[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <3a9269bf-0d1c-59b4-f80f-afbbdf9c45b4@amd.com>
Date: Mon, 27 Feb 2023 15:42:46 +0530
From: Raghavendra K T <raghavendra.kt@....com>
To: Peter Zijlstra <peterz@...radead.org>
Cc: linux-kernel@...r.kernel.org, linux-mm@...ck.org,
Ingo Molnar <mingo@...hat.com>, Mel Gorman <mgorman@...e.de>,
Andrew Morton <akpm@...ux-foundation.org>,
David Hildenbrand <david@...hat.com>, rppt@...nel.org,
Bharata B Rao <bharata@....com>,
Disha Talreja <dishaa.talreja@....com>
Subject: Re: [PATCH V2 2/3] sched/numa: Enhance vma scanning logic
On 2/27/2023 3:36 PM, Peter Zijlstra wrote:
> On Mon, Feb 27, 2023 at 12:10:41PM +0530, Raghavendra K T wrote:
>> In summary: I do see that access to VMAs from disjoint sets is not fully
>> fair, But on the other hand it is not very bad too. There is definitely
>> some scope or possibility to explore/improve fairness in this area
>> further.
>
> Ok, might be good to summarize some of this in a comment near here, so
> that readers are aware of the caveat of this code.
>
Sure will do.
>> PS: I have also tested above applying V3 patch (which incorporates your
>> suggestions), have not seen much deviation in observation with patch.
>
> I'll see if I can find it in this dumpester fire I call inbox :-)
Sorry I wasn't clear there.. Still in inbox and am about to post.. It
was a heads up.
Powered by blists - more mailing lists