Re: [PATCH 2/4] mm: khugepaged: remove mm when all memory has been collapsed

["David Hildenbrand (Red Hat)" <david@kernel.org>]

On 12/19/25 06:24, Vernon Yang wrote:
> On Thu, Dec 18, 2025 at 10:29:18AM +0100, David Hildenbrand (Red Hat) wrote:
>> On 12/15/25 10:04, Vernon Yang wrote:
>>> The following data is traced by bpftrace on a desktop system. After
>>> the system has been left idle for 10 minutes upon booting, a lot of
>>> SCAN_PMD_MAPPED or SCAN_PMD_NONE are observed during a full scan by
>>> khugepaged.
>>>
>>> @scan_pmd_status[1]: 1           ## SCAN_SUCCEED
>>> @scan_pmd_status[4]: 158         ## SCAN_PMD_MAPPED
>>> @scan_pmd_status[3]: 174         ## SCAN_PMD_NONE
>>> total progress size: 701 MB
>>> Total time         : 440 seconds ## include khugepaged_scan_sleep_millisecs
>>>
>>> The khugepaged_scan list save all task that support collapse into hugepage,
>>> as long as the take is not destroyed, khugepaged will not remove it from
>>> the khugepaged_scan list. This exist a phenomenon where task has already
>>> collapsed all memory regions into hugepage, but khugepaged continues to
>>> scan it, which wastes CPU time and invalid, and due to
>>> khugepaged_scan_sleep_millisecs (default 10s) causes a long wait for
>>> scanning a large number of invalid task, so scanning really valid task
>>> is later.
>>>
>>> After applying this patch, when all memory is either SCAN_PMD_MAPPED or
>>> SCAN_PMD_NONE, the mm is automatically removed from khugepaged's scan
>>> list. If the page fault or MADV_HUGEPAGE again, it is added back to
>>> khugepaged.
>>
>> I don't like that, as it assumes that memory within such a process would be
>> rather static, which is easily not the case (e.g., allocators just doing
>> MADV_DONTNEED to free memory).
>>
>> If most stuff is collapsed to PMDs already, can't we just skip over these
>> regions a bit faster?
> 
> /* default scan 8*HPAGE_PMD_NR ptes (or vmas) every 10 second */
> static unsigned int khugepaged_pages_to_scan __read_mostly;
> 
> The observed phenomenon is that when scanning these regions, the loop is
> broken upon reaching the number of khugepaged_pages_to_scan, thereforce
> the khugepaged enters 10s sleep.
BTW, the 10s sleep is ridiculous :)

I wonder whether we were more careful in the past regarding canning 
overhead due to the mmap read lock. Nowadays page faults typicaly use 
per-vma locks, so I wonder whether the scanning overhead is still a 
problem. (I assume there is more to optimize long-term)

-- 
Cheers

David