From: Charan Teja Kalla <charante@codeaurora.org>
To: David Rientjes <rientjes@google.com>, Vlastimil Babka <vbabka@suse.cz>
Cc: akpm@linux-foundation.org, mhocko@suse.com,
khalid.aziz@oracle.com, ngupta@nitingupta.dev,
vinmenon@codeaurora.org, linux-mm@kvack.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH V3] mm/compaction: correct deferral logic for proactive compaction
Date: Wed, 27 Jan 2021 21:17:58 +0530 [thread overview]
Message-ID: <7ce8f4f1-0d83-bb85-e516-33071d85ad3a@codeaurora.org> (raw)
In-Reply-To: <627a82ec-94ef-a233-4637-28bc82a886e9@google.com>
On 1/25/2021 4:24 AM, David Rientjes wrote:
> On Wed, 20 Jan 2021, Vlastimil Babka wrote:
>
>> On 1/19/21 8:26 PM, David Rientjes wrote:
>>> On Mon, 18 Jan 2021, Charan Teja Reddy wrote:
>>>
>>>> should_proactive_compact_node() returns true when sum of the
>>>> weighted fragmentation score of all the zones in the node is greater
>>>> than the wmark_high of compaction, which then triggers the proactive
>>>> compaction that operates on the individual zones of the node. But
>>>> proactive compaction runs on the zone only when its weighted
>>>> fragmentation score is greater than wmark_low(=wmark_high - 10).
>>>>
>>>> This means that the sum of the weighted fragmentation scores of all the
>>>> zones can exceed the wmark_high but individual weighted fragmentation
>>>> zone scores can still be less than wmark_low which makes the unnecessary
>>>> trigger of the proactive compaction only to return doing nothing.
>>>>
>>>> Issue with the return of proactive compaction with out even trying is
>>>> its deferral. It is simply deferred for 1 << COMPACT_MAX_DEFER_SHIFT if
>>>> the scores across the proactive compaction is same, thinking that
>>>> compaction didn't make any progress but in reality it didn't even try.
>>>
>>> Isn't this an issue in deferred compaction as well? It seems like
>>> deferred compaction should check that work was actually performed before
>>> deferring subsequent calls to compaction.
>>
>> Direct compaction does, proactive not.
>>
>>> In other words, I don't believe deferred compaction is intended to avoid
>>> checks to determine if compaction is worth it; it should only defer
>>> *additional* work that was not productive.
>>
>> Yeah, that should be more optimal.
>>
>
> Charan, is this something you'd like to follow up on, or should I take a
> look instead?
>
Sure David. Happy to follow up on this. Thanks!
> Thanks!
>
--
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora
Forum, a Linux Foundation Collaborative Project
next prev parent reply other threads:[~2021-01-27 15:48 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-18 17:12 [PATCH V3] mm/compaction: correct deferral logic for proactive compaction Charan Teja Reddy
2021-01-18 17:41 ` Vlastimil Babka
2021-01-19 15:42 ` Khalid Aziz
2021-01-19 19:26 ` David Rientjes
2021-01-20 11:04 ` Vlastimil Babka
2021-01-24 22:54 ` David Rientjes
2021-01-27 15:47 ` Charan Teja Kalla [this message]
2021-01-25 15:56 ` Vlastimil Babka
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=7ce8f4f1-0d83-bb85-e516-33071d85ad3a@codeaurora.org \
--to=charante@codeaurora.org \
--cc=akpm@linux-foundation.org \
--cc=khalid.aziz@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@suse.com \
--cc=ngupta@nitingupta.dev \
--cc=rientjes@google.com \
--cc=vbabka@suse.cz \
--cc=vinmenon@codeaurora.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).