Thank you! I see that this is communication spi not discovery spi. But in other nodes there are many zk session timeout message or zk reconnect fail message. And the starvation message only print in the node which have the zk server(not cluster,just three zk node in one machine) in the same machine. In the log:"Completed: 17156 and blockCnt=0, waitCnt=17103 ". Why there are so many waitCnt? Is this a countdownlatch?
-- Sent from: http://apache-ignite-users.70518.x6.nabble.com/