Re: [PATCH 1/1] mm/khugepaged: bypassing unnecessary scans with MMF_DISABLE_THP check

[Lance Yang]

Hey Andrew,

Thanks for taking time to review!

I appreciate your suggestion and will be
supplementing with test results shortly.

Best,
Lance

On Thu, Feb 22, 2024 at 6:12 AM Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> wrote:
>
> On Wed, 31 Jan 2024 17:30:11 +0800 Lance Yang <ioworker0@xxxxxxxxx> wrote:
>
> > Updating the change log.
> >
> > khugepaged scans the entire address space in the
> > background for each given mm, looking for
> > opportunities to merge sequences of basic pages
> > into huge pages. However, when an mm is inserted
> > to the mm_slots list, and the MMF_DISABLE_THP
> > flag is set later, this scanning process becomes
> > unnecessary for that mm and can be skipped to
> > avoid redundant operations, especially in scenarios
> > with a large address space.
> >
> > This commit introduces a check before each scanning
> > process to test the MMF_DISABLE_THP flag for the
> > given mm; if the flag is set, the scanning process is
> > bypassed, thereby improving the efficiency of khugepaged.
> >
> > This optimization is not a correctness issue but rather an
> > enhancement to save expensive checks on each VMA
> > when userspace cannot prctl itself before spawning
> > into the new process.
> >
> > On some servers within our company, we deploy a
> > daemon responsible for monitoring and updating local
> > applications. Some applications prefer not to use THP,
> > so the daemon calls prctl to disable THP before fork/exec.
> > Conversely, for other applications, the daemon calls prctl
> > to enable THP before fork/exec.
> >
> > Ideally, the daemon should invoke prctl after the fork,
> > but its current implementation follows the described
> > approach. In the Go standard library, there is no direct
> > encapsulation of the fork system call; instead, fork and
> > execve are combined into one through syscall.ForkExec.
>
> I pasted the above into the v1 patch's changelog.
>
> However I'm not seeing a good level of reviewer enthusiasm.  Pertially
> because of the lack of quantitative testing results.  Is is possible to
> generate such results, to give people an overall feel of the
> desirability of this change?
>