Clear tasktracker's file cache before it re-initializes, to avoid confusion. Contributed by Owen.

git-svn-id: https://svn.apache.org/repos/asf/lucene/hadoop/trunk@549200 13f79535-47bb-0310-9956-ffa450edef68

CHANGES.txt

@@ -182,6 +182,9 @@ Trunk (unreleased changes)
  56. HADOOP-1207.  Fix FsShell's 'rm' command to not stop when one of
      the named files does not exist.  (Tsz Wo Sze via cutting)
 
+ 57. HADOOP-1475.  Clear tasktracker's file cache before it
+     re-initializes, to avoid confusion.  (omalley via cutting)
+
 
 Release 0.13.0 - 2007-06-08
 

src/java/org/apache/hadoop/filecache/DistributedCache.java

@@ -40,6 +40,8 @@ public class DistributedCache {
   private static TreeMap<String, CacheStatus> cachedArchives = new TreeMap<String, CacheStatus>();
   // buffer size for reading checksum files
   private static final int CRC_BUFFER_SIZE = 64 * 1024;
+  private static final Log LOG =
+    LogFactory.getLog(DistributedCache.class);
   
   /**
    * 
@@ -679,4 +681,22 @@ public class DistributedCache {
     public byte[] md5;
   }
 
+  /**
+   * Clear the entire contents of the cache and delete the backing files. This
+   * should only be used when the server is reinitializing, because the users
+   * are going to lose their files.
+   */
+  public static void purgeCache(Configuration conf) throws IOException {
+    synchronized (cachedArchives) {
+      FileSystem localFs = FileSystem.getLocal(conf);
+      for (Map.Entry<String,CacheStatus> f: cachedArchives.entrySet()) {
+        try {
+          localFs.delete(f.getValue().localLoadPath);
+        } catch (IOException ie) {
+          LOG.debug("Error cleaning up cache", ie);
+        }
+      }
+      cachedArchives.clear();
+    }
+  }
 }

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

@@ -45,6 +45,7 @@ import javax.servlet.http.HttpServletResponse;
 
 import org.apache.commons.logging.Log;
 import org.apache.commons.logging.LogFactory;
+import org.apache.hadoop.filecache.DistributedCache;
 import org.apache.hadoop.fs.DF;
 import org.apache.hadoop.fs.FSDataInputStream;
 import org.apache.hadoop.fs.FSError;
@@ -349,6 +350,7 @@ public class TaskTracker
     LOG.info("Starting tracker " + taskTrackerName);
 
     // Clear out temporary files that might be lying around
+    DistributedCache.purgeCache(this.fConf);
     this.mapOutputFile.cleanupStorage();
     this.justStarted = true;