From d29f0e83a935a0443537064d1e7290ea67301045 Mon Sep 17 00:00:00 2001
From: Ayush Saxena <ayushsaxena@apache.org>
Date: Tue, 14 Dec 2021 13:51:51 +0530
Subject: [PATCH] HDFS-16373. Fix MiniDFSCluster restart in case of multiple
 namenodes. (#3756)

Reviewed-by: Viraj Jasani <vjasani@apache.org>
Reviewed-by: litao <tomleescut@gmail.com>
Signed-off-by: Takanobu Asanuma <tasanuma@apache.org>
---
 .../apache/hadoop/hdfs/MiniDFSCluster.java    | 43 ++++++++++---------
 .../hadoop/hdfs/TestMiniDFSCluster.java       |  8 ++++
 2 files changed, 30 insertions(+), 21 deletions(-)

diff --git a/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/MiniDFSCluster.java b/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/MiniDFSCluster.java
index e4b6434b48..703111ed2f 100644
--- a/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/MiniDFSCluster.java
+++ b/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/MiniDFSCluster.java
@@ -2267,9 +2267,11 @@ public synchronized void restartNameNode(int nnIndex, boolean waitActive,
     info.nameNode = nn;
     info.setStartOpt(startOpt);
     if (waitActive) {
-      waitClusterUp();
+      if (numDataNodes > 0) {
+        waitNameNodeUp(nnIndex);
+      }
       LOG.info("Restarted the namenode");
-      waitActive();
+      waitActive(nnIndex);
     }
   }
 
@@ -2775,11 +2777,25 @@ public void waitActive(int nnIndex) throws IOException {
     DFSClient client = new DFSClient(addr, conf);
 
     // ensure all datanodes have registered and sent heartbeat to the namenode
-    while (shouldWait(client.datanodeReport(DatanodeReportType.LIVE), addr)) {
+    int failedCount = 0;
+    while (true) {
       try {
-        LOG.info("Waiting for cluster to become active");
-        Thread.sleep(100);
+        while (shouldWait(client.datanodeReport(DatanodeReportType.LIVE), addr)) {
+          LOG.info("Waiting for cluster to become active");
+          Thread.sleep(100);
+        }
+        break;
+      } catch (IOException e) {
+        failedCount++;
+        // Cached RPC connection to namenode, if any, is expected to fail once
+        if (failedCount > 1) {
+          LOG.warn("Tried waitActive() " + failedCount
+              + " time(s) and failed, giving up.  " + StringUtils
+              .stringifyException(e));
+          throw e;
+        }
       } catch (InterruptedException e) {
+        throw new IOException(e);
       }
     }
 
@@ -2815,22 +2831,7 @@ public Boolean get() {
    */
   public void waitActive() throws IOException {
     for (int index = 0; index < namenodes.size(); index++) {
-      int failedCount = 0;
-      while (true) {
-        try {
-          waitActive(index);
-          break;
-        } catch (IOException e) {
-          failedCount++;
-          // Cached RPC connection to namenode, if any, is expected to fail once
-          if (failedCount > 1) {
-            LOG.warn("Tried waitActive() " + failedCount
-                + " time(s) and failed, giving up.  "
-                + StringUtils.stringifyException(e));
-            throw e;
-          }
-        }
-      }
+      waitActive(index);
     }
     LOG.info("Cluster is active");
   }
diff --git a/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/TestMiniDFSCluster.java b/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/TestMiniDFSCluster.java
index 74cfe9d673..737795b88d 100644
--- a/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/TestMiniDFSCluster.java
+++ b/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/TestMiniDFSCluster.java
@@ -309,6 +309,14 @@ public void testSetUpFederatedCluster() throws Exception {
             DFSUtil.addKeySuffixes(
             DFS_NAMENODE_HTTP_ADDRESS_KEY, "ns1", "nn1")));
       }
+
+      // Shutdown namenodes individually.
+      cluster.shutdownNameNode(0);
+      cluster.shutdownNameNode(1);
+
+      // Restart namenodes individually with wait active, both should be successful.
+      cluster.restartNameNode(0);
+      cluster.restartNameNode(1);
     }
   }
 }