I believe that this is an instance of https://issues.apache.org/jira/browse/SPARK-10422, which should be fixed in upcoming 1.5.1 release.
On Thu, Sep 24, 2015 at 12:52 PM, Mark Hamstra <m...@clearstorydata.com> wrote: > Where do you see a race in the DAGScheduler? On a quick look at your > stack trace, this just looks to me like a Job where a Stage failed and then > the DAGScheduler aborted the failed Job. > > On Thu, Sep 24, 2015 at 12:00 PM, robin_up <robin...@gmail.com> wrote: > >> Hi >> >> After upgrade to 1.5, we found a possible racing condition in DAGScheduler >> similar to https://issues.apache.org/jira/browse/SPARK-4454. >> >> Here is the code creating the problem: >> >> >> app_cpm_load = sc.textFile("/user/a/app_ecpm.txt").map(lambda x: >> x.split(',')).map(lambda p: Row(app_id=str(p[0]), loc_filter=str(p[1]), >> cpm_required=float(p[2]) )) >> app_cpm = sqlContext.createDataFrame(app_cpm_load) >> app_cpm.registerTempTable("app_cpm") >> >> app_rev_cpm_sql = '''select loc_filter from app_cpm''' >> app_rev_cpm = sqlContext.sql(app_rev_cpm_sql) >> app_rev_cpm.cache() >> app_rev_cpm.show() >> >> >> >> Traceback (most recent call last): >> File "<stdin>", line 1, in <module> >> File "/opt/spark/python/pyspark/sql/dataframe.py", line 256, in show >> print(self._jdf.showString(n, truncate)) >> File "/opt/spark/python/lib/py4j-0.8.2.1-src.zip/py4j/java_gateway.py", >> line 538, in __call__ >> File "/opt/spark/python/pyspark/sql/utils.py", line 36, in deco >> return f(*a, **kw) >> File "/opt/spark/python/lib/py4j-0.8.2.1-src.zip/py4j/protocol.py", line >> 300, in get_return_value >> py4j.protocol.Py4JJavaError: An error occurred while calling >> o46.showString. >> : org.apache.spark.SparkException: Job aborted due to stage failure: Task >> 0 >> in stage 1.0 failed 4 times, most recent failure: Lost task 0.3 in stage >> 1.0 >> (TID 4, spark-yarn-dn02): java.util.NoSuchElementException: key not found: >> UK >> at scala.collection.MapLike$class.default(MapLike.scala:228) >> at scala.collection.AbstractMap.default(Map.scala:58) >> at scala.collection.mutable.HashMap.apply(HashMap.scala:64) >> at >> >> org.apache.spark.sql.columnar.compression.DictionaryEncoding$Encoder.compress(compressionSchemes.scala:258) >> at >> >> org.apache.spark.sql.columnar.compression.CompressibleColumnBuilder$class.build(CompressibleColumnBuilder.scala:110) >> at >> >> org.apache.spark.sql.columnar.NativeColumnBuilder.build(ColumnBuilder.scala:87) >> at >> >> org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1$$anonfun$next$2.apply(InMemoryColumnarTableScan.scala:152) >> at >> >> org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1$$anonfun$next$2.apply(InMemoryColumnarTableScan.scala:152) >> at >> >> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) >> at >> >> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) >> at >> >> scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33) >> at >> scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108) >> at >> scala.collection.TraversableLike$class.map(TraversableLike.scala:244) >> at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:108) >> at >> >> org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1.next(InMemoryColumnarTableScan.scala:152) >> at >> >> org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1.next(InMemoryColumnarTableScan.scala:120) >> at >> org.apache.spark.storage.MemoryStore.unrollSafely(MemoryStore.scala:278) >> at >> org.apache.spark.CacheManager.putInBlockManager(CacheManager.scala:171) >> at >> org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:78) >> at org.apache.spark.rdd.RDD.iterator(RDD.scala:262) >> at >> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) >> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) >> at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) >> at >> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) >> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) >> at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) >> at >> org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) >> at org.apache.spark.scheduler.Task.run(Task.scala:88) >> at >> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) >> at >> >> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) >> at >> >> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) >> at java.lang.Thread.run(Thread.java:745) >> >> Driver stacktrace: >> at >> org.apache.spark.scheduler.DAGScheduler.org >> $apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1280) >> at >> >> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1268) >> at >> >> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1267) >> at >> >> scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) >> at >> scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) >> at >> >> org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1267) >> at >> >> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697) >> at >> >> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697) >> at scala.Option.foreach(Option.scala:236) >> at >> >> org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697) >> at >> >> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1493) >> at >> >> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1455) >> at >> >> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1444) >> at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) >> at >> org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567) >> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1813) >> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1826) >> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1839) >> at >> org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:215) >> at >> >> org.apache.spark.sql.execution.Limit.executeCollect(basicOperators.scala:207) >> at >> >> org.apache.spark.sql.DataFrame$$anonfun$collect$1.apply(DataFrame.scala:1386) >> at >> >> org.apache.spark.sql.DataFrame$$anonfun$collect$1.apply(DataFrame.scala:1386) >> at >> >> org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56) >> at >> org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:1904) >> at org.apache.spark.sql.DataFrame.collect(DataFrame.scala:1385) >> at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1315) >> at org.apache.spark.sql.DataFrame.take(DataFrame.scala:1378) >> at org.apache.spark.sql.DataFrame.showString(DataFrame.scala:178) >> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) >> at >> >> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) >> at >> >> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) >> at java.lang.reflect.Method.invoke(Method.java:606) >> at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231) >> at >> py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:379) >> at py4j.Gateway.invoke(Gateway.java:259) >> at >> py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133) >> at py4j.commands.CallCommand.execute(CallCommand.java:79) >> at py4j.GatewayConnection.run(GatewayConnection.java:207) >> at java.lang.Thread.run(Thread.java:745) >> Caused by: java.util.NoSuchElementException: key not found: UK >> at scala.collection.MapLike$class.default(MapLike.scala:228) >> at scala.collection.AbstractMap.default(Map.scala:58) >> at scala.collection.mutable.HashMap.apply(HashMap.scala:64) >> at >> >> org.apache.spark.sql.columnar.compression.DictionaryEncoding$Encoder.compress(compressionSchemes.scala:258) >> at >> >> org.apache.spark.sql.columnar.compression.CompressibleColumnBuilder$class.build(CompressibleColumnBuilder.scala:110) >> at >> >> org.apache.spark.sql.columnar.NativeColumnBuilder.build(ColumnBuilder.scala:87) >> at >> >> org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1$$anonfun$next$2.apply(InMemoryColumnarTableScan.scala:152) >> at >> >> org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1$$anonfun$next$2.apply(InMemoryColumnarTableScan.scala:152) >> at >> >> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) >> at >> >> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) >> at >> >> scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33) >> at >> scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108) >> at >> scala.collection.TraversableLike$class.map(TraversableLike.scala:244) >> at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:108) >> at >> >> org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1.next(InMemoryColumnarTableScan.scala:152) >> at >> >> org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1.next(InMemoryColumnarTableScan.scala:120) >> at >> org.apache.spark.storage.MemoryStore.unrollSafely(MemoryStore.scala:278) >> at >> org.apache.spark.CacheManager.putInBlockManager(CacheManager.scala:171) >> at >> org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:78) >> at org.apache.spark.rdd.RDD.iterator(RDD.scala:262) >> at >> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) >> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) >> at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) >> at >> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) >> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) >> at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) >> at >> org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) >> at org.apache.spark.scheduler.Task.run(Task.scala:88) >> at >> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) >> at >> >> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) >> at >> >> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) >> ... 1 more >> >> >> >> >> >> ----- >> -- Robin Li >> -- >> View this message in context: >> http://apache-spark-user-list.1001560.n3.nabble.com/Potential-racing-condition-in-DAGScheduler-when-Spark-1-5-caching-tp24810.html >> Sent from the Apache Spark User List mailing list archive at Nabble.com. >> >> --------------------------------------------------------------------- >> To unsubscribe, e-mail: user-unsubscr...@spark.apache.org >> For additional commands, e-mail: user-h...@spark.apache.org >> >> >
