Return-Path: Delivered-To: apmail-hadoop-hdfs-commits-archive@minotaur.apache.org Received: (qmail 34842 invoked from network); 3 Jan 2011 07:51:38 -0000 Received: from hermes.apache.org (HELO mail.apache.org) (140.211.11.3) by minotaur.apache.org with SMTP; 3 Jan 2011 07:51:38 -0000 Received: (qmail 68898 invoked by uid 500); 3 Jan 2011 07:51:38 -0000 Delivered-To: apmail-hadoop-hdfs-commits-archive@hadoop.apache.org Received: (qmail 68804 invoked by uid 500); 3 Jan 2011 07:51:36 -0000 Mailing-List: contact hdfs-commits-help@hadoop.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: hdfs-dev@hadoop.apache.org Delivered-To: mailing list hdfs-commits@hadoop.apache.org Received: (qmail 68796 invoked by uid 99); 3 Jan 2011 07:51:35 -0000 Received: from athena.apache.org (HELO athena.apache.org) (140.211.11.136) by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 03 Jan 2011 07:51:35 +0000 X-ASF-Spam-Status: No, hits=-2000.0 required=10.0 tests=ALL_TRUSTED X-Spam-Check-By: apache.org Received: from [140.211.11.4] (HELO eris.apache.org) (140.211.11.4) by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 03 Jan 2011 07:51:34 +0000 Received: by eris.apache.org (Postfix, from userid 65534) id 9B62C23888E8; Mon, 3 Jan 2011 07:51:14 +0000 (UTC) Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: svn commit: r1054544 - in /hadoop/hdfs/trunk: CHANGES.txt src/java/org/apache/hadoop/hdfs/server/datanode/DataNode.java Date: Mon, 03 Jan 2011 07:51:14 -0000 To: hdfs-commits@hadoop.apache.org From: dhruba@apache.org X-Mailer: svnmailer-1.0.8 Message-Id: <20110103075114.9B62C23888E8@eris.apache.org> Author: dhruba Date: Mon Jan 3 07:51:14 2011 New Revision: 1054544 URL: http://svn.apache.org/viewvc?rev=1054544&view=rev Log: HDFS-1540. Make Datanode handle errors from RPC calls to namenode more elegantly. (dhruba) Modified: hadoop/hdfs/trunk/CHANGES.txt hadoop/hdfs/trunk/src/java/org/apache/hadoop/hdfs/server/datanode/DataNode.java Modified: hadoop/hdfs/trunk/CHANGES.txt URL: http://svn.apache.org/viewvc/hadoop/hdfs/trunk/CHANGES.txt?rev=1054544&r1=1054543&r2=1054544&view=diff ============================================================================== --- hadoop/hdfs/trunk/CHANGES.txt (original) +++ hadoop/hdfs/trunk/CHANGES.txt Mon Jan 3 07:51:14 2011 @@ -51,6 +51,9 @@ Trunk (unreleased changes) HDFS-1509. A savenamespace command writes the fsimage and edits into all configured directories. (dhruba) + HDFS-1540. Make Datanode handle errors from RPC calls to namenode + more elegantly. (dhruba) + Release 0.22.0 - Unreleased NEW FEATURES Modified: hadoop/hdfs/trunk/src/java/org/apache/hadoop/hdfs/server/datanode/DataNode.java URL: http://svn.apache.org/viewvc/hadoop/hdfs/trunk/src/java/org/apache/hadoop/hdfs/server/datanode/DataNode.java?rev=1054544&r1=1054543&r2=1054544&view=diff ============================================================================== --- hadoop/hdfs/trunk/src/java/org/apache/hadoop/hdfs/server/datanode/DataNode.java (original) +++ hadoop/hdfs/trunk/src/java/org/apache/hadoop/hdfs/server/datanode/DataNode.java Mon Jan 3 07:51:14 2011 @@ -548,12 +548,12 @@ public class DataNode extends Configured try { nsInfo = namenode.versionRequest(); break; - } catch(SocketTimeoutException e) { // namenode is busy - LOG.info("Problem connecting to server: " + getNameNodeAddr()); - try { - Thread.sleep(1000); - } catch (InterruptedException ie) {} + } catch(IOException e) { // namenode cannot be contacted + LOG.info("Problem connecting to server: " + getNameNodeAddr(), e); } + try { + Thread.sleep(1000); + } catch (InterruptedException ie) {} } String errorMsg = null; // verify build version @@ -683,12 +683,21 @@ public class DataNode extends Configured dnRegistration.name = machineName + ":" + dnRegistration.getPort(); dnRegistration = namenode.registerDatanode(dnRegistration); break; - } catch(SocketTimeoutException e) { // namenode is busy - LOG.info("Problem connecting to server: " + getNameNodeAddr()); - try { - Thread.sleep(1000); - } catch (InterruptedException ie) {} + } catch(RemoteException re) { + IOException ue = re.unwrapRemoteException( + UnregisteredNodeException.class, + DisallowedDatanodeException.class, + IncorrectVersionException.class); + if (ue != re) { + LOG.warn("DataNode is shutting down: ", re); + throw ue; + } + } catch(IOException e) { // namenode cannot be contacted + LOG.info("Problem connecting to server: " + getNameNodeAddr(), e); } + try { + Thread.sleep(1000); + } catch (InterruptedException ie) {} } assert ("".equals(storage.getStorageID()) && !"".equals(dnRegistration.getStorageID()))