我為一個邏輯回歸模型,我繼續這個錯誤。這個問題會發生更多的數據建模,但是不管我有多增加服務集群內存,它仍然錯誤。堆棧跟蹤:
22/06/14 15:24:47警告TaskSetManager:在舞台上失去了任務0.0 17.0 (TID 17)(10.24.7.205執行人司機):TaskResultLost(結果丟失塊經理)
22/06/14 15:24:47錯誤TaskSetManager:任務0階段17.0失敗1次;流產的工作
22/06/14 15:24:47錯誤儀表:org.apache.spark。SparkException:工作階段失敗而終止:任務0階段17.0失敗1次,最近的失敗:在舞台上失去了任務0.0 17.0 (TID 17)(10.24.7.205執行人司機):TaskResultLost(結果丟失塊經理)
司機加:
org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages (DAGScheduler.scala: 2403)
在org.apache.spark.scheduler.DAGScheduler。anonfun abortStage美元2美元(DAGScheduler.scala: 2352)
org.apache.spark.scheduler.DAGScheduler。anonfun abortStage美元$ 2 $改編(DAGScheduler.scala: 2351)
scala.collection.mutable.ResizableArray.foreach (ResizableArray.scala: 62)
在scala.collection.mutable.ResizableArray.foreach $ (ResizableArray.scala: 55)
在scala.collection.mutable.ArrayBuffer.foreach (ArrayBuffer.scala: 49)
org.apache.spark.scheduler.DAGScheduler.abortStage (DAGScheduler.scala: 2351)
在org.apache.spark.scheduler.DAGScheduler。anonfun handleTaskSetFailed美元1美元(DAGScheduler.scala: 1109)
org.apache.spark.scheduler.DAGScheduler。anonfun handleTaskSetFailed美元$ 1 $改編(DAGScheduler.scala: 1109)
scala.Option.foreach (Option.scala: 407)
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed (DAGScheduler.scala: 1109)
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive (DAGScheduler.scala: 2591)
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive (DAGScheduler.scala: 2533)
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive (DAGScheduler.scala: 2522)
在org.apache.spark.util.EventLoop不久美元1.美元運行(EventLoop.scala: 49)
org.apache.spark.scheduler.DAGScheduler.runJob (DAGScheduler.scala: 898)
org.apache.spark.SparkContext.runJob (SparkContext.scala: 2214)
org.apache.spark.SparkContext.runJob (SparkContext.scala: 2235)
org.apache.spark.SparkContext.runJob (SparkContext.scala: 2254)
org.apache.spark.sql.execution.SparkPlan.executeTake (SparkPlan.scala: 476)
org.apache.spark.sql.execution.SparkPlan.executeTake (SparkPlan.scala: 429)
在org.apache.spark.sql.execution.CollectLimitExec.executeCollect (limit.scala: 48)
org.apache.spark.sql.Dataset.collectFromPlan (Dataset.scala: 3715)
org.apache.spark.sql.Dataset。anonfun頭1美元美元(Dataset.scala: 2728)
在org.apache.spark.sql.Dataset。anonfun withAction美元1美元(Dataset.scala: 3706)
在org.apache.spark.sql.execution.SQLExecution。美元anonfun withNewExecutionId 5美元(SQLExecution.scala: 103)
org.apache.spark.sql.execution.SQLExecution .withSQLConfPropagated美元(SQLExecution.scala: 163)
在org.apache.spark.sql.execution.SQLExecution。美元anonfun withNewExecutionId 1美元(SQLExecution.scala: 90)
org.apache.spark.sql.SparkSession.withActive (SparkSession.scala: 775)
org.apache.spark.sql.execution.SQLExecution .withNewExecutionId美元(SQLExecution.scala: 64)
org.apache.spark.sql.Dataset.withAction (Dataset.scala: 3704)
org.apache.spark.sql.Dataset.head (Dataset.scala: 2728)
org.apache.spark.sql.Dataset.head (Dataset.scala: 2735)
org.apache.spark.ml.classification.LogisticRegressionModel LogisticRegressionModelReader.load美元(LogisticRegression.scala: 1352)
org.apache.spark.ml.classification.LogisticRegressionModel LogisticRegressionModelReader.load美元(LogisticRegression.scala: 1324)
在org.apache.spark.ml.Pipeline SharedReadWrite。美元anonfun負載5美元美元(Pipeline.scala: 277)
org.apache.spark.ml.MLEvents.withLoadInstanceEvent (events.scala: 160)
在org.apache.spark.ml.MLEvents.withLoadInstanceEvent (events.scala: 155美元)
在org.apache.spark.ml.util.Instrumentation.withLoadInstanceEvent (Instrumentation.scala: 42)
在org.apache.spark.ml.Pipeline SharedReadWrite。美元美元anonfun負載4美元(Pipeline.scala: 277)
scala.collection.TraversableLike。anonfun地圖1美元美元(TraversableLike.scala: 286)
在scala.collection.IndexedSeqOptimized.foreach (IndexedSeqOptimized.scala: 36)
在scala.collection.IndexedSeqOptimized.foreach (IndexedSeqOptimized.scala: 33美元)
scala.collection.mutable.ArrayOps ofRef.foreach美元(ArrayOps.scala: 198)
scala.collection.TraversableLike.map (TraversableLike.scala: 286)
在scala.collection.TraversableLike.map (TraversableLike.scala: 279美元)
scala.collection.mutable.ArrayOps ofRef.map美元(ArrayOps.scala: 198)
在org.apache.spark.ml.Pipeline SharedReadWrite。美元anonfun負載3美元美元(Pipeline.scala: 274)
在org.apache.spark.ml.util.Instrumentation。美元anonfun檢測1美元(Instrumentation.scala: 191)
在美元scala.util.Try蘋果(Try.scala: 213)
org.apache.spark.ml.util.Instrumentation .instrumented美元(Instrumentation.scala: 191)
在org.apache.spark.ml.Pipeline SharedReadWrite .load美元(Pipeline.scala: 268)
org.apache.spark.ml.PipelineModel PipelineModelReader美元。anonfun負載美元7美元(Pipeline.scala: 356)
org.apache.spark.ml.MLEvents.withLoadInstanceEvent (events.scala: 160)
在org.apache.spark.ml.MLEvents.withLoadInstanceEvent (events.scala: 155美元)
在org.apache.spark.ml.util.Instrumentation.withLoadInstanceEvent (Instrumentation.scala: 42)
在org.apache.spark.ml.PipelineModel PipelineModelReader。美元anonfun負載6美元(Pipeline.scala: 355)
在org.apache.spark.ml.util.Instrumentation。美元anonfun檢測1美元(Instrumentation.scala: 191)
在美元scala.util.Try蘋果(Try.scala: 213)
org.apache.spark.ml.util.Instrumentation .instrumented美元(Instrumentation.scala: 191)
org.apache.spark.ml.PipelineModel PipelineModelReader.load美元(Pipeline.scala: 355)
org.apache.spark.ml.PipelineModel PipelineModelReader.load美元(Pipeline.scala: 349)
在sun.reflect.NativeMethodAccessorImpl。invoke0(本地方法)
sun.reflect.NativeMethodAccessorImpl.invoke (NativeMethodAccessorImpl.java: 62)
sun.reflect.DelegatingMethodAccessorImpl.invoke (DelegatingMethodAccessorImpl.java: 43)
java.lang.reflect.Method.invoke (Method.java: 498)
py4j.reflection.MethodInvoker.invoke (MethodInvoker.java: 244)
py4j.reflection.ReflectionEngine.invoke (ReflectionEngine.java: 357)
py4j.Gateway.invoke (Gateway.java: 282)
py4j.commands.AbstractCommand.invokeMethod (AbstractCommand.java: 132)
py4j.commands.CallCommand.execute (CallCommand.java: 79)
py4j.ClientServerConnection.waitForCommands (ClientServerConnection.java: 182)
py4j.ClientServerConnection.run (ClientServerConnection.java: 106)
java.lang.Thread.run (Thread.java: 748)