Re: [PATCH v2 3/4] mm: khugepaged: set VM_NOHUGEPAGE flag when MADV_COLD/MADV_FREE

[Vernon Yang <vernon2gm@gmail.com>]

On Tue, Dec 30, 2025 at 08:54:33PM +0100, David Hildenbrand (Red Hat) wrote:
> On 12/29/25 06:51, Vernon Yang wrote:
> > For example, create three task: hot1 -> cold -> hot2. After all three
> > task are created, each allocate memory 128MB. the hot1/hot2 task
> > continuously access 128 MB memory, while the cold task only accesses
> > its memory briefly andthen call madvise(MADV_COLD). However, khugepaged
> > still prioritizes scanning the cold task and only scans the hot2 task
> > after completing the scan of the cold task.
> >
> > So if the user has explicitly informed us via MADV_COLD/FREE that this
> > memory is cold or will be freed, it is appropriate for khugepaged to
> > skip it only, thereby avoiding unnecessary scan and collapse operations
> > to reducing CPU wastage.
> >
> > Here are the performance test results:
> > (Throughput bigger is better, other smaller is better)
> >
> > Testing on x86_64 machine:
> >
> > | task hot2           | without patch | with patch    |  delta  |
> > |---------------------|---------------|---------------|---------|
> > | total accesses time |  3.14 sec     |  2.93 sec     | -6.69%  |
> > | cycles per access   |  4.96         |  2.21         | -55.44% |
> > | Throughput          |  104.38 M/sec |  111.89 M/sec | +7.19%  |
> > | dTLB-load-misses    |  284814532    |  69597236     | -75.56% |
> >
> > Testing on qemu-system-x86_64 -enable-kvm:
> >
> > | task hot2           | without patch | with patch    |  delta  |
> > |---------------------|---------------|---------------|---------|
> > | total accesses time |  3.35 sec     |  2.96 sec     | -11.64% |
> > | cycles per access   |  7.29         |  2.07         | -71.60% |
> > | Throughput          |  97.67 M/sec  |  110.77 M/sec | +13.41% |
> > | dTLB-load-misses    |  241600871    |  3216108      | -98.67% |
> >
> > Signed-off-by: Vernon Yang <yanglincheng@kylinos.cn>
> > ---
>
> As raised in v1, this is not the way to go. Just because something was once
> indicated to be cold does not meant that it will stay like that forever.
>
> Also,
>
> (1) You are turning this into an operation that will perform VMA
>     modifications and require the mmap lock in write mode, bad.
>
> (2) You might now create many VMAs, possibly breaking user space, bad.
>
> If user space knows that memory will stay cold, it can use madvise() to
> indicate that these regions are not a good fit for THPs.
>
> But are they really not a good fit? What about smaller-order THPs?
>
> Nobody knows, but changing the behavior like you suggest is definetly bad.
> :)
>

Thank you for review and explanation. I got it.

For MADV_FREE, we will skip the lazy-free folios instead.
For MADV_COLD, it will be removed in the next version.

--
Thanks,
Vernon