Created 05-05-2017 03:00 PM
I am getting this error when i try to save a dataframe into a file
17/05/05 17:19:20 ERROR DefaultWriterContainer: Job job_201705051719_0000 aborted. Traceback (most recent call last): File "/opt/sqlscrapper.py", line 24, in <module> df.write.format("orc").save("/tmp/orc_query_output") File "/usr/hdp/2.5.3.0-37/spark/python/lib/pyspark.zip/pyspark/sql/readwriter.py", line 397, in save File "/usr/hdp/2.5.3.0-37/spark/python/lib/py4j-0.9-src.zip/py4j/java_gateway.py", line 813, in __call__ File "/usr/hdp/2.5.3.0-37/spark/python/lib/pyspark.zip/pyspark/sql/utils.py", line 45, in deco File "/usr/hdp/2.5.3.0-37/spark/python/lib/py4j-0.9-src.zip/py4j/protocol.py", line 308, in get_return_value py4j.protocol.Py4JJavaError: An error occurred while calling o51.save. : org.apache.spark.SparkException: Job aborted. at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply$mcV$sp(InsertIntoHadoopFsRelation.scala:154) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply(InsertIntoHadoopFsRelation.scala:106) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply(InsertIntoHadoopFsRelation.scala:106) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation.run(InsertIntoHadoopFsRelation.scala:106) at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:58) at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:56) at org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:70) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:55) at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:55) at org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:256) at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:148) at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:139) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:498) at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231) at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381) at py4j.Gateway.invoke(Gateway.java:259) at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133) at py4j.commands.CallCommand.execute(CallCommand.java:79) at py4j.GatewayConnection.run(GatewayConnection.java:209) at java.lang.Thread.run(Thread.java:745) Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 4 times, most recent failure: Lost task 0.3 in stage 0.0 (TID 3, db-hdp-dn2.darbeirut.com): java.lang.ClassNotFoundException: com.microsoft.sqlserver.jdbc.SQLServerDriver at java.net.URLClassLoader.findClass(URLClassLoader.java:381) at java.lang.ClassLoader.loadClass(ClassLoader.java:424) at java.lang.ClassLoader.loadClass(ClassLoader.java:357) at org.apache.spark.sql.execution.datasources.jdbc.DriverRegistry$.register(DriverRegistry.scala:38) at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2.apply(JdbcUtils.scala:53) at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2.apply(JdbcUtils.scala:52) at org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$$anon$1.<init>(JDBCRDD.scala:347) at org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD.compute(JDBCRDD.scala:339) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:313) at org.apache.spark.rdd.RDD.iterator(RDD.scala:277) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) at org.apache.spark.scheduler.Task.run(Task.scala:89) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:227) 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)
import os from pyspark import SparkConf,SparkContext from pyspark.sql import HiveContext import pandas as pd conf = (SparkConf() .setAppName("data_import") .set("spark.dynamicAllocation.enabled","true") .set("spark.shuffle.service.enabled","true")) sc = SparkContext(conf = conf) sqlctx = HiveContext(sc) df = sqlctx.load( source="jdbc", url="jdbc:sqlserver://db-sqltech:1433;database=WebUsage;user=username;password=password", dbtable="EmployeeMobiles", properties={"driver": 'com.sqlserver.jdbc.Driver'}) df.write.format("orc").save("/tmp/orc_query_output") df.write.mode('overwrite').format('orc').saveAsTable("WebLog")
Created 05-05-2017 05:18 PM
Your exception is java.lang.ClassNotFoundException: com.microsoft.sqlserver.jdbc.SQLServerDriver
Are you passing the jdbc driver to your program. Also you are specifying com.sqlserver.jdbc.Driver. It is looking for com.microsoft.sqlserver.jdbc.SQLServerDriver? I am not sure where is this coming from but your issue is not having a driver to connect to SQL Server.