From: peterz@infradead.org (Peter Zijlstra)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH/RFCv4 0/6] The Contiguous Memory Allocator framework
Date: Thu, 26 Aug 2010 10:18:57 +0200 [thread overview]
Message-ID: <1282810737.1975.240.camel@laptop> (raw)
In-Reply-To: <op.vh0xp8ix7p4s8u@localhost>
On Thu, 2010-08-26 at 04:40 +0200, Micha? Nazarewicz wrote:
> I think that the biggest problem is fragmentation here. For instance,
> I think that a situation where there is enough free space but it's
> fragmented so no single contiguous chunk can be allocated is a serious
> problem. However, I would argue that if there's simply no space left,
> a multimedia device could fail and even though it's not desirable, it
> would not be such a big issue in my eyes.
>
> So, if only movable or discardable pages are allocated in CMA managed
> regions all should work well. When a device needs memory discardable
> pages would get freed and movable moved unless there is no space left
> on the device in which case allocation would fail.
If you'd actually looked at the page allocator you'd see its capable of
doing exactly that!
I has the notion of movable pages, it can defragment free space (called
compaction).
Use it!
WARNING: multiple messages have this Message-ID (diff)
From: Peter Zijlstra <peterz@infradead.org>
To: "Michał Nazarewicz" <m.nazarewicz@samsung.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Hans Verkuil <hverkuil@xs4all.nl>,
Daniel Walker <dwalker@codeaurora.org>,
Russell King <linux@arm.linux.org.uk>,
Jonathan Corbet <corbet@lwn.net>, Mel Gorman <mel@csn.ul.ie>,
Pawel Osciak <p.osciak@samsung.com>,
Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
linux-kernel@vger.kernel.org,
FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>,
linux-mm@kvack.org, Kyungmin Park <kyungmin.park@samsung.com>,
Zach Pfeffer <zpfeffer@codeaurora.org>,
Mark Brown <broonie@opensource.wolfsonmicro.com>,
linux-media@vger.kernel.org,
linux-arm-kernel@lists.infradead.org,
Marek Szyprowski <m.szyprowski@samsung.com>
Subject: Re: [PATCH/RFCv4 0/6] The Contiguous Memory Allocator framework
Date: Thu, 26 Aug 2010 10:18:57 +0200 [thread overview]
Message-ID: <1282810737.1975.240.camel@laptop> (raw)
In-Reply-To: <op.vh0xp8ix7p4s8u@localhost>
On Thu, 2010-08-26 at 04:40 +0200, Michał Nazarewicz wrote:
> I think that the biggest problem is fragmentation here. For instance,
> I think that a situation where there is enough free space but it's
> fragmented so no single contiguous chunk can be allocated is a serious
> problem. However, I would argue that if there's simply no space left,
> a multimedia device could fail and even though it's not desirable, it
> would not be such a big issue in my eyes.
>
> So, if only movable or discardable pages are allocated in CMA managed
> regions all should work well. When a device needs memory discardable
> pages would get freed and movable moved unless there is no space left
> on the device in which case allocation would fail.
If you'd actually looked at the page allocator you'd see its capable of
doing exactly that!
I has the notion of movable pages, it can defragment free space (called
compaction).
Use it!
WARNING: multiple messages have this Message-ID (diff)
From: Peter Zijlstra <peterz@infradead.org>
To: "Michał Nazarewicz" <m.nazarewicz@samsung.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Hans Verkuil <hverkuil@xs4all.nl>,
Daniel Walker <dwalker@codeaurora.org>,
Russell King <linux@arm.linux.org.uk>,
Jonathan Corbet <corbet@lwn.net>, Mel Gorman <mel@csn.ul.ie>,
Pawel Osciak <p.osciak@samsung.com>,
Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
linux-kernel@vger.kernel.org,
FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>,
linux-mm@kvack.org, Kyungmin Park <kyungmin.park@samsung.com>,
Zach Pfeffer <zpfeffer@codeaurora.org>,
Mark Brown <broonie@opensource.wolfsonmicro.com>,
linux-media@vger.kernel.org,
linux-arm-kernel@lists.infradead.org,
Marek Szyprowski <m.szyprowski@samsung.com>
Subject: Re: [PATCH/RFCv4 0/6] The Contiguous Memory Allocator framework
Date: Thu, 26 Aug 2010 10:18:57 +0200 [thread overview]
Message-ID: <1282810737.1975.240.camel@laptop> (raw)
In-Reply-To: <op.vh0xp8ix7p4s8u@localhost>
On Thu, 2010-08-26 at 04:40 +0200, Michał Nazarewicz wrote:
> I think that the biggest problem is fragmentation here. For instance,
> I think that a situation where there is enough free space but it's
> fragmented so no single contiguous chunk can be allocated is a serious
> problem. However, I would argue that if there's simply no space left,
> a multimedia device could fail and even though it's not desirable, it
> would not be such a big issue in my eyes.
>
> So, if only movable or discardable pages are allocated in CMA managed
> regions all should work well. When a device needs memory discardable
> pages would get freed and movable moved unless there is no space left
> on the device in which case allocation would fail.
If you'd actually looked at the page allocator you'd see its capable of
doing exactly that!
I has the notion of movable pages, it can defragment free space (called
compaction).
Use it!
--
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:[~2010-08-26 8:18 UTC|newest]
Thread overview: 180+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-08-20 9:50 [PATCH/RFCv4 0/6] The Contiguous Memory Allocator framework Michal Nazarewicz
2010-08-20 9:50 ` Michal Nazarewicz
2010-08-20 9:50 ` Michal Nazarewicz
2010-08-20 9:50 ` [PATCH/RFCv4 1/6] lib: rbtree: rb_root_init() function added Michal Nazarewicz
2010-08-20 9:50 ` Michal Nazarewicz
2010-08-20 9:50 ` Michal Nazarewicz
2010-08-20 9:50 ` [PATCH/RFCv4 2/6] mm: cma: Contiguous Memory Allocator added Michal Nazarewicz
2010-08-20 9:50 ` Michal Nazarewicz
2010-08-20 9:50 ` Michal Nazarewicz
2010-08-20 9:50 ` [PATCH/RFCv4 3/6] mm: cma: Added SysFS support Michal Nazarewicz
2010-08-20 9:50 ` Michal Nazarewicz
2010-08-20 9:50 ` Michal Nazarewicz
2010-08-20 9:50 ` [PATCH/RFCv4 4/6] mm: cma: Added command line parameters support Michal Nazarewicz
2010-08-20 9:50 ` Michal Nazarewicz
2010-08-20 9:50 ` Michal Nazarewicz
2010-08-20 9:50 ` [PATCH/RFCv4 5/6] mm: cma: Test device and application added Michal Nazarewicz
2010-08-20 9:50 ` Michal Nazarewicz
2010-08-20 9:50 ` Michal Nazarewicz
2010-08-20 9:50 ` [PATCH/RFCv4 6/6] arm: Added CMA to Aquila and Goni Michal Nazarewicz
2010-08-20 9:50 ` Michal Nazarewicz
2010-08-20 9:50 ` Michal Nazarewicz
2010-08-25 20:37 ` [PATCH/RFCv4 3/6] mm: cma: Added SysFS support Konrad Rzeszutek Wilk
2010-08-25 20:37 ` Konrad Rzeszutek Wilk
2010-08-25 20:37 ` Konrad Rzeszutek Wilk
2010-08-26 1:20 ` Michał Nazarewicz
2010-08-26 1:20 ` Michał Nazarewicz
2010-08-26 1:20 ` Michał Nazarewicz
2010-08-25 20:32 ` [PATCH/RFCv4 2/6] mm: cma: Contiguous Memory Allocator added Konrad Rzeszutek Wilk
2010-08-25 20:32 ` Konrad Rzeszutek Wilk
2010-08-25 20:32 ` Konrad Rzeszutek Wilk
2010-08-26 1:22 ` Michał Nazarewicz
2010-08-26 1:22 ` Michał Nazarewicz
2010-08-26 1:22 ` Michał Nazarewicz
2010-08-26 6:25 ` [PATCH/RFCv4.1 " Michal Nazarewicz
2010-08-26 6:25 ` Michal Nazarewicz
2010-08-26 6:25 ` Michal Nazarewicz
2010-08-26 13:47 ` [PATCH/RFCv4 " Mel Gorman
2010-08-26 13:47 ` Mel Gorman
2010-08-26 13:47 ` Mel Gorman
2010-08-27 2:09 ` Michał Nazarewicz
2010-08-27 2:09 ` Michał Nazarewicz
2010-08-27 2:09 ` Michał Nazarewicz
2010-08-28 12:37 ` Hans Verkuil
2010-08-28 12:37 ` Hans Verkuil
2010-08-28 12:37 ` Hans Verkuil
2010-08-29 1:48 ` Michał Nazarewicz
2010-08-29 1:48 ` Michał Nazarewicz
2010-08-29 1:48 ` Michał Nazarewicz
2010-08-20 13:15 ` [PATCH/RFCv4 0/6] The Contiguous Memory Allocator framework Peter Zijlstra
2010-08-20 13:15 ` Peter Zijlstra
2010-08-20 13:15 ` Peter Zijlstra
2010-08-25 22:58 ` Andrew Morton
2010-08-25 22:58 ` Andrew Morton
2010-08-25 22:58 ` Andrew Morton
2010-08-25 23:26 ` Daniel Walker
2010-08-25 23:26 ` Daniel Walker
2010-08-25 23:26 ` Daniel Walker
2010-08-26 1:38 ` Michał Nazarewicz
2010-08-26 1:38 ` Michał Nazarewicz
2010-08-26 1:38 ` Michał Nazarewicz
2010-08-25 23:31 ` Jonathan Corbet
2010-08-25 23:31 ` Jonathan Corbet
2010-08-25 23:31 ` Jonathan Corbet
2010-08-26 1:38 ` Pawel Osciak
2010-08-26 1:38 ` Pawel Osciak
2010-08-26 1:38 ` Pawel Osciak
2010-08-26 1:49 ` Michał Nazarewicz
2010-08-26 1:49 ` Michał Nazarewicz
2010-08-26 1:49 ` Michał Nazarewicz
2010-08-26 2:49 ` Minchan Kim
2010-08-26 2:49 ` Minchan Kim
2010-08-26 2:49 ` Minchan Kim
2010-08-26 3:04 ` Minchan Kim
2010-08-26 3:04 ` Minchan Kim
2010-08-26 3:04 ` Minchan Kim
2010-08-26 8:20 ` Peter Zijlstra
2010-08-26 8:20 ` Peter Zijlstra
2010-08-26 8:20 ` Peter Zijlstra
2010-08-26 9:29 ` Minchan Kim
2010-08-26 9:29 ` Minchan Kim
2010-08-26 9:29 ` Minchan Kim
2010-08-26 10:06 ` Peter Zijlstra
2010-08-26 10:06 ` Peter Zijlstra
2010-08-26 10:06 ` Peter Zijlstra
2010-08-26 10:21 ` Minchan Kim
2010-08-26 10:21 ` Minchan Kim
2010-08-26 10:21 ` Minchan Kim
2010-08-26 11:05 ` Peter Zijlstra
2010-08-26 11:05 ` Peter Zijlstra
2010-08-26 11:05 ` Peter Zijlstra
2010-08-26 0:58 ` KAMEZAWA Hiroyuki
2010-08-26 0:58 ` KAMEZAWA Hiroyuki
2010-08-26 0:58 ` KAMEZAWA Hiroyuki
2010-08-26 2:12 ` Michał Nazarewicz
2010-08-26 2:12 ` Michał Nazarewicz
2010-08-26 2:12 ` Michał Nazarewicz
2010-08-26 2:50 ` KAMEZAWA Hiroyuki
2010-08-26 2:50 ` KAMEZAWA Hiroyuki
2010-08-26 2:50 ` KAMEZAWA Hiroyuki
2010-08-26 3:44 ` KAMEZAWA Hiroyuki
2010-08-26 3:44 ` KAMEZAWA Hiroyuki
2010-08-26 3:44 ` KAMEZAWA Hiroyuki
2010-08-26 4:01 ` Michał Nazarewicz
2010-08-26 4:01 ` Michał Nazarewicz
2010-08-26 4:01 ` Michał Nazarewicz
2010-08-26 4:39 ` KAMEZAWA Hiroyuki
2010-08-26 4:39 ` KAMEZAWA Hiroyuki
2010-08-26 4:39 ` KAMEZAWA Hiroyuki
2010-08-26 5:54 ` Américo Wang
2010-08-26 5:54 ` Américo Wang
2010-08-26 5:54 ` Américo Wang
2010-08-26 4:06 ` Minchan Kim
2010-08-26 4:06 ` Minchan Kim
2010-08-26 4:06 ` Minchan Kim
2010-08-26 4:14 ` Minchan Kim
2010-08-26 4:14 ` Minchan Kim
2010-08-26 4:14 ` Minchan Kim
2010-08-26 4:30 ` KAMEZAWA Hiroyuki
2010-08-26 4:30 ` KAMEZAWA Hiroyuki
2010-08-26 4:30 ` KAMEZAWA Hiroyuki
2010-08-26 9:36 ` Minchan Kim
2010-08-26 9:36 ` Minchan Kim
2010-08-26 9:36 ` Minchan Kim
2010-08-27 8:16 ` KAMEZAWA Hiroyuki
2010-08-27 8:16 ` KAMEZAWA Hiroyuki
2010-08-27 8:16 ` KAMEZAWA Hiroyuki
2010-08-27 8:37 ` Peter Zijlstra
2010-08-27 8:37 ` Peter Zijlstra
2010-08-27 8:37 ` Peter Zijlstra
2010-09-02 8:54 ` KAMEZAWA Hiroyuki
2010-09-02 8:54 ` KAMEZAWA Hiroyuki
2010-09-02 8:54 ` KAMEZAWA Hiroyuki
2010-09-03 10:29 ` KAMEZAWA Hiroyuki
2010-09-03 10:29 ` KAMEZAWA Hiroyuki
2010-09-03 10:29 ` KAMEZAWA Hiroyuki
2010-09-05 15:57 ` Minchan Kim
2010-09-05 15:57 ` Minchan Kim
2010-09-05 15:57 ` Minchan Kim
2010-09-06 0:08 ` KAMEZAWA Hiroyuki
2010-09-06 0:08 ` KAMEZAWA Hiroyuki
2010-09-06 0:08 ` KAMEZAWA Hiroyuki
2010-08-26 1:22 ` Pawel Osciak
2010-08-26 1:22 ` Pawel Osciak
2010-08-26 1:22 ` Pawel Osciak
2010-08-26 2:40 ` Michał Nazarewicz
2010-08-26 2:40 ` Michał Nazarewicz
2010-08-26 2:40 ` Michał Nazarewicz
2010-08-26 8:18 ` Peter Zijlstra [this message]
2010-08-26 8:18 ` Peter Zijlstra
2010-08-26 8:18 ` Peter Zijlstra
2010-08-26 10:18 ` Mel Gorman
2010-08-26 10:18 ` Mel Gorman
2010-08-26 10:18 ` Mel Gorman
2010-08-28 13:08 ` Hans Verkuil
2010-08-28 13:08 ` Hans Verkuil
2010-08-28 13:08 ` Hans Verkuil
2010-08-28 13:34 ` Peter Zijlstra
2010-08-28 13:34 ` Peter Zijlstra
2010-08-28 13:34 ` Peter Zijlstra
2010-08-28 13:58 ` Hans Verkuil
2010-08-28 13:58 ` Hans Verkuil
2010-08-28 13:58 ` Hans Verkuil
2010-08-28 14:16 ` Peter Zijlstra
2010-08-28 14:16 ` Peter Zijlstra
2010-08-28 14:16 ` Peter Zijlstra
2010-08-30 8:27 ` Clemens Ladisch
2010-08-30 8:27 ` Clemens Ladisch
2010-08-30 8:27 ` Clemens Ladisch
2010-08-26 1:28 ` Michał Nazarewicz
2010-08-26 1:28 ` Michał Nazarewicz
2010-08-26 1:28 ` Michał Nazarewicz
2010-08-26 8:17 ` Peter Zijlstra
2010-08-26 8:17 ` Peter Zijlstra
2010-08-26 8:17 ` Peter Zijlstra
2010-08-27 2:41 ` Michał Nazarewicz
2010-08-27 2:41 ` Michał Nazarewicz
2010-08-27 2:41 ` Michał Nazarewicz
2010-08-26 10:12 ` Mel Gorman
2010-08-26 10:12 ` Mel Gorman
2010-08-26 10:12 ` Mel Gorman
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=1282810737.1975.240.camel@laptop \
--to=peterz@infradead.org \
--cc=linux-arm-kernel@lists.infradead.org \
/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.