Consistent Connection Reset by Peer Errors During trainMatch Execution with IOException Stack Trace
My customer is hitting this error consistently when running trainMatch: In the driver logs, we see stack traces like this:
25/11/04 20:23:36 WARN TransportChannelHandler: Exception in connection from /<redact>:40654
java.io.IOException: Connection reset by peer
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:379)
at io.netty.buffer.PooledByteBuf.setBytes(PooledByteBuf.java:254)
at io.netty.buffer.AbstractByteBuf.writeBytes(AbstractByteBuf.java:1132)
at io.netty.channel.socket.nio.NioSocketChannel.doReadBytes(NioSocketChannel.java:357)
at io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:151)
at io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:788)
at io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:724)
at io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:650)
at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:562)
at io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997)
at io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74)
at io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30)
at java.lang.Thread.run(Thread.java:750)
25/11/04 20:23:36 ERROR TransportResponseHandler: Still have 15 requests outstanding when connection from /<redact>:40654 is closed
25/11/04 20:23:36 WARN BlockManagerMasterEndpoint: Error trying to remove broadcast 31337 from block manager BlockManagerId(7, <redact>, 34471, None)
java.io.IOException: Connection reset by peer
at sun.nio.ch.FileDispatcherImpl.read0(Native Method)
at sun.nio.ch.SocketDispatcher.read(SocketDispatcher.java:39)
at sun.nio.ch.IOUtil.readIntoNativeBuffer(IOUtil.java:223)
at sun.nio.ch.IOUtil.read(IOUtil.java:192)
at sun.nio.ch.SocketChannelImpl.read(SocketChannelImpl.java:379)
at io.netty.buffer.PooledByteBuf.setBytes(PooledByteBuf.java:254)
at io.netty.buffer.AbstractByteBuf.writeBytes(AbstractByteBuf.java:1132)
at io.netty.channel.socket.nio.NioSocketChannel.doReadBytes(NioSocketChannel.java:357)
at io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:151)
at io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:788)
at io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:724)
at io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:650)
at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:562)
at io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997)
at io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74)
at io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30)
at java.lang.Thread.run(Thread.java:750)
