[GitHub] [hadoop] lokeshj1703 commented on a change in pull request #782: HDDS-1461. Optimize listStatus api in OzoneFileSystem

[GitBox <gi...@apache.org>]

lokeshj1703 commented on a change in pull request #782: HDDS-1461. Optimize listStatus api in OzoneFileSystem
URL: https://github.com/apache/hadoop/pull/782#discussion_r282951671
 
 

 ##########
 File path: hadoop-ozone/ozone-manager/src/main/java/org/apache/hadoop/ozone/om/KeyManagerImpl.java
 ##########
 @@ -1546,6 +1552,101 @@ public OmKeyInfo lookupFile(OmKeyArgs args) throws IOException {
         ResultCodes.NOT_A_FILE);
   }
 
+  /**
+   * List the status for a file or a directory and its contents.
+   *
+   * @param args       Key args
+   * @param recursive  For a directory if true all the descendants of a
+   *                   particular directory are listed
+   * @param startKey   Key from which listing needs to start. If startKey exists
+   *                   its status is included in the final list.
+   * @param numEntries Number of entries to list from the start key
+   * @return list of file status
+   */
+  public List<OzoneFileStatus> listStatus(OmKeyArgs args, boolean recursive,
+      String startKey, long numEntries) throws IOException {
+    Preconditions.checkNotNull(args, "Key args can not be null");
+    String volumeName = args.getVolumeName();
+    String bucketName = args.getBucketName();
+    String keyName = args.getKeyName();
+
+    List<OzoneFileStatus> fileStatusList = new ArrayList<>();
+    try {
+      metadataManager.getLock().acquireBucketLock(volumeName, bucketName);
+      if (Strings.isNullOrEmpty(startKey)) {
+        OzoneFileStatus fileStatus = getFileStatus(args);
+        if (fileStatus.isFile()) {
+          return Collections.singletonList(fileStatus);
+        }
+        startKey = OzoneFSUtils.addTrailingSlashIfNeeded(keyName);
+      }
+
+      String seekKeyInDb =
+          metadataManager.getOzoneKey(volumeName, bucketName, startKey);
+      String keyInDb = OzoneFSUtils.addTrailingSlashIfNeeded(
+          metadataManager.getOzoneKey(volumeName, bucketName, keyName));
+      TableIterator<String, ? extends Table.KeyValue<String, OmKeyInfo>>
+          iterator = metadataManager.getKeyTable().iterator();
+      iterator.seek(seekKeyInDb);
+
+      if (!iterator.hasNext()) {
+        return Collections.emptyList();
+      }
+
+      if (iterator.key().equals(keyInDb)) {
+        // skip the key which needs to be listed
+        iterator.next();
+      }
+
+      while (iterator.hasNext() && numEntries - fileStatusList.size() > 0) {
+        String entryInDb = iterator.key();
+        OmKeyInfo value = iterator.value().getValue();
+        if (entryInDb.startsWith(keyInDb)) {
+          String entryKeyName = value.getKeyName();
+          if (recursive) {
+            // for recursive list all the entries
+            fileStatusList.add(new OzoneFileStatus(value, scmBlockSize,
+                !OzoneFSUtils.isFile(entryKeyName)));
+            iterator.next();
+          } else {
+            // get the child of the directory to list from the entry. For
+            // example if directory to list is /a and entry is /a/b/c where
+            // c is a file. The immediate child is b which is a directory. c
+            // should not be listed as child of a.
+            String immediateChild = OzoneFSUtils
+                .getImmediateChild(entryKeyName, keyName);
+            boolean isFile = OzoneFSUtils.isFile(immediateChild);
+            if (isFile) {
+              fileStatusList
+                  .add(new OzoneFileStatus(value, scmBlockSize, !isFile));
+              iterator.next();
+            } else {
+              // if entry is a directory
+              fileStatusList.add(new OzoneFileStatus(immediateChild));
+              // skip the other descendants of this child directory.
+              iterator.seek(
+                  getNextGreaterString(volumeName, bucketName, immediateChild));
+            }
+          }
+        } else {
+          break;
+        }
+      }
+    } finally {
+      metadataManager.getLock().releaseBucketLock(volumeName, bucketName);
+    }
+    return fileStatusList;
+  }
+
+  private String getNextGreaterString(String volumeName, String bucketName,
+      String keyPrefix) {
+    // TODO: Use string codec
+    // Increment the last character of the string and return the new ozone key.
+    String nextPrefix = keyPrefix.substring(0, keyPrefix.length() - 1) +
+        String.valueOf((char) (keyPrefix.charAt(keyPrefix.length() - 1) + 1));
 
 Review comment:
   The first character in the ASCII table would not work in our case.
   The second commit uses codec of RDBStore for handling the UTF-8 case.

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: common-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: common-issues-help@hadoop.apache.org