| 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
| ||
|
Message-Id: <20090717085108.A8FD.A69D9226@jp.fujitsu.com>
Date: Fri, 17 Jul 2009 08:53:46 +0900 (JST)
From: KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>
To: Wu Fengguang <fengguang.wu@...el.com>
Cc: kosaki.motohiro@...fujitsu.com, Rik van Riel <riel@...hat.com>,
Christoph Lameter <cl@...ux-foundation.org>,
Peter Zijlstra <peterz@...radead.org>,
Minchan Kim <minchan.kim@...il.com>,
Johannes Weiner <hannes@...xchg.org>,
David Howells <dhowells@...hat.com>,
Andrew Morton <akpm@...ux-foundation.org>,
LKML <linux-kernel@...r.kernel.org>,
"tytso@....edu" <tytso@....edu>,
"linux-mm@...ck.org" <linux-mm@...ck.org>,
"elladan@...imo.com" <elladan@...imo.com>,
"npiggin@...e.de" <npiggin@...e.de>,
"Barnes, Jesse" <jesse.barnes@...el.com>
Subject: Re: [PATCH] mm: count only reclaimable lru pages v2
> ---
> mm: count only reclaimable lru pages
>
> global_lru_pages() / zone_lru_pages() can be used in two ways:
> - to estimate max reclaimable pages in determine_dirtyable_memory()
> - to calculate the slab scan ratio
>
> When swap is full or not present, the anon lru lists are not reclaimable
> and also won't be scanned. So the anon pages shall not be counted in both
> usage scenarios. Also rename to _reclaimable_pages: now they are counting
> the possibly reclaimable lru pages.
>
> It can greatly (and correctly) increase the slab scan rate under high memory
> pressure (when most file pages have been reclaimed and swap is full/absent),
> thus reduce false OOM kills.
>
> Acked-by: Peter Zijlstra <a.p.zijlstra@...llo.nl>
> Reviewed-by: Rik van Riel <riel@...hat.com>
> Reviewed-by: Christoph Lameter <cl@...ux-foundation.org>
> Reviewed-by: Minchan Kim <minchan.kim@...il.com>
> Cc: KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>
> Signed-off-by: Wu Fengguang <fengguang.wu@...el.com>
> ---
> include/linux/vmstat.h | 11 +-------
> mm/page-writeback.c | 5 ++-
> mm/vmscan.c | 50 ++++++++++++++++++++++++++++++---------
> 3 files changed, 44 insertions(+), 22 deletions(-)
>
> --- linux.orig/include/linux/vmstat.h
> +++ linux/include/linux/vmstat.h
> @@ -166,15 +166,8 @@ static inline unsigned long zone_page_st
> return x;
> }
>
> -extern unsigned long global_lru_pages(void);
> -
> -static inline unsigned long zone_lru_pages(struct zone *zone)
> -{
> - return (zone_page_state(zone, NR_ACTIVE_ANON)
> - + zone_page_state(zone, NR_ACTIVE_FILE)
> - + zone_page_state(zone, NR_INACTIVE_ANON)
> - + zone_page_state(zone, NR_INACTIVE_FILE));
> -}
> +extern unsigned long global_reclaimable_pages(void);
> +extern unsigned long zone_reclaimable_pages(struct zone *zone);
>
> #ifdef CONFIG_NUMA
> /*
> --- linux.orig/mm/page-writeback.c
> +++ linux/mm/page-writeback.c
> @@ -380,7 +380,8 @@ static unsigned long highmem_dirtyable_m
> struct zone *z =
> &NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
>
> - x += zone_page_state(z, NR_FREE_PAGES) + zone_lru_pages(z);
> + x += zone_page_state(z, NR_FREE_PAGES) +
> + zone_reclaimable_pages(z);
> }
> /*
> * Make sure that the number of highmem pages is never larger
> @@ -404,7 +405,7 @@ unsigned long determine_dirtyable_memory
> {
> unsigned long x;
>
> - x = global_page_state(NR_FREE_PAGES) + global_lru_pages();
> + x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages();
>
> if (!vm_highmem_is_dirtyable)
> x -= highmem_dirtyable_memory(x);
> --- linux.orig/mm/vmscan.c
> +++ linux/mm/vmscan.c
> @@ -1735,7 +1735,7 @@ static unsigned long do_try_to_free_page
> if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
> continue;
>
> - lru_pages += zone_lru_pages(zone);
> + lru_pages += zone_reclaimable_pages(zone);
> }
> }
>
> @@ -1952,7 +1952,7 @@ loop_again:
> for (i = 0; i <= end_zone; i++) {
> struct zone *zone = pgdat->node_zones + i;
>
> - lru_pages += zone_lru_pages(zone);
> + lru_pages += zone_reclaimable_pages(zone);
> }
>
> /*
> @@ -1996,7 +1996,7 @@ loop_again:
> if (zone_is_all_unreclaimable(zone))
> continue;
> if (nr_slab == 0 && zone->pages_scanned >=
> - (zone_lru_pages(zone) * 6))
> + (zone_reclaimable_pages(zone) * 6))
> zone_set_flag(zone,
> ZONE_ALL_UNRECLAIMABLE);
> /*
> @@ -2163,12 +2163,39 @@ void wakeup_kswapd(struct zone *zone, in
> wake_up_interruptible(&pgdat->kswapd_wait);
> }
>
> -unsigned long global_lru_pages(void)
> +/*
> + * The reclaimable count would be mostly accurate.
> + * The less reclaimable pages may be
> + * - mlocked pages, which will be moved to unevictable list when encountered
> + * - mapped pages, which may require several travels to be reclaimed
> + * - dirty pages, which is not "instantly" reclaimable
> + */
> +unsigned long global_reclaimable_pages(void)
> {
> - return global_page_state(NR_ACTIVE_ANON)
> - + global_page_state(NR_ACTIVE_FILE)
> - + global_page_state(NR_INACTIVE_ANON)
> - + global_page_state(NR_INACTIVE_FILE);
> + int nr;
> +
> + nr = global_page_state(NR_ACTIVE_FILE) +
> + global_page_state(NR_INACTIVE_FILE);
> +
> + if (nr_swap_pages > 0)
> + nr += global_page_state(NR_ACTIVE_ANON) +
> + global_page_state(NR_INACTIVE_ANON);
> +
> + return nr;
> +}
> +
> +unsigned long zone_reclaimable_pages(struct zone *zone)
> +{
> + int nr;
> +
> + nr = zone_page_state(zone, NR_ACTIVE_FILE) +
> + zone_page_state(zone, NR_INACTIVE_FILE);
> +
> + if (nr_swap_pages > 0)
> + nr += zone_page_state(zone, NR_ACTIVE_ANON) +
> + zone_page_state(zone, NR_INACTIVE_ANON);
> +
> + return nr;
> }
>
> #ifdef CONFIG_HIBERNATION
> @@ -2240,7 +2267,7 @@ unsigned long shrink_all_memory(unsigned
>
> current->reclaim_state = &reclaim_state;
>
> - lru_pages = global_lru_pages();
> + lru_pages = global_reclaimable_pages();
> nr_slab = global_page_state(NR_SLAB_RECLAIMABLE);
> /* If slab caches are huge, it's better to hit them first */
> while (nr_slab >= lru_pages) {
> @@ -2282,7 +2309,7 @@ unsigned long shrink_all_memory(unsigned
>
> reclaim_state.reclaimed_slab = 0;
> shrink_slab(sc.nr_scanned, sc.gfp_mask,
> - global_lru_pages());
> + global_reclaimable_pages());
> sc.nr_reclaimed += reclaim_state.reclaimed_slab;
> if (sc.nr_reclaimed >= nr_pages)
> goto out;
> @@ -2299,7 +2326,8 @@ unsigned long shrink_all_memory(unsigned
> if (!sc.nr_reclaimed) {
> do {
> reclaim_state.reclaimed_slab = 0;
> - shrink_slab(nr_pages, sc.gfp_mask, global_lru_pages());
> + shrink_slab(nr_pages, sc.gfp_mask,
> + global_reclaimable_pages());
> sc.nr_reclaimed += reclaim_state.reclaimed_slab;
> } while (sc.nr_reclaimed < nr_pages &&
> reclaim_state.reclaimed_slab > 0);
>
I feel like I already reviewed this patch past days..
Anyway,
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>
--
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