Re: [PATCH] mm: madvise: fix uneven accounting of psi

[Pavan Kondeti <quic_pkondeti@quicinc.com>]

On Fri, Jun 09, 2023 at 06:12:28PM +0530, Charan Teja Kalla wrote:
> Thanks Suren & Johannes,
> 
> On 6/7/2023 1:18 AM, Suren Baghdasaryan wrote:
> > Hi Folks. Sorry for being late to the party.
> > Yeah, userspace does not have a crystal ball to predict future user
> > behavior, so there will always be pathological cases when usual
> > assumptions and resulting madvise() would make things worse.
> > 
> > I think this discussion can be split into several questions/issues:
> > 1. Inconsistency in how madvise(MADV_PAGEOUT) would affect PSI
> > calculation when the page is refaulted, based on the path it took
> > before being evicted by madvise(). In your initial description case
> > (a) is inconsistent with (b) and (c) and it's probably worth fixing.
> > IMHO (a) should be made consistent with others, not the other way
> > around. My reasoning is that page was expelled from the active list,
> > so it was part of the active workingset.
> > 
> That means we should be setting Workingset on the page while it is on
> the active list and when it is being pageout through madvising. Right? I
> see, this makes it consistent.
> 
> On the same note, discussing with Suren offline, Should the refaulted
> madvise pages start always at the inactive list? If they are really
> active, they get promoted anyway..
> 
Can you elaborate on the rationale why refaulted madvise pages needs to
be on inactive list? If it had not been paged out via madvise, it would
have been activated no?

Thanks,
Pavan