From: Vlastimil Babka <vbabka@suse.cz>
To: Alex Shi <alex.shi@linux.alibaba.com>,
Anshuman Khandual <anshuman.khandual@arm.com>,
Matthew Wilcox <willy@infradead.org>,
David Hildenbrand <david@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Hugh Dickins <hughd@google.com>,
Alexander Duyck <alexander.h.duyck@linux.intel.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
Mel Gorman <mgorman@techsingularity.net>
Subject: Re: [PATCH v2 2/2] mm/pageblock: remove false sharing in pageblock_flags
Date: Tue, 1 Sep 2020 19:04:06 +0200 [thread overview]
Message-ID: <11d6c4ae-6eae-aef9-5652-73a8680cd6e4@suse.cz> (raw)
In-Reply-To: <a7376a9c-82e8-7dc1-b656-9c0516738801@linux.alibaba.com>
On 8/19/20 10:09 AM, Alex Shi wrote:
>
>
> 在 2020/8/19 下午3:57, Anshuman Khandual 写道:
>>
>>
>> On 08/19/2020 11:17 AM, Alex Shi wrote:
>>> Current pageblock_flags is only 4 bits, so it has to share a char size
>>> in cmpxchg when get set, the false sharing cause perf drop.
>>>
>>> If we incrase the bits up to 8, false sharing would gone in cmpxchg. and
>>> the only cost is half char per pageblock, which is half char per 128MB
>>> on x86, 4 chars in 1 GB.
>>
>> Agreed that increase in memory utilization is negligible here but does
>> this really improve performance ?
>>
>
> It's no doubt in theory. and it would had a bad impact according to
> commit e380bebe4771548 mm, compaction: keep migration source private to a single
I don't think that commit is doing the test_and_set_skip() under lock to avoid
false sharing. I think it's done to simply make the test and set protected
against races without relying on e.g. a truly atomic test_and_set_bit(). It's
still noted that it's just a hint so it's not protected to others calling
set_pageblock_skip() from other contexts not under a lock.
> but I do have some problem in running thpscale/mmtest. I'd like to see if anyone
> could give a try.
>
> BTW, I naturally hate the false sharing even it's in theory. Anyone who doesn't? :)
>
> Thanks
> Alex
>
next prev parent reply other threads:[~2020-09-01 17:04 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-08-19 5:47 [PATCH v2 1/2] mm/pageblock: mitigation cmpxchg false sharing in pageblock flags Alex Shi
2020-08-19 5:47 ` [PATCH v2 2/2] mm/pageblock: remove false sharing in pageblock_flags Alex Shi
2020-08-19 7:57 ` Anshuman Khandual
2020-08-19 8:09 ` Alex Shi
2020-08-19 8:13 ` David Hildenbrand
2020-08-19 8:36 ` Alex Shi
2020-08-19 16:50 ` Alexander Duyck
2020-08-30 10:00 ` Alex Shi
2020-08-30 20:32 ` Alexander Duyck
2020-09-03 5:35 ` Alex Shi
2020-09-01 17:04 ` Vlastimil Babka [this message]
2020-08-19 7:55 ` [PATCH v2 1/2] mm/pageblock: mitigation cmpxchg false sharing in pageblock flags Anshuman Khandual
2020-08-19 8:04 ` David Hildenbrand
2020-08-30 10:08 ` Alex Shi
2020-08-30 10:14 ` Alex Shi
2020-08-30 10:18 ` Matthew Wilcox
2020-08-31 8:40 ` Alex Shi
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=11d6c4ae-6eae-aef9-5652-73a8680cd6e4@suse.cz \
--to=vbabka@suse.cz \
--cc=akpm@linux-foundation.org \
--cc=alex.shi@linux.alibaba.com \
--cc=alexander.h.duyck@linux.intel.com \
--cc=anshuman.khandual@arm.com \
--cc=david@redhat.com \
--cc=hughd@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@techsingularity.net \
--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).