Hi there, I have a serious problem in my Hadoop cluster, that YARN Timeline server generates very high load, 800% CPU when there are 8 Spark Streaming jobs running in parallel. I discuss this problem on Hadoop group in parallel:
http://mail-archives.apache.org/mod_mbox/hadoop-user/201509.mbox/%3CCABtLTB=qaRFjVmChULNJ2h6GF2Uwvkq=Dz=fjygvmcacaeb...@mail.gmail.com%3E I would kindly like to ask you Spark users if you encountered this problem or know what to do with it? I'm at least desperately looking for a workaround. Like can I say to spark to not use YARN timeline server ? That would fix me for some time... Thanks for any help! Krzysiek
