Hi ARN, ZooKeeper returns success when write is persisted (i.e. fsync'ed to disk) to the majority of the cluster.
http://zookeeper.apache.org/doc/r3.1.2/zookeeperInternals.html#sc_guaranteesPropertiesDefinitions --Michi On Tue, May 29, 2012 at 11:32 AM, Narayanan A R <[email protected]> wrote: > Hi, > > How does ZK persistence work. Is it synchronous? The documentation says it > is a change journal like implementation. I assume a write request will not > return until the data is replicated to all the machines in the cluster and > each machine has successfully persisted to the disk? > > Regards, > ARN
