Я создаю фрейм данных с использованием Apache Spark версии 2.3.1.Когда я пытаюсь подсчитать фрейм данных, я получаю следующую ошибку:
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 12, analitik11.{hostname}, executor 1): java.lang.ArrayIndexOutOfBoundsException: 2
at org.apache.spark.sql.vectorized.ColumnarBatch.column(ColumnarBatch.java:98)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.datasourcev2scan_nextBatch_0$(Unknown Source)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$10$$anon$1.hasNext(WholeStageCodegenExec.scala:614)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:125)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
at org.apache.spark.scheduler.Task.run(Task.scala:109)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1602)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1590)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1589)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1589)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:831)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:831)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:831)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1823)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1772)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1761)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:642)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2034)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2055)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2074)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2099)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:939)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
at org.apache.spark.rdd.RDD.collect(RDD.scala:938)
at org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:297)
at org.apache.spark.sql.Dataset$$anonfun$count$1.apply(Dataset.scala:2770)
at org.apache.spark.sql.Dataset$$anonfun$count$1.apply(Dataset.scala:2769)
at org.apache.spark.sql.Dataset$$anonfun$52.apply(Dataset.scala:3254)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:77)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3253)
at org.apache.spark.sql.Dataset.count(Dataset.scala:2769)
... 49 elided
Caused by: java.lang.ArrayIndexOutOfBoundsException: 2
at org.apache.spark.sql.vectorized.ColumnarBatch.column(ColumnarBatch.java:98)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.datasourcev2scan_nextBatch_0$(Unknown Source)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$10$$anon$1.hasNext(WholeStageCodegenExec.scala:614)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:125)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
at org.apache.spark.scheduler.Task.run(Task.scala:109)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Мы используем com.hortonworks.spark.sql.hive.llap.HiveWarehouseBuilder для подключения и чтения таблиц из Hive.Код для создания кадра данных выглядит следующим образом:
val hive = com.hortonworks.spark.sql.hive.llap.HiveWarehouseBuilder.session(spark).build()
val edgesTest = hive.executeQuery("select trim(s_vno) as src ,trim(a_vno) as dst, share, administrator, account, all_share " +
"from ebyn.babs_edges_2018 where (share <> 0 or administrator <> 0 or account <> 0 or all_share <> 0) and trim(date) = '201801'")
val share_org_edges = edgesTest.alias("df1").
join(edgesTest.alias("df2"), "src").
where("df1.dst <> df2.dst").
groupBy(
greatest("df1.dst", "df2.dst").as("src"),
least("df1.dst", "df2.dst").as("dst")).
agg(max("df1.share").as("share"), max("df1.administrator").as("administrator"), max("df1.account").as("account"), max("df1.all_share").as("all_share")).persist
share_org_edges.count
Свойства таблицы следующие:
CREATE TABLE `EBYN.BABS_EDGES_2018`(
`date` string,
`a_vno` string,
`s_vno` string,
`amount` double,
`num` int,
`share` int,
`share_ratio` int,
`administrator` int,
`account` int,
`share-all` int)
COMMENT 'Imported by sqoop on 2018/10/11 11:10:16'
ROW FORMAT SERDE
'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'
WITH SERDEPROPERTIES (
'field.delim'='',
'line.delim'='\n',
'serialization.format'='')
STORED AS INPUTFORMAT
'org.apache.hadoop.mapred.TextInputFormat'
OUTPUTFORMAT
'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'
LOCATION
'hdfs://ggmprod/warehouse/tablespace/managed/hive/ebyn.db/babs_edges_2018'
TBLPROPERTIES (
'bucketing_version'='2',
'transactional'='true',
'transactional_properties'='insert_only',
'transient_lastDdlTime'='1539245438')