On Wed, 14 Jan 2015 17:06:59 +0530 Vinayak Menon <vinme...@codeaurora.org>
wrote:
> It is observed that sometimes multiple tasks get blocked for long
> in the congestion_wait loop below, in shrink_inactive_list. This
> is because of vm_stat values not being synced.
>
> (__schedule) from [<c0a03328>]
> (schedule_timeout) from [<c0a04940>]
> (io_schedule_timeout) from [<c01d585c>]
> (congestion_wait) from [<c01cc9d8>]
> (shrink_inactive_list) from [<c01cd034>]
> (shrink_zone) from [<c01cdd08>]
> (try_to_free_pages) from [<c01c442c>]
> (__alloc_pages_nodemask) from [<c01f1884>]
> (new_slab) from [<c09fcf60>]
> (__slab_alloc) from [<c01f1a6c>]
>
> In one such instance, zone_page_state(zone, NR_ISOLATED_FILE)
> had returned 14, zone_page_state(zone, NR_INACTIVE_FILE)
> returned 92, and GFP_IOFS was set, and this resulted
> in too_many_isolated returning true. But one of the CPU's
> pageset vm_stat_diff had NR_ISOLATED_FILE as "-14". So the
> actual isolated count was zero. As there weren't any more
> updates to NR_ISOLATED_FILE and vmstat_update deffered work
> had not been scheduled yet, 7 tasks were spinning in the
> congestion wait loop for around 4 seconds, in the direct
> reclaim path.
>
> This patch uses zone_page_state_snapshot instead, but restricts
> its usage to avoid performance penalty.
Seems reasonable.
>
> ...
>
> @@ -1516,15 +1531,18 @@ shrink_inactive_list(unsigned long nr_to_scan, struct
> lruvec *lruvec,
> unsigned long nr_immediate = 0;
> isolate_mode_t isolate_mode = 0;
> int file = is_file_lru(lru);
> + int safe = 0;
> struct zone *zone = lruvec_zone(lruvec);
> struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
>
> - while (unlikely(too_many_isolated(zone, file, sc))) {
> + while (unlikely(too_many_isolated(zone, file, sc, safe))) {
> congestion_wait(BLK_RW_ASYNC, HZ/10);
>
> /* We are about to die and free our memory. Return now. */
> if (fatal_signal_pending(current))
> return SWAP_CLUSTER_MAX;
> +
> + safe = 1;
> }
But here and under the circumstances you describe, we'll call
congestion_wait() a single time. That shouldn't have occurred.
So how about we put the fallback logic into too_many_isolated() itself?
From: Andrew Morton <a...@linux-foundation.org>
Subject: mm-vmscan-fix-the-page-state-calculation-in-too_many_isolated-fix
Move the zone_page_state_snapshot() fallback logic into
too_many_isolated(), so shrink_inactive_list() doesn't incorrectly call
congestion_wait().
Cc: Johannes Weiner <han...@cmpxchg.org>
Cc: Mel Gorman <mgor...@suse.de>
Cc: Michal Hocko <mho...@suse.cz>
Cc: Minchan Kim <minc...@kernel.org>
Cc: Vinayak Menon <vinme...@codeaurora.org>
Cc: Vladimir Davydov <vdavy...@parallels.com>
Signed-off-by: Andrew Morton <a...@linux-foundation.org>
---
mm/vmscan.c | 23 +++++++++++------------
1 file changed, 11 insertions(+), 12 deletions(-)
diff -puN
mm/vmscan.c~mm-vmscan-fix-the-page-state-calculation-in-too_many_isolated-fix
mm/vmscan.c
---
a/mm/vmscan.c~mm-vmscan-fix-the-page-state-calculation-in-too_many_isolated-fix
+++ a/mm/vmscan.c
@@ -1402,7 +1402,7 @@ int isolate_lru_page(struct page *page)
}
static int __too_many_isolated(struct zone *zone, int file,
- struct scan_control *sc, int safe)
+ struct scan_control *sc, int safe)
{
unsigned long inactive, isolated;
@@ -1435,7 +1435,7 @@ static int __too_many_isolated(struct zo
* unnecessary swapping, thrashing and OOM.
*/
static int too_many_isolated(struct zone *zone, int file,
- struct scan_control *sc, int safe)
+ struct scan_control *sc)
{
if (current_is_kswapd())
return 0;
@@ -1443,12 +1443,14 @@ static int too_many_isolated(struct zone
if (!global_reclaim(sc))
return 0;
- if (unlikely(__too_many_isolated(zone, file, sc, 0))) {
- if (safe)
- return __too_many_isolated(zone, file, sc, safe);
- else
- return 1;
- }
+ /*
+ * __too_many_isolated(safe=0) is fast but inaccurate, because it
+ * doesn't account for the vm_stat_diff[] counters. So if it looks
+ * like too_many_isolated() is about to return true, fall back to the
+ * slower, more accurate zone_page_state_snapshot().
+ */
+ if (unlikely(__too_many_isolated(zone, file, sc, 0)))
+ return __too_many_isolated(zone, file, sc, safe);
return 0;
}
@@ -1540,18 +1542,15 @@ shrink_inactive_list(unsigned long nr_to
unsigned long nr_immediate = 0;
isolate_mode_t isolate_mode = 0;
int file = is_file_lru(lru);
- int safe = 0;
struct zone *zone = lruvec_zone(lruvec);
struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
- while (unlikely(too_many_isolated(zone, file, sc, safe))) {
+ while (unlikely(too_many_isolated(zone, file, sc))) {
congestion_wait(BLK_RW_ASYNC, HZ/10);
/* We are about to die and free our memory. Return now. */
if (fatal_signal_pending(current))
return SWAP_CLUSTER_MAX;
-
- safe = 1;
}
lru_add_drain();
_
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
