I'm trying to write two rows to a cassandra table via pyspark. I use datastax cassandra connector by launching the pyspark 2 shell with the following command:
pyspark2 --num-executors 1 --executor-cores 1 --packages datastax:spark-cassandra-connector:2.0.1-s_2.10 --conf spark.cassandra.connection.host=192.168.0.1
I create a dataframe with the following code:
rdd = sc.parallelize([('Peter',1), ('Sam',2)])
df = sqlContext.createDataFrame(rdd, ["user", "year"])
df.write.format("org.apache.spark.sql.cassandra").mode('append').options(table="users", keyspace="excelsior").save()
The table users is already created in the keyspace excelsior via cassandra shell.
I get the following exception:
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/opt/cloudera/parcels/SPARK2-2.0.0.cloudera2-1.cdh5.7.0.p0.118100/lib/spark2/python/pyspark/sql/readwriter.py", line 545, in save
self._jwrite.save()
File "/opt/cloudera/parcels/SPARK2-2.0.0.cloudera2-1.cdh5.7.0.p0.118100/lib/spark2/python/lib/py4j-0.10.3-src.zip/py4j/java_gateway.py", line 1133, in __call__
File "/opt/cloudera/parcels/SPARK2-2.0.0.cloudera2-1.cdh5.7.0.p0.118100/lib/spark2/python/pyspark/sql/utils.py", line 63, in deco
return f(*a, **kw)
File "/opt/cloudera/parcels/SPARK2-2.0.0.cloudera2-1.cdh5.7.0.p0.118100/lib/spark2/python/lib/py4j-0.10.3-src.zip/py4j/protocol.py", line 319, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o449.save.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 13.0 failed 4 times, most recent failure: Lost task 0.3 in stage 13.0 (TID 56, node6.agatha-cluster, executor 8): java.io.IOException: Failed to write statements to excelsior.users.
at com.datastax.spark.connector.writer.TableWriter$$anonfun$writeInternal$1.apply(TableWriter.scala:207)
at com.datastax.spark.connector.writer.TableWriter$$anonfun$writeInternal$1.apply(TableWriter.scala:175)
at com.datastax.spark.connector.cql.CassandraConnector$$anonfun$withSessionDo$1.apply(CassandraConnector.scala:112)
at com.datastax.spark.connector.cql.CassandraConnector$$anonfun$withSessionDo$1.apply(CassandraConnector.scala:111)
at com.datastax.spark.connector.cql.CassandraConnector.closeResourceAfterUse(CassandraConnector.scala:145)
at com.datastax.spark.connector.cql.CassandraConnector.withSessionDo(CassandraConnector.scala:111)
at com.datastax.spark.connector.writer.TableWriter.writeInternal(TableWriter.scala:175)
at com.datastax.spark.connector.writer.TableWriter.insert(TableWriter.scala:162)
at com.datastax.spark.connector.writer.TableWriter.write(TableWriter.scala:149)
at com.datastax.spark.connector.RDDFunctions$$anonfun$saveToCassandra$1.apply(RDDFunctions.scala:36)
at com.datastax.spark.connector.RDDFunctions$$anonfun$saveToCassandra$1.apply(RDDFunctions.scala:36)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
at org.apache.spark.scheduler.Task.run(Task.scala:86)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
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$$failJobAndIndependentStages(DAGScheduler.scala:1454)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1442)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1441)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1441)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:811)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1669)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1624)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1613)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:632)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1893)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1906)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1926)
at com.datastax.spark.connector.RDDFunctions.saveToCassandra(RDDFunctions.scala:36)
at org.apache.spark.sql.cassandra.CassandraSourceRelation.insert(CassandraSourceRelation.scala:65)
at org.apache.spark.sql.cassandra.DefaultSource.createRelation(DefaultSource.scala:86)
at org.apache.spark.sql.execution.datasources.DataSource.write(DataSource.scala:457)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:211)
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:237)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:214)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException: Failed to write statements to excelsior.users.
at com.datastax.spark.connector.writer.TableWriter$$anonfun$writeInternal$1.apply(TableWriter.scala:207)
at com.datastax.spark.connector.writer.TableWriter$$anonfun$writeInternal$1.apply(TableWriter.scala:175)
at com.datastax.spark.connector.cql.CassandraConnector$$anonfun$withSessionDo$1.apply(CassandraConnector.scala:112)
at com.datastax.spark.connector.cql.CassandraConnector$$anonfun$withSessionDo$1.apply(CassandraConnector.scala:111)
at com.datastax.spark.connector.cql.CassandraConnector.closeResourceAfterUse(CassandraConnector.scala:145)
at com.datastax.spark.connector.cql.CassandraConnector.withSessionDo(CassandraConnector.scala:111)
at com.datastax.spark.connector.writer.TableWriter.writeInternal(TableWriter.scala:175)
at com.datastax.spark.connector.writer.TableWriter.insert(TableWriter.scala:162)
at com.datastax.spark.connector.writer.TableWriter.write(TableWriter.scala:149)
at com.datastax.spark.connector.RDDFunctions$$anonfun$saveToCassandra$1.apply(RDDFunctions.scala:36)
at com.datastax.spark.connector.RDDFunctions$$anonfun$saveToCassandra$1.apply(RDDFunctions.scala:36)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
at org.apache.spark.scheduler.Task.run(Task.scala:86)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
... 1 more
>>> 17/06/07 14:47:10 WARN scheduler.TaskSetManager: Lost task 1.3 in stage 13.0 (TID 57, node6.agatha-cluster, executor 8): org.apache.spark.TaskKilledException
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:264)
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)
Can anyone help me?
Cassandra version is 3.10 and spark version is 2.0.0 from cloudera.
Thank you
