The patch titled
memcg: fix calclation of active_ratio
has been added to the -mm tree. Its filename is
memcg-fix-calclation-of-active_ratio.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: memcg: fix calclation of active_ratio
From: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Currently, inactive_ratio of memcg is calculated at setting limit.
because page_alloc.c does so and current implementation is straightforward
porting.
However, memcg introduced hierarchy feature recently. In hierarchy
restriction, memory limit is not only decided memory.limit_in_bytes of
current cgroup, but also parent limit and sibling memory usage.
Then, The optimal inactive_ratio is changed frequently. So, everytime
calculation is better.
Tested-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/memcontrol.h | 3 -
mm/memcontrol.c | 64 ++++++++++++++++-------------------
mm/vmscan.c | 2 -
3 files changed, 33 insertions(+), 36 deletions(-)
diff -puN include/linux/memcontrol.h~memcg-fix-calclation-of-active_ratio include/linux/memcontrol.h
--- a/include/linux/memcontrol.h~memcg-fix-calclation-of-active_ratio
+++ a/include/linux/memcontrol.h
@@ -97,8 +97,7 @@ extern void mem_cgroup_note_reclaim_prio
int priority);
extern void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem,
int priority);
-int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg,
- struct zone *zone);
+int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg);
unsigned long mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg,
struct zone *zone,
enum lru_list lru);
diff -puN mm/memcontrol.c~memcg-fix-calclation-of-active_ratio mm/memcontrol.c
--- a/mm/memcontrol.c~memcg-fix-calclation-of-active_ratio
+++ a/mm/memcontrol.c
@@ -166,9 +166,6 @@ struct mem_cgroup {
unsigned int swappiness;
-
- unsigned int inactive_ratio;
-
/*
* statistics. This must be placed at the end of memcg.
*/
@@ -432,15 +429,43 @@ void mem_cgroup_record_reclaim_priority(
spin_unlock(&mem->reclaim_param_lock);
}
-int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg, struct zone *zone)
+static int calc_inactive_ratio(struct mem_cgroup *memcg, unsigned long *present_pages)
{
unsigned long active;
unsigned long inactive;
+ unsigned long gb;
+ unsigned long inactive_ratio;
inactive = mem_cgroup_get_all_zonestat(memcg, LRU_INACTIVE_ANON);
active = mem_cgroup_get_all_zonestat(memcg, LRU_ACTIVE_ANON);
- if (inactive * memcg->inactive_ratio < active)
+ gb = (inactive + active) >> (30 - PAGE_SHIFT);
+ if (gb)
+ inactive_ratio = int_sqrt(10 * gb);
+ else
+ inactive_ratio = 1;
+
+ if (present_pages) {
+ present_pages[0] = inactive;
+ present_pages[1] = active;
+ }
+
+ return inactive_ratio;
+}
+
+int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg)
+{
+ unsigned long active;
+ unsigned long inactive;
+ unsigned long present_pages[2];
+ unsigned long inactive_ratio;
+
+ inactive_ratio = calc_inactive_ratio(memcg, present_pages);
+
+ inactive = present_pages[0];
+ active = present_pages[1];
+
+ if (inactive * inactive_ratio < active)
return 1;
return 0;
@@ -1427,29 +1452,6 @@ int mem_cgroup_shrink_usage(struct mm_st
return 0;
}
-/*
- * The inactive anon list should be small enough that the VM never has to
- * do too much work, but large enough that each inactive page has a chance
- * to be referenced again before it is swapped out.
- *
- * this calculation is straightforward porting from
- * page_alloc.c::setup_per_zone_inactive_ratio().
- * it describe more detail.
- */
-static void mem_cgroup_set_inactive_ratio(struct mem_cgroup *memcg)
-{
- unsigned int gb, ratio;
-
- gb = res_counter_read_u64(&memcg->res, RES_LIMIT) >> 30;
- if (gb)
- ratio = int_sqrt(10 * gb);
- else
- ratio = 1;
-
- memcg->inactive_ratio = ratio;
-
-}
-
static DEFINE_MUTEX(set_limit_mutex);
static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
@@ -1491,9 +1493,6 @@ static int mem_cgroup_resize_limit(struc
if (!progress) retry_count--;
}
- if (!ret)
- mem_cgroup_set_inactive_ratio(memcg);
-
return ret;
}
@@ -1853,7 +1852,7 @@ static int mem_control_stat_show(struct
}
#ifdef CONFIG_DEBUG_VM
- cb->fill(cb, "inactive_ratio", mem_cont->inactive_ratio);
+ cb->fill(cb, "inactive_ratio", calc_inactive_ratio(mem_cont, NULL));
{
int nid, zid;
@@ -2145,7 +2144,6 @@ mem_cgroup_create(struct cgroup_subsys *
res_counter_init(&mem->res, NULL);
res_counter_init(&mem->memsw, NULL);
}
- mem_cgroup_set_inactive_ratio(mem);
mem->last_scanned_child = NULL;
spin_lock_init(&mem->reclaim_param_lock);
diff -puN mm/vmscan.c~memcg-fix-calclation-of-active_ratio mm/vmscan.c
--- a/mm/vmscan.c~memcg-fix-calclation-of-active_ratio
+++ a/mm/vmscan.c
@@ -1387,7 +1387,7 @@ static int inactive_anon_is_low(struct z
if (scanning_global_lru(sc))
low = inactive_anon_is_low_global(zone);
else
- low = mem_cgroup_inactive_anon_is_low(sc->mem_cgroup, zone);
+ low = mem_cgroup_inactive_anon_is_low(sc->mem_cgroup);
return low;
}
_
Patches currently in -mm which might be from kosaki.motohiro@xxxxxxxxxxxxxx are
linux-next.patch
mm-report-the-pagesize-backing-a-vma-in-proc-pid-smaps.patch
mm-report-the-mmu-pagesize-in-proc-pid-smaps.patch
oom-fix-zone_scan_mutex-name.patch
mm-get-rid-of-pagevec_release_nonlru.patch
cleanup-get-rid-of-ifdef-config_migration.patch
mm-more-likely-reclaim-madv_sequential-mappings.patch
mm-make-page_lock_anon_vma-static.patch
memcg-reclaim-shouldnt-change-zone-recent_rotated-statistics.patch
mm-make-init_section_page_cgroup-static.patch
mm-make-maddr-__iomem.patch
mm-make-mem_cgroup_resize_limit-static.patch
mm-make-scan_all_zones_unevictable_pages-static.patch
mm-make-scan_zone_unevictable_pages-static.patch
mm-make-setup_per_zone_inactive_ratio-static.patch
mm-make-vread-and-vwrite-declaration.patch
vmscan-bail-out-of-direct-reclaim-after-swap_cluster_max-pages.patch
vmscan-improve-reclaim-throughput-to-bail-out-patch.patch
mm-kill-zone_is_near_oom.patch
mm-make-get_user_pages-interruptible.patch
mm-make-get_user_pages-interruptible-mmotm-ignore-sigkill-in-get_user_pages-during-munlock.patch
softirq-introduce-statistics-for-softirq.patch
proc-export-statistics-for-softirq-to-proc.patch
proc-update-document-for-proc-softirqs-and-proc-stat.patch
devices-cgroup-allow-mkfifo.patch
memcg-new-force_empty-to-free-pages-under-group-fix.patch
memcg-new-force_empty-to-free-pages-under-group-fix-fix.patch
memcg-revert-gfp-mask-fix.patch
memcg-check-group-leader-fix.patch
memcg-memoryswap-controller-fix-limit-check.patch
memcg-swapout-refcnt-fix.patch
memcg-hierarchy-avoid-unnecessary-reclaim.patch
inactive_anon_is_low-move-to-vmscan.patch
mm-introduce-zone_reclaim-struct.patch
mm-add-zone-nr_pages-helper-function.patch
mm-make-get_scan_ratio-safe-for-memcg.patch
memcg-add-null-check-to-page_cgroup_zoneinfo.patch
memcg-add-inactive_anon_is_low.patch
memcg-add-inactive_anon_is_low-vmscan-style-cleanup.patch
memcg-add-mem_cgroup_zone_nr_pages.patch
memcg-add-zone_reclaim_stat.patch
memcg-add-zone_reclaim_stat-reclaim-stat-trivial-fixes.patch
memcg-remove-mem_cgroup_cal_reclaim.patch
memcg-show-reclaim-stat.patch
memcg-rename-scan-global-lru.patch
memcg-protect-prev_priority.patch
memcg-swappiness.patch
memcg-fix-calclation-of-active_ratio.patch
memcg-explain-details-and-test-document.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
