://lkml.kernel.org/r/1469433119-1543-1-git-send-email-minchan@kernel.org Signed-off-by: Minchan Kim <minchan@kernel.org> Acked-by: Mel Gorman <mgorman@techsingularity.net> 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/vmscan.c')
-rw-r--r--mm/vmscan.c27
1 files changed, 27 insertions, 0 deletions
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 0294ab34f475..650d26832569 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1652,6 +1652,30 @@ static int current_may_throttle(void)
bdi_write_congested(current->backing_dev_info);
}
+static bool inactive_reclaimable_pages(struct lruvec *lruvec,
+ struct scan_control *sc, enum lru_list lru)
+{
+ int zid;
+ struct zone *zone;
+ int file = is_file_lru(lru);
+ struct pglist_data *pgdat = lruvec_pgdat(lruvec);
+
+ if (!global_reclaim(sc))
+ return true;
+
+ for (zid = sc->reclaim_idx; zid >= 0; zid--) {
+ zone = &pgdat->node_zones[zid];
+ if (!populated_zone(zone))
+ continue;
+
+ if (zone_page_state_snapshot(zone, NR_ZONE_LRU_BASE +
+ LRU_FILE * file) >= SWAP_CLUSTER_MAX)
+ return true;
+ }
+
+ return false;
+}
+
/*
* shrink_inactive_list() is a helper for shrink_node(). It returns the number
* of reclaimed pages
@@ -1674,6 +1698,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
+ if (!inactive_reclaimable_pages(lruvec, sc, lru))
+ return 0;
+
while (unlikely(too_many_isolated(pgdat, file, sc))) {
congestion_wait(BLK_RW_ASYNC, HZ/10);