StorageListener & StorageStatusListener needs to synchronize internally to be thread-safe

Author: squito

core/src/main/scala/org/apache/spark/status/api/v1/AllRDDResource.scala

@@ -30,7 +30,6 @@ private[v1] class AllRDDResource(uiRoot: UIRoot) {
     @PathParam("appId") appId: String
   ): Seq[RDDStorageInfo] = {
     uiRoot.withSparkUI(appId) { ui =>
-      // should all access on storageListener also be synchronized?
       val storageStatusList = ui.storageListener.storageStatusList
       val rddInfos = ui.storageListener.rddInfoList
       rddInfos.map{rddInfo =>

core/src/main/scala/org/apache/spark/storage/StorageStatusListener.scala

@@ -25,13 +25,17 @@ import org.apache.spark.scheduler._
 /**
  * :: DeveloperApi ::
  * A SparkListener that maintains executor storage status.
+ *
+ * Unlike JobProgressListener, this class is thread-safe, so users do not need to synchronize
  */
 @DeveloperApi
 class StorageStatusListener extends SparkListener {
   // This maintains only blocks that are cached (i.e. storage level is not StorageLevel.NONE)
   private[storage] val executorIdToStorageStatus = mutable.Map[String, StorageStatus]()
 
-  def storageStatusList: Seq[StorageStatus] = executorIdToStorageStatus.values.toSeq
+  def storageStatusList: Seq[StorageStatus] = synchronized {
+    executorIdToStorageStatus.values.toSeq
+  }
 
   /** Update storage status list to reflect updated block statuses */
   private def updateStorageStatus(execId: String, updatedBlocks: Seq[(BlockId, BlockStatus)]) {

core/src/main/scala/org/apache/spark/ui/storage/StorageTab.scala

@@ -35,6 +35,8 @@ private[ui] class StorageTab(parent: SparkUI) extends SparkUITab(parent, "storag
 /**
  * :: DeveloperApi ::
  * A SparkListener that prepares information to be displayed on the BlockManagerUI.
+ *
+ * Unlike JobProgressListener, this class is thread-safe, so users do not need to synchronize
  */
 @DeveloperApi
 class StorageListener(storageStatusListener: StorageStatusListener) extends SparkListener {
@@ -43,7 +45,9 @@ class StorageListener(storageStatusListener: StorageStatusListener) extends Spar
   def storageStatusList: Seq[StorageStatus] = storageStatusListener.storageStatusList
 
   /** Filter RDD info to include only those with cached partitions */
-  def rddInfoList: Seq[RDDInfo] = _rddInfoMap.values.filter(_.numCachedPartitions > 0).toSeq
+  def rddInfoList: Seq[RDDInfo] = synchronized {
+    _rddInfoMap.values.filter(_.numCachedPartitions > 0).toSeq
+  }
 
   /** Update the storage info of the RDDs whose blocks are among the given updated blocks */
   private def updateRDDInfo(updatedBlocks: Seq[(BlockId, BlockStatus)]): Unit = {