diff --git a/hadoop-hdfs-project/hadoop-hdfs/CHANGES.txt b/hadoop-hdfs-project/hadoop-hdfs/CHANGES.txt index 6b9f94052c5..94dac845fac 100644 --- a/hadoop-hdfs-project/hadoop-hdfs/CHANGES.txt +++ b/hadoop-hdfs-project/hadoop-hdfs/CHANGES.txt @@ -2201,6 +2201,9 @@ Release 0.23.7 - UNRELEASED HDFS-3367. WebHDFS doesn't use the logged in user when opening connections (daryn) + HDFS-4581. checkDiskError should not be called on network errors (Rohit + Kochar via kihwal) + Release 0.23.6 - UNRELEASED INCOMPATIBLE CHANGES diff --git a/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/datanode/DataNode.java b/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/datanode/DataNode.java index 0be46de22c8..104bfcd3567 100644 --- a/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/datanode/DataNode.java +++ b/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/datanode/DataNode.java @@ -60,8 +60,11 @@ import java.io.PrintStream; import java.net.InetSocketAddress; import java.net.ServerSocket; import java.net.Socket; +import java.net.SocketException; +import java.net.SocketTimeoutException; import java.net.URI; import java.net.UnknownHostException; +import java.nio.channels.ClosedByInterruptException; import java.nio.channels.ServerSocketChannel; import java.nio.channels.SocketChannel; import java.security.PrivilegedExceptionAction; @@ -1172,7 +1175,13 @@ public class DataNode extends Configured protected void checkDiskError(Exception e ) throws IOException { LOG.warn("checkDiskError: exception: ", e); - + if (e instanceof SocketException || e instanceof SocketTimeoutException + || e instanceof ClosedByInterruptException + || e.getMessage().startsWith("Broken pipe")) { + LOG.info("Not checking disk as checkDiskError was called on a network" + + " related exception"); + return; + } if (e.getMessage() != null && e.getMessage().startsWith("No space left on device")) { throw new DiskOutOfSpaceException("No space left on device"); @@ -1484,8 +1493,12 @@ public class DataNode extends Configured } catch (IOException ie) { LOG.warn(bpReg + ":Failed to transfer " + b + " to " + targets[0] + " got ", ie); - // check if there are any disk problem - checkDiskError(); + // check if there are any disk problem + try{ + checkDiskError(ie); + } catch(IOException e) { + LOG.warn("DataNode.checkDiskError failed in run() with: ", e); + } } finally { xmitsInProgress.getAndDecrement();