HDFS-4569. Merge r1454233 from trunk

git-svn-id: https://svn.apache.org/repos/asf/hadoop/common/branches/branch-2@1454236 13f79535-47bb-0310-9956-ffa450edef68

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

@@ -20,6 +20,9 @@ Release 2.0.5-beta - UNRELEASED
     HDFS-4519. Support overriding jsvc binary and log file locations
     when launching secure datanode. (Chris Nauroth via suresh)
 
+    HDFS-4569. Small image transfer related cleanups.
+    (Andrew Wang via suresh)
+
   OPTIMIZATIONS
 
   BUG FIXES

hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/DFSConfigKeys.java

@@ -361,7 +361,7 @@ public class DFSConfigKeys extends CommonConfigurationKeys {
 
   // Image transfer timeout
   public static final String DFS_IMAGE_TRANSFER_TIMEOUT_KEY = "dfs.image.transfer.timeout";
-  public static final int DFS_IMAGE_TRANSFER_TIMEOUT_DEFAULT = 60 * 1000;
+  public static final int DFS_IMAGE_TRANSFER_TIMEOUT_DEFAULT = 10 * 60 * 1000;
 
   //Keys with no defaults
   public static final String  DFS_DATANODE_PLUGINS_KEY = "dfs.datanode.plugins";

hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/namenode/TransferFsImage.java

@@ -230,7 +230,6 @@ public class TransferFsImage {
       SecurityUtil.openSecureHttpConnection(url);
 
     if (timeout <= 0) {
-      // Set the ping interval as timeout
       Configuration conf = new HdfsConfiguration();
       timeout = conf.getInt(DFSConfigKeys.DFS_IMAGE_TRANSFER_TIMEOUT_KEY,
           DFSConfigKeys.DFS_IMAGE_TRANSFER_TIMEOUT_DEFAULT);

hadoop-hdfs-project/hadoop-hdfs/src/main/resources/hdfs-default.xml

@@ -733,12 +733,29 @@
   </description>
 </property>
 
+<property>
+  <name>dfs.image.transfer.timeout</name>
+  <value>600000</value>
+  <description>
+        Timeout for image transfer in milliseconds. This timeout and the related
+        dfs.image.transfer.bandwidthPerSec parameter should be configured such
+        that normal image transfer can complete within the timeout.
+        This timeout prevents client hangs when the sender fails during
+        image transfer, which is particularly important during checkpointing.
+        Note that this timeout applies to the entirety of image transfer, and
+        is not a socket timeout.
+  </description>
+</property>
+
 <property>
   <name>dfs.image.transfer.bandwidthPerSec</name>
   <value>0</value>
   <description>
-        Specifies the maximum amount of bandwidth that can be utilized for image
-        transfer in term of the number of bytes per second.
+        Maximum bandwidth used for image transfer in bytes per second.
+        This can help keep normal namenode operations responsive during
+        checkpointing. The maximum bandwidth and timeout in
+        dfs.image.transfer.timeout should be set such that normal image
+        transfers can complete successfully.
         A default value of 0 indicates that throttling is disabled. 
   </description>
 </property>