Re: [RFC PATCH]: Dynamically sized routing cache hash table.

[Eric Dumazet <dada1@cosmosbay.com>]

On Tuesday 06 March 2007 18:05, Robert Olsson wrote:
> Eric Dumazet writes:
>  > Indeed. It would be nice to see how it performs with say 2^20
>  > elements... Because with your data, I wonder if the extra complexity of
>  > the trash is worth it (since most lookups are going to only hit the hash
>  > and give the answer without intermediate nodes)
>
>  I don't know if I understand you fully. Yes in most cases the first lookup
> via "hash-header" will take us to direct to the correct leaf. If there are
> "collisions" we have to sort them out by adding intermediate nodes.

With 2^20 entries, your actual limit of 2^19 entries in root node will 
probably show us quite different numbers for order-1,2,3,4... tnodes

>
>  Something like where you have resizable hash where is each bucket in turn
> is a resizable hash etc.

Yes, numbers you gave us basically showed a big root node, and mainly leaves 
and very few tnodes.

I was interested to see the distribution in case the root-node limit is hit, 
and we load into the table a *lot* of entries.