mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-06 10:57:46 +00:00
mm/vmscan.c: prevent useless kswapd loops
commitdffcac2cb8
upstream. 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:e716f2eb24
("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> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
parent
c854d9b6ef
commit
27ce6c2675
1 changed files with 15 additions and 12 deletions
27
mm/vmscan.c
27
mm/vmscan.c
|
@ -3599,19 +3599,18 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
|
|||
}
|
||||
|
||||
/*
|
||||
* 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,
|
||||
|
@ -3752,7 +3751,7 @@ static int kswapd(void *p)
|
|||
|
||||
/* 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;
|
||||
|
||||
|
@ -3806,8 +3805,12 @@ 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;
|
||||
|
|
Loading…
Reference in a new issue