SPARK-5217 Spark UI should report pending stages during job execution…

… on AllStagesPage.
apache · Jan 19, 2015 · c19d82a · c19d82a
1 parent 1955645
commit c19d82a
Show file tree

Hide file tree

Showing 2 changed files with 16 additions and 1 deletion.
diff --git a/core/src/main/scala/org/apache/spark/ui/jobs/AllStagesPage.scala b/core/src/main/scala/org/apache/spark/ui/jobs/AllStagesPage.scala
@@ -37,12 +37,18 @@ private[ui] class AllStagesPage(parent: StagesTab) extends WebUIPage("") {
       val numCompletedStages = listener.numCompletedStages
       val failedStages = listener.failedStages.reverse.toSeq
       val numFailedStages = listener.numFailedStages
+      val pendingStages = listener.pendingStages.values.toSeq
+      val numWaitingStages = pendingStages.size
       val now = System.currentTimeMillis
 
       val activeStagesTable =
         new StageTableBase(activeStages.sortBy(_.submissionTime).reverse,
           parent.basePath, parent.listener, isFairScheduler = parent.isFairScheduler,
           killEnabled = parent.killEnabled)
+      val pendingStagesTable =
+        new StageTableBase(pendingStages.sortBy(_.submissionTime).reverse,
+          parent.basePath, parent.listener, isFairScheduler = parent.isFairScheduler,
+          killEnabled = false)
       val completedStagesTable =
         new StageTableBase(completedStages.sortBy(_.submissionTime).reverse, parent.basePath,
           parent.listener, isFairScheduler = parent.isFairScheduler, killEnabled = false)
@@ -68,6 +74,10 @@ private[ui] class AllStagesPage(parent: StagesTab) extends WebUIPage("") {
               <strong>Scheduling Mode: </strong>
               {listener.schedulingMode.map(_.toString).getOrElse("Unknown")}
             </li>
+            <li>
+              <a href="#pending"><strong>Pending Stages:</strong></a>
+              {pendingStages.size}
+            </li>
             <li>
               <a href="#active"><strong>Active Stages:</strong></a>
               {activeStages.size}
@@ -89,6 +99,8 @@ private[ui] class AllStagesPage(parent: StagesTab) extends WebUIPage("") {
         } else {
           Seq[Node]()
         }} ++
+        <h4 id="pending">Pending Stages ({pendingStages.size})</h4> ++
+        pendingStagesTable.toNodeSeq ++
         <h4 id="active">Active Stages ({activeStages.size})</h4> ++
         activeStagesTable.toNodeSeq ++
         <h4 id="completed">Completed Stages ({numCompletedStages})</h4> ++

diff --git a/core/src/main/scala/org/apache/spark/ui/jobs/JobProgressListener.scala b/core/src/main/scala/org/apache/spark/ui/jobs/JobProgressListener.scala
@@ -56,6 +56,7 @@ class JobProgressListener(conf: SparkConf) extends SparkListener with Logging {
   val jobIdToData = new HashMap[JobId, JobUIData]
 
   // Stages:
+  val pendingStages = new HashMap[StageId, StageInfo]
   val activeStages = new HashMap[StageId, StageInfo]
   val completedStages = ListBuffer[StageInfo]()
   val skippedStages = ListBuffer[StageInfo]()
@@ -157,6 +158,7 @@ class JobProgressListener(conf: SparkConf) extends SparkListener with Logging {
         stageIds = jobStart.stageIds,
         jobGroup = jobGroup,
         status = JobExecutionStatus.RUNNING)
+    jobStart.stageInfos.foreach(x => pendingStages(x.stageId) = x)
     // Compute (a potential underestimate of) the number of tasks that will be run by this job.
     // This may be an underestimate because the job start event references all of the result
     // stages' transitive stage dependencies, but some of these stages might be skipped if their
@@ -187,6 +189,7 @@ class JobProgressListener(conf: SparkConf) extends SparkListener with Logging {
     }
     jobData.completionTime = Option(jobEnd.time).filter(_ >= 0)
 
+    jobData.stageIds.foreach(pendingStages.remove)
     jobEnd.jobResult match {
       case JobSucceeded =>
         completedJobs += jobData
@@ -257,7 +260,7 @@ class JobProgressListener(conf: SparkConf) extends SparkListener with Logging {
   override def onStageSubmitted(stageSubmitted: SparkListenerStageSubmitted) = synchronized {
     val stage = stageSubmitted.stageInfo
     activeStages(stage.stageId) = stage
-
+    pendingStages.remove(stage.stageId)
     val poolName = Option(stageSubmitted.properties).map {
       p => p.getProperty("spark.scheduler.pool", DEFAULT_POOL_NAME)
     }.getOrElse(DEFAULT_POOL_NAME)