Re: Gossip Analysis

2014-09-30 Thread William Katsak
Thanks for this info, I will read it now. The idea is, I have a modified version of Cassandra for a specific research application. I want to be able to make a supportable statement like this: After a state change, we wait x*gossip_interval in order to ensure with 0.9 probability that all

Re: Gossip Analysis

2014-09-30 Thread Brandon Williams
There is this very old ticket: https://issues.apache.org/jira/browse/CASSANDRA-617 But note that is gossip simulation, not the actual gossiper Cassandra uses (and also very antiquated.) Using the actual gossiper under simulation is unfortunately complicated by https://issues.apache.org/jira/brows