[squid-users] Clustering/Redundancy with reverse proxy accelerators

OS = (linux RH 8.0 on IBM hardware)
The company I work for is currently using squid as an accelerator for a
large cluster of
servers that do image processing. We have one squid server sitting in
front of the
imageserver cluster which caches the image urls and reduces the load on
the servers
enormously. I've recently been trying to find a way in which I can run
2 squid accelerators
side by side, load-balanced using LVS. Ideally I'd like to get the 2
squid accelerators
to peer in such a way that if a request comes in to Accelerator-A it can
ask Accelerator-B
if it has it cached and if Accelerator-B doesn't have it cached then
Accelerator-A will contact
the origin servers directly and likewise if a request comes in to
Accelerator-B, contact Accelerator-A
in the same fashion. I thought that a dual-sibling relationship would
accomplish this
but from what I am observing there is no ICP communication between two
siblings in a parent-less
environment. Has anyone done this before? Any help would be greatly
appreciated.

-- 
Christopher Arnold
System Administrator
Pictage, Inc.