Dynamo Systems Work Too Hard

Re:Dynamo Systems Work Too Hard by damienkatz on Friday May 03, 2013 @10:34PM (#5653710)

Good point. But "writes" are very fast, in our tests write latency is less than half read latency, so we can easily do master to slave replication within the SLA. But you point is correct, a Dynamo system is faster to achieve the same replication factor.

[ Parent | on HN ]

Re:Dynamo Systems Work Too Hard by jbellis on Saturday May 04, 2013 @01:13AM (#5654090)

I think it's worth elaborating that the primary advantage to the dynamo model is not in the best- or average- case, but when everything does not go as planned -- when the master gets behind, when ec2 network latency spikes, etc. Then "any two replicas" instead of "master plus one more" is much more robust.

[ Parent | on HN ]

Re:Dynamo Systems Work Too Hard by banachtarski on Saturday May 04, 2013 @03:29AM (#5654373)

Do you surround the word "writes" in quotes because they aren't truly writes in the durable sense?

[ Parent | on HN ]