Mailing-List: contact common-commits-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
From: yjzhangal@apache.org
To: common-commits@hadoop.apache.org
Message-Id: <879c45b6369d44dca454c8eea14ba139@git.apache.org>
Subject: hadoop git commit: HDFS-11914. Add more diagnosis info for fsimage
 transfer failure. Contributed by Yongjun Zhang.
Date: Tue,  6 Jun 2017 00:32:30 +0000 (UTC)
archived-at: Tue, 06 Jun 2017 00:32:32 -0000

Repository: hadoop
Updated Branches:
  refs/heads/trunk 5fd9742c8 -> 6a28a2b91


HDFS-11914. Add more diagnosis info for fsimage transfer failure. Contributed by Yongjun Zhang.


Project: http://git-wip-us.apache.org/repos/asf/hadoop/repo
Commit: http://git-wip-us.apache.org/repos/asf/hadoop/commit/6a28a2b9
Tree: http://git-wip-us.apache.org/repos/asf/hadoop/tree/6a28a2b9
Diff: http://git-wip-us.apache.org/repos/asf/hadoop/diff/6a28a2b9

Branch: refs/heads/trunk
Commit: 6a28a2b914664fbbb5267f13e82d42b3bb49610c
Parents: 5fd9742
Author: Yongjun Zhang <yzhang@cloudera.com>
Authored: Mon Jun 5 16:31:03 2017 -0700
Committer: Yongjun Zhang <yzhang@cloudera.com>
Committed: Mon Jun 5 16:31:03 2017 -0700

----------------------------------------------------------------------
 .../apache/hadoop/hdfs/server/common/Util.java  |  6 ++---
 .../hdfs/server/namenode/TransferFsImage.java   | 23 +++++++++++++++++---
 2 files changed, 23 insertions(+), 6 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/hadoop/blob/6a28a2b9/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/common/Util.java
----------------------------------------------------------------------
diff --git a/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/common/Util.java b/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/common/Util.java
index e9ceeb0..5dee16a 100644
--- a/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/common/Util.java
+++ b/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/common/Util.java
@@ -225,6 +225,7 @@ public final class Util {
       stream = new DigestInputStream(stream, digester);
     }
     boolean finishedReceiving = false;
+    int num = 1;
 
     List<FileOutputStream> outputStreams = Lists.newArrayList();
 
@@ -256,7 +257,6 @@ public final class Util {
         }
       }
 
-      int num = 1;
       byte[] buf = new byte[IO_FILE_BUFFER_SIZE];
       while (num > 0) {
         num = stream.read(buf);
@@ -305,8 +305,8 @@ public final class Util {
         // exception that makes it look like a server-side problem!
         deleteTmpFiles(localPaths);
         throw new IOException("File " + url + " received length " + received +
-            " is not of the advertised size " +
-            advertisedSize);
+            " is not of the advertised size " + advertisedSize +
+            ". Fsimage name: " + fsImageName + " lastReceived: " + num);
       }
     }
     xferStats.insert(0, String.format("Combined time for file download and" +

http://git-wip-us.apache.org/repos/asf/hadoop/blob/6a28a2b9/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/namenode/TransferFsImage.java
----------------------------------------------------------------------
diff --git a/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/namenode/TransferFsImage.java b/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/namenode/TransferFsImage.java
index 7316414..771a43e 100644
--- a/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/namenode/TransferFsImage.java
+++ b/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/namenode/TransferFsImage.java
@@ -339,6 +339,11 @@ public class TransferFsImage {
       FileInputStream infile, DataTransferThrottler throttler,
       Canceler canceler) throws IOException {
     byte buf[] = new byte[IO_FILE_BUFFER_SIZE];
+    long total = 0;
+    int num = 1;
+    IOException ioe = null;
+    String reportStr = "Sending fileName: " + localfile.getAbsolutePath()
+      + ", fileSize: " + localfile.length() + ".";
     try {
       CheckpointFaultInjector.getInstance()
           .aboutToSendFile(localfile);
@@ -352,7 +357,6 @@ public class TransferFsImage {
           // and the rest of the image will be sent over the wire
           infile.read(buf);
       }
-      int num = 1;
       while (num > 0) {
         if (canceler != null && canceler.isCancelled()) {
           throw new SaveNamespaceCancelledException(
@@ -368,16 +372,29 @@ public class TransferFsImage {
           LOG.warn("SIMULATING A CORRUPT BYTE IN IMAGE TRANSFER!");
           buf[0]++;
         }
-        
+
         out.write(buf, 0, num);
+        total += num;
         if (throttler != null) {
           throttler.throttle(num, canceler);
         }
       }
     } catch (EofException e) {
-      LOG.info("Connection closed by client");
+      reportStr += " Connection closed by client.";
+      ioe = e;
       out = null; // so we don't close in the finally
+    } catch (IOException ie) {
+      ioe = ie;
+      throw ie;
     } finally {
+      reportStr += " Sent total: " + total +
+          " bytes. Size of last segment intended to send: " + num
+          + " bytes.";
+      if (ioe != null) {
+        LOG.info(reportStr, ioe);
+      } else {
+        LOG.info(reportStr);
+      }
       if (out != null) {
         out.close();
       }


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