From: Andrea Arcangeli <aarcange@redhat.com>
To: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>,
Andrew Morton <akpm@linux-foundation.org>,
Mel Gorman <mgorman@suse.de>, Rik van Riel <riel@surriel.com>,
Zlatko Calusic <zcalusic@bitsync.net>,
Minchan Kim <minchan@kernel.org>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [patch v2 3/3] mm: page_alloc: fair zone allocator policy
Date: Mon, 5 Aug 2013 13:34:23 +0200 [thread overview]
Message-ID: <20130805113423.GB6703@redhat.com> (raw)
In-Reply-To: <20130805103456.GB1039@hacker.(null)>
On Mon, Aug 05, 2013 at 06:34:56PM +0800, Wanpeng Li wrote:
> Why round robin allocator don't consume ZONE_DMA?
I guess lowmem reserve reserves it all, 4GB/256(ratio)=16MB.
The only way to relax it would be 1) to account depending on memblock
types and allow only the movable ones to bypass the lowmem reserve and
prevent a change from movable type if lowmem reserve doesn't pass, 2)
use memory migration to move the movable pages from the lower zones to
the highest zone if reclaim fails if __GFP_DMA32 or __GFP_DMA is set,
or highmem is missing on 32bit kernels. The last point involving
memory migration would work similarly to compaction but it isn't black
and white, and it would cost CPU as well. The memory used by the
simple lowmem reserve mechanism is probably not significant enough to
warrant such an effort.
WARNING: multiple messages have this Message-ID (diff)
From: Andrea Arcangeli <aarcange@redhat.com>
To: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>,
Andrew Morton <akpm@linux-foundation.org>,
Mel Gorman <mgorman@suse.de>, Rik van Riel <riel@surriel.com>,
Zlatko Calusic <zcalusic@bitsync.net>,
Minchan Kim <minchan@kernel.org>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [patch v2 3/3] mm: page_alloc: fair zone allocator policy
Date: Mon, 5 Aug 2013 13:34:23 +0200 [thread overview]
Message-ID: <20130805113423.GB6703@redhat.com> (raw)
In-Reply-To: <20130805103456.GB1039@hacker.(null)>
On Mon, Aug 05, 2013 at 06:34:56PM +0800, Wanpeng Li wrote:
> Why round robin allocator don't consume ZONE_DMA?
I guess lowmem reserve reserves it all, 4GB/256(ratio)=16MB.
The only way to relax it would be 1) to account depending on memblock
types and allow only the movable ones to bypass the lowmem reserve and
prevent a change from movable type if lowmem reserve doesn't pass, 2)
use memory migration to move the movable pages from the lower zones to
the highest zone if reclaim fails if __GFP_DMA32 or __GFP_DMA is set,
or highmem is missing on 32bit kernels. The last point involving
memory migration would work similarly to compaction but it isn't black
and white, and it would cost CPU as well. The memory used by the
simple lowmem reserve mechanism is probably not significant enough to
warrant such an effort.
--
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:[~2013-08-05 11:35 UTC|newest]
Thread overview: 82+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-08-02 15:37 [patch v2 0/3] mm: improve page aging fairness between zones/nodes Johannes Weiner
2013-08-02 15:37 ` Johannes Weiner
2013-08-02 15:37 ` [patch v2 1/3] mm: vmscan: fix numa reclaim balance problem in kswapd Johannes Weiner
2013-08-02 15:37 ` Johannes Weiner
2013-08-07 14:15 ` Mel Gorman
2013-08-07 14:15 ` Mel Gorman
2013-08-02 15:37 ` [patch v2 2/3] mm: page_alloc: rearrange watermark checking in get_page_from_freelist Johannes Weiner
2013-08-02 15:37 ` Johannes Weiner
2013-08-07 14:20 ` Mel Gorman
2013-08-07 14:20 ` Mel Gorman
2013-08-02 15:37 ` [patch v2 3/3] mm: page_alloc: fair zone allocator policy Johannes Weiner
2013-08-02 15:37 ` Johannes Weiner
2013-08-02 17:51 ` Rik van Riel
2013-08-02 17:51 ` Rik van Riel
2013-08-05 1:15 ` Minchan Kim
2013-08-05 1:15 ` Minchan Kim
2013-08-05 3:43 ` Johannes Weiner
2013-08-05 3:43 ` Johannes Weiner
2013-08-05 4:48 ` Minchan Kim
2013-08-05 4:48 ` Minchan Kim
2013-08-05 5:01 ` Johannes Weiner
2013-08-05 5:01 ` Johannes Weiner
2013-08-05 10:34 ` Wanpeng Li
2013-08-05 10:34 ` Wanpeng Li
2013-08-05 11:34 ` Andrea Arcangeli [this message]
2013-08-05 11:34 ` Andrea Arcangeli
2013-08-05 13:11 ` Wanpeng Li
2013-08-05 13:11 ` Wanpeng Li
2013-08-07 14:58 ` Mel Gorman
2013-08-07 14:58 ` Mel Gorman
2013-08-07 15:37 ` Johannes Weiner
2013-08-07 15:37 ` Johannes Weiner
2013-08-08 4:16 ` Johannes Weiner
2013-08-08 4:16 ` Johannes Weiner
2013-08-08 9:21 ` Mel Gorman
2013-08-08 9:21 ` Mel Gorman
2013-08-09 18:45 ` Rik van Riel
2013-08-09 18:45 ` Rik van Riel
2013-08-16 17:07 ` Kevin Hilman
2013-08-16 17:17 ` Kevin Hilman
2013-08-16 20:18 ` Johannes Weiner
2013-08-16 20:18 ` Johannes Weiner
2013-08-16 20:18 ` Johannes Weiner
2013-08-16 21:24 ` Stephen Warren
2013-08-16 21:24 ` Stephen Warren
2013-08-16 21:24 ` Stephen Warren
2013-08-16 21:52 ` Kevin Hilman
2013-08-16 21:52 ` Kevin Hilman
2013-08-16 21:52 ` Kevin Hilman
2013-08-19 0:48 ` Stephen Rothwell
2013-08-19 0:48 ` Stephen Rothwell
2014-04-02 14:26 ` Thomas Schwinge
2014-04-02 14:26 ` Thomas Schwinge
2014-04-24 13:37 ` radeon: screen garbled after page allocator change, was: " Johannes Weiner
2014-04-24 13:37 ` Johannes Weiner
2014-04-24 13:37 ` Johannes Weiner
2014-04-25 21:47 ` Jerome Glisse
2014-04-25 21:47 ` Jerome Glisse
2014-04-25 21:47 ` Jerome Glisse
2014-04-25 21:50 ` Jerome Glisse
2014-04-25 21:50 ` Jerome Glisse
2014-04-25 23:03 ` Jerome Glisse
2014-04-25 23:03 ` Jerome Glisse
2014-04-25 23:03 ` Jerome Glisse
2014-04-28 8:03 ` Thomas Schwinge
2014-04-28 9:09 ` Thomas Schwinge
2014-04-27 3:31 ` Jerome Glisse
2014-04-27 3:31 ` Jerome Glisse
2014-04-27 3:31 ` Jerome Glisse
2014-04-27 19:55 ` Jerome Glisse
2014-04-27 19:55 ` Jerome Glisse
2014-04-27 19:55 ` Jerome Glisse
2014-04-28 7:30 ` Christian König
2014-04-28 7:30 ` Christian König
2014-04-28 12:51 ` Deucher, Alexander
2014-04-28 12:51 ` Deucher, Alexander
2014-04-28 12:52 ` Deucher, Alexander
2014-04-28 12:52 ` Deucher, Alexander
2014-04-28 8:09 ` Thomas Schwinge
2014-06-16 7:11 ` Thomas Schwinge
2013-08-02 19:59 ` [patch v2 0/3] mm: improve page aging fairness between zones/nodes Andrea Arcangeli
2013-08-02 19:59 ` Andrea Arcangeli
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=20130805113423.GB6703@redhat.com \
--to=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=hannes@cmpxchg.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=liwanp@linux.vnet.ibm.com \
--cc=mgorman@suse.de \
--cc=minchan@kernel.org \
--cc=riel@surriel.com \
--cc=zcalusic@bitsync.net \
/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.