https://community.cloudera.com/t5/Support-Questions/DataXceiver-error-processing-read-and-write-operations/m-p/229680#M191533 <P> 0 down vote <A href="https://stackoverflow.com/questions/45932926/dataxceiver-error-processing-read-and-write-operations-hadoop#">favorite</A> </P><P>iam using hadoop apache 2.7.1 on centos 7 </P> <P>in HA cluster that consists of two namenodes and 6 data nodes and i realized the following error that always found in my log </P> <PRE><CODE>DataXceiver error processing WRITE_BLOCK operation src: /172.16.1.153:38360 dst: /172.16.1.153:50010 java.io.IOException: Connection reset by peer </CODE></PRE><P>so i updated the following propetey in hdfs-site.xml in order to increase the number of available threads in all datanodes </P><PRE><CODE>&lt;property&gt; &lt;name&gt;dfs.datanode.max.transfer.threads&lt;/name&gt; &lt;value&gt;16000&lt;/value&gt; &lt;/property&gt; </CODE></PRE><P>and i increased the number of open files too by editing baschrc </P><PRE><CODE>ulimit -n 16384 </CODE></PRE><P>but i still getting this error in my data nodes logs </P><P>so while sending write requests to the cluster </P><P>i issued the following command on data nodes to know number of threads </P><PRE><CODE>cat /proc/processid/status </CODE></PRE><P>and they never exceeds 100 thread </P><P>and in in order to know open files number issued sysctl fs.file-nr</P><P>and they never exceeds 300 open files</P><P>so why iam always getting this error in data node logs and what is it's effect on performance </P> Tue, 29 Aug 2017 14:17:03 GMT oula_alshiekh 2017-08-29T14:17:03Z