Re: [RESEND PATCH] mm:page_alloc.c: lower the order requirement of should_reclaim_retry

[Zhenhua Huang <quic_zhenhuah@quicinc.com>]

Thanks Michal again!

On 2022/9/20 19:20, Michal Hocko wrote:
> On Tue 20-09-22 17:38:30, Zhenhua Huang wrote:
> [...]
>>>>> Also this patch doesn't really explain why it should work and honestly
>>>>> it doesn't really make much sense to me either.
>>>> Sorry, my fault. IMO, The reason it should work is, say for this case of
>>>> order 3 allocation: we can perform direct reclaim more times as we have only
>>>> order 2 pages(which *lowered* by this change) in free_list(8214*16kB (UEC)).
>>>> The order requirement which I have lowered is should_reclaim_retry ->
>>>> __zone_watermark_ok:
>>>>          for (o = order; o < MAX_ORDER; o++) {
>>>>                   struct free_area *area = &z->free_area[o];
>>>> ...
>>>>                   for (mt = 0; mt < MIGRATE_PCPTYPES; mt++) {
>>>>                           if (!free_area_empty(area, mt))
>>>>                                   return true;
>>>>                   }
>>>>
>>>> Order 2 pages can be more easily met, hence VM has more chance to return
>>>> true from should_reclaim_retry.
>>>
>>> This is a wrong approach to the problem because there is no real
>>> guarantee the reclaim round will do anything useful. You should be
>>> really looking at the compaction side of the thing.
>>
>> Thanks Michal for the advice, I'll look at from compaction side also. But I
>> have one further question, IMO reclaim(~2GB LRU pages can be reclaimed)
>> should be more feasible compared to compaction(already tried with highest
>> prio and failed) in this case? Could you please elaborate more...it seems I
>> still not fully understand why it's a wrong approach to check from reclaim
>> phase.
> 
> Mel, has explained a large part I would go with let me just be more
> explicit about one part. Memory reclaim is not order aware and that
> means that probability of higher order pages are not directly related to
> the number of reclaimed pages. You might be lucky and reclaim a THP to
> form many order-3 pages or just reclaim those few that would create one
> order-3 but all that is very unpredictable and hence we rely on the
> compaction. Memory reclaim mostly assists compaction to allow some spare
> memory to do the migration.

Thanks for your kind sharing between reclaim VS compaction for high 
order allocations, Michal. Now I agreed with Mel and you, compaction 
should play a more important role in this.. or we have to use CMA instead.

Thanks,
Zhenhua