I have following code: object LoaderProcessor extendsApp{val logger =LoggerFactory.getLogger(this.getClass()) execute() def execute():Unit={ val spark = get_spark() import spark.implicits._ var df = spark.read .format("csv") .option("delimiter",",") .option("header",true) .option("inferSchema","true") .option("timestampFormat","yyyy/MM/dd HH:mm:ss") .load(args(2)) df = df.withColumn("zs_source", lit(1))//the only operation on dataframe val o_file =Config().getString("myapp.dataFolder")+"/8/1/data.csv" logger.info("Writing output to: {}", o_file) df.write.mode("overwrite").option("header","true").csv(o_file) } def get_spark():SparkSession={ val env =System.getenv("MYAPP_ENV") var spark:SparkSession=null if(env ==null|| env =="dev_local"){ spark = org.apache.spark.sql.SparkSession.builder .master("local").appName("MyApp").getOrCreate; }else{ spark = org.apache.spark.sql.SparkSession.builder .appName("MyApp")//.enableHiveSupport().getOrCreate; } spark.sparkContext.setCheckpointDir(Config().getString("myapp.rddcp"))return spark } } It works well in client mode. Could not figure out the problem. I have my clusters on HDInsight. Also noticed that the "write" operation keeps writing on output folder like this: part-00000-3e9566ae-c13c-468a-8732-e7b8a8df5335-c000.csv and then in few seconds: part-00000-4f4979a0-d9f9-481b-aac4-115e63b9f59c-c000.csv 8/12/01 15:08:53 INFO ApplicationMaster: Starting the user application in a separate Thread 18/12/01 15:08:53 INFO ApplicationMaster: Waiting for spark context initialization... 18/12/01 15:08:55 INFO Config$: Environment: dev 18/12/01 15:08:55 ERROR ApplicationMaster: Uncaught exception: java.lang.IllegalStateException: User did not initialize spark context! at org.apache.spark.deploy.yarn.ApplicationMaster.runDriver(ApplicationMaster.scala:510) at org.apache.spark.deploy.yarn.ApplicationMaster.org$apache$spark$deploy$yarn$ApplicationMaster$$runImpl(ApplicationMaster.scala:345) at org.apache.spark.deploy.yarn.ApplicationMaster$$anonfun$run$2.apply$mcV$sp(ApplicationMaster.scala:260) at org.apache.spark.deploy.yarn.ApplicationMaster$$anonfun$run$2.apply(ApplicationMaster.scala:260) at org.apache.spark.deploy.yarn.ApplicationMaster$$anonfun$run$2.apply(ApplicationMaster.scala:260) at org.apache.spark.deploy.yarn.ApplicationMaster$$anon$5.run(ApplicationMaster.scala:815) at java.security.AccessController.doPrivileged(Native Method) at javax.security.auth.Subject.doAs(Subject.java:422) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1869) at org.apache.spark.deploy.yarn.ApplicationMaster.doAsUser(ApplicationMaster.scala:814) at org.apache.spark.deploy.yarn.ApplicationMaster.run(ApplicationMaster.scala:259) at org.apache.spark.deploy.yarn.ApplicationMaster$.main(ApplicationMaster.scala:839) at org.apache.spark.deploy.yarn.ApplicationMaster.main(ApplicationMaster.scala) spark-submit --master yarn --deploy-mode cluster --jars "wasb://xx@yy/zs/jars/config-1.3.1.jar" --class myapp.LoaderProcessor "wasb://xx@yy/zs/jars/myapp.jar" l 8 /data/8_data.csv 1 , true false -->PROBLEM spark-submit --deploy-mode client --jars "wasb://xx@yy/zs/jars/config-1.3.1.jar" --class myapp.LoaderProcessor "wasb://xx@yy/zs/jars/myapp.jar" l 8 /data/8_data.csv 1 , true false -->WORKS!!! ... View more