The patch titled
mm: do batched scans for mem_cgroup
has been added to the -mm tree. Its filename is
mm-do-batched-scans-for-mem_cgroup.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 ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: mm: do batched scans for mem_cgroup
From: Wu Fengguang <fengguang.wu@xxxxxxxxx>
For mem_cgroup, shrink_zone() may call shrink_list() with nr_to_scan=1, in
which case shrink_list() _still_ calls isolate_pages() with the much
larger SWAP_CLUSTER_MAX. It effectively scales up the inactive list scan
rate by up to 32 times.
For example, with 16k inactive pages and DEF_PRIORITY=12, (16k >> 12)=4.
So when shrink_zone() expects to scan 4 pages in the active/inactive list,
the active list will be scanned 4 pages, while the inactive list will be
(over) scanned SWAP_CLUSTER_MAX=32 pages in effect. And that could break
the balance between the two lists.
It can further impact the scan of anon active list, due to the anon
active/inactive ratio rebalance logic in balance_pgdat()/shrink_zone():
inactive anon list over scanned => inactive_anon_is_low() == TRUE
=> shrink_active_list()
=> active anon list over scanned
So the end result may be
- anon inactive => over scanned
- anon active => over scanned (maybe not as much)
- file inactive => over scanned
- file active => under scanned (relatively)
The accesses to nr_saved_scan are not lock protected and so not 100%
accurate, however we can tolerate small errors and the resulted small
imbalanced scan rates between zones.
Cc: Rik van Riel <riel@xxxxxxxxxx>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Acked-by: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx>
Reviewed-by: Minchan Kim <minchan.kim@xxxxxxxxx>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Signed-off-by: Wu Fengguang <fengguang.wu@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/mmzone.h | 6 +++++-
mm/page_alloc.c | 2 +-
mm/vmscan.c | 20 +++++++++++---------
3 files changed, 17 insertions(+), 11 deletions(-)
diff -puN include/linux/mmzone.h~mm-do-batched-scans-for-mem_cgroup include/linux/mmzone.h
--- a/include/linux/mmzone.h~mm-do-batched-scans-for-mem_cgroup
+++ a/include/linux/mmzone.h
@@ -273,6 +273,11 @@ struct zone_reclaim_stat {
*/
unsigned long recent_rotated[2];
unsigned long recent_scanned[2];
+
+ /*
+ * accumulated for batching
+ */
+ unsigned long nr_saved_scan[NR_LRU_LISTS];
};
struct zone {
@@ -327,7 +332,6 @@ struct zone {
spinlock_t lru_lock;
struct zone_lru {
struct list_head list;
- unsigned long nr_saved_scan; /* accumulated for batching */
} lru[NR_LRU_LISTS];
struct zone_reclaim_stat reclaim_stat;
diff -puN mm/page_alloc.c~mm-do-batched-scans-for-mem_cgroup mm/page_alloc.c
--- a/mm/page_alloc.c~mm-do-batched-scans-for-mem_cgroup
+++ a/mm/page_alloc.c
@@ -3830,7 +3830,7 @@ static void __paginginit free_area_init_
zone_pcp_init(zone);
for_each_lru(l) {
INIT_LIST_HEAD(&zone->lru[l].list);
- zone->lru[l].nr_saved_scan = 0;
+ zone->reclaim_stat.nr_saved_scan[l] = 0;
}
zone->reclaim_stat.recent_rotated[0] = 0;
zone->reclaim_stat.recent_rotated[1] = 0;
diff -puN mm/vmscan.c~mm-do-batched-scans-for-mem_cgroup mm/vmscan.c
--- a/mm/vmscan.c~mm-do-batched-scans-for-mem_cgroup
+++ a/mm/vmscan.c
@@ -1586,6 +1586,7 @@ static void shrink_zone(int priority, st
enum lru_list l;
unsigned long nr_reclaimed = sc->nr_reclaimed;
unsigned long swap_cluster_max = sc->swap_cluster_max;
+ struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
int noswap = 0;
/* If we have no swap space, do not bother scanning anon pages. */
@@ -1605,12 +1606,9 @@ static void shrink_zone(int priority, st
scan >>= priority;
scan = (scan * percent[file]) / 100;
}
- if (scanning_global_lru(sc))
- nr[l] = nr_scan_try_batch(scan,
- &zone->lru[l].nr_saved_scan,
- swap_cluster_max);
- else
- nr[l] = scan;
+ nr[l] = nr_scan_try_batch(scan,
+ &reclaim_stat->nr_saved_scan[l],
+ swap_cluster_max);
}
while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
@@ -2220,6 +2218,7 @@ static void shrink_all_zones(unsigned lo
{
struct zone *zone;
unsigned long nr_reclaimed = 0;
+ struct zone_reclaim_stat *reclaim_stat;
for_each_populated_zone(zone) {
enum lru_list l;
@@ -2236,11 +2235,14 @@ static void shrink_all_zones(unsigned lo
l == LRU_ACTIVE_FILE))
continue;
- zone->lru[l].nr_saved_scan += (lru_pages >> prio) + 1;
- if (zone->lru[l].nr_saved_scan >= nr_pages || pass > 3) {
+ reclaim_stat = get_reclaim_stat(zone, sc);
+ reclaim_stat->nr_saved_scan[l] +=
+ (lru_pages >> prio) + 1;
+ if (reclaim_stat->nr_saved_scan[l]
+ >= nr_pages || pass > 3) {
unsigned long nr_to_scan;
- zone->lru[l].nr_saved_scan = 0;
+ reclaim_stat->nr_saved_scan[l] = 0;
nr_to_scan = min(nr_pages, lru_pages);
nr_reclaimed += shrink_list(l, nr_to_scan, zone,
sc, prio);
_
Patches currently in -mm which might be from fengguang.wu@xxxxxxxxx are
origin.patch
linux-next.patch
mm-fix-for-infinite-churning-of-mlocked-pages.patch
readahead-add-blk_run_backing_dev.patch
readahead-add-blk_run_backing_dev-fix.patch
readahead-add-blk_run_backing_dev-fix-fix-2.patch
mm-clean-up-page_remove_rmap.patch
mm-oom-analysis-add-per-zone-statistics-to-show_free_areas.patch
mm-oom-analysis-add-buffer-cache-information-to-show_free_areas.patch
mm-oom-analysis-add-shmem-vmstat.patch
mm-shrink_inactive_list-nr_scan-accounting-fix-fix.patch
mm-vmstat-add-isolate-pages.patch
mm-vmstat-add-isolate-pages-fix.patch
vmscan-throttle-direct-reclaim-when-too-many-pages-are-isolated-already.patch
mm-remove-__addsub_zone_page_state.patch
mm-count-only-reclaimable-lru-pages-v2.patch
vmscan-move-clearpageactive-from-move_active_pages-to-shrink_active_list.patch
vmscan-kill-unnecessary-page-flag-test.patch
vmscan-kill-unnecessary-prefetch.patch
ksm-add-mmu_notifier-set_pte_at_notify.patch
ksm-first-tidy-up-madvise_vma.patch
ksm-define-madv_mergeable-and-madv_unmergeable.patch
ksm-the-mm-interface-to-ksm.patch
ksm-no-debug-in-page_dup_rmap.patch
ksm-identify-pageksm-pages.patch
ksm-kernel-samepage-merging.patch
ksm-prevent-mremap-move-poisoning.patch
ksm-change-copyright-message.patch
ksm-change-ksm-nice-level-to-be-5.patch
mm-balance_dirty_pages-reduce-calls-to-global_page_state-to-reduce-cache-references.patch
mm-do-batched-scans-for-mem_cgroup.patch
documentation-vm-gitignore-add-page-types.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
