RubyForge: Starling. “Starling is a light-weight persistent queue server that speaks the MemCache protocol. It was built to drive Twitter’s backend, and is in production across Twitter’s cluster.”
Sign in with 
OpenID
RubyForge: Starling. “Starling is a light-weight persistent queue server that speaks the MemCache protocol. It was built to drive Twitter’s backend, and is in production across Twitter’s cluster.”
Considering Twitter suffered from a lot of scaling issues, is mentioning it really a good idea?
Since Starling was part of the solution to a lot of their scaling issues, I certainly think so. I don't think Twitter deserves to be used as an example of something that doesn't scale - they deal with an extraordinary amount of highly dynamic traffic and stay up most of the time. It would be great to hear an update from their engineering team on how they're dealing with scale though; it might help dispel some of the long-running myths.