HADOOP-497. Permit the specification of the network interface and nameserver to be used when determining the local hostname advertised by datanodes and tasktrackers. Contributed by Lorenzo Thione.

git-svn-id: https://svn.apache.org/repos/asf/lucene/hadoop/trunk@441204 13f79535-47bb-0310-9956-ffa450edef68

CHANGES.txt

@@ -143,6 +143,11 @@ Trunk (unreleased changes)
     connection is closed, conserving resources on both client and
     server. (Devaraj Das via cutting)
 
+36. HADOOP-497.  Permit the specification of the network interface and
+    nameserver to be used when determining the local hostname
+    advertised by datanodes and tasktrackers.
+    (Lorenzo Thione via cutting)
+
 
 Release 0.5.0 - 2006-08-04
 

conf/hadoop-default.xml

@@ -111,6 +111,23 @@ creations/deletions), or "all".</description>
   </description>
 </property>
 
+ <property>
+  <name>dfs.datanode.dns.interface</name>
+  <value>default</value>
+  <description>The name of the Network Interface from which a data node should 
+  report its IP address.
+  </description>
+ </property>
+ 
+<property>
+  <name>dfs.datanode.dns.nameserver</name>
+  <value>default</value>
+  <description>The host name or IP address of the name server (DNS)
+  which a DataNode should use to determine the host name used by the
+  NameNode for communication and display purposes.
+  </description>
+ </property>
+ 
 <property>
   <name>dfs.default.chunk.view.size</name>
   <value>2048</value>
@@ -372,6 +389,24 @@ creations/deletions), or "all".</description>
   </description>
 </property>
 
+
+<property>
+  <name>mapred.tasktracker.dns.interface</name>
+  <value>default</value>
+  <description>The name of the Network Interface from which a task
+  tracker should report its IP address.
+  </description>
+ </property>
+ 
+<property>
+  <name>mapred.tasktracker.dns.nameserver</name>
+  <value>default</value>
+  <description>The host name or IP address of the name server (DNS)
+  which a TaskTracker should use to determine the host name used by
+  the JobTracker for communication and display purposes.
+  </description>
+ </property>
+ 
 <property>
   <name>tasktracker.http.threads</name>
   <value>40</value>

src/java/org/apache/hadoop/dfs/DataNode.java

@@ -20,6 +20,7 @@ import org.apache.commons.logging.*;
 import org.apache.hadoop.ipc.*;
 import org.apache.hadoop.conf.*;
 import org.apache.hadoop.metrics.Metrics;
+import org.apache.hadoop.net.DNS;
 import org.apache.hadoop.util.*;
 import org.apache.hadoop.util.DiskChecker.DiskErrorException;
 import org.apache.hadoop.util.DiskChecker.DiskOutOfSpaceException;
@@ -182,6 +183,13 @@ public class DataNode implements FSConstants, Runnable {
       for (int idx = 0; idx < dataDirs.length; idx++) {
         volumes[idx] = new File(dataDirs[idx]);
       }
+
+      // use configured nameserver & interface to get local hostname
+      machineName =
+        DNS.getDefaultHost
+        (conf.get("dfs.datanode.dns.interface","default"),
+         conf.get("dfs.datanode.dns.nameserver","default"));
+ 
       // get storage info and lock the data dirs
       storage = new DataStorage( volumes );
       int numDirs = storage.getNumLocked();

src/java/org/apache/hadoop/mapred/TaskTracker.java

@@ -31,6 +31,7 @@ import java.util.regex.Pattern;
 import org.apache.hadoop.metrics.ContextFactory;
 import org.apache.hadoop.metrics.MetricsContext;
 import org.apache.hadoop.metrics.MetricsRecord;
+import org.apache.hadoop.net.DNS;
 
 /*******************************************************
  * TaskTracker is a process that starts and tracks MR Tasks
@@ -153,8 +154,12 @@ public class TaskTracker
      * close().
      */
     synchronized void initialize() throws IOException {
-        this.localHostname = InetAddress.getLocalHost().getHostName();
-
+        // use configured nameserver & interface to get local hostname
+        this.localHostname =
+          DNS.getDefaultHost
+          (fConf.get("mapred.tasktracker.dns.interface","default"),
+           fConf.get("mapred.tasktracker.dns.nameserver","default"));
+ 
         //check local disk
         checkLocalDirs(this.fConf.getLocalDirs());
         fConf.deleteLocalFiles(SUBDIR);

src/java/org/apache/hadoop/net/DNS.java

@@ -0,0 +1,194 @@
+package org.apache.hadoop.net;
+
+import java.io.IOException;
+import java.net.InetAddress;
+import java.net.NetworkInterface;
+import java.net.SocketException;
+import java.net.UnknownHostException;
+import java.util.Enumeration;
+import java.util.Vector;
+
+import javax.naming.NamingException;
+import javax.naming.directory.Attributes;
+import javax.naming.directory.DirContext;
+import javax.naming.directory.InitialDirContext;
+
+/**
+ * 
+ * A class that provides direct and reverse lookup functionalities, allowing
+ * the querying of specific network interfaces or nameservers.
+ * 
+ * @author Lorenzo Thione
+ * 
+ */
+public class DNS {
+
+  /**
+   * Returns the hostname associated with the specified IP address by the
+   * provided nameserver.
+   * 
+   * @param hostIp
+   *            The address to reverse lookup
+   * @param ns
+   *            The host name of a reachable DNS server
+   * @return The host name associated with the provided IP
+   * @throws NamingException
+   *             If a NamingException is encountered
+   */
+  public static String reverseDns(InetAddress hostIp, String ns)
+    throws NamingException {
+    //
+    // Builds the reverse IP lookup form
+    // This is formed by reversing the IP numbers and appending in-addr.arpa
+    //
+    String[] parts = hostIp.getHostAddress().split("\\.");
+    String reverseIP = parts[3] + "." + parts[2] + "." + parts[1] + "."
+      + parts[0] + ".in-addr.arpa";
+
+    DirContext ictx = new InitialDirContext();
+    Attributes attribute =
+      ictx.getAttributes("dns://"               // Use "dns:///" if the default
+                         + ((ns == null) ? "" : ns) + 
+                         // nameserver is to be used
+                         "/" + reverseIP, new String[] { "PTR" });
+    ictx.close();
+    
+    return attribute.get("PTR").get().toString();
+  }
+
+  /**
+   * Returns all the IPs associated with the provided interface, if any, in
+   * textual form.
+   * 
+   * @param strInterface
+   *            The name of the network interface to query (e.g. eth0)
+   * @return A string vector of all the IPs associated with the provided
+   *         interface
+   * @throws UnknownHostException
+   *             If an UnknownHostException is encountered in querying the
+   *             default interface
+   * 
+   */
+  public static String[] getIPs(String strInterface)
+    throws UnknownHostException {
+    try {
+      NetworkInterface netIF = NetworkInterface.getByName(strInterface);
+      if (netIF == null)
+        return new String[] { InetAddress.getLocalHost()
+                              .getHostAddress() };
+      else {
+        Vector ips = new Vector();
+        Enumeration e = netIF.getInetAddresses();
+        while (e.hasMoreElements())
+          ips.add(((InetAddress) e.nextElement()).getHostAddress());
+        return (String[]) ips.toArray(new String[] {});
+      }
+    } catch (SocketException e) {
+      return new String[] { InetAddress.getLocalHost().getHostAddress() };
+    }
+  }
+
+  /**
+   * Returns the first available IP address associated with the provided
+   * network interface
+   * 
+   * @param strInterface
+   *            The name of the network interface to query (e.g. eth0)
+   * @return The IP address in text form
+   * @throws UnknownHostException
+   *             If one is encountered in querying the default interface
+   */
+  public static String getDefaultIP(String strInterface)
+    throws UnknownHostException {
+    String[] ips = getIPs(strInterface);
+    return ips[0];
+  }
+
+  /**
+   * Returns all the host names associated by the provided nameserver with the
+   * address bound to the specified network interface
+   * 
+   * @param strInterface
+   *            The name of the network interface to query (e.g. eth0)
+   * @param nameserver
+   *            The DNS host name
+   * @return A string vector of all host names associated with the IPs tied to
+   *         the specified interface
+   * @throws UnknownHostException
+   */
+  public static String[] getHosts(String strInterface, String nameserver)
+    throws UnknownHostException {
+    String[] ips = getIPs(strInterface);
+    Vector hosts = new Vector();
+    for (int ctr = 0; ctr < ips.length; ctr++)
+      try {
+        hosts.add(reverseDns(InetAddress.getByName(ips[ctr]),
+                             nameserver));
+      } catch (Exception e) {
+      }
+
+    if (hosts.size() == 0)
+      return new String[] { InetAddress.getLocalHost().getHostName() };
+    else
+      return (String[]) hosts.toArray(new String[] {});
+  }
+
+  /**
+   * Returns all the host names associated by the default nameserver with the
+   * address bound to the specified network interface
+   * 
+   * @param strInterface
+   *            The name of the network interface to query (e.g. eth0)
+   * @return The list of host names associated with IPs bound to the network
+   *         interface
+   * @throws UnknownHostException
+   *             If one is encountered while querying the deault interface
+   * 
+   */
+  public static String[] getHosts(String strInterface)
+    throws UnknownHostException {
+    return getHosts(strInterface, null);
+  }
+
+  /**
+   * Returns the default (first) host name associated by the provided
+   * nameserver with the address bound to the specified network interface
+   * 
+   * @param strInterface
+   *            The name of the network interface to query (e.g. eth0)
+   * @param nameserver
+   *            The DNS host name
+   * @return The default host names associated with IPs bound to the network
+   *         interface
+   * @throws UnknownHostException
+   *             If one is encountered while querying the deault interface
+   */
+  public static String getDefaultHost(String strInterface, String nameserver)
+    throws UnknownHostException {
+    if (strInterface.equals("default")) 
+      return InetAddress.getLocalHost().getHostName();
+
+    if (nameserver.equals("default"))
+      return getDefaultHost(strInterface);
+
+    String[] hosts = getHosts(strInterface, nameserver);
+    return hosts[0];
+  }
+
+  /**
+   * Returns the default (first) host name associated by the default
+   * nameserver with the address bound to the specified network interface
+   * 
+   * @param strInterface
+   *            The name of the network interface to query (e.g. eth0)
+   * @return The default host name associated with IPs bound to the network
+   *         interface
+   * @throws UnknownHostException
+   *             If one is encountered while querying the deault interface
+   */
+  public static String getDefaultHost(String strInterface)
+    throws UnknownHostException {
+    return getDefaultHost(strInterface, null);
+  }
+
+}

src/java/org/apache/hadoop/net/package.html

@@ -0,0 +1,5 @@
+<html>
+<body>
+Network-related classes.
+</body>
+</html>