Re: Limiting the number of small objects

Duane Wessels wrote:

> This new replacement algorithm couldn't use the 'store_list'
> structure. It would have to use the heap structure instead. Squid
> already has support for non-LRU algorithms, but you have to give
> --enable-help-repalcement on the configure command.

Okay, so I made a mistake in not starting from 2.3 :-)

> It should be just a matter of defining a new "key" function for
> your size-based algorithm. The GDS algorithm already accounts
> for size, but probably not as strongly as you'd like.

Sounds like major progress has already been made.

I'll revisit the thing when I start looking at the next generation of
caching proxy server. For now, I need to roll out two dozen servers
across Europe in a month, and I'm reluctant to put 2.3 on a box I won't
be able to touch for the next year. Fortunately, I can test stuff on the
heavily hit central proxy in my office (that's why we've got two of
them!)

Thanks for the insight,

                                -- Bert

-- 
Bert Driehuis, MIS -- bert_driehuis@nl.compuware.com -- +31-20-3116119
Every nonzero finite dimensional inner product space has an
orthonormal basis. It makes sense, when you don't think about it.