On Fri, Sep 03, 2010 at 07:29:43PM +0900, KAMEZAWA Hiroyuki wrote:
On Thu, 2 Sep 2010 17:54:24 +0900
KAMEZAWA Hiroyuki kamezawa.hir...@jp.fujitsu.com wrote:
Here is a rough code for this.
here is a _tested_ one.
If I tested correctly, I allocated 40MB of contigous pages by the new
On Mon, 6 Sep 2010 00:57:53 +0900
Minchan Kim minchan@gmail.com wrote:
Thanks,
-Kame
==
From: KAMEZAWA Hiroyuki kamezawa.hir...@jp.fujitsu.com
This patch as a memory allocator for contiguous memory larger than
MAX_ORDER.
alloc_contig_pages(hint, size, list);
On Thu, 2 Sep 2010 17:54:24 +0900
KAMEZAWA Hiroyuki kamezawa.hir...@jp.fujitsu.com wrote:
Here is a rough code for this.
here is a _tested_ one.
If I tested correctly, I allocated 40MB of contigous pages by the new funciton.
I'm grad this can be some hints for people.
Thanks,
-Kame
==
From:
On Fri, 27 Aug 2010 17:16:39 +0900
KAMEZAWA Hiroyuki kamezawa.hir...@jp.fujitsu.com wrote:
On Thu, 26 Aug 2010 18:36:24 +0900
Minchan Kim minchan@gmail.com wrote:
On Thu, Aug 26, 2010 at 1:30 PM, KAMEZAWA Hiroyuki
kamezawa.hir...@jp.fujitsu.com wrote:
On Thu, 26 Aug 2010 13:06:28
Andrew Morton wrote:
It would help (a lot) if we could get more attention and buyin and
fedback from the potential clients of this code. rmk's feedback is
valuable. Have we heard from the linux-media people? What other
subsystems might use it? ieee1394 perhaps?
All FireWire controllers
On Thursday, August 26, 2010 00:58:14 Andrew Morton wrote:
On Fri, 20 Aug 2010 15:15:10 +0200
Peter Zijlstra pet...@infradead.org wrote:
On Fri, 2010-08-20 at 11:50 +0200, Michal Nazarewicz wrote:
Hello everyone,
The following patchset implements a Contiguous Memory Allocator. For
On Sat, 2010-08-28 at 15:08 +0200, Hans Verkuil wrote:
That would be good. Although I expect that the allocation would need
to be 100% rock-solid reliable, otherwise the end user has a
non-functioning device.
Yes, indeed. And you have to be careful as well how you move pages around.
On Saturday, August 28, 2010 15:34:46 Peter Zijlstra wrote:
On Sat, 2010-08-28 at 15:08 +0200, Hans Verkuil wrote:
That would be good. Although I expect that the allocation would need
to be 100% rock-solid reliable, otherwise the end user has a
non-functioning device.
Yes,
On Sat, 2010-08-28 at 15:58 +0200, Hans Verkuil wrote:
Isn't the proposed CMA thing vulnerable to the exact same problem? If
you allow sharing of regions and plug some allocator in there you get
the same problem. If you can solve it there, you can solve it for any
kind of reservation
On Thu, 26 Aug 2010 18:36:24 +0900
Minchan Kim minchan@gmail.com wrote:
On Thu, Aug 26, 2010 at 1:30 PM, KAMEZAWA Hiroyuki
kamezawa.hir...@jp.fujitsu.com wrote:
On Thu, 26 Aug 2010 13:06:28 +0900
Minchan Kim minchan@gmail.com wrote:
On Thu, Aug 26, 2010 at 12:44 PM, KAMEZAWA
On Fri, 2010-08-27 at 17:16 +0900, KAMEZAWA Hiroyuki wrote:
How about changing following this?
The thing is MAX_ORDER is static. But we want to avoid too big
MAX_ORDER of whole zones to support devices which requires big
allocation chunk.
So let's add MAX_ORDER into each zone and then,
On Thu, 2010-08-26 at 03:28 +0200, Michał Nazarewicz wrote:
On Fri, 20 Aug 2010 15:15:10 +0200, Peter Zijlstra pet...@infradead.org
wrote:
So the idea is to grab a large chunk of memory at boot time and then
later allow some device to use it?
I'd much rather we'd improve the regular
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
On Thu, 2010-08-26 at 11:49 +0900, Minchan Kim wrote:
But one of
problems is anonymous page which can be has a role of pinned page in
non-swapsystem.
Well, compaction can move those around, but if you've got too many of
them its a simple matter of over-commit and for that we've got the
On Thu, Aug 26, 2010 at 5:20 PM, Peter Zijlstra pet...@infradead.org wrote:
On Thu, 2010-08-26 at 11:49 +0900, Minchan Kim wrote:
But one of
problems is anonymous page which can be has a role of pinned page in
non-swapsystem.
Well, compaction can move those around, but if you've got too many
On Thu, Aug 26, 2010 at 1:30 PM, KAMEZAWA Hiroyuki
kamezawa.hir...@jp.fujitsu.com wrote:
On Thu, 26 Aug 2010 13:06:28 +0900
Minchan Kim minchan@gmail.com wrote:
On Thu, Aug 26, 2010 at 12:44 PM, KAMEZAWA Hiroyuki
kamezawa.hir...@jp.fujitsu.com wrote:
On Thu, 26 Aug 2010 11:50:17 +0900
On Thu, 2010-08-26 at 18:29 +0900, Minchan Kim wrote:
As I said following mail, I said about free space problem.
Of course, compaction could move anon pages into somewhere.
What's is somewhere? At last, it's same zone.
It can prevent fragment problem but not size of free space.
So I mean it
On Fri, Aug 20, 2010 at 03:15:10PM +0200, Peter Zijlstra wrote:
On Fri, 2010-08-20 at 11:50 +0200, Michal Nazarewicz wrote:
Hello everyone,
The following patchset implements a Contiguous Memory Allocator. For
those who have not yet stumbled across CMA an excerpt from
documentation:
On Thu, Aug 26, 2010 at 04:40:46AM +0200, Micha?? Nazarewicz wrote:
Hello Andrew,
I think Pawel has replied to most of your comments, so I'll just add my own
0.02 KRW. ;)
Peter Zijlstra pet...@infradead.org wrote:
So the idea is to grab a large chunk of memory at boot time and then
later
On Thu, Aug 26, 2010 at 7:06 PM, Peter Zijlstra pet...@infradead.org wrote:
On Thu, 2010-08-26 at 18:29 +0900, Minchan Kim wrote:
As I said following mail, I said about free space problem.
Of course, compaction could move anon pages into somewhere.
What's is somewhere? At last, it's same zone.
Even more offtopic ;-)
On Thu, 2010-08-26 at 19:21 +0900, Minchan Kim wrote:
I agree highmem isn't a gorgeous. But my desktop isn't real machine?
Important thing is that we already have a highmem and many guys
include you(kmap stacking patch :))try to improve highmem problems. :)
I have
On Thu, 26 Aug 2010 10:17:07 +0200, Peter Zijlstra pet...@infradead.org wrote:
So why not work on the page allocator to improve its contiguous
allocation behaviour. If you look at the thing you'll find pageblocks
and migration types. If you change it so that you pin the migration type
of one or
On Fri, 20 Aug 2010 15:15:10 +0200
Peter Zijlstra pet...@infradead.org wrote:
On Fri, 2010-08-20 at 11:50 +0200, Michal Nazarewicz wrote:
Hello everyone,
The following patchset implements a Contiguous Memory Allocator. For
those who have not yet stumbled across CMA an excerpt from
On Wed, 2010-08-25 at 15:58 -0700, Andrew Morton wrote:
That would be good. Although I expect that the allocation would need
to be 100% rock-solid reliable, otherwise the end user has a
non-functioning device. Could generic core VM provide the required
level
of service?
Anyway, these
On Wed, 25 Aug 2010 15:58:14 -0700
Andrew Morton a...@linux-foundation.org wrote:
On Fri, 20 Aug 2010 15:15:10 +0200
Peter Zijlstra pet...@infradead.org wrote:
On Fri, 2010-08-20 at 11:50 +0200, Michal Nazarewicz wrote:
Hello everyone,
The following patchset implements a
Hi Andrew,
Thank you for your comments and interest in this!
On 08/26/2010 07:58 AM, Andrew Morton wrote:
On Fri, 20 Aug 2010 15:15:10 +0200
Peter Zijlstrapet...@infradead.org wrote:
On Fri, 2010-08-20 at 11:50 +0200, Michal Nazarewicz wrote:
Hello everyone,
The following
On Fri, 20 Aug 2010 15:15:10 +0200, Peter Zijlstra pet...@infradead.org wrote:
So the idea is to grab a large chunk of memory at boot time and then
later allow some device to use it?
I'd much rather we'd improve the regular page allocator to be smarter
about this. We recently added a lot of
On Thu, 26 Aug 2010 01:26:34 +0200, Daniel Walker dwal...@codeaurora.org
wrote:
If Michal is active, and follows community comments (including Zach's,
but I haven't seen any) then we can defer to that solution ..
Comments are always welcome. :)
--
Best regards,
On 08/26/2010 08:31 AM, Jonathan Corbet wrote:
On Wed, 25 Aug 2010 15:58:14 -0700
Andrew Mortona...@linux-foundation.org wrote:
If you want guarantees you can free stuff, why not add constraints to
the page allocation type and only allow MIGRATE_MOVABLE pages inside a
certain region,
On Thu, 26 Aug 2010 01:31:25 +0200, Jonathan Corbet cor...@lwn.net wrote:
The original OLPC has a camera controller which requires three contiguous,
image-sized buffers in memory. That system is a little memory constrained
(OK, it's desperately short of memory), so, in the past, the chances of
On Thu, 26 Aug 2010 02:58:57 +0200, KAMEZAWA Hiroyuki
kamezawa.hir...@jp.fujitsu.com wrote:
Hmm, you may not like this..but how about following kind of interface ?
Now, memoyr hotplug supports following operation to free and _isolate_
memory region.
# echo offline
Hello Andrew,
I think Pawel has replied to most of your comments, so I'll just add my own
0.02 KRW. ;)
Peter Zijlstra pet...@infradead.org wrote:
So the idea is to grab a large chunk of memory at boot time and then
later allow some device to use it?
I'd much rather we'd improve the regular
On Thu, Aug 26, 2010 at 8:31 AM, Jonathan Corbet cor...@lwn.net wrote:
On Wed, 25 Aug 2010 15:58:14 -0700
Andrew Morton a...@linux-foundation.org wrote:
If you want guarantees you can free stuff, why not add constraints to
the page allocation type and only allow MIGRATE_MOVABLE pages inside
On Thu, 26 Aug 2010 04:12:10 +0200
Michał Nazarewicz m.nazarew...@samsung.com wrote:
On Thu, 26 Aug 2010 02:58:57 +0200, KAMEZAWA Hiroyuki
kamezawa.hir...@jp.fujitsu.com wrote:
Hmm, you may not like this..but how about following kind of interface ?
Now, memoyr hotplug supports following
On Thu, Aug 26, 2010 at 11:49 AM, Minchan Kim minchan@gmail.com wrote:
On Thu, Aug 26, 2010 at 8:31 AM, Jonathan Corbet cor...@lwn.net wrote:
On Wed, 25 Aug 2010 15:58:14 -0700
Andrew Morton a...@linux-foundation.org wrote:
If you want guarantees you can free stuff, why not add
On Thu, 26 Aug 2010 11:50:17 +0900
KAMEZAWA Hiroyuki kamezawa.hir...@jp.fujitsu.com wrote:
128MB...too big ? But it's depend on config.
IBM's ppc guys used 16MB section, and recently, a new interface to shrink
the number of /sys files are added, maybe usable.
Something good with this
KAMEZAWA Hiroyuki kamezawa.hir...@jp.fujitsu.com wrote:
128MB...too big ? But it's depend on config.
On embedded systems it may be like half of the RAM. Or a quarter. So bigger
granularity could be desired on some platforms.
IBM's ppc guys used 16MB section, and recently, a new interface
On Thu, Aug 26, 2010 at 12:44 PM, KAMEZAWA Hiroyuki
kamezawa.hir...@jp.fujitsu.com wrote:
On Thu, 26 Aug 2010 11:50:17 +0900
KAMEZAWA Hiroyuki kamezawa.hir...@jp.fujitsu.com wrote:
128MB...too big ? But it's depend on config.
IBM's ppc guys used 16MB section, and recently, a new interface to
On Thu, Aug 26, 2010 at 1:06 PM, Minchan Kim minchan@gmail.com wrote:
On Thu, Aug 26, 2010 at 12:44 PM, KAMEZAWA Hiroyuki
kamezawa.hir...@jp.fujitsu.com wrote:
On Thu, 26 Aug 2010 11:50:17 +0900
KAMEZAWA Hiroyuki kamezawa.hir...@jp.fujitsu.com wrote:
128MB...too big ? But it's depend on
On Thu, 26 Aug 2010 13:06:28 +0900
Minchan Kim minchan@gmail.com wrote:
On Thu, Aug 26, 2010 at 12:44 PM, KAMEZAWA Hiroyuki
kamezawa.hir...@jp.fujitsu.com wrote:
On Thu, 26 Aug 2010 11:50:17 +0900
KAMEZAWA Hiroyuki kamezawa.hir...@jp.fujitsu.com wrote:
128MB...too big ? But it's
On Thu, 26 Aug 2010 06:01:56 +0200
Michał Nazarewicz m.nazarew...@samsung.com wrote:
KAMEZAWA Hiroyuki kamezawa.hir...@jp.fujitsu.com wrote:
128MB...too big ? But it's depend on config.
On embedded systems it may be like half of the RAM. Or a quarter. So bigger
granularity could be
On Thu, Aug 26, 2010 at 06:01:56AM +0200, Michał Nazarewicz wrote:
KAMEZAWA Hiroyuki kamezawa.hir...@jp.fujitsu.com wrote:
128MB...too big ? But it's depend on config.
On embedded systems it may be like half of the RAM. Or a quarter. So bigger
granularity could be desired on some platforms.
Hello everyone,
The following patchset implements a Contiguous Memory Allocator. For
those who have not yet stumbled across CMA an excerpt from
documentation:
The Contiguous Memory Allocator (CMA) is a framework, which allows
setting up a machine-specific configuration for
On Fri, 2010-08-20 at 11:50 +0200, Michal Nazarewicz wrote:
Hello everyone,
The following patchset implements a Contiguous Memory Allocator. For
those who have not yet stumbled across CMA an excerpt from
documentation:
The Contiguous Memory Allocator (CMA) is a framework, which allows
44 matches
Mail list logo