OK. There could have been a temporary network issue between the server and client node.
However, I was expecting the server node to throw the client out of the cluster and resume normal functioning. But what bothers me is that the server node never recovered after the network issue and finally got stuck in dumping threads. If there was a bigger network issue, I would have expected the server to report segmentation and go to the failure handler. This did not happen. Feels like the handling of this scenario is not proper in ignite code. -- Sent from: http://apache-ignite-users.70518.x6.nabble.com/