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.
> 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.
--
Michal Hocko
SUSE Labs
