Re: [PATCH/RFCv4 0/6] The Contiguous Memory Allocator framework

From: Minchan Kim
Date: Wed Aug 25 2010 - 23:05:12 EST


On Thu, Aug 26, 2010 at 11:49 AM, Minchan Kim <minchan.kim@xxxxxxxxx> wrote:
> On Thu, Aug 26, 2010 at 8:31 AM, Jonathan Corbet <corbet@xxxxxxx> wrote:
>> On Wed, 25 Aug 2010 15:58:14 -0700
>> Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> 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, those pages are easily freed/moved aside to satisfy
>>> > large contiguous allocations.
>>>
>>> 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?
>>
>> 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
>> being able to allocate those buffers anytime some kid decides to start
>> taking pictures was poor.  Thus, cafe_ccic.c has an option to snag the
>> memory at initialization time and never let go even if you threaten its
>> family.  Hell hath no fury like a little kid whose new toy^W educational
>> tool stops taking pictures.
>>
>> That, of course, is not a hugely efficient use of memory on a
>> memory-constrained system.  If the VM could reliably satisfy those
>> allocation requestss, life would be wonderful.  Seems difficult.  But it
>> would be a nicer solution than CMA, which, to a great extent, is really
>> just a standardized mechanism for grabbing memory and never letting go.
>>
>>> 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?  Please help identify
>>> specific subsystems and I can perhaps help to wake people up.
>>
>> If this code had been present when I did the Cafe driver, I would have used
>> it.  I think it could be made useful to a number of low-end camera drivers
>> if the videobuf layer were made to talk to it in a way which Just Works.
>>
>> With a bit of tweaking, I think it could be made useful in other
>> situations: the viafb driver, for example, really needs an allocator for
>> framebuffer memory and it seems silly to create one from scratch.  Of
>> course, there might be other possible solutions, like adding a "zones"
>> concept to LMB^W memblock.
>>
>> The problem which is being addressed here is real.
>>
>> That said, the complexity of the solution still bugs me a bit, and the core
>> idea is still to take big chunks of memory out of service for specific
>> needs.  It would be far better if the VM could just provide big chunks on
>> demand.  Perhaps compaction and the pressures of making transparent huge
>> pages work will get us there, but I'm not sure we're there yet.
>>
>> jon
>
> I agree. compaction and movable zone will be one of good solutions.
>
> If some driver needs big contiguous chunk to work, it should make sure
> to be allowable to have memory size for it before going. To make sure
> it, we have to consider compaction of ZONE_MOVABLE zone. But one of
> problems is anonymous page which can be has a role of pinned page in
> non-swapsystem. Even most of embedded system has no swap.
> But it's not hard to solve it.
>
> We needs Mel's opinion, too.

I elaborates my statement for preventing confusing due to using _pinned page_.
I means that anon pages isn't not a fragment problem but space problem
for the devices.
It would be better to move the pages into !ZONE_MOVABLE zone.

>
> --
> Kind regards,
> Minchan Kim
>



--
Kind regards,
Minchan Kim
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/