Server Fault is a question and answer site for system and network administrators. It's 100% free, no registration required.

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

I'm looking to replace memcached. We have a LOT of traffic to our central memcached node which I'd like to split. There's only so much trunking networks I can do.

My general idea is to install a memcached-type daemon on every webserver and have the daemons replicate set/delete/updates over all the daemons, so that each webserver connects to a socket or on localhost. All data should be available on all nodes.

The alternatives: - repcached (max 2 masters) - redis (single master) - couchdb/mongodb/handlersocket - persistent data on disk, I'd like to remove the disk part to gain more performance.

Any hints?

share|improve this question

Consider using Membase in caching (memory-only) mode, it's memcached-based

share|improve this answer
Membase is "Couchbase" now: – the-wabbit Jul 11 '12 at 16:54
@Alex, does Couchbase have a (synchronous) replication mechanism between nodes in a cluster? – HTTP500 Jul 14 '12 at 1:53

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.