HDFS-4649. Webhdfs cannot list large directories. Contributed by Daryn Sharp.

git-svn-id: https://svn.apache.org/repos/asf/hadoop/common/branches/branch-0.23@1463700 13f79535-47bb-0310-9956-ffa450edef68

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

@@ -90,6 +90,8 @@ Release 0.23.7 - UNRELEASED
     HDFS-4581. checkDiskError should not be called on network errors (Rohit
     Kochar via kihwal)
 
+    HDFS-4649. Webhdfs cannot list large directories (daryn via kihwal)
+
 Release 0.23.6 - 2013-02-06
 
   INCOMPATIBLE CHANGES

hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/namenode/web/resources/NamenodeWebHdfsMethods.java

@@ -622,9 +622,15 @@ public class NamenodeWebHdfsMethods {
   
   private static StreamingOutput getListingStream(final NamenodeProtocols np, 
       final String p) throws IOException {
-    final DirectoryListing first = getDirectoryListing(np, p,
+    // allows exceptions like FNF or ACE to prevent http response of 200 for
+    // a failure since we can't (currently) return error responses in the
+    // middle of a streaming operation
+    final DirectoryListing firstDirList = getDirectoryListing(np, p,
         HdfsFileStatus.EMPTY_NAME);
 
+    // must save ugi because the streaming object will be executed outside
+    // the remote user's ugi
+    final UserGroupInformation ugi = UserGroupInformation.getCurrentUser();
     return new StreamingOutput() {
       @Override
       public void write(final OutputStream outstream) throws IOException {
@@ -632,21 +638,32 @@ public class NamenodeWebHdfsMethods {
         out.println("{\"" + FileStatus.class.getSimpleName() + "es\":{\""
             + FileStatus.class.getSimpleName() + "\":[");
 
-        final HdfsFileStatus[] partial = first.getPartialListing();
-        if (partial.length > 0) {
-          out.print(JsonUtil.toJsonString(partial[0], false));
-        }
-        for(int i = 1; i < partial.length; i++) {
-          out.println(',');
-          out.print(JsonUtil.toJsonString(partial[i], false));
-        }
-
-        for(DirectoryListing curr = first; curr.hasMore(); ) { 
-          curr = getDirectoryListing(np, p, curr.getLastName());
-          for(HdfsFileStatus s : curr.getPartialListing()) {
-            out.println(',');
-            out.print(JsonUtil.toJsonString(s, false));
-          }
+        try {
+          // restore remote user's ugi
+          ugi.doAs(new PrivilegedExceptionAction<Void>() {
+            @Override
+            public Void run() throws IOException {
+              long n = 0;
+              for (DirectoryListing dirList = firstDirList; ;
+                   dirList = getDirectoryListing(np, p, dirList.getLastName())
+              ) {
+                // send each segment of the directory listing
+                for (HdfsFileStatus s : dirList.getPartialListing()) {
+                  if (n++ > 0) {
+                    out.println(',');
+                  }
+                  out.print(JsonUtil.toJsonString(s, false));
+                }
+                // stop if last segment
+                if (!dirList.hasMore()) {
+                  break;
+                }
+              }
+              return null;
+            }
+          });
+        } catch (InterruptedException e) {
+          throw new IOException(e);
         }
         
         out.println();

hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/web/TestWebHDFS.java

@@ -19,16 +19,22 @@
 package org.apache.hadoop.hdfs.web;
 
 import java.io.IOException;
+import java.net.URISyntaxException;
+import java.security.PrivilegedExceptionAction;
 import java.util.Random;
 
 import org.apache.commons.logging.Log;
 import org.apache.commons.logging.LogFactory;
 import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.permission.FsAction;
+import org.apache.hadoop.fs.permission.FsPermission;
 import org.apache.hadoop.fs.FSDataInputStream;
 import org.apache.hadoop.fs.FSDataOutputStream;
 import org.apache.hadoop.fs.FileSystem;
 import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hdfs.DFSConfigKeys;
 import org.apache.hadoop.hdfs.MiniDFSCluster;
+import org.apache.hadoop.security.UserGroupInformation;
 import org.junit.Assert;
 import org.junit.Test;
 
@@ -196,4 +202,48 @@ public class TestWebHDFS {
     in.close();
     t.end(checked);
   }
+  
+  @Test(timeout=300000)
+  public void testLargeDirectory() throws Exception {
+    final Configuration conf = WebHdfsTestUtil.createConf();
+    final int listLimit = 2;
+    // force small chunking of directory listing
+    conf.setInt(DFSConfigKeys.DFS_LIST_LIMIT, listLimit);
+    // force paths to be only owner-accessible to ensure ugi isn't changing
+    // during listStatus
+    FsPermission.setUMask(conf, new FsPermission((short)0077));
+    
+    final MiniDFSCluster cluster =
+        new MiniDFSCluster.Builder(conf).numDataNodes(3).build();
+    try {
+      cluster.waitActive();
+      WebHdfsTestUtil.getWebHdfsFileSystem(conf).setPermission(
+          new Path("/"),
+          new FsPermission(FsAction.ALL, FsAction.ALL, FsAction.ALL));
+
+      // trick the NN into not believing it's not the superuser so we can
+      // tell if the correct user is used by listStatus
+      UserGroupInformation.setLoginUser(
+          UserGroupInformation.createUserForTesting(
+              "not-superuser", new String[]{"not-supergroup"}));
+
+      UserGroupInformation.createUserForTesting("me", new String[]{"my-group"})
+        .doAs(new PrivilegedExceptionAction<Void>() {
+          @Override
+          public Void run() throws IOException, URISyntaxException {
+            FileSystem fs = WebHdfsTestUtil.getWebHdfsFileSystem(conf);
+            Path d = new Path("/my-dir");
+            Assert.assertTrue(fs.mkdirs(d));
+            for (int i=0; i < listLimit*3; i++) {
+              Path p = new Path(d, "file-"+i);
+              Assert.assertTrue(fs.createNewFile(p));
+            }
+            Assert.assertEquals(listLimit*3, fs.listStatus(d).length);
+            return null;
+          }
+        });
+    } finally {
+      cluster.shutdown();
+    }
+  }
 }