From: Alex Shi <alex.shi@linux.alibaba.com>
To: David Rientjes <rientjes@google.com>,
David Hildenbrand <david@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>, Michal Hocko <mhocko@suse.com>,
Hugh Dickins <hughd@google.com>,
Andrea Arcangeli <aarcange@redhat.com>,
"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
Song Liu <songliubraving@fb.com>,
Matthew Wilcox <willy@infradead.org>,
Minchan Kim <minchan@kernel.org>,
Chris Kennelly <ckennelly@google.com>,
linux-mm@kvack.org, linux-api@vger.kernel.org
Subject: Re: [RFC] Hugepage collapse in process context
Date: Wed, 24 Feb 2021 17:44:58 +0800 [thread overview]
Message-ID: <25d9347b-9359-efab-e1e3-f98bd0012af9@linux.alibaba.com> (raw)
In-Reply-To: <5127b9c-a147-8ef5-c942-ae8c755413d0@google.com>
在 2021/2/19 上午6:34, David Rientjes 写道:
> On Thu, 18 Feb 2021, David Hildenbrand wrote:
>
>>>>> Hi everybody,
>>>>>
>>>>> Khugepaged is slow by default, it scans at most 4096 pages every 10s.
>>>>> That's normally fine as a system-wide setting, but some applications
>>>>> would
>>>>> benefit from a more aggressive approach (as long as they are willing to
>>>>> pay for it).
>>>>>
>>>>> Instead of adding priorities for eligible ranges of memory to
>>>>> khugepaged,
>>>>> temporarily speeding khugepaged up for the whole system, or sharding its
>>>>> work for memory belonging to a certain process, one approach would be to
>>>>> allow userspace to induce hugepage collapse.
>>>>>
>>>>> The benefit to this approach would be that this is done in process
>>>>> context
>>>>> so its cpu is charged to the process that is inducing the collapse.
>>>>> Khugepaged is not involved.
>>>>
>>>> Yes, this makes a lot of sense to me.
>>>>
>>>>> Idea was to allow userspace to induce hugepage collapse through the new
>>>>> process_madvise() call. This allows us to collapse hugepages on behalf
>>>>> of
>>>>> current or another process for a vectored set of ranges.
>>>>
>>>> Yes, madvise sounds like a good fit for the purpose.
>>>
>>> Agreed on both points.
>>>
>>>>> This could be done through a new process_madvise() mode *or* it could be
>>>>> a
>>>>> flag to MADV_HUGEPAGE since process_madvise() allows for a flag
>>>>> parameter
>>>>> to be passed. For example, MADV_F_SYNC.
>>>>
>>>> Would this MADV_F_SYNC be applicable to other madvise modes? Most
>>>> existing madvise modes do not seem to make much sense. We can argue that
>>>> MADV_PAGEOUT would guarantee the range was indeed reclaimed but I am not
>>>> sure we want to provide such a strong semantic because it can limit
>>>> future reclaim optimizations.
>>>>
>>>> To me MADV_HUGEPAGE_COLLAPSE sounds like the easiest way forward.
>>>
>>> I guess in the old madvise(2) we could create a new combo of MADV_HUGEPAGE |
>>> MADV_WILLNEED with this semantic? But you are probably more interested in
>>> process_madvise() anyway. There the new flag would make more sense. But
>>> there's
>>> also David H.'s proposal for MADV_POPULATE and there might be benefit in
>>> considering both at the same time? Should e.g. MADV_POPULATE with
>>> MADV_HUGEPAGE
>>> have the collapse semantics? But would MADV_POPULATE be added to
>>> process_madvise() as well? Just thinking out loud so we don't end up with
>>> more
>>> flags than necessary, it's already confusing enough as it is.
>>>
>>
>> Note that madvise() eats only a single value, not flags. Combinations as you
>> describe are not possible.
>>
>> Something MADV_HUGEPAGE_COLLAPSE make sense to me that does not need the mmap
>> lock in write and does not modify the actual VMA, only a mapping.
>>
>
> Agreed, and happy to see that there's a general consensus for the
> direction. Benefit of a new madvise mode is that it can be used for
> madvise() as well if you are interested in only a single range of your own
> memory and then it doesn't need to reconcile with any of the already
> overloaded semantics of MADV_HUGEPAGE.
It's a good idea to let process deal with its own THP policy.
but current applications will miss the benefit w/o changes, and change is
expensive for end users. So except this work, may a per memcg collapse benefit
apps and free for them, we often deploy apps in cgroups on server now.
Thanks
Alex
>
> Otherwise, process_madvise() can be used for other processes and/or
> vectored ranges.
>
> Song's use case for this to prioritize thp usage is very important for us
> as well. I hadn't thought of the madvise(MADV_HUGEPAGE) +
> madvise(MADV_HUGEPAGE_COLLAPSE) use case: I was anticipating the latter
> would allocate the hugepage with khugepaged's gfp mask so it would always
> compact. But it seems like this would actually be better to use the gfp
> mask that would be used at fault for the vma and left to userspace to
> determine whether that's MADV_HUGEPAGE or not. Makes sense.
>
> (Userspace could even do madvise(MADV_NOHUGEPAGE) +
> madvise(MADV_HUGEPAGE_COLLAPSE) to do the synchronous collapse but
> otherwise exclude it from khugepaged's consideration if it were inclined.)
>
> Two other minor points:
>
> - Currently, process_madvise() doesn't use the flags parameter at all so
> there's the question of whether we need generalized flags that apply to
> most madvise modes or whether the flags can be specific to the mode
> being used. For example, a natural extension of this new mode would be
> to determine the hugepage size if we were ever to support synchronous
> collapse into a 1GB gigantic page on x86 (MADV_F_1GB? :)
>
> - We haven't discussed the future of khugepaged with this new mode: it
> seems like we could simply implement khugepaged fully in userspace and
> remove it from the kernel? :)
>
next prev parent reply other threads:[~2021-02-24 9:45 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-02-17 4:24 [RFC] Hugepage collapse in process context David Rientjes
2021-02-17 8:21 ` Michal Hocko
2021-02-18 13:43 ` Vlastimil Babka
2021-02-18 13:52 ` David Hildenbrand
2021-02-18 22:34 ` David Rientjes
2021-02-19 16:16 ` Zi Yan
2021-02-24 9:44 ` Alex Shi [this message]
2021-03-01 20:56 ` David Rientjes
2021-03-04 10:52 ` Alex Shi
2021-02-17 15:49 ` Zi Yan
2021-02-18 8:11 ` Song Liu
2021-02-18 8:39 ` Michal Hocko
2021-02-18 9:53 ` Song Liu
2021-02-18 10:01 ` Michal Hocko
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=25d9347b-9359-efab-e1e3-f98bd0012af9@linux.alibaba.com \
--to=alex.shi@linux.alibaba.com \
--cc=aarcange@redhat.com \
--cc=ckennelly@google.com \
--cc=david@redhat.com \
--cc=hughd@google.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=linux-api@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@suse.com \
--cc=minchan@kernel.org \
--cc=rientjes@google.com \
--cc=songliubraving@fb.com \
--cc=vbabka@suse.cz \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).