CPU overload due to a java exception


#1

Hi everyone,
I have a problem. The load Average of my server up abnormally during 5 minutes randomly during the day. I checked my elasticsearch logs and i saw :

[2016-02-26 12:55:54,106][WARN ][http.netty ] [elasticsearch-node-1] Caught exception while handling client http traffic, closing connection [id: 0xb472ab56, /127.0.0.1:52092 => /127.0.0.1:17198] java.io.IOException: Connexion ré-initialisée par le correspondant at sun.nio.ch.FileDispatcherImpl.read0(Native Method) at sun.nio.ch.SocketDispatcher.read(SocketDispatcher.java:39) at sun.nio.ch.IOUtil.readIntoNativeBuffer(IOUtil.java:223) at sun.nio.ch.IOUtil.read(IOUtil.java:192) at sun.nio.ch.SocketChannelImpl.read(SocketChannelImpl.java:384) at org.jboss.netty.channel.socket.nio.NioWorker.read(NioWorker.java:64) at org.jboss.netty.channel.socket.nio.AbstractNioWorker.process(AbstractNioWorker.java:108) at org.jboss.netty.channel.socket.nio.AbstractNioSelector.run(AbstractNioSelector.java:337) at org.jboss.netty.channel.socket.nio.AbstractNioWorker.run(AbstractNioWorker.java:89) at org.jboss.netty.channel.socket.nio.NioWorker.run(NioWorker.java:178) at org.jboss.netty.util.ThreadRenamingRunnable.run(ThreadRenamingRunnable.java:108) at org.jboss.netty.util.internal.DeadLockProofWorker$1.run(DeadLockProofWorker.java:42) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745)

I only have logstash and kibana in communication with my elastic search.

Any ideas ?


(Mark Walkom) #2

What version are you on?


#3

I use the latest version of elasticsearch / kibana and logstash.


(Thomas Decaux) #4

Hello, look like a network issue between logstash and elasticsearch, maybe a too big bulk size.

Can you post your logstash configuration and CLI options. And runs HTTP GET "{ES}/_nodes/stats/thread_pool" to see if bulk threads pool is normal or not.


(system) #5