| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Wed, 31 Aug 2011 10:19:57 -0700
From: Ying Han <yinghan@...gle.com>
To: Johannes Weiner <jweiner@...hat.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>,
Rik van Riel <riel@...hat.com>,
KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>,
KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>,
Daisuke Nishimura <nishimura@....nes.nec.co.jp>,
Balbir Singh <bsingharora@...il.com>, linux-mm@...ck.org,
linux-kernel@...r.kernel.org
Subject: Re: [patch] memcg: skip scanning active lists based on individual size
On Wed, Aug 31, 2011 at 2:08 AM, Johannes Weiner <jweiner@...hat.com> wrote:
> Reclaim decides to skip scanning an active list when the corresponding
> inactive list is above a certain size in comparison to leave the
> assumed working set alone while there are still enough reclaim
> candidates around.
>
> The memcg implementation of comparing those lists instead reports
> whether the whole memcg is low on the requested type of inactive
> pages, considering all nodes and zones.
>
> This can lead to an oversized active list not being scanned because of
> the state of the other lists in the memcg, as well as an active list
> being scanned while its corresponding inactive list has enough pages.
>
> Not only is this wrong, it's also a scalability hazard, because the
> global memory state over all nodes and zones has to be gathered for
> each memcg and zone scanned.
>
> Make these calculations purely based on the size of the two LRU lists
> that are actually affected by the outcome of the decision.
>
> Signed-off-by: Johannes Weiner <jweiner@...hat.com>
> Cc: Rik van Riel <riel@...hat.com>
> Cc: KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>
> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
> Cc: Daisuke Nishimura <nishimura@....nes.nec.co.jp>
> Cc: Balbir Singh <bsingharora@...il.com>
> ---
> include/linux/memcontrol.h | 10 +++++---
> mm/memcontrol.c | 51 ++++++++++++++-----------------------------
> mm/vmscan.c | 4 +-
> 3 files changed, 25 insertions(+), 40 deletions(-)
>
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index 343bd76..cbb45ce 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -105,8 +105,10 @@ extern void mem_cgroup_end_migration(struct mem_cgroup *mem,
> /*
> * For memory reclaim.
> */
> -int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg);
> -int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg);
> +int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg,
> + struct zone *zone);
> +int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg,
> + struct zone *zone);
> int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
> unsigned long mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg,
> int nid, int zid, unsigned int lrumask);
> @@ -292,13 +294,13 @@ static inline bool mem_cgroup_disabled(void)
> }
>
> static inline int
> -mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg)
> +mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg, struct zone *zone)
> {
> return 1;
> }
>
> static inline int
> -mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg)
> +mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg, struct zone *zone)
> {
> return 1;
> }
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 3508777..d63dfb2 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -1101,15 +1101,19 @@ int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
> return ret;
> }
>
> -static int calc_inactive_ratio(struct mem_cgroup *memcg, unsigned long *present_pages)
> +int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg, struct zone *zone)
> {
> - unsigned long active;
> + unsigned long inactive_ratio;
> + int nid = zone_to_nid(zone);
> + int zid = zone_idx(zone);
> unsigned long inactive;
> + unsigned long active;
> unsigned long gb;
> - unsigned long inactive_ratio;
>
> - inactive = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_INACTIVE_ANON));
> - active = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_ACTIVE_ANON));
> + inactive = mem_cgroup_zone_nr_lru_pages(memcg, nid, zid,
> + BIT(LRU_INACTIVE_ANON));
> + active = mem_cgroup_zone_nr_lru_pages(memcg, nid, zid,
> + BIT(LRU_ACTIVE_ANON));
>
> gb = (inactive + active) >> (30 - PAGE_SHIFT);
> if (gb)
> @@ -1117,39 +1121,20 @@ static int calc_inactive_ratio(struct mem_cgroup *memcg, unsigned long *present_
> else
> inactive_ratio = 1;
>
> - if (present_pages) {
> - present_pages[0] = inactive;
> - present_pages[1] = active;
> - }
> -
> - return inactive_ratio;
> + return inactive * inactive_ratio < active;
> }
>
> -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;
> -}
> -
> -int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg)
> +int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg, struct zone *zone)
> {
> unsigned long active;
> unsigned long inactive;
> + int zid = zone_idx(zone);
> + int nid = zone_to_nid(zone);
>
> - inactive = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_INACTIVE_FILE));
> - active = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_ACTIVE_FILE));
> + inactive = mem_cgroup_zone_nr_lru_pages(memcg, nid, zid,
> + BIT(LRU_INACTIVE_FILE));
> + active = mem_cgroup_zone_nr_lru_pages(memcg, nid, zid,
> + BIT(LRU_ACTIVE_FILE));
>
> return (active > inactive);
> }
> @@ -4188,8 +4173,6 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
> }
>
> #ifdef CONFIG_DEBUG_VM
> - cb->fill(cb, "inactive_ratio", calc_inactive_ratio(mem_cont, NULL));
> -
> {
> int nid, zid;
> struct mem_cgroup_per_zone *mz;
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 6588746..a023778 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -1699,7 +1699,7 @@ static int inactive_anon_is_low(struct zone *zone, struct scan_control *sc)
> if (scanning_global_lru(sc))
> low = inactive_anon_is_low_global(zone);
> else
> - low = mem_cgroup_inactive_anon_is_low(sc->mem_cgroup);
> + low = mem_cgroup_inactive_anon_is_low(sc->mem_cgroup, zone);
> return low;
> }
> #else
> @@ -1742,7 +1742,7 @@ static int inactive_file_is_low(struct zone *zone, struct scan_control *sc)
> if (scanning_global_lru(sc))
> low = inactive_file_is_low_global(zone);
> else
> - low = mem_cgroup_inactive_file_is_low(sc->mem_cgroup);
> + low = mem_cgroup_inactive_file_is_low(sc->mem_cgroup, zone);
> return low;
> }
>
> --
> 1.7.6
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@...ck.org. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
> Don't email: <a href=mailto:"dont@...ck.org"> email@...ck.org </a>
>
Reviewed-by: Ying Han <yinghan@...gle.com>
--Ying
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists