Strategies for splitting load across varnish instances? And avoiding single-point-of-failure?

[Bendik Heltne]

> A couple more questions:
>
> (1) Are they any good strategies for splitting load across Varnish
> front-ends? Or is the common practice to have just one Varnish server?

We have 3 servers. A bit overkill, but then we have redundancy even if
one fail. I guess 2 is the minimum option if you have an important
site and 99,5% uptime guarantee.

> (2) How do people avoid single-point-of-failure for Varnish? Do people
> run Varnish on two servers, amassing similar local caches, but put
> something in front of the two Varnishes? Or round-robin-DNS?

We use a loadbalancer from F5 called BigIP. It's no exactly free, but
there are free alternatives that will probably do much of the basic
stuff:
http://lcic.org/load_balancing.html

- Bendik