From: "Huang\, Ying" <ying.huang@intel.com>
To: Mel Gorman <mgorman@suse.de>
Cc: David Hildenbrand <david@redhat.com>,
Michal Hocko <mhocko@kernel.org>,
Johannes Weiner <hannes@cmpxchg.org>,
Matthew Wilcox <willy@infradead.org>,
Andrew Morton <akpm@linux-foundation.org>, <linux-mm@kvack.org>,
<linux-kernel@vger.kernel.org>, Vlastimil Babka <vbabka@suse.cz>,
Zi Yan <ziy@nvidia.com>, Peter Zijlstra <peterz@infradead.org>,
Dave Hansen <dave.hansen@linux.intel.com>,
Minchan Kim <minchan@kernel.org>, Hugh Dickins <hughd@google.com>,
Alexander Duyck <alexander.duyck@gmail.com>
Subject: Re: [RFC 0/3] mm: Discard lazily freed pages when migrating
Date: Wed, 04 Mar 2020 08:33:08 +0800 [thread overview]
Message-ID: <874kv53qnv.fsf@yhuang-dev.intel.com> (raw)
In-Reply-To: <20200303130241.GE3772@suse.de> (Mel Gorman's message of "Tue, 3 Mar 2020 13:02:41 +0000")
Mel Gorman <mgorman@suse.de> writes:
> On Tue, Mar 03, 2020 at 09:51:56AM +0800, Huang, Ying wrote:
>> Mel Gorman <mgorman@suse.de> writes:
>> > On Mon, Mar 02, 2020 at 07:23:12PM +0800, Huang, Ying wrote:
>> >> If some applications cannot tolerate the latency incurred by the memory
>> >> allocation and zeroing. Then we cannot discard instead of migrate
>> >> always. While in some situations, less memory pressure can help. So
>> >> it's better to let the administrator and the application choose the
>> >> right behavior in the specific situation?
>> >>
>> >
>> > Is there an application you have in mind that benefits from discarding
>> > MADV_FREE pages instead of migrating them?
>> >
>> > Allowing the administrator or application to tune this would be very
>> > problematic. An application would require an update to the system call
>> > to take advantage of it and then detect if the running kernel supports
>> > it. An administrator would have to detect that MADV_FREE pages are being
>> > prematurely discarded leading to a slowdown and that is hard to detect.
>> > It could be inferred from monitoring compaction stats and checking
>> > if compaction activity is correlated with higher minor faults in the
>> > target application. Proving the correlation would require using the perf
>> > software event PERF_COUNT_SW_PAGE_FAULTS_MIN and matching the addresses
>> > to MADV_FREE regions that were freed prematurely. That is not an obvious
>> > debugging step to take when an application detects latency spikes.
>> >
>> > Now, you could add a counter specifically for MADV_FREE pages freed for
>> > reasons other than memory pressure and hope the administrator knows about
>> > the counter and what it means. That type of knowledge could take a long
>> > time to spread so it's really very important that there is evidence of
>> > an application that suffers due to the current MADV_FREE and migration
>> > behaviour.
>>
>> OK. I understand that this patchset isn't a universal win, so we need
>> some way to justify it. I will try to find some application for that.
>>
>> Another thought, as proposed by David Hildenbrand, it's may be a
>> universal win to discard clean MADV_FREE pages when migrating if there are
>> already memory pressure on the target node. For example, if the free
>> memory on the target node is lower than high watermark?
>>
>
> That is an extremely specific corner case that is not likely to occur.
> NUMA balancing is not going to migrate a MADV_FREE page under these
> circumstances as a write cancels MADV_FREE is read attempt will probably
> fail to allocate a destination page in alloc_misplaced_dst_page so the
> data gets lost instead of remaining remote. sys_movepages is a possibility
> but the circumstances of an application delibertly trying to migrate to
> a loaded node is low. Compaction never migrates cross-node so the state
> of a remote node under pressure do not matter.
>
> Once again, there needs to be a reasonable use case to be able to
> meaningfully balance between the benefits and risks of changing the
> MADV_FREE semantics.
OK. Will try to find some workloads for this.
Best Regards,
Huang, Ying
next prev parent reply other threads:[~2020-03-04 0:33 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-02-28 3:38 [RFC 0/3] mm: Discard lazily freed pages when migrating Huang, Ying
2020-02-28 3:38 ` [RFC 1/3] mm, migrate: Check return value of try_to_unmap() Huang, Ying
2020-02-28 3:38 ` [RFC 2/3] mm: Add a new page flag PageLayzyFree() for MADV_FREE Huang, Ying
2020-02-28 6:13 ` David Hildenbrand
2020-02-28 6:47 ` Huang, Ying
2020-03-15 8:18 ` Wei Yang
2020-03-15 8:54 ` Mika Penttilä
2020-03-15 12:22 ` Wei Yang
2020-03-16 1:21 ` Huang, Ying
2020-03-16 22:38 ` Wei Yang
2020-02-28 3:38 ` [RFC 3/3] mm: Discard lazily freed pages when migrating Huang, Ying
2020-02-28 3:42 ` [RFC 0/3] " Matthew Wilcox
2020-02-28 7:25 ` Huang, Ying
2020-02-28 8:22 ` David Hildenbrand
2020-02-28 8:55 ` Huang, Ying
2020-02-28 9:49 ` Mel Gorman
2020-03-02 11:23 ` Huang, Ying
2020-03-02 15:16 ` Mel Gorman
2020-03-03 1:51 ` Huang, Ying
2020-03-03 8:09 ` Michal Hocko
2020-03-03 8:47 ` Huang, Ying
2020-03-03 8:58 ` Michal Hocko
2020-03-03 11:49 ` Huang, Ying
2020-03-04 9:58 ` Michal Hocko
2020-03-04 10:56 ` Mel Gorman
2020-03-05 1:42 ` Huang, Ying
2020-03-04 11:15 ` Huang, Ying
2020-03-04 11:26 ` Michal Hocko
2020-03-05 1:45 ` Huang, Ying
2020-03-05 10:48 ` Mel Gorman
2020-03-06 4:05 ` Huang, Ying
2020-03-09 5:26 ` Huang, Ying
2020-03-03 13:02 ` Mel Gorman
2020-03-04 0:33 ` Huang, Ying [this message]
2020-02-28 9:50 ` Michal Hocko
2020-02-28 10:15 ` Michal Hocko
2020-02-28 13:45 ` Johannes Weiner
2020-03-02 14:12 ` Huang, Ying
2020-03-02 14:23 ` David Hildenbrand
2020-03-03 0:25 ` Huang, Ying
2020-03-02 14:25 ` Michal Hocko
2020-03-03 1:30 ` Huang, Ying
2020-03-03 8:19 ` Michal Hocko
2020-03-03 11:36 ` Huang, Ying
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=874kv53qnv.fsf@yhuang-dev.intel.com \
--to=ying.huang@intel.com \
--cc=akpm@linux-foundation.org \
--cc=alexander.duyck@gmail.com \
--cc=dave.hansen@linux.intel.com \
--cc=david@redhat.com \
--cc=hannes@cmpxchg.org \
--cc=hughd@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=mhocko@kernel.org \
--cc=minchan@kernel.org \
--cc=peterz@infradead.org \
--cc=vbabka@suse.cz \
--cc=willy@infradead.org \
--cc=ziy@nvidia.com \
/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).