mån 2010-06-21 klockan 13:08 +0100 skrev Nick Cairncross:
> Hi All,
>
> I'm just looking into clustering Squid and wanted to see what experiences people have had.
>
> Currently we have two non-Squid proxies on two different sites. Each has a virtual IP (the VIP network is extended over the two sites) and a physical IP (though different VLANs)
>
> Site A: VIP 172.16.10.8 IP 172.16.40.60
> Site B: VIP 172.16.10.7 IP 172.16.8.60
Why two VIP and how do clients select which VIP they should connect to?
> Each box also has multicast addresses assigned to them. e.g..
>
> 172.16.10.7:
> 244.0.99.2
> 244.0.99.1
>
> 172.16.10.8:
> 244.0.99.1
> 244.0.99.2
WHat is the multicast addresses used for?
> Using the config tool of the proxies, you set the priority of each 'home' VIP as 100 and the other site as 50. This means they act on each site, servicing requests etc. However, should one proxy fail I can raise the priority of the other so that it also hosts the VIP of the broken proxy and takes over.
>
> All this is a long way round to saying I can flip my users to whatever proxy I want, take one out of commission etc and it works nicely. I'd like to use something similar is Squid. The added complication is that I use Kerberos authentication, which is dependent on host name. I can't quite see a way to achieve what I want yet.
I usually do a setup very similar to what you describe by using Linux
heartbeat using it's ldirectord component for managing the load
balancing. This scales to pretty much any number of hosts using one or
more VIP.
Regards
Henrik
Received on Mon Jun 21 2010 - 12:34:07 MDT
This archive was generated by hypermail 2.2.0 : Mon Jun 21 2010 - 12:00:03 MDT