YARN-1083. Changed ResourceManager to fail when the expiry interval is less than the configured node-heartbeat interval. Contributed by Zhijie Shen.

git-svn-id: https://svn.apache.org/repos/asf/hadoop/common/trunk@1518036 13f79535-47bb-0310-9956-ffa450edef68

hadoop-yarn-project/CHANGES.txt

@@ -54,6 +54,9 @@ Release 2.1.1-beta - UNRELEASED
     YARN-942. In Fair Scheduler documentation, inconsistency on which
     properties have prefix (Akira Ajisaka via Sandy Ryza)
 
+    YARN-1083. Changed ResourceManager to fail when the expiry interval is less
+    than the configured node-heartbeat interval. (Zhijie Shen via vinodkv)
+
   OPTIMIZATIONS
 
   BUG FIXES

hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/ResourceManager.java

@@ -365,6 +365,20 @@ public class ResourceManager extends CompositeService implements Recoverable {
           + ", " + YarnConfiguration.RM_AM_MAX_ATTEMPTS
           + "=" + globalMaxAppAttempts + ", it should be a positive integer.");
     }
+
+    // validate expireIntvl >= heartbeatIntvl
+    long expireIntvl = conf.getLong(YarnConfiguration.RM_NM_EXPIRY_INTERVAL_MS,
+        YarnConfiguration.DEFAULT_RM_NM_EXPIRY_INTERVAL_MS);
+    long heartbeatIntvl =
+        conf.getLong(YarnConfiguration.RM_NM_HEARTBEAT_INTERVAL_MS,
+            YarnConfiguration.DEFAULT_RM_NM_HEARTBEAT_INTERVAL_MS);
+    if (expireIntvl < heartbeatIntvl) {
+      throw new YarnRuntimeException("Nodemanager expiry interval should be no"
+          + " less than heartbeat interval, "
+          + YarnConfiguration.RM_NM_EXPIRY_INTERVAL_MS + "=" + expireIntvl
+          + ", " + YarnConfiguration.RM_NM_HEARTBEAT_INTERVAL_MS + "="
+          + heartbeatIntvl);
+    }
   }
 
   @Private

hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/test/java/org/apache/hadoop/yarn/server/resourcemanager/TestResourceManager.java

@@ -203,4 +203,21 @@ public class TestResourceManager {
     }
   }
 
+  @Test
+  public void testNMExpiryAndHeartbeatIntervalsValidation() throws Exception {
+    Configuration conf = new YarnConfiguration();
+    conf.setLong(YarnConfiguration.RM_NM_EXPIRY_INTERVAL_MS, 1000);
+    conf.setLong(YarnConfiguration.RM_NM_HEARTBEAT_INTERVAL_MS, 1001);
+    resourceManager = new ResourceManager();;
+    try {
+      resourceManager.init(conf);
+    } catch (YarnRuntimeException e) {
+      // Exception is expected.
+      if (!e.getMessage().startsWith("Nodemanager expiry interval should be no"
+          + " less than heartbeat interval")) {
+        throw e;
+      }
+    }
+  }
+
 }