Very strange. I've never encountered something like that with any database or cache. Wonder if it's somehow related to the way that your cluster is setup?
How big is this cluster? Are you writing and reading to the entire cluster, or do you have certain nodes that you write to and others that you read from?
How big is this cluster? Are you writing and reading to the entire cluster, or do you have certain nodes that you write to and others that you read from?