Re: [PATCH v7 06/12] khugepaged: introduce khugepaged_scan_bitmap for mTHP support

[Baolin Wang <baolin.wang@linux.alibaba.com>]

On 2025/5/20 18:26, David Hildenbrand wrote:
> On 20.05.25 12:09, Baolin Wang wrote:
>> Sorry for late reply.
>>
>> On 2025/5/17 14:47, Nico Pache wrote:
>>> On Thu, May 15, 2025 at 9:20 PM Baolin Wang
>>> <baolin.wang@linux.alibaba.com> wrote:
>>>>
>>>>
>>>>
>>>> On 2025/5/15 11:22, Nico Pache wrote:
>>>>> khugepaged scans anons PMD ranges for potential collapse to a 
>>>>> hugepage.
>>>>> To add mTHP support we use this scan to instead record chunks of 
>>>>> utilized
>>>>> sections of the PMD.
>>>>>
>>>>> khugepaged_scan_bitmap uses a stack struct to recursively scan a 
>>>>> bitmap
>>>>> that represents chunks of utilized regions. We can then determine what
>>>>> mTHP size fits best and in the following patch, we set this bitmap 
>>>>> while
>>>>> scanning the anon PMD. A minimum collapse order of 2 is used as 
>>>>> this is
>>>>> the lowest order supported by anon memory.
>>>>>
>>>>> max_ptes_none is used as a scale to determine how "full" an order must
>>>>> be before being considered for collapse.
>>>>>
>>>>> When attempting to collapse an order that has its order set to 
>>>>> "always"
>>>>> lets always collapse to that order in a greedy manner without
>>>>> considering the number of bits set.
>>>>>
>>>>> Signed-off-by: Nico Pache <npache@redhat.com>
>>>>
>>>> Sigh. You still haven't addressed or explained the issues I previously
>>>> raised [1], so I don't know how to review this patch again...
>>> Can you still reproduce this issue?
>>
>> Yes, I can still reproduce this issue with today's (5/20) mm-new branch.
>>
>> I've disabled PMD-sized THP in my system:
>> [root]# cat /sys/kernel/mm/transparent_hugepage/enabled
>> always madvise [never]
>> [root]# cat /sys/kernel/mm/transparent_hugepage/hugepages-2048kB/enabled
>> always inherit madvise [never]
> 
> Thanks for the easy reproducer, Baolin! It's certainly something that 
> must be fixed.
> 
>>
>> And I tried calling madvise() with MADV_COLLAPSE for anonymous memory,
>> and I can still see it collapsing to a PMD-sized THP.
> 
> This almost sounds like it could be converted into an easy selftest.
> 
> Baolin, do you have other ideas for easy selftests? It might be good to 
> include some in the next version. >
> I can think of: enable only a single size, then MADV_COLLAPSE X times 
> and see if it worked. etc.

Yes. And some easy test cases I want to write are:

(1) Enable all mTHP size, tuning 'max_ptes_none' parameter to check if 
the suitable sized mTHP is being collapsed (including MADV_COLLAPSE and 
khugepaged).
(2) Enable only a single size, calling MADV_COLLAPSE madvise() or 
khugepaged to check if the suitable sized mTHP is being collapsed.