我正在向Hive加载几个Oracle表，它似乎正在工作但是有两个表出错 - IllegalArgumentException: requirement failed: Decimal precision 136 exceeds max precision 38
我检查了Oracle表，并且源中没有精度为Decimal（136）的列。
以下是spark-shell中的Spark / Scala代码：
val df_oracle = spark.read.format("jdbc").option("url", "jdbc:oracle:thin:@hostname:port:SID").option("user",userName).option("password",passWord).option("driver", "oracle.jdbc.driver.OracleDriver").option("dbtable", inputTable).load()
df_oracle.repartition(10).write.format("orc").mode("overwrite").saveAsTable(outputTable)
以下是完整的错误消息 -
java.lang.IllegalArgumentException: requirement failed: Decimal precision 136 exceeds max precision 38
at scala.Predef$.require(Predef.scala:224)
at org.apache.spark.sql.types.Decimal.set(Decimal.scala:113)
at org.apache.spark.sql.types.Decimal$.apply(Decimal.scala:434)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$makeGetter$3$$anonfun$9.apply(JdbcUtils.scala:337)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$makeGetter$3$$anonfun$9.apply(JdbcUtils.scala:337)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$nullSafeConvert(JdbcUtils.scala:438)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$makeGetter$3.apply(JdbcUtils.scala:337)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$makeGetter$3.apply(JdbcUtils.scala:335)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:286)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:268)
at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:32)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:147)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
at org.apache.spark.scheduler.Task.run(Task.scala:99)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:322)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
17/10/28 07:56:58 ERROR TaskSetManager: Task 0 in stage 36.0 failed 4 times; aborting job
17/10/28 07:56:58 ERROR FileFormatWriter: Aborting job null.
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 36.0 failed 4 times, most recent failure: Lost task 0.3 in stage 36.0 (TID 201, alphd1dx009.dlx.idc.ge.com, executor 1): java.lang.IllegalArgumentException: requirement failed: Decimal precision 136 exceeds max precision 38
at scala.Predef$.require(Predef.scala:224)
at org.apache.spark.sql.types.Decimal.set(Decimal.scala:113)
at org.apache.spark.sql.types.Decimal$.apply(Decimal.scala:434)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$makeGetter$3$$anonfun$9.apply(JdbcUtils.scala:337)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$makeGetter$3$$anonfun$9.apply(JdbcUtils.scala:337)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$nullSafeConvert(JdbcUtils.scala:438)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$makeGetter$3.apply(JdbcUtils.scala:337)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$makeGetter$3.apply(JdbcUtils.scala:335)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:286)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:268)
at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:32)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:147)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
at org.apache.spark.scheduler.Task.run(Task.scala:99)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:322)
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$$failJobAndIndependentStages(DAGScheduler.scala:1435)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1423)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1422)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1422)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:802)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1650)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1605)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1594)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:628)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1928)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1941)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1961)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply$mcV$sp(FileFormatWriter.scala:127)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:121)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:121)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:121)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:101)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:92)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:92)
at org.apache.spark.sql.execution.datasources.DataSource.writeInFileFormat(DataSource.scala:484)
at org.apache.spark.sql.execution.datasources.DataSource.writeAndRead(DataSource.scala:500)
at org.apache.spark.sql.execution.command.CreateDataSourceTableAsSelectCommand.run(createDataSourceTables.scala:263)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:92)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:92)
at org.apache.spark.sql.DataFrameWriter.saveAsTable(DataFrameWriter.scala:404)
at org.apache.spark.sql.DataFrameWriter.saveAsTable(DataFrameWriter.scala:358)
at $line34.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$anonfun$1.apply(<console>:41)
at $line34.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$anonfun$1.apply(<console>:28)
at scala.collection.immutable.List.foreach(List.scala:381)
at $line34.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw.<init>(<console>:28)
at $line34.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw.<init>(<console>:54)
at $line34.$read$$iw$$iw$$iw$$iw$$iw$$iw.<init>(<console>:56)
at $line34.$read$$iw$$iw$$iw$$iw$$iw.<init>(<console>:58)
at $line34.$read$$iw$$iw$$iw$$iw.<init>(<console>:60)
at $line34.$read$$iw$$iw$$iw.<init>(<console>:62)
at $line34.$read$$iw$$iw.<init>(<console>:64)
at $line34.$read$$iw.<init>(<console>:66)
at $line34.$read.<init>(<console>:68)
at $line34.$read$.<init>(<console>:72)
at $line34.$read$.<clinit>(<console>)
at $line34.$eval$.$print$lzycompute(<console>:7)
at $line34.$eval$.$print(<console>:6)
at $line34.$eval.$print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at scala.tools.nsc.interpreter.IMain$ReadEvalPrint.call(IMain.scala:786)
at scala.tools.nsc.interpreter.IMain$Request.loadAndRun(IMain.scala:1047)
at scala.tools.nsc.interpreter.IMain$WrappedRequest$$anonfun$loadAndRunReq$1.apply(IMain.scala:638)
at scala.tools.nsc.interpreter.IMain$WrappedRequest$$anonfun$loadAndRunReq$1.apply(IMain.scala:637)
at scala.reflect.internal.util.ScalaClassLoader$class.asContext(ScalaClassLoader.scala:31)
at scala.reflect.internal.util.AbstractFileClassLoader.asContext(AbstractFileClassLoader.scala:19)
at scala.tools.nsc.interpreter.IMain$WrappedRequest.loadAndRunReq(IMain.scala:637)
at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:569)
at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:565)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:807)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:825)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:825)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:825)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:825)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:825)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:825)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:825)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:825)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:825)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:825)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:825)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:825)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:825)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:825)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:825)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:825)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:825)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:825)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:825)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:825)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:825)
at scala.tools.nsc.interpreter.ILoop.command(ILoop.scala:681)
at scala.tools.nsc.interpreter.ILoop.processLine(ILoop.scala:395)
at scala.tools.nsc.interpreter.ILoop.loop(ILoop.scala:415)
at scala.tools.nsc.interpreter.ILoop$$anonfun$process$1.apply$mcZ$sp(ILoop.scala:923)
at scala.tools.nsc.interpreter.ILoop$$anonfun$process$1.apply(ILoop.scala:909)
at scala.tools.nsc.interpreter.ILoop$$anonfun$process$1.apply(ILoop.scala:909)
at scala.reflect.internal.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:97)
at scala.tools.nsc.interpreter.ILoop.process(ILoop.scala:909)
at org.apache.spark.repl.Main$.doMain(Main.scala:69)
at org.apache.spark.repl.Main$.main(Main.scala:52)
at org.apache.spark.repl.Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:751)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:187)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:212)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:126)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.IllegalArgumentException: requirement failed: Decimal precision 136 exceeds max precision 38
at scala.Predef$.require(Predef.scala:224)
at org.apache.spark.sql.types.Decimal.set(Decimal.scala:113)
at org.apache.spark.sql.types.Decimal$.apply(Decimal.scala:434)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$makeGetter$3$$anonfun$9.apply(JdbcUtils.scala:337)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$makeGetter$3$$anonfun$9.apply(JdbcUtils.scala:337)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$nullSafeConvert(JdbcUtils.scala:438)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$makeGetter$3.apply(JdbcUtils.scala:337)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$makeGetter$3.apply(JdbcUtils.scala:335)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:286)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:268)
at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:32)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:147)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
at org.apache.spark.scheduler.Task.run(Task.scala:99)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:322)
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)
请让我知道我错过了什么。
由于
Spark version 2.1.1.2.6.2.0-205
答案 0 :(得分：0)
解决方法1：
在Oracle DB中创建一个视图：
#include <iostream>
#include <list>
#include <cstdlib>
#include <ctime>
void DisplayListForward(std::list<int>& list)
{
std::cout << "The sorted list contains\n";
for (auto iter = list.rbegin(); iter != list.rend(); ++iter)
{
std::cout << *iter << " ";
}
std::cout << '\n';
}
void InsertRandomInts()
{
std::list<int> list;
std::srand(static_cast<unsigned>(std::time(nullptr)));
for (int i = 0; i < 50; ++i)
{
auto const b = std::rand() % 100 + 1;
list.push_back(b);
}
list.sort();
DisplayListForward(list);
}
int main()
{
InsertRandomInts();
}
并使用该视图而不是table_name
解决方法2：即时在Spark端执行相同的操作：
for (int pos = listPtr->getLength(); pos >= 1; pos--)
答案 1 :(得分：0)