HDFS-7579. Improve log reporting during block report rpc failure. Contributed by Charles Lamb.

(cherry picked from commit 7e2d9a32426d04b5f08c2835f61882b053612a20)
(cherry picked from commit f0acb7c2a284db61640efee15a1648c6c26d24f5)
(cherry picked from commit 33fb7b45195a89b6464e4a1cb3fbf6bbad2bcecb)

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

@@ -14,6 +14,9 @@ Release 2.6.1 - UNRELEASED
     HDFS-7531. Improve the concurrent access on FsVolumeList (Lei Xu via Colin
     P. McCabe)
 
+    HDFS-7579. Improve log reporting during block report rpc failure.
+    (Charles Lamb via cnauroth)
+
   OPTIMIZATIONS
 
   BUG FIXES

hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/datanode/BPServiceActor.java

@@ -22,7 +22,10 @@
 import java.io.IOException;
 import java.net.InetSocketAddress;
 import java.net.SocketTimeoutException;
-import java.util.*;
+import java.util.ArrayList;
+import java.util.Collection;
+import java.util.List;
+import java.util.Map;
 
 import com.google.common.base.Joiner;
 import org.apache.commons.logging.Log;
@@ -457,7 +460,7 @@ List<DatanodeCommand> blockReport() throws IOException {
       return null;
     }
 
-    ArrayList<DatanodeCommand> cmds = new ArrayList<DatanodeCommand>();
+    final ArrayList<DatanodeCommand> cmds = new ArrayList<DatanodeCommand>();
 
     // Flush any block information that precedes the block report. Otherwise
     // we have a chance that we will miss the delHint information
@@ -484,40 +487,54 @@ List<DatanodeCommand> blockReport() throws IOException {
     }
 
     // Send the reports to the NN.
-    int numReportsSent;
+    int numReportsSent = 0;
+    int numRPCs = 0;
+    boolean success = false;
     long brSendStartTime = now();
-    if (totalBlockCount < dnConf.blockReportSplitThreshold) {
-      // Below split threshold, send all reports in a single message.
-      numReportsSent = 1;
-      DatanodeCommand cmd =
-          bpNamenode.blockReport(bpRegistration, bpos.getBlockPoolId(), reports);
-      if (cmd != null) {
-        cmds.add(cmd);
-      }
-    } else {
-      // Send one block report per message.
-      numReportsSent = i;
-      for (StorageBlockReport report : reports) {
-        StorageBlockReport singleReport[] = { report };
+    try {
+      if (totalBlockCount < dnConf.blockReportSplitThreshold) {
+        // Below split threshold, send all reports in a single message.
         DatanodeCommand cmd = bpNamenode.blockReport(
-            bpRegistration, bpos.getBlockPoolId(), singleReport);
+            bpRegistration, bpos.getBlockPoolId(), reports);
+        numRPCs = 1;
+        numReportsSent = reports.length;
         if (cmd != null) {
           cmds.add(cmd);
         }
+      } else {
+        // Send one block report per message.
+        for (StorageBlockReport report : reports) {
+          StorageBlockReport singleReport[] = { report };
+          DatanodeCommand cmd = bpNamenode.blockReport(
+              bpRegistration, bpos.getBlockPoolId(), singleReport);
+          numReportsSent++;
+          numRPCs++;
+          if (cmd != null) {
+            cmds.add(cmd);
+          }
+        }
       }
+      success = true;
+    } finally {
+      // Log the block report processing stats from Datanode perspective
+      long brSendCost = now() - brSendStartTime;
+      long brCreateCost = brSendStartTime - brCreateStartTime;
+      dn.getMetrics().addBlockReport(brSendCost);
+      final int nCmds = cmds.size();
+      LOG.info((success ? "S" : "Uns") +
+          "uccessfully sent " + numReportsSent +
+          " of " + reports.length +
+          " blockreports for " + totalBlockCount +
+          " total blocks using " + numRPCs +
+          " RPCs. This took " + brCreateCost +
+          " msec to generate and " + brSendCost +
+          " msecs for RPC and NN processing." +
+          " Got back " +
+          ((nCmds == 0) ? "no commands" :
+              ((nCmds == 1) ? "one command: " + cmds.get(0) :
+                  (nCmds + " commands: " + Joiner.on("; ").join(cmds)))) +
+          ".");
     }
-
-    // Log the block report processing stats from Datanode perspective
-    long brSendCost = now() - brSendStartTime;
-    long brCreateCost = brSendStartTime - brCreateStartTime;
-    dn.getMetrics().addBlockReport(brSendCost);
-    LOG.info("Sent " + numReportsSent + " blockreports " + totalBlockCount +
-        " blocks total. Took " + brCreateCost +
-        " msec to generate and " + brSendCost +
-        " msecs for RPC and NN processing. " +
-        " Got back commands " +
-            (cmds.size() == 0 ? "none" : Joiner.on("; ").join(cmds)));
-
     scheduleNextBlockReport(startTime);
     return cmds.size() == 0 ? null : cmds;
   }
@@ -967,7 +984,6 @@ int putMissingBlockInfos(ReceivedDeletedBlockInfo[] blockArray) {
 
     /**
      * Add pending incremental block report for a single block.
-     * @param blockID
      * @param blockInfo
      */
     void putBlockInfo(ReceivedDeletedBlockInfo blockInfo) {

hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/server/protocol/ServerCommand.java

@@ -52,4 +52,12 @@ public ServerCommand(int action) {
   public int getAction() {
     return this.action;
   }
+
+  public String toString() {
+    final StringBuilder sb = new StringBuilder();
+    sb.append(getClass().getSimpleName());
+    sb.append("/");
+    sb.append(action);
+    return sb.toString();
+  }
 }