Subject: + mm-vmscan-stall-page-reclaim-after-a-list-of-pages-have-been-processed-v3.patch added to -mm tree
To: mgorman@xxxxxxx,Valdis.Kletnieks@xxxxxx,dormando@xxxxxxxxx,hannes@xxxxxxxxxxx,jslaby@xxxxxxx,kamezawa.hiroyu@xxxxxxxxxxxxxx,mhocko@xxxxxxx,riel@xxxxxxxxxx,trond.myklebust@xxxxxxxxxx,zcalusic@xxxxxxxxxxx
From: akpm@xxxxxxxxxxxxxxxxxxxx
Date: Thu, 30 May 2013 12:55:00 -0700
The patch titled
Subject: mm: vmscan: stall page reclaim after a list of pages have been processed
has been added to the -mm tree. Its filename is
mm-vmscan-stall-page-reclaim-after-a-list-of-pages-have-been-processed-v3.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Mel Gorman <mgorman@xxxxxxx>
Subject: mm: vmscan: stall page reclaim after a list of pages have been processed
Commit "mm: vmscan: Block kswapd if it is encountering pages under
writeback" blocks page reclaim if it encounters pages under writeback
marked for immediate reclaim. It blocks while pages are still isolated
from the LRU which is unnecessary. This patch defers the blocking until
after the isolated pages have been processed and tidies up some of the
comments.
Signed-off-by: Mel Gorman <mgorman@xxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: Jiri Slaby <jslaby@xxxxxxx>
Cc: Valdis Kletnieks <Valdis.Kletnieks@xxxxxx>
Cc: Zlatko Calusic <zcalusic@xxxxxxxxxxx>
Cc: dormando <dormando@xxxxxxxxx>
Cc: Trond Myklebust <trond.myklebust@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/vmscan.c | 49 +++++++++++++++++++++++++++++++++----------------
1 file changed, 33 insertions(+), 16 deletions(-)
diff -puN mm/vmscan.c~mm-vmscan-stall-page-reclaim-after-a-list-of-pages-have-been-processed-v3 mm/vmscan.c
--- a/mm/vmscan.c~mm-vmscan-stall-page-reclaim-after-a-list-of-pages-have-been-processed-v3
+++ a/mm/vmscan.c
@@ -697,6 +697,7 @@ static unsigned long shrink_page_list(st
enum ttu_flags ttu_flags,
unsigned long *ret_nr_unqueued_dirty,
unsigned long *ret_nr_writeback,
+ unsigned long *ret_nr_immediate,
bool force_reclaim)
{
LIST_HEAD(ret_pages);
@@ -707,6 +708,7 @@ static unsigned long shrink_page_list(st
unsigned long nr_congested = 0;
unsigned long nr_reclaimed = 0;
unsigned long nr_writeback = 0;
+ unsigned long nr_immediate = 0;
cond_resched();
@@ -773,8 +775,8 @@ static unsigned long shrink_page_list(st
* IO can complete. Waiting on the page itself risks an
* indefinite stall if it is impossible to writeback the
* page due to IO error or disconnected storage so instead
- * block for HZ/10 or until some IO completes then clear the
- * ZONE_WRITEBACK flag to recheck if the condition exists.
+ * note that the LRU is being scanned too quickly and the
+ * caller can stall after page list has been processed.
*
* 2) Global reclaim encounters a page, memcg encounters a
* page that is not marked for immediate reclaim or
@@ -804,10 +806,8 @@ static unsigned long shrink_page_list(st
if (current_is_kswapd() &&
PageReclaim(page) &&
zone_is_reclaim_writeback(zone)) {
- unlock_page(page);
- congestion_wait(BLK_RW_ASYNC, HZ/10);
- zone_clear_flag(zone, ZONE_WRITEBACK);
- goto keep;
+ nr_immediate++;
+ goto keep_locked;
/* Case 2 above */
} else if (global_reclaim(sc) ||
@@ -1033,6 +1033,7 @@ keep:
mem_cgroup_uncharge_end();
*ret_nr_unqueued_dirty += nr_unqueued_dirty;
*ret_nr_writeback += nr_writeback;
+ *ret_nr_immediate += nr_immediate;
return nr_reclaimed;
}
@@ -1044,7 +1045,7 @@ unsigned long reclaim_clean_pages_from_l
.priority = DEF_PRIORITY,
.may_unmap = 1,
};
- unsigned long ret, dummy1, dummy2;
+ unsigned long ret, dummy1, dummy2, dummy3;
struct page *page, *next;
LIST_HEAD(clean_pages);
@@ -1057,7 +1058,7 @@ unsigned long reclaim_clean_pages_from_l
ret = shrink_page_list(&clean_pages, zone, &sc,
TTU_UNMAP|TTU_IGNORE_ACCESS,
- &dummy1, &dummy2, true);
+ &dummy1, &dummy2, &dummy3, true);
list_splice(&clean_pages, page_list);
__mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret);
return ret;
@@ -1353,6 +1354,7 @@ shrink_inactive_list(unsigned long nr_to
unsigned long nr_taken;
unsigned long nr_unqueued_dirty = 0;
unsigned long nr_writeback = 0;
+ unsigned long nr_immediate = 0;
isolate_mode_t isolate_mode = 0;
int file = is_file_lru(lru);
struct zone *zone = lruvec_zone(lruvec);
@@ -1394,7 +1396,8 @@ shrink_inactive_list(unsigned long nr_to
return 0;
nr_reclaimed = shrink_page_list(&page_list, zone, sc, TTU_UNMAP,
- &nr_unqueued_dirty, &nr_writeback, false);
+ &nr_unqueued_dirty, &nr_writeback, &nr_immediate,
+ false);
spin_lock_irq(&zone->lru_lock);
@@ -1447,14 +1450,28 @@ shrink_inactive_list(unsigned long nr_to
}
/*
- * Similarly, if many dirty pages are encountered that are not
- * currently being written then flag that kswapd should start
- * writing back pages and stall to give a chance for flushers
- * to catch up.
+ * memcg will stall in page writeback so only consider forcibly
+ * stalling for global reclaim
*/
- if (global_reclaim(sc) && nr_unqueued_dirty == nr_taken) {
- congestion_wait(BLK_RW_ASYNC, HZ/10);
- zone_set_flag(zone, ZONE_TAIL_LRU_DIRTY);
+ if (global_reclaim(sc)) {
+ /*
+ * If dirty pages are scanned that are not queued for IO, it
+ * implies that flushers are not keeping up. In this case, flag
+ * the zone ZONE_TAIL_LRU_DIRTY and kswapd will start writing
+ * pages from reclaim context. It will forcibly stall in the
+ * next check.
+ */
+ if (nr_unqueued_dirty == nr_taken)
+ zone_set_flag(zone, ZONE_TAIL_LRU_DIRTY);
+
+ /*
+ * In addition, if kswapd scans pages marked marked for
+ * immediate reclaim and under writeback (nr_immediate), it
+ * implies that pages are cycling through the LRU faster than
+ * they are written so also forcibly stall.
+ */
+ if (nr_unqueued_dirty == nr_taken || nr_immediate)
+ congestion_wait(BLK_RW_ASYNC, HZ/10);
}
trace_mm_vmscan_lru_shrink_inactive(zone->zone_pgdat->node_id,
_
Patches currently in -mm which might be from mgorman@xxxxxxx are
linux-next.patch
mm-page_alloc-factor-out-setting-of-pcp-high-and-pcp-batch.patch
mm-page_alloc-prevent-concurrent-updaters-of-pcp-batch-and-high.patch
mm-page_alloc-insert-memory-barriers-to-allow-async-update-of-pcp-batch-and-high.patch
mm-page_alloc-protect-pcp-batch-accesses-with-access_once.patch
mm-page_alloc-convert-zone_pcp_update-to-rely-on-memory-barriers-instead-of-stop_machine.patch
mm-page_alloc-when-handling-percpu_pagelist_fraction-dont-unneedly-recalulate-high.patch
mm-page_alloc-factor-setup_pageset-into-pageset_init-and-pageset_set_batch.patch
mm-page_alloc-relocate-comment-to-be-directly-above-code-it-refers-to.patch
mm-page_alloc-factor-zone_pageset_init-out-of-setup_zone_pageset.patch
mm-page_alloc-in-zone_pcp_update-uze-zone_pageset_init.patch
mm-page_alloc-rename-setup_pagelist_highmark-to-match-naming-of-pageset_set_batch.patch
mm-vmscan-limit-the-number-of-pages-kswapd-reclaims-at-each-priority.patch
mm-vmscan-obey-proportional-scanning-requirements-for-kswapd.patch
mm-vmscan-flatten-kswapd-priority-loop.patch
mm-vmscan-decide-whether-to-compact-the-pgdat-based-on-reclaim-progress.patch
mm-vmscan-do-not-allow-kswapd-to-scan-at-maximum-priority.patch
mm-vmscan-have-kswapd-writeback-pages-based-on-dirty-pages-encountered-not-priority.patch
mm-vmscan-block-kswapd-if-it-is-encountering-pages-under-writeback.patch
mm-vmscan-block-kswapd-if-it-is-encountering-pages-under-writeback-fix.patch
mm-vmscan-block-kswapd-if-it-is-encountering-pages-under-writeback-fix-2.patch
mm-vmscan-check-if-kswapd-should-writepage-once-per-pgdat-scan.patch
mm-vmscan-move-logic-from-balance_pgdat-to-kswapd_shrink_zone.patch
mm-vmscan-stall-page-reclaim-and-writeback-pages-based-on-dirty-writepage-pages-encountered-v3.patch
mm-vmscan-stall-page-reclaim-after-a-list-of-pages-have-been-processed-v3.patch
mm-vmscan-set-zone-flags-before-blocking.patch
mm-vmscan-move-direct-reclaim-wait_iff_congested-into-shrink_list.patch
mm-vmscan-treat-pages-marked-for-immediate-reclaim-as-zone-congestion.patch
mm-vmscan-take-page-buffers-dirty-and-locked-state-into-account-v3.patch
fs-nfs-inform-the-vm-about-pages-being-committed-or-unstable.patch
mm-add-tracepoints-for-lru-activation-and-insertions.patch
mm-pagevec-defer-deciding-what-lru-to-add-a-page-to-until-pagevec-drain-time.patch
mm-activate-pagelru-pages-on-mark_page_accessed-if-page-is-on-local-pagevec.patch
mm-remove-lru-parameter-from-__pagevec_lru_add-and-remove-parts-of-pagevec-api.patch
mm-remove-lru-parameter-from-__lru_cache_add-and-lru_cache_add_lru.patch
mm-memmap_init_zone-performance-improvement.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
