It seems Spark executors are not being provided with the requisite
dependencies. With spark-shell I can pass --jars /path/to/dep.jar. How can
we achieve this with Zeppelin, preferable inside a Note?
%spark.dep
z.addRepo("hortonworks").url("
http://repo.hortonworks.com/content/repositories/releases/";)
z.load("org.apache.phoenix:phoenix-spark:4.4.0.2.3.0.0-2557")
z.load("org.apache.phoenix:phoenix-core:4.4.0.2.3.0.0-2557")
z.load("com.databricks:spark-csv_2.10:1.2.0")
%spark
import org.apache.spark.sql._
import org.apache.phoenix.spark._
import java.sql.Connection
import java.sql.DriverManager
val input = "/user/root/crimes/atlanta"
val zkUrl = "docker.dev:2181:/hbase-unsecure"
val table = "CRIMES"
// Read CSV file, clean field names
var df =
sqlContext.read.format("com.databricks.spark.csv").option("header",
"true").option("DROPMALFORMED", "true").load(input)
val columns = df.columns.map(x => x.toUpperCase.replaceAll(" ", "_"))
df = df.toDF(columns:_*)
df.save("org.apache.phoenix.spark", SaveMode.Overwrite, Map("table" ->
table, "zkUrl" -> zkUrl))
Results:
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 5, docker.dev): java.lang.RuntimeException: java.sql.SQLException:
No suitable driver found for jdbc:phoenix:docker.dev:2181:/hbase-unsecure;
at
org.apache.phoenix.mapreduce.PhoenixOutputFormat.getRecordWriter(PhoenixOutputFormat.java:58)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1$$anonfun$12.apply(PairRDDFunctions.scala:1030)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1$$anonfun$12.apply(PairRDDFunctions.scala:1014)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63) at
org.apache.spark.scheduler.Task.run(Task.scala:70) at
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213) at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745) Caused by: java.sql.SQLException:
No suitable driver found for jdbc:phoenix:docker.dev:2181:/hbase-unsecure;
at java.sql.DriverManager.getConnection(DriverManager.java:689) at
java.sql.DriverManager.getConnection(DriverManager.java:208) at
org.apache.phoenix.mapreduce.util.ConnectionUtil.getConnection(ConnectionUtil.java:92)
at
org.apache.phoenix.mapreduce.util.ConnectionUtil.getOutputConnection(ConnectionUtil.java:80)
at
org.apache.phoenix.mapreduce.util.ConnectionUtil.getOutputConnection(ConnectionUtil.java:68)
at
org.apache.phoenix.mapreduce.PhoenixRecordWriter.<init>(PhoenixRecordWriter.java:49)
at
org.apache.phoenix.mapreduce.PhoenixOutputFormat.getRecordWriter(PhoenixOutputFormat.java:55)
... 8 more Driver stacktrace: at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1273)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1264)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1263)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1263)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730)
at scala.Option.foreach(Option.scala:236) at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:730)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1457)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1418)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
