From 96281cd0c3ffb4c0fbdb64b8f7b705f863d46b33 Mon Sep 17 00:00:00 2001
From: Liang-Chi Hsieh <viirya@gmail.com>
Date: Tue, 23 Dec 2014 14:58:33 -0800
Subject: [PATCH] [SPARK-4913] Fix incorrect event log path

SPARK-2261 uses a single file to log events for an app. `eventLogDir` in `ApplicationDescription` is replaced with `eventLogFile`. However, `ApplicationDescription` in `SparkDeploySchedulerBackend` is initialized with `SparkContext`'s `eventLogDir`. It is just the log directory, not the actual log file path. `Master.rebuildSparkUI` can not correctly rebuild a new SparkUI for the app.

Because the `ApplicationDescription` is remotely registered with `Master` and the app's id is then generated in `Master`, we can not get the app id in advance before registration. So the received description needs to be modified with correct `eventLogFile` value.

Author: Liang-Chi Hsieh <viirya@gmail.com>

Closes #3755 from viirya/fix_app_logdir and squashes the following commits:

5e0ea35 [Liang-Chi Hsieh] Revision for comment.
b5730a1 [Liang-Chi Hsieh] Fix incorrect event log path.

Closes #3777 (a duplicate PR for the same JIRA)
---
 .../spark/deploy/ApplicationDescription.scala |  2 +-
 .../apache/spark/deploy/master/Master.scala   | 20 +++++++++++++++----
 2 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/core/src/main/scala/org/apache/spark/deploy/ApplicationDescription.scala b/core/src/main/scala/org/apache/spark/deploy/ApplicationDescription.scala
index b10b7b8d32..65a1a8fd7e 100644
--- a/core/src/main/scala/org/apache/spark/deploy/ApplicationDescription.scala
+++ b/core/src/main/scala/org/apache/spark/deploy/ApplicationDescription.scala
@@ -23,7 +23,7 @@ private[spark] class ApplicationDescription(
     val memoryPerSlave: Int,
     val command: Command,
     var appUiUrl: String,
-    val eventLogFile: Option[String] = None)
+    val eventLogDir: Option[String] = None)
   extends Serializable {
 
   val user = System.getProperty("user.name", "<unknown>")
diff --git a/core/src/main/scala/org/apache/spark/deploy/master/Master.scala b/core/src/main/scala/org/apache/spark/deploy/master/Master.scala
index f8137bf93c..81fa0770bb 100644
--- a/core/src/main/scala/org/apache/spark/deploy/master/Master.scala
+++ b/core/src/main/scala/org/apache/spark/deploy/master/Master.scala
@@ -719,14 +719,26 @@ private[spark] class Master(
   def rebuildSparkUI(app: ApplicationInfo): Boolean = {
     val appName = app.desc.name
     val notFoundBasePath = HistoryServer.UI_PATH_PREFIX + "/not-found"
-    val eventLogFile = app.desc.eventLogFile.getOrElse {
-      // Event logging is not enabled for this application
-      app.desc.appUiUrl = notFoundBasePath
+    val eventLogFile = app.desc.eventLogDir
+      .map { dir => EventLoggingListener.getLogPath(dir, app.id) }
+      .getOrElse {
+        // Event logging is not enabled for this application
+        app.desc.appUiUrl = notFoundBasePath
+        return false
+    }
+    val fs = Utils.getHadoopFileSystem(eventLogFile, hadoopConf)
+
+    if (fs.exists(new Path(eventLogFile + EventLoggingListener.IN_PROGRESS))) {
+      // Event logging is enabled for this application, but the application is still in progress
+      val title = s"Application history not found (${app.id})"
+      var msg = s"Application $appName is still in progress."
+      logWarning(msg)
+      msg = URLEncoder.encode(msg, "UTF-8")
+      app.desc.appUiUrl = notFoundBasePath + s"?msg=$msg&title=$title"
       return false
     }
 
     try {
-      val fs = Utils.getHadoopFileSystem(eventLogFile, hadoopConf)
       val (logInput, sparkVersion) = EventLoggingListener.openEventLog(new Path(eventLogFile), fs)
       val replayBus = new ReplayListenerBus()
       val ui = SparkUI.createHistoryUI(new SparkConf, replayBus, new SecurityManager(conf),