From: Vlastimil Babka <vbabka@suse.cz>
To: David Rientjes <rientjes@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Christoph Lameter <cl@linux.com>,
Pekka Enberg <penberg@kernel.org>,
Joonsoo Kim <iamjoonsoo.kim@lge.com>,
Johannes Weiner <hannes@cmpxchg.org>,
Mel Gorman <mgorman@suse.de>, Pravin Shelar <pshelar@nicira.com>,
Jarno Rajahalme <jrajahalme@nicira.com>,
Greg Thelen <gthelen@google.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
netdev@vger.kernel.org, dev@openvswitch.org
Subject: Re: [patch 1/2] mm: remove GFP_THISNODE
Date: Fri, 27 Feb 2015 23:52:56 +0100 [thread overview]
Message-ID: <54F0F548.6070109@suse.cz> (raw)
In-Reply-To: <alpine.DEB.2.10.1502271428320.7225@chino.kir.corp.google.com>
On 27.2.2015 23:31, David Rientjes wrote:
> On Fri, 27 Feb 2015, Vlastimil Babka wrote:
>
>>> Do you see any issues with either patch 1/2 or patch 2/2 besides the
>>> s/GFP_TRANSHUGE/GFP_THISNODE/ that is necessary on the changelog?
>> Well, my point is, what if the node we are explicitly trying to allocate
>> hugepage on, is in fact not allowed by our cpuset? This could happen in the page
>> fault case, no? Although in a weird configuration when process can (and really
>> gets scheduled to run) on a node where it is not allowed to allocate from...
>>
> If the process is running a node that is not allowed by the cpuset, then
> alloc_hugepage_vma() now fails with VM_FAULT_FALLBACK. That was the
> intended policy change of commit 077fcf116c8c ("mm/thp: allocate
> transparent hugepages on local node").
Ah, right, didn't realize that mempolicy also takes that into account.
Thanks for removing the exception anyway.
>
> [ alloc_hugepage_vma() should probably be using numa_mem_id() instead for
> memoryless node platforms. ]
--
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>
WARNING: multiple messages have this Message-ID (diff)
From: Vlastimil Babka <vbabka@suse.cz>
To: David Rientjes <rientjes@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Christoph Lameter <cl@linux.com>,
Pekka Enberg <penberg@kernel.org>,
Joonsoo Kim <iamjoonsoo.kim@lge.com>,
Johannes Weiner <hannes@cmpxchg.org>,
Mel Gorman <mgorman@suse.de>, Pravin Shelar <pshelar@nicira.com>,
Jarno Rajahalme <jrajahalme@nicira.com>,
Greg Thelen <gthelen@google.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
netdev@vger.kernel.org, dev@openvswitch.org
Subject: Re: [patch 1/2] mm: remove GFP_THISNODE
Date: Fri, 27 Feb 2015 23:52:56 +0100 [thread overview]
Message-ID: <54F0F548.6070109@suse.cz> (raw)
In-Reply-To: <alpine.DEB.2.10.1502271428320.7225@chino.kir.corp.google.com>
On 27.2.2015 23:31, David Rientjes wrote:
> On Fri, 27 Feb 2015, Vlastimil Babka wrote:
>
>>> Do you see any issues with either patch 1/2 or patch 2/2 besides the
>>> s/GFP_TRANSHUGE/GFP_THISNODE/ that is necessary on the changelog?
>> Well, my point is, what if the node we are explicitly trying to allocate
>> hugepage on, is in fact not allowed by our cpuset? This could happen in the page
>> fault case, no? Although in a weird configuration when process can (and really
>> gets scheduled to run) on a node where it is not allowed to allocate from...
>>
> If the process is running a node that is not allowed by the cpuset, then
> alloc_hugepage_vma() now fails with VM_FAULT_FALLBACK. That was the
> intended policy change of commit 077fcf116c8c ("mm/thp: allocate
> transparent hugepages on local node").
Ah, right, didn't realize that mempolicy also takes that into account.
Thanks for removing the exception anyway.
>
> [ alloc_hugepage_vma() should probably be using numa_mem_id() instead for
> memoryless node platforms. ]
next prev parent reply other threads:[~2015-02-27 22:53 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-02-26 0:23 [patch 1/2] mm: remove GFP_THISNODE David Rientjes
2015-02-26 0:23 ` David Rientjes
2015-02-26 0:56 ` Christoph Lameter
2015-02-26 0:56 ` Christoph Lameter
2015-02-26 1:04 ` David Rientjes
2015-02-26 1:04 ` David Rientjes
2015-02-26 8:30 ` Vlastimil Babka
2015-02-26 8:30 ` Vlastimil Babka
2015-02-27 3:09 ` David Rientjes
2015-02-27 3:09 ` David Rientjes
2015-02-27 7:34 ` Vlastimil Babka
2015-02-27 7:34 ` Vlastimil Babka
2015-02-27 22:03 ` David Rientjes
2015-02-27 22:03 ` David Rientjes
2015-02-27 22:19 ` Vlastimil Babka
2015-02-27 22:19 ` Vlastimil Babka
2015-02-27 22:31 ` David Rientjes
2015-02-27 22:31 ` David Rientjes
2015-02-27 22:52 ` Vlastimil Babka [this message]
2015-02-27 22:52 ` Vlastimil Babka
[not found] ` <alpine.DEB.2.10.1502251621010.10303-X6Q0R45D7oAcqpCFd4KODRPsWskHk0ljAL8bYrjMMd8@public.gmane.org>
2015-02-27 22:16 ` [patch v2 1/3] " David Rientjes
2015-02-27 22:16 ` David Rientjes
2015-02-27 22:16 ` David Rientjes
2015-02-27 22:17 ` [patch v2 2/3] mm, thp: really limit transparent hugepage allocation to local node David Rientjes
2015-02-27 22:17 ` David Rientjes
[not found] ` <alpine.DEB.2.10.1502271416580.7225-X6Q0R45D7oAcqpCFd4KODRPsWskHk0ljAL8bYrjMMd8@public.gmane.org>
2015-03-02 13:47 ` Vlastimil Babka
2015-03-02 13:47 ` Vlastimil Babka
2015-03-02 13:47 ` Vlastimil Babka
2015-02-27 22:17 ` [patch v2 3/3] kernel, cpuset: remove exception for __GFP_THISNODE David Rientjes
2015-02-27 22:17 ` David Rientjes
2015-03-02 13:47 ` Vlastimil Babka
2015-03-02 13:47 ` Vlastimil Babka
2015-02-27 22:53 ` [patch v2 1/3] mm: remove GFP_THISNODE Christoph Lameter
2015-02-27 22:53 ` Christoph Lameter
2015-02-28 3:21 ` David Rientjes
2015-02-28 3:21 ` David Rientjes
[not found] ` <alpine.DEB.2.10.1502271415510.7225-X6Q0R45D7oAcqpCFd4KODRPsWskHk0ljAL8bYrjMMd8@public.gmane.org>
2015-03-02 13:46 ` Vlastimil Babka
2015-03-02 13:46 ` Vlastimil Babka
2015-03-02 13:46 ` Vlastimil Babka
2015-03-02 15:46 ` Christoph Lameter
2015-03-02 15:46 ` Christoph Lameter
2015-03-02 16:02 ` Vlastimil Babka
2015-03-02 16:02 ` Vlastimil Babka
2015-03-02 16:08 ` Christoph Lameter
2015-03-02 16:08 ` Christoph Lameter
[not found] ` <alpine.DEB.2.11.1503021007030.6245-gkYfJU5Cukgdnm+yROfE0A@public.gmane.org>
2015-03-02 16:23 ` Vlastimil Babka
2015-03-02 16:23 ` Vlastimil Babka
2015-03-02 16:23 ` Vlastimil Babka
2015-03-02 20:40 ` David Rientjes
2015-03-02 20:40 ` David Rientjes
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=54F0F548.6070109@suse.cz \
--to=vbabka@suse.cz \
--cc=akpm@linux-foundation.org \
--cc=cl@linux.com \
--cc=dev@openvswitch.org \
--cc=gthelen@google.com \
--cc=hannes@cmpxchg.org \
--cc=iamjoonsoo.kim@lge.com \
--cc=jrajahalme@nicira.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=netdev@vger.kernel.org \
--cc=penberg@kernel.org \
--cc=pshelar@nicira.com \
--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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.