[SPARK-18143][SQL]Ignore Structured Streaming event logs to avoid breaking history server

core/src/main/scala/org/apache/spark/scheduler/ReplayListenerBus.scala

@@ -72,6 +72,13 @@ private[spark] class ReplayListenerBus extends SparkListenerBus with Logging {
 
           postToAll(JsonProtocol.sparkEventFromJson(parse(currentLine)))
         } catch {
+          case e: java.lang.ClassNotFoundException if
+            e.getMessage == "org.apache.spark.sql.streaming.StreamingQueryListener$QueryProgress" ||
+            e.getMessage == "org.apache.spark.sql.streaming.StreamingQueryListener$QueryTerminated"
+            =>
+            // Ignore events generated by Structured Streaming in Spark 2.0.0 and 2.0.1.
+            // It's safe since no place uses them.
+            logWarning(s"Dropped incompatible Structured Streaming log: $currentLine")
           case jpe: JsonParseException =>
             // We can only ignore exception from last line of the file that might be truncated
             // the last entry may not be the very last line in the event log, but we treat it

sql/core/src/test/resources/history-server/structured-streaming-query-event-logs-2.0.0.txt

@@ -0,0 +1,4 @@
+{"Event":"org.apache.spark.sql.streaming.StreamingQueryListener$QueryProgress","queryInfo":{"name":"hello","id":0,"sourceStatuses":[{"description":"FileStreamSource[file:/Users/zsx/stream]","offsetDesc":"#0"}],"sinkStatus":{"description":"org.apache.spark.sql.execution.streaming.MemorySink@2b85b3a5","offsetDesc":"[#0]"}}}
+{"Event":"org.apache.spark.sql.streaming.StreamingQueryListener$QueryTerminated","queryInfo":{"name":"hello","id":0,"sourceStatuses":[{"description":"FileStreamSource[file:/Users/zsx/stream]","offsetDesc":"#0"}],"sinkStatus":{"description":"org.apache.spark.sql.execution.streaming.MemorySink@2b85b3a5","offsetDesc":"[#0]"}},"exception":null,"stackTrace":[]}
+{"Event":"org.apache.spark.sql.streaming.StreamingQueryListener$QueryTerminated","queryInfo":{"name":"hello","id":0,"sourceStatuses":[{"description":"FileStreamSource[file:/Users/zsx/stream]","offsetDesc":"#0"}],"sinkStatus":{"description":"org.apache.spark.sql.execution.streaming.MemorySink@514502dc","offsetDesc":"[-]"}},"exception":"Query hello terminated with exception: Job aborted due to stage failure: Task 0 in stage 0.0 failed 1 times, most recent failure: Lost task 0.0 in stage 0.0 (TID 0, localhost): java.lang.ArithmeticException: / by zero\n\tat $line15.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$anonfun$1.apply(<console>:25)\n\tat $line15.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$anonfun$1.apply(<console>:25)\n\tat org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)\n\tat org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)\n\tat org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:370)\n\tat org.apache.spark.sql.execution.SparkPlan$$anonfun$4.apply(SparkPlan.scala:246)\n\tat org.apache.spark.sql.execution.SparkPlan$$anonfun$4.apply(SparkPlan.scala:240)\n\tat org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:784)\n\tat org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:784)\n\tat org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)\n\tat org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:319)\n\tat org.apache.spark.rdd.RDD.iterator(RDD.scala:283)\n\tat org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)\n\tat org.apache.spark.scheduler.Task.run(Task.scala:85)\n\tat org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)\n\tat java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)\n\tat java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)\n\tat java.lang.Thread.run(Thread.java:745)\n\nDriver stacktrace:","stackTrace":[{"methodName":"org$apache$spark$sql$execution$streaming$StreamExecution$$runBatches","fileName":"StreamExecution.scala","lineNumber":208,"className":"org.apache.spark.sql.execution.streaming.StreamExecution","nativeMethod":false},{"methodName":"run","fileName":"StreamExecution.scala","lineNumber":120,"className":"org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1","nativeMethod":false}]}
+{"Event":"SparkListenerApplicationEnd","Timestamp":1477593059313}

sql/core/src/test/resources/history-server/structured-streaming-query-event-logs-2.0.1.txt

@@ -0,0 +1,4 @@
+{"Event":"org.apache.spark.sql.streaming.StreamingQueryListener$QueryProgress","queryInfo":{"name":"hello","id":0,"sourceStatuses":[{"description":"FileStreamSource[file:/Users/zsx/stream]","offsetDesc":"#0"}],"sinkStatus":{"description":"org.apache.spark.sql.execution.streaming.MemorySink@611c739e","offsetDesc":"[#0]"}}}
+{"Event":"org.apache.spark.sql.streaming.StreamingQueryListener$QueryTerminated","queryInfo":{"name":"hello","id":0,"sourceStatuses":[{"description":"FileStreamSource[file:/Users/zsx/stream]","offsetDesc":"#0"}],"sinkStatus":{"description":"org.apache.spark.sql.execution.streaming.MemorySink@611c739e","offsetDesc":"[#0]"}},"exception":null,"stackTrace":[]}
+{"Event":"org.apache.spark.sql.streaming.StreamingQueryListener$QueryTerminated","queryInfo":{"name":"hello","id":0,"sourceStatuses":[{"description":"FileStreamSource[file:/Users/zsx/stream]","offsetDesc":"#0"}],"sinkStatus":{"description":"org.apache.spark.sql.execution.streaming.MemorySink@76959af6","offsetDesc":"[-]"}},"exception":"Query hello terminated with exception: Job aborted due to stage failure: Task 0 in stage 0.0 failed 1 times, most recent failure: Lost task 0.0 in stage 0.0 (TID 0, localhost): java.lang.ArithmeticException: / by zero\n\tat $line15.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$anonfun$1.apply(<console>:25)\n\tat $line15.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$anonfun$1.apply(<console>:25)\n\tat org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)\n\tat org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)\n\tat org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:370)\n\tat org.apache.spark.sql.execution.SparkPlan$$anonfun$4.apply(SparkPlan.scala:246)\n\tat org.apache.spark.sql.execution.SparkPlan$$anonfun$4.apply(SparkPlan.scala:240)\n\tat org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:784)\n\tat org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:784)\n\tat org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)\n\tat org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:319)\n\tat org.apache.spark.rdd.RDD.iterator(RDD.scala:283)\n\tat org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)\n\tat org.apache.spark.scheduler.Task.run(Task.scala:85)\n\tat org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)\n\tat java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)\n\tat java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)\n\tat java.lang.Thread.run(Thread.java:745)\n\nDriver stacktrace:","stackTrace":[{"methodName":"org$apache$spark$sql$execution$streaming$StreamExecution$$runBatches","fileName":"StreamExecution.scala","lineNumber":208,"className":"org.apache.spark.sql.execution.streaming.StreamExecution","nativeMethod":false},{"methodName":"run","fileName":"StreamExecution.scala","lineNumber":120,"className":"org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1","nativeMethod":false}]}
+{"Event":"SparkListenerApplicationEnd","Timestamp":1477594073785}

sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamingQueryListenerSuite.scala

@@ -17,11 +17,14 @@
 
 package org.apache.spark.sql.streaming
 
+import scala.collection.mutable
+
 import org.scalactic.TolerantNumerics
 import org.scalatest.BeforeAndAfter
 import org.scalatest.PrivateMethodTester._
 
 import org.apache.spark.SparkException
+import org.apache.spark.scheduler._
 import org.apache.spark.sql.DataFrame
 import org.apache.spark.sql.execution.streaming._
 import org.apache.spark.sql.functions._
@@ -206,6 +209,45 @@ class StreamingQueryListenerSuite extends StreamTest with BeforeAndAfter {
     assert(queryQueryTerminated.exception === newQueryTerminated.exception)
   }
 
+  test("ReplayListenerBus should ignore broken event jsons generated in 2.0.0") {
+    // structured-streaming-query-event-logs-2.0.0.txt has all types of events generated by
+    // Structured Streaming in Spark 2.0.0.
+    // SparkListenerApplicationEnd is the only valid event and it's the last event. We use it
+    // to verify that we can skip broken jsons generated by Structured Streaming.
+    testReplayListenerBusWithBorkenEventJsons("structured-streaming-query-event-logs-2.0.0.txt")
+  }
+
+  test("ReplayListenerBus should ignore broken event jsons generated in 2.0.1") {
+    // structured-streaming-query-event-logs-2.0.1.txt has all types of events generated by
+    // Structured Streaming in Spark 2.0.1.
+    // SparkListenerApplicationEnd is the only valid event and it's the last event. We use it
+    // to verify that we can skip broken jsons generated by Structured Streaming.
+    testReplayListenerBusWithBorkenEventJsons("structured-streaming-query-event-logs-2.0.1.txt")
+  }
+
+  private def testReplayListenerBusWithBorkenEventJsons(fileName: String): Unit = {
+    val input = getClass.getResourceAsStream(s"/history-server/$fileName")
+    val events = mutable.ArrayBuffer[SparkListenerEvent]()
+    try {
+      val replayer = new ReplayListenerBus() {
+        // Redirect all parsed events to `events`
+        override def doPostEvent(
+            listener: SparkListenerInterface,
+            event: SparkListenerEvent): Unit = {
+          events += event
+        }
+      }
+      // Add a dummy listener so that "doPostEvent" will be called.
+      replayer.addListener(new SparkListener {})
+      replayer.replay(input, fileName)
+      // SparkListenerApplicationEnd is the only valid event
+      assert(events.size === 1)
+      assert(events(0).isInstanceOf[SparkListenerApplicationEnd])
+    } finally {
+      input.close()
+    }
+  }
+
   private def assertStreamingQueryInfoEquals(
       expected: StreamingQueryStatus,
       actual: StreamingQueryStatus): Unit = {