On Tue, Apr 28, 2020 at 6:43 PM Michal Hocko <mhocko@xxxxxxxxxx> wrote:
>
> On Tue 28-04-20 16:22:46, Yafang Shao wrote:
> > On Tue, Apr 28, 2020 at 4:05 PM Michal Hocko <mhocko@xxxxxxxxxx> wrote:
> > >
> > > On Tue 28-04-20 09:45:27, Yafang Shao wrote:
> > > [...]
> > > > Seems we can't get an agreement on how to improve current code.
> > > > So I will submit a patch to revert the commit 9783aa9917f8 ("mm,
> > > > memcg: proportional memory.{low,min} reclaim") first.
> > >
> > > My current understanding is that the issue we are discussing here is
> > > mostly theoretical. Your changelog doesn't really talk about any real
> > > life workloads that would be suffering.
> >
> > Is real life workload really important ?
>
> It is really important to make cost vs. benefit decisions. Like whether
> to rever the said commit or not.
>
> > If so, why an issue[1] occured in the real workload report by me in
> > 2019 that memcg proection can't protect inactive pages (inodes) is
> > ignored again and again ?
>
> I do not think it is ignored. IIRC there was not an agreement on the way
> to fix this. I could get involved very much because there were other
> higher priority things to take care. People are simply busy.
>
In your theory - issues with real life workload has a higher priority,
you should pay more attention to that one, rather than wasting your
time on a comment war in this one.
Alright, the comment war really wastes time, that is not expected by me.
So let's turn back to the techichal discussion.
> > So I'm questioning that what is the real life workload ?
>
> It is a workload which does something useful for their users.
> [...]
> > > So it would be really more helpful to not insist on unrelated
> > > implementation details and focus on two things 1) split up the effective
> > > values calculation from the predicate (cleanup without any functional
> > > changes) 2) make the calculation more robust against racing reclaimers.
> > >
> >
> > Another thing should be considered as well, 0) don't access
> > memroy.emin and elow in get_scan_count().
>
> If you can achieve the gradual transition over protections by other
> means then I am really interested in more details.
sc->protection
I make my statement again - accessing the realy fragile emin & elow
in very deep reclaiming code is a totally horrible HACK, that is the
root of all evil.
--
Thanks
Yafang
