Re: [PATCH v5 0/6] fs/dcache: Track & limit # of negative dentries

[Pavel Machek]

> > Yes, "should be".  I could understand that the presence of huge
> > nunmbers of -ve dentries could result in undesirable reclaim of
> > pagecache, etc.  Triggering oom-killings is very bad, and presumably
> > has the same cause.
> > 
> > Before we go and add a large amount of code to do the shrinker's job
> > for it, we should get a full understanding of what's going wrong.  Is
> > it because the dentry_lru had a mixture of +ve and -ve dentries? 
> > Should we have a separate LRU for -ve dentries?  Are we appropriately
> > aging the various dentries?  etc.
> > 
> > It could be that tuning/fixing the current code will fix whatever
> > problems inspired this patchset.
> 
> What I think is contributing to the problems and could lead to reclaim
> oddities is the internal fragmentation of dentry slab cache. Dentries are
> relatively small, you get 21 per page on my system, so if trivial to
> reclaim negative dentries get mixed with a small amount of unreclaimable
> positive dentries, you can get a lot of pages in dentry slab cache that are
> unreclaimable.

Could we allocate -ve entries from separate slab?

-- 
(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html