Re: [Patch v2] mm/rmap.c: split huge pmd when it really is

[Wei Yang <richardw.yang@linux.intel.com>]

On Fri, Jan 03, 2020 at 04:26:50PM +0300, Kirill A. Shutemov wrote:
>On Fri, Jan 03, 2020 at 09:05:54PM +0800, Wei Yang wrote:
>> On Fri, Jan 03, 2020 at 03:18:46PM +0800, Wei Yang wrote:
>> >On Tue, Dec 24, 2019 at 06:28:56AM +0800, Wei Yang wrote:
>> >>When page is not NULL, function is called by try_to_unmap_one() with
>> >>TTU_SPLIT_HUGE_PMD set. There are two cases to call try_to_unmap_one()
>> >>with TTU_SPLIT_HUGE_PMD set:
>> >>
>> >>  * unmap_page()
>> >>  * shrink_page_list()
>> >>
>> >>In both case, the page passed to try_to_unmap_one() is PageHead() of the
>> >>THP. If this page's mapping address in process is not HPAGE_PMD_SIZE
>> >>aligned, this means the THP is not mapped as PMD THP in this process.
>> >>This could happen when we do mremap() a PMD size range to an un-aligned
>> >>address.
>> >>
>> >>Currently, this case is handled by following check in __split_huge_pmd()
>> >>luckily.
>> >>
>> >>  page != pmd_page(*pmd)
>> >>
>> >>This patch checks the address to skip some work.
>> >
>> >I am sorry to forget address Kirill's comment in 1st version.
>> >
>> >The first one is the performance difference after this change for a PTE
>> >mappged THP.
>> >
>> >Here is the result:(in cycle)
>> >
>> >        Before     Patched
>> >
>> >        963        195
>> >        988        40
>> >        895        78
>> >
>> >Average 948        104
>> >
>> >So the change reduced 90% time for function split_huge_pmd_address().
>
>Right.
>
>But do we have a scenario, where the performance of
>split_huge_pmd_address() matters? I mean, it it called as part of rmap
>walk, attempt to split huge PMD where we don't have huge PMD should be
>within noise.

Sorry for my poor English.

I don't catch the meaning of the last sentence. "within noise" here means
non-huge PMD is an expected scenario and we could tolerate this? 

>
>> >For the 2nd comment, the vma check. Let me take a further look to analysis.
>> >
>> >Thanks for Kirill's suggestion.
>> >
>> 
>> For 2nd comment, check vma could hold huge page.
>> 
>> You mean do this check ?
>> 
>>   vma->vm_start <= address && vma->vm_end >= address + HPAGE_PMD_SIZE
>> 
>> This happens after munmap a partial of the THP range? After doing so, we can
>> skip split_pmd for this case.
>
>Okay, you are right. This kind of check would not be safe as we
>split_huge_pmd_address() after adjusting VMA with expectation of splitting
>PMD on boundary of the VMA.
>
>-- 
> Kirill A. Shutemov

-- 
Wei Yang
Help you, Help me