> Don't know of anyone offhand... The code related to the slabber isn't too
> complex, so you'd get an idea from a read-through.

Yeah, that is why I think this idea may work, tweak something very
simple, yet very well tested.

> slabs.c just defines what sizes memory is, what to hand out where, etc. 
> Managing it outside of
> that (hash table, lru, etc) is up to your application.

Right, that is what I want, my app will do its own eviction.

> It still has a weakness of not being able to reassign memory if you put it
> all into one slab class pool.

I have 16 fixed sizes (ranging from 1K-6K, all slightly irregular size
[e.g. 1028 bytes]), so I will use the slab allocator every time I need
one of these fixed sizes. So I will have 16 different slab-classes
(unsure of terminology) and there may be minimal overhead (possibly
1MB per slab-class that is underunused) but I can live w/ that.

Are my assumptions correct?

and thanks,
 jak

Reply via email to