Messages in this thread | | | Date | Mon, 27 Feb 2023 15:42:46 +0530 | Subject | Re: [PATCH V2 2/3] sched/numa: Enhance vma scanning logic | From | Raghavendra K T <> |
| |
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.
| |