Techwizz/kernel-fxtec-pro1x
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

revert "memcg, vmscan: do not fall into reclaim-all pass too quickly"

Browse source 
Revert commit e975de998b ("memcg, vmscan: do not fall into reclaim-all
pass too quickly")

I merged this prematurely - Michal and Johannes still disagree about the
overall design direction and the future remains unclear.

Cc: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Andrew Morton 2013-09-24 15:27:33 -07:00 committed by Linus Torvalds
parent 99d7a8824a
commit 20ba27f52e
1 changed files with 2 additions and 17 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

19
mm/vmscan.c
View file

@ -2176,11 +2176,10 @@ static inline bool should_continue_reclaim(struct zone *zone,
}
}
static int
static void
__shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim)
{
unsigned long nr_reclaimed, nr_scanned;
int groups_scanned = 0;
do {
struct mem_cgroup *root = sc->target_mem_cgroup;
@ -2198,7 +2197,6 @@ __shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim)
while ((memcg = mem_cgroup_iter_cond(root, memcg, &reclaim, filter))) {
struct lruvec *lruvec;
groups_scanned++;
lruvec = mem_cgroup_zone_lruvec(zone, memcg);
shrink_lruvec(lruvec, sc);
@ -2226,8 +2224,6 @@ __shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim)
} while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed,
sc->nr_scanned - nr_scanned, sc));
return groups_scanned;
}
@ -2235,19 +2231,8 @@ static void shrink_zone(struct zone *zone, struct scan_control *sc)
{
bool do_soft_reclaim = mem_cgroup_should_soft_reclaim(sc);
unsigned long nr_scanned = sc->nr_scanned;
int scanned_groups;
scanned_groups = __shrink_zone(zone, sc, do_soft_reclaim);
/*
* memcg iterator might race with other reclaimer or start from
* a incomplete tree walk so the tree walk in __shrink_zone
* might have missed groups that are above the soft limit. Try
* another loop to catch up with others. Do it just once to
* prevent from reclaim latencies when other reclaimers always
* preempt this one.
*/
if (do_soft_reclaim && !scanned_groups)
__shrink_zone(zone, sc, do_soft_reclaim);
__shrink_zone(zone, sc, do_soft_reclaim);
/*
* No group is over the soft limit or those that are do not have