HDFS-7714. Simultaneous restart of HA NameNodes and DataNode can cause DataNode to register successfully with only one NameNode.(Contributed by Vinayakumar B)

hadoop-hdfs-project/hadoop-hdfs/CHANGES.txt

@@ -896,6 +896,9 @@ Release 2.7.0 - UNRELEASED
     HDFS-7718. Store KeyProvider in ClientContext to avoid leaking key provider
     threads when using FileContext (Arun Suresh via Colin P. McCabe)
 
+    HDFS-7714. Simultaneous restart of HA NameNodes and DataNode can cause
+    DataNode to register successfully with only one NameNode.(vinayakumarb)
+
 Release 2.6.1 - UNRELEASED
 
   INCOMPATIBLE CHANGES

hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/datanode/BPServiceActor.java

@@ -19,6 +19,7 @@ package org.apache.hadoop.hdfs.server.datanode;
 
 import static org.apache.hadoop.util.Time.now;
 
+import java.io.EOFException;
 import java.io.IOException;
 import java.net.InetSocketAddress;
 import java.net.SocketTimeoutException;
@@ -797,6 +798,10 @@ class BPServiceActor implements Runnable {
         // Use returned registration from namenode with updated fields
         bpRegistration = bpNamenode.registerDatanode(bpRegistration);
         break;
+      } catch(EOFException e) {  // namenode might have just restarted
+        LOG.info("Problem connecting to server: " + nnAddr + " :"
+            + e.getLocalizedMessage());
+        sleepAndLogInterrupts(1000, "connecting to server");
       } catch(SocketTimeoutException e) {  // namenode is busy
         LOG.info("Problem connecting to server: " + nnAddr);
         sleepAndLogInterrupts(1000, "connecting to server");