Repository: hadoop
Updated Branches:
  refs/heads/trunk 5149dc7b9 -> 1970ca7cb


YARN-2392. Add more diags about app retry limits on AM failures. Contributed by 
Steve Loughran


Project: http://git-wip-us.apache.org/repos/asf/hadoop/repo
Commit: http://git-wip-us.apache.org/repos/asf/hadoop/commit/1970ca7c
Tree: http://git-wip-us.apache.org/repos/asf/hadoop/tree/1970ca7c
Diff: http://git-wip-us.apache.org/repos/asf/hadoop/diff/1970ca7c

Branch: refs/heads/trunk
Commit: 1970ca7cbcdb7efa160d0cedc2e3e22c1401fad6
Parents: 5149dc7
Author: Jian He <[email protected]>
Authored: Thu Jun 4 11:14:09 2015 -0700
Committer: Jian He <[email protected]>
Committed: Thu Jun 4 11:14:09 2015 -0700

----------------------------------------------------------------------
 hadoop-yarn-project/CHANGES.txt                     |  3 +++
 .../server/resourcemanager/rmapp/RMAppImpl.java     | 16 +++++++++++++---
 .../rmapp/attempt/RMAppAttemptImpl.java             |  4 ++--
 3 files changed, 18 insertions(+), 5 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/hadoop/blob/1970ca7c/hadoop-yarn-project/CHANGES.txt
----------------------------------------------------------------------
diff --git a/hadoop-yarn-project/CHANGES.txt b/hadoop-yarn-project/CHANGES.txt
index a3954e0..5a9d8ca 100644
--- a/hadoop-yarn-project/CHANGES.txt
+++ b/hadoop-yarn-project/CHANGES.txt
@@ -289,6 +289,9 @@ Release 2.8.0 - UNRELEASED
     YARN-3467. Expose allocatedMB, allocatedVCores, and runningContainers 
metrics on 
     running Applications in RM Web UI. (Anubhav Dhoot via kasha)
 
+    YARN-2392. Add more diags about app retry limits on AM failures. (Steve
+    Loughran via jianhe)
+
   OPTIMIZATIONS
 
     YARN-3339. TestDockerContainerExecutor should pull a single image and not

http://git-wip-us.apache.org/repos/asf/hadoop/blob/1970ca7c/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/rmapp/RMAppImpl.java
----------------------------------------------------------------------
diff --git 
a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/rmapp/RMAppImpl.java
 
b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/rmapp/RMAppImpl.java
index f3dacd6..90e63c1 100644
--- 
a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/rmapp/RMAppImpl.java
+++ 
b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/rmapp/RMAppImpl.java
@@ -1014,9 +1014,19 @@ public class RMAppImpl implements RMApp, Recoverable {
               + " failed due to " + failedEvent.getDiagnostics()
               + ". Failing the application.";
     } else if (this.isNumAttemptsBeyondThreshold) {
-      msg = "Application " + this.getApplicationId() + " failed "
-              + this.maxAppAttempts + " times due to "
-              + failedEvent.getDiagnostics() + ". Failing the application.";
+      int globalLimit = conf.getInt(YarnConfiguration.RM_AM_MAX_ATTEMPTS,
+          YarnConfiguration.DEFAULT_RM_AM_MAX_ATTEMPTS);
+      msg = String.format(
+        "Application %s failed %d times%s%s due to %s. Failing the 
application.",
+          getApplicationId(),
+          maxAppAttempts,
+          (attemptFailuresValidityInterval <= 0 ? ""
+               : (" in previous " + attemptFailuresValidityInterval
+                  + " milliseconds")),
+          (globalLimit == maxAppAttempts) ? ""
+              : (" (global limit =" + globalLimit
+                 + "; local limit is =" + maxAppAttempts + ")"),
+          failedEvent.getDiagnostics());
     }
     return msg;
   }

http://git-wip-us.apache.org/repos/asf/hadoop/blob/1970ca7c/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/rmapp/attempt/RMAppAttemptImpl.java
----------------------------------------------------------------------
diff --git 
a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/rmapp/attempt/RMAppAttemptImpl.java
 
b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/rmapp/attempt/RMAppAttemptImpl.java
index 684dde8..5171bba 100644
--- 
a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/rmapp/attempt/RMAppAttemptImpl.java
+++ 
b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/rmapp/attempt/RMAppAttemptImpl.java
@@ -1459,9 +1459,9 @@ public class RMAppAttemptImpl implements RMAppAttempt, 
Recoverable {
         .append(status.getDiagnostics());
     if (this.getTrackingUrl() != null) {
       diagnosticsBuilder.append("For more detailed output,").append(
-        " check application tracking page: ").append(
+        " check the application tracking page: ").append(
         this.getTrackingUrl()).append(
-        " Then, click on links to logs of each attempt.\n");
+        " Then click on links to logs of each attempt.\n");
     }
     return diagnosticsBuilder.toString();
   }

Reply via email to