On 10/16/2013 04:13 PM, Prakash Surya wrote:
> Actually, I think I've convinced myself I was wrong here. It should
> scale well with increased amounts of RAM, due to the table's size being
> proportional to the RAM size. It's the case when using more/smaller
> buffers with the same amount of RAM which could cause worse performance.

I am not that attached to the use of AVL trees myself. I just wanted to
provide an alternative method to addressing your concern of whether or
not we are handling hash collisions gracefully.

In trying to be helpful, I did convince myself that a large number of
AVL trees would be a slight improvement on Saso's work, but quite
honestly Saso's approach is fine. We are hopefully close enough to
splitting hairs on this that it would not matter too much either way.

Attachment: signature.asc
Description: OpenPGP digital signature

_______________________________________________
developer mailing list
[email protected]
http://lists.open-zfs.org/mailman/listinfo/developer

Reply via email to