Hi Stephan, Anyways the Async exception is gone.
I have increased my instance type to r3.2xlarge having 60GB of memory. BUt what I have observed here is that for two task managers the memory usage is close to 30GB but for other two it goes up to 55GB, the load is equally distributed among all TM's. Why does this happen ? -- View this message in context: http://apache-flink-user-mailing-list-archive.2336050.n4.nabble.com/Re-Checkpointing-with-RocksDB-as-statebackend-tp11752p11831.html Sent from the Apache Flink User Mailing List archive. mailing list archive at Nabble.com.