I can find the WARN in logs. The stuck should be caused by a long running cache operations. How to locate what cause the long running cache operations. My map-reduce job can run successfully without ignite hadoop accelerator.
[GridCachePartitionExchangeManager] Found long running cache operations, dump IO statistics. -- View this message in context: http://apache-ignite-users.70518.x6.nabble.com/MapReduce-Job-stuck-when-using-ignite-hadoop-accelerator-tp9216p9251.html Sent from the Apache Ignite Users mailing list archive at Nabble.com.