我正在将 TimesTen 数据库与 Spark 2.3.0
我需要在spark-submit命令中引用.so文件，以便连接到Timesten db。
spark-submit中是否有相同的选项？
我尝试在--conf spark.executor.extraLibraryPath中添加文件，但仍然无法解决错误。
错误，我得到的是：
Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 135 in stage 8.0 failed 4 times, most recent failure: Lost task 135.3 in stage 8.0 (TID 5308, 10.180.25.241, executor 3): java.sql.SQLException: Problems with loading native library/missing methods: no ttJdbcCS in java.library.path
at com.timesten.jdbc.JdbcOdbcConnection.connect(JdbcOdbcConnection.java:1809)
at com.timesten.jdbc.TimesTenDriver.connect(TimesTenDriver.java:305)
at com.timesten.jdbc.TimesTenDriver.connect(TimesTenDriver.java:161)
at org.apache.spark.sql.execution.datasources.jdbc.DriverWrapper.connect(DriverWrapper.scala:45)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$1.apply(JdbcUtils.scala:63)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$1.apply(JdbcUtils.scala:54)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.savePartition(JdbcUtils.scala:600)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$saveTable$1.apply(JdbcUtils.scala:821)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$saveTable$1.apply(JdbcUtils.scala:821)
at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1$$anonfun$apply$29.apply(RDD.scala:929)
at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1$$anonfun$apply$29.apply(RDD.scala:929)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2067)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2067)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:109)
at org.apache.spark.executor.Executor$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$$failJobAndIndependentStages(DAGScheduler.scala:1599)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1587)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1586)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1586)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:831)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:831)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:831)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1820)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1769)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1758)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:642)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2027)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2048)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2067)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2092)
at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1.apply(RDD.scala:929)
at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1.apply(RDD.scala:927)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
at org.apache.spark.rdd.RDD.foreachPartition(RDD.scala:927)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.saveTable(JdbcUtils.scala:821)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcRelationProvider.createRelation(JdbcRelationProvider.scala:83)
at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:46)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:86)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:80)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:80)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:654)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:654)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:77)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:654)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:273)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:267)
at com.sample.Transformation.main(Transformation.java:195)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:879)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:197)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:227)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:136)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.sql.SQLException: Problems with loading native library/missing methods: no ttJdbcCS in java.library.path
at com.timesten.jdbc.JdbcOdbcConnection.connect(JdbcOdbcConnection.java:1809)
at com.timesten.jdbc.TimesTenDriver.connect(TimesTenDriver.java:305)
at com.timesten.jdbc.TimesTenDriver.connect(TimesTenDriver.java:161)
at org.apache.spark.sql.execution.datasources.jdbc.DriverWrapper.connect(DriverWrapper.scala:45)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$1.apply(JdbcUtils.scala:63)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$1.apply(JdbcUtils.scala:54)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.savePartition(JdbcUtils.scala:600)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$saveTable$1.apply(JdbcUtils.scala:821)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$saveTable$1.apply(JdbcUtils.scala:821)
at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1$$anonfun$apply$29.apply(RDD.scala:929)
at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1$$anonfun$apply$29.apply(RDD.scala:929)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2067)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2067)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:109)
at org.apache.spark.executor.Executor$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)
我的提交火花的命令
./spark-submit \
--class com.sample.Transformation \
--conf spark.sql.shuffle.partitions=5001 \
--conf spark.yarn.executor.memoryOverhead=11264 \
--conf spark.executor.extraLibraryPath=/scratch/rmbbuild/Timesten/TimesTen/tt1122/lib \
--executor-memory=91GB \
--conf spark.yarn.driver.memoryOverhead=11264 \
--driver-memory=91G \
--executor-cores=17 \
--driver-cores=17 \
--conf spark.default.parallelism=306 \
--jars /scratch/rmbbuild/spark_ormb/drools-jars/ojdbc6.jar,/scratch/rmbbuild/spark_ormb/drools-jars/kie-api-7.7.0.Final.jar,/scratch/rmbbuild/spark_ormb/drools-jars/drools-core-7.7.0.Final.jar,/scratch/rmbbuild/spark_ormb/drools-jars/drools-compiler-7.7.0.Final.jar,/scratch/rmbbuild/spark_ormb/drools-jars/kie-soup-maven-support-7.7.0.Final.jar,/scratch/rmbbuild/spark_ormb/drools-jars/kie-internal-7.7.0.Final.jar,/scratch/rmbbuild/spark_ormb/drools-jars/xstream-1.4.10.jar,/scratch/rmbbuild/spark_ormb/drools-jars/kie-soup-commons-7.7.0.Final.jar,/scratch/rmbbuild/spark_ormb/drools-jars/ecj-4.4.2.jar,/scratch/rmbbuild/spark_ormb/drools-jars/mvel2-2.4.0.Final.jar,/scratch/rmbbuild/spark_ormb/drools-jars/kie-soup-project-datamodel-commons-7.7.0.Final.jar,/scratch/rmbbuild/spark_ormb/drools-jars/kie-soup-project-datamodel-api-7.7.0.Final.jar,/scratch/rmbbuild/Timesten/TimesTen/tt1122/lib/ttjdbc8.jar --driver-class-path /scratch/rmbbuild/spark_ormb/drools-jars/ojdbc6.jar:/scratch/rmbbuild/Timesten/TimesTen/tt1122/lib/ttjdbc8.jar \
--master spark://10.180.181.189:7077 \
"/scratch/rmbbuild/spark_ormb/POC-jar/Transformation-0.0.1-SNAPSHOT.jar" \
> /scratch/rmbbuild/spark_ormb/POC-jar/logs/logstt21.txt
答案 0 :(得分：1)
顾名思义，spark.executor.extraLibraryPath是执行器上使用的路径，因此您的.so必须在所有执行器上的该位置都可用。
要么必须将其安装在所有执行程序节点上的指定绝对路径上（即，在/scratch/rmbbuild/Timesten/TimesTen/tt1122/lib上），要么可以使用--files的{{1}}选项将其上传到执行程序，在执行者的工作目录中可以将其用于您的工作。
另请参阅此问题：