From b83348c2e339bfea143e47217d837f1ad569dfbe Mon Sep 17 00:00:00 2001
From: Kihwal Lee <kihwal@apache.org>
Date: Thu, 18 Feb 2016 13:27:39 -0600
Subject: [PATCH] HDFS-4946. Allow preferLocalNode in
 BlockPlacementPolicyDefault to be configurable. Contributed by James Kinley
 and Nathan Roberts.

(cherry picked from commit ba6d5ed955aa34cdcb7aaa4b1025da6ee5e91355)
---
 hadoop-hdfs-project/hadoop-hdfs/CHANGES.txt          |  3 +++
 .../java/org/apache/hadoop/hdfs/DFSConfigKeys.java   |  3 +++
 .../blockmanagement/BlockPlacementPolicyDefault.java |  7 ++++++-
 .../hadoop-hdfs/src/main/resources/hdfs-default.xml  | 12 ++++++++++++
 4 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/hadoop-hdfs-project/hadoop-hdfs/CHANGES.txt b/hadoop-hdfs-project/hadoop-hdfs/CHANGES.txt
index 57700766745..8076f577ab8 100644
--- a/hadoop-hdfs-project/hadoop-hdfs/CHANGES.txt
+++ b/hadoop-hdfs-project/hadoop-hdfs/CHANGES.txt
@@ -1890,6 +1890,9 @@ Release 2.7.3 - UNRELEASED
     HDFS-9669. TcpPeerServer should respect ipc.server.listen.queue.size
     (Elliot Clark via cmccabe)
 
+    HDFS-4946. Allow preferLocalNode in BlockPlacementPolicyDefault to be
+    configurable (James Kinley and Nathan Roberts via kihwal)
+
   OPTIMIZATIONS
 
   BUG FIXES
diff --git a/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/DFSConfigKeys.java b/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/DFSConfigKeys.java
index 71e931ada40..98c1bae7502 100644
--- a/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/DFSConfigKeys.java
+++ b/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/DFSConfigKeys.java
@@ -636,6 +636,9 @@ public class DFSConfigKeys extends CommonConfigurationKeys {
       "dfs.namenode.available-space-block-placement-policy.balanced-space-preference-fraction";
   public static final float   DFS_NAMENODE_AVAILABLE_SPACE_BLOCK_PLACEMENT_POLICY_BALANCED_SPACE_PREFERENCE_FRACTION_DEFAULT =
       0.6f;
+  public static final String  DFS_NAMENODE_BLOCKPLACEMENTPOLICY_DEFAULT_PREFER_LOCAL_NODE_KEY =
+      "dfs.namenode.block-placement-policy.default.prefer-local-node";
+  public static final boolean  DFS_NAMENODE_BLOCKPLACEMENTPOLICY_DEFAULT_PREFER_LOCAL_NODE_DEFAULT = true;
 
   public static final String DFS_BLOCK_LOCAL_PATH_ACCESS_USER_KEY = "dfs.block.local-path-access.user";
   public static final String DFS_DOMAIN_SOCKET_PATH_KEY =
diff --git a/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/blockmanagement/BlockPlacementPolicyDefault.java b/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/blockmanagement/BlockPlacementPolicyDefault.java
index 14439e74c73..ee891a5e689 100644
--- a/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/blockmanagement/BlockPlacementPolicyDefault.java
+++ b/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/blockmanagement/BlockPlacementPolicyDefault.java
@@ -59,7 +59,7 @@ public class BlockPlacementPolicyDefault extends BlockPlacementPolicy {
 
   protected boolean considerLoad; 
   protected double considerLoadFactor;
-  private boolean preferLocalNode = true;
+  private boolean preferLocalNode;
   protected NetworkTopology clusterMap;
   protected Host2NodesMap host2datanodeMap;
   private FSClusterStats stats;
@@ -95,6 +95,11 @@ public class BlockPlacementPolicyDefault extends BlockPlacementPolicy {
     this.staleInterval = conf.getLong(
         DFSConfigKeys.DFS_NAMENODE_STALE_DATANODE_INTERVAL_KEY, 
         DFSConfigKeys.DFS_NAMENODE_STALE_DATANODE_INTERVAL_DEFAULT);
+    this.preferLocalNode = conf.getBoolean(
+        DFSConfigKeys.
+            DFS_NAMENODE_BLOCKPLACEMENTPOLICY_DEFAULT_PREFER_LOCAL_NODE_KEY,
+        DFSConfigKeys.
+            DFS_NAMENODE_BLOCKPLACEMENTPOLICY_DEFAULT_PREFER_LOCAL_NODE_DEFAULT);
   }
 
   @Override
diff --git a/hadoop-hdfs-project/hadoop-hdfs/src/main/resources/hdfs-default.xml b/hadoop-hdfs-project/hadoop-hdfs/src/main/resources/hdfs-default.xml
index a1fe2778257..32a771150d4 100644
--- a/hadoop-hdfs-project/hadoop-hdfs/src/main/resources/hdfs-default.xml
+++ b/hadoop-hdfs-project/hadoop-hdfs/src/main/resources/hdfs-default.xml
@@ -921,6 +921,18 @@
   </description>
 </property>
 
+<property>
+  <name>dfs.namenode.block-placement-policy.default.prefer-local-node</name>
+  <value>true</value>
+  <description>Controls how the default block placement policy places
+  the first replica of a block. When true, it will prefer the node where
+  the client is running.  When false, it will prefer a node in the same rack
+  as the client. Setting to false avoids situations where entire copies of
+  large files end up on a single node, thus creating hotspots.
+  </description>
+</property>
+
+
 <property>
   <name>dfs.stream-buffer-size</name>
   <value>4096</value>