Re: [PATCH v3 7/8] mm, compaction: restrict async compaction to pageblocks of same migratetype
From: Vlastimil Babka
Date: Thu May 04 2017 - 02:13:12 EST
On 04/07/2017 02:38 AM, Joonsoo Kim wrote:
> On Wed, Mar 29, 2017 at 06:06:41PM +0200, Vlastimil Babka wrote:
>> On 03/16/2017 03:14 AM, Joonsoo Kim wrote:
>>> On Tue, Mar 07, 2017 at 02:15:44PM +0100, Vlastimil Babka wrote:
>>>> The migrate scanner in async compaction is currently limited to MIGRATE_MOVABLE
>>>> pageblocks. This is a heuristic intended to reduce latency, based on the
>>>> assumption that non-MOVABLE pageblocks are unlikely to contain movable pages.
>>>> However, with the exception of THP's, most high-order allocations are not
>>>> movable. Should the async compaction succeed, this increases the chance that
>>>> the non-MOVABLE allocations will fallback to a MOVABLE pageblock, making the
>>>> long-term fragmentation worse.
>>> I agree with this idea but have some concerns on this change.
>>> *ASYNC* compaction is designed for reducing latency and this change
>>> doesn't fit it. If everything works fine, there is a few movable pages
>>> in non-MOVABLE pageblocks as you noted above. Moreover, there is quite
>>> less the number of non-MOVABLE pageblock than MOVABLE one so finding
>>> non-MOVABLE pageblock takes long time. These two factors will increase
>>> the latency of *ASYNC* compaction.
>> Right. I lately started to doubt the whole idea of async compaction (for
>> non-movable allocations). Seems it's one of the compaction heuristics tuned
>> towards the THP usecase. But for non-movable allocations, we just can't have
>> both the low latency and long-term fragmentation avoidance. I see now even my
>> own skip_on_failure mode in isolate_migratepages_block() as a mistake for
>> non-movable allocations.
> Why do you think that skip_on_failure mode is a mistake? I think that
> it would lead to reduce the latency and it fits the goal of async
Yes, but the downside is that compaction will create just the single
high-order page that is requested, while previously it would also
migrate away some more lower-order pages. When compacting for
MIGRATE_UNMOVABLE allocation, we then can't steal extra pages, so next
allocation might pollute a different pageblock. It's not a good tradeoff.
>> Ideally I'd like to make async compaction redundant by kcompactd, and direct
>> compaction would mean a serious situation which should warrant sync compaction.
>> Meanwhile I see several options to modify this patch
>> - async compaction for non-movable allocations will stop doing the
>> skip_on_failure mode, and won't restrict the pageblock at all. patch 8/8 will
>> make sure that also this kind of compaction finishes the whole pageblock
>> - non-movable allocations will skip async compaction completely and go for sync
>> compaction immediately
> IMO, concept of async compaction is also important for non-movable allocation.
> Non-movable allocation is essential for some workload and they hope
> the low latency.
The low latency should not be at the expense of making long-term