From: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
To: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: kosaki.motohiro@jp.fujitsu.com,
"linux-mm@kvack.org" <linux-mm@kvack.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"akpm@linux-foundation.org" <akpm@linux-foundation.org>,
cl@linux-foundation.org, rientjes@google.com
Subject: Re: [BUGFIX][PATCH] oom-kill: fix NUMA consraint check with nodemask v2
Date: Tue, 10 Nov 2009 16:24:22 +0900 (JST) [thread overview]
Message-ID: <20091110162121.361B.A69D9226@jp.fujitsu.com> (raw)
In-Reply-To: <20091106090202.dc2472b3.kamezawa.hiroyu@jp.fujitsu.com>
Hi
> ===================================================================
> --- mmotm-2.6.32-Nov2.orig/mm/oom_kill.c
> +++ mmotm-2.6.32-Nov2/mm/oom_kill.c
> @@ -196,27 +196,40 @@ unsigned long badness(struct task_struct
> /*
> * Determine the type of allocation constraint.
> */
> +#ifdef CONFIG_NUMA
> static inline enum oom_constraint constrained_alloc(struct zonelist *zonelist,
> - gfp_t gfp_mask)
> + gfp_t gfp_mask, nodemask_t *nodemask)
> {
> -#ifdef CONFIG_NUMA
> struct zone *zone;
> struct zoneref *z;
> enum zone_type high_zoneidx = gfp_zone(gfp_mask);
> - nodemask_t nodes = node_states[N_HIGH_MEMORY];
> + int ret = CONSTRAINT_NONE;
>
> - for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
> - if (cpuset_zone_allowed_softwall(zone, gfp_mask))
> - node_clear(zone_to_nid(zone), nodes);
> - else
> + /*
> + * The nodemask here is a nodemask passed to alloc_pages(). Now,
> + * cpuset doesn't use this nodemask for its hardwall/softwall/hierarchy
> + * feature. Then, only mempolicy use this nodemask.
> + */
> + if (nodemask && nodes_equal(*nodemask, node_states[N_HIGH_MEMORY]))
> + ret = CONSTRAINT_MEMORY_POLICY;
!nodes_equal() ?
> +
> + /* Check this allocation failure is caused by cpuset's wall function */
> + for_each_zone_zonelist_nodemask(zone, z, zonelist,
> + high_zoneidx, nodemask)
> + if (!cpuset_zone_allowed_softwall(zone, gfp_mask))
> return CONSTRAINT_CPUSET;
If cpuset and MPOL_BIND are both used, Probably CONSTRAINT_MEMORY_POLICY is
better choice.
>
> - if (!nodes_empty(nodes))
> - return CONSTRAINT_MEMORY_POLICY;
> -#endif
> + /* __GFP_THISNODE never calls OOM.*/
>
> + return ret;
> +}
> +#else
> +static inline enum oom_constraint constrained_alloc(struct zonelist *zonelist,
> + gfp_t gfp_mask, nodemask_t *nodemask)
> +{
> return CONSTRAINT_NONE;
> }
> +#endif
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2009-11-10 7:24 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-11-04 8:09 [BUGFIX][PATCH] oom-kill: fix NUMA consraint check with nodemask KAMEZAWA Hiroyuki
2009-11-06 0:02 ` [BUGFIX][PATCH] oom-kill: fix NUMA consraint check with nodemask v2 KAMEZAWA Hiroyuki
2009-11-10 7:24 ` KOSAKI Motohiro [this message]
2009-11-10 7:24 ` KAMEZAWA Hiroyuki
2009-11-10 7:39 ` KOSAKI Motohiro
2009-11-10 7:40 ` KAMEZAWA Hiroyuki
2009-11-10 8:03 ` Daisuke Nishimura
2009-11-10 8:17 ` KAMEZAWA Hiroyuki
2009-11-11 2:24 ` [BUGFIX][PATCH] oom-kill: fix NUMA consraint check with nodemask v3 KAMEZAWA Hiroyuki
2009-11-11 2:36 ` KOSAKI Motohiro
2009-11-11 2:49 ` David Rientjes
2009-11-11 3:02 ` KOSAKI Motohiro
2009-11-11 3:10 ` KAMEZAWA Hiroyuki
2009-11-11 3:14 ` David Rientjes
2009-11-11 3:23 ` KOSAKI Motohiro
2009-11-11 3:27 ` David Rientjes
2009-11-11 3:04 ` KAMEZAWA Hiroyuki
2009-11-11 4:45 ` [BUGFIX][PATCH] oom-kill: fix NUMA consraint check with nodemask v4 KAMEZAWA Hiroyuki
2009-11-11 5:28 ` [BUGFIX][PATCH] oom-kill: fix NUMA consraint check with nodemask v4.1 KAMEZAWA Hiroyuki
2009-11-11 5:58 ` David Rientjes
2009-11-11 6:20 ` KAMEZAWA Hiroyuki
2009-11-11 6:26 ` David Rientjes
2009-11-11 6:34 ` [BUGFIX][PATCH] oom-kill: fix NUMA consraint check with nodemask v4.2 KAMEZAWA Hiroyuki
2009-11-11 7:32 ` David Rientjes
2009-11-18 0:11 ` David Rientjes
2009-11-18 0:58 ` KAMEZAWA Hiroyuki
2009-11-18 2:13 ` David Rientjes
2009-12-15 1:16 ` Andrew Morton
2009-12-15 1:32 ` KAMEZAWA Hiroyuki
2009-12-15 1:38 ` KOSAKI Motohiro
2009-12-15 4:30 ` David Rientjes
2009-12-15 4:35 ` KAMEZAWA Hiroyuki
2009-12-15 4:54 ` David Rientjes
2009-12-15 5:19 ` KOSAKI Motohiro
2009-12-17 22:21 ` David Rientjes
2009-12-18 4:30 ` KOSAKI Motohiro
2009-12-18 10:04 ` David Rientjes
2009-12-15 4:57 ` KAMEZAWA Hiroyuki
2009-12-15 4:43 ` KAMEZAWA Hiroyuki
2009-12-15 4:57 ` David Rientjes
2009-12-15 5:09 ` KAMEZAWA Hiroyuki
2009-12-17 22:23 ` David Rientjes
2009-12-17 23:33 ` KAMEZAWA Hiroyuki
2009-12-15 4:47 ` KOSAKI Motohiro
2009-12-15 5:03 ` David Rientjes
2009-11-18 1:41 ` Daisuke Nishimura
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20091110162121.361B.A69D9226@jp.fujitsu.com \
--to=kosaki.motohiro@jp.fujitsu.com \
--cc=akpm@linux-foundation.org \
--cc=cl@linux-foundation.org \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=rientjes@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox