On Tue, 21 Mar 2000, Bert Driehuis wrote:
> Well, yes and no. The problem as I see it is that unless you move the
> big objects around in the store_list, you have to skip them anyway on
> each expiration pass. My gut feeling tells me that skipping all those
> entries each second would be prohibitively expensive (for a 100GB disk
> cache with 600000 objecs, you would be able to store 100000 1MB objects
> and 500000 small ones, if I calculate this right, and you would probably
> wind up scanning all 100000 every time).
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.
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.
Received on Tue Mar 21 2000 - 09:14:36 MST
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:12:22 MST