From: Shile Zhang <shile.zhang@linux.alibaba.com>
To: Pavel Tatashin <pasha.tatashin@soleen.com>,
Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Kirill Tkhai <ktkhai@virtuozzo.com>,
linux-mm <linux-mm@kvack.org>,
LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH v3] mm: fix tick timer stall during deferred page init
Date: Fri, 27 Mar 2020 12:39:18 +0800 [thread overview]
Message-ID: <427ce795-0274-56e5-16e4-7be00c7145f7@linux.alibaba.com> (raw)
In-Reply-To: <CA+CK2bDQ6qPfLsx=81L3_DVzvoCjkBRKvcw0Tz4Gd=Fd6pgQ3A@mail.gmail.com>
On 2020/3/27 03:36, Pavel Tatashin wrote:
> I agree with Daniel, we should look into approach where
> pgdat_resize_lock is taken only for the duration of updating tracking
> values such as pgdat->first_deferred_pfn (perhaps we would need to add
> another tracker that would show chunks that are currently being worked
> on).
>
> The vast duration of struct page initialization process should happen
> outside of this lock, and only be taken when we update globally seen
> data structures: lists, tracking variables. This way we can solve
> several problems: 1. allow interrupt threads to grow zones if
> required. 2. keep jiffies happy. 3. allow future scaling when we will
> add inner node threads to initialize struct pages (i.e. ktasks from
> Daniel).
It make sense, looking forward to the inner node parallel init.
@Daniel
Is there schedule about ktasks?
Thanks!
>
> Pasha
>
> On Thu, Mar 26, 2020 at 2:58 PM Daniel Jordan
> <daniel.m.jordan@oracle.com> wrote:
>> On Thu, Mar 19, 2020 at 03:05:12PM -0400, Daniel Jordan wrote:
>>> Regardless,
>>> Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com>
>> Darn, I spoke too soon.
>>
>> On a two-socket Xeon, smaller values of TICK_PAGE_COUNT caused the deferred
>> init timestamp to grow by over 25%. This was with pgdatinit0 bound to the
>> timer interrupt CPU to make sure the issue always reproduces.
>>
>> TICK_PAGE_COUNT node 0 deferred
>> init time (ms)
>> --------------- ---------------
>> 4096 610
>> 8192 587
>> 16384 487
>> 32768 480 // used in the patch
>>
>> Instead of trying to find a constant that lets the timer interrupt run often
>> enough, I think a better way forward is to reconsider how we handle the resize
>> lock. I plan to prototype something and reply back with what I get.
Yes, the time spend of pages init depends on the CPU frequency,
and the jiffies update controlled by HZ, so it's hard to find a general
constant.
It seems we need a bigger refactors about the lock to get a better solution.
next prev parent reply other threads:[~2020-03-27 4:41 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-11 12:38 [PATCH v3] mm: fix tick timer stall during deferred page init Shile Zhang
2020-03-11 17:45 ` Pavel Tatashin
2020-03-11 20:16 ` Kirill Tkhai
2020-03-11 20:25 ` Pavel Tatashin
2020-03-19 19:05 ` Daniel Jordan
2020-03-26 18:58 ` Daniel Jordan
2020-03-26 19:36 ` Pavel Tatashin
2020-03-27 4:39 ` Shile Zhang [this message]
2020-03-28 0:17 ` Daniel Jordan
2020-04-01 14:26 ` David Hildenbrand
2020-04-01 15:42 ` Michal Hocko
2020-04-01 15:50 ` David Hildenbrand
2020-04-01 16:00 ` Michal Hocko
2020-04-01 16:09 ` Daniel Jordan
2020-04-01 16:12 ` Michal Hocko
2020-04-01 16:15 ` David Hildenbrand
2020-04-01 16:18 ` Daniel Jordan
2020-04-01 16:26 ` Michal Hocko
2020-04-01 16:41 ` Pavel Tatashin
2020-04-01 16:46 ` Michal Hocko
2020-04-01 16:51 ` Pavel Tatashin
2020-04-01 17:13 ` Daniel Jordan
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=427ce795-0274-56e5-16e4-7be00c7145f7@linux.alibaba.com \
--to=shile.zhang@linux.alibaba.com \
--cc=akpm@linux-foundation.org \
--cc=daniel.m.jordan@oracle.com \
--cc=ktkhai@virtuozzo.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=pasha.tatashin@soleen.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).