Clifton Royston <cliftonr@lava.net> wrote:
> Some products also have an option for attempting to partition the URL
> space between the cache servers based on a hash of the destination
> host; that would help too, and might achieve more effective use of your
> cache disk by reducing storage duplication across the two servers.
Currently, we're just using Squid in an http_accel mode, so our cache size
is well-bounded, but when I was pondering how our load-balanced setup should
be structured, I considered having the Squids setup to proxy content from
their sibling's memory, while not caching it on their own disk. The notion
being that it would be faster to retrieve from a sibling's memory than from
your own disk - effectively, you'd have Nx as much caching memory, but much
of that memory would be slower than the local memory. Never got far enough
down that road to thoroughly test the notion, though...
Later,
scott
Received on Wed Aug 18 1999 - 13:50:47 MDT
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:48:03 MST