[squid-users] Preferred origin server in redundant system, accelerator mode

Hi,

I've looked through the documentation and posts and haven't found
exactly what I'm looking for.

I have a Squid in front of two Apache servers for high availability
reasons. Because sessions are involved for some functions, I'd like to
configure Squid to send all requests to a particular Apache instance,
and only to the other one if the preferred Apache fails.

None of the peer selection methods in the cache_peer documentation seems
to fit this exactly, although it looks like setting "default" to the
failover instance would do the trick. However, the documentation
indicates that ICP is needed for those options and these are Apaches
rather than Squids.

Has anyone else set up a configuration like this one before? Any help
would be gratefully received.

Kind Regards,
Micky
Received on Thu Jan 06 2011 - 01:19:54 MST