Enable detection of slow DataNodes

When slow DataNode detection is enabled, DataNodes collect latency statistics on their peers during write pipelines, and use periodic outlier detection to determine slow peers. The NameNode aggregates reports from all DataNodes and flags potentially slow nodes. Slow DataNode detection is disabled by default.

  1. To enable slow DataNode detection, set the value of the dfs.datanode.peer.stats.enabled property to true in hdfs-site.xml.
  2. Access the slow DataNode statistics either from the NameNode JMX page at http://<namenode_host>:50070/jmx or from the DataNode JMX page at http://<datanode_host>:50075/jmx.
    In the following JMX output example, the time unit is milliseconds, and the peer DataNodes are healthy because the latencies are in milliseconds:
    "name" : "Hadoop:service=DataNode,name=DataNodeInfo",
    "modelerType" : "org.apache.hadoop.hdfs.server.datanode.DataNode",    "SendPacketDownstreamAvgInfo" : "{        
            \"[]RollingAvgTime\" : 1.4476967370441458,
            \"[]RollingAvgTime\" : 1.5569170444798432