Have you contacted spark-cassandra-connector related mailing list ?
I wonder where the port 9042 came from.
Cheers
On Tue, Mar 8, 2016 at 6:02 PM, Andy Davidson <a...@santacruzintegration.com
> wrote:
>
> I am using spark-1.6.0-bin-hadoop2.6. I am trying to write a python
> notebook that reads a data frame from Cassandra.
>
> *I connect to cassadra using an ssh tunnel running on port 9043.* CQLSH
> works how ever I can not figure out how to configure my notebook. I have
> tried various hacks any idea what I am doing wrong
>
> : java.io.IOException: Failed to open native connection to Cassandra at
> {192.168.1.126}:9042
>
>
>
>
> Thanks in advance
>
> Andy
>
>
>
> $ extraPkgs="--packages com.databricks:spark-csv_2.11:1.3.0 \
> --packages datastax:spark-cassandra-connector:1.6.0-M1-s_2.11"
>
> $ export PYSPARK_PYTHON=python3
> $ export PYSPARK_DRIVER_PYTHON=python3
> $ IPYTHON_OPTS=notebook $SPARK_ROOT/bin/pyspark $extraPkgs $*
>
>
>
> In [15]:
> 1
>
> sqlContext.setConf("spark.cassandra.connection.host”,”127.0.0.1:9043")
>
> 2
>
> df = sqlContext.read\
>
> 3
>
> .format("org.apache.spark.sql.cassandra")\
>
> 4
>
> .options(table=“time_series", keyspace="notification")\
>
> 5
>
> .load()
>
> 6
>
>
>
> 7
>
> df.printSchema()
>
> 8
>
> df.show()
>
> ---------------------------------------------------------------------------Py4JJavaError
> Traceback (most recent call
> last)<ipython-input-15-9d8f6dcf210f> in <module>() 1
> sqlContext.setConf("spark.cassandra.connection.host","localhost:9043")----> 2
> df = sqlContext.read .format("org.apache.spark.sql.cassandra")
> .options(table="kv", keyspace="notification") .load() 3 4
> df.printSchema() 5 df.show()
> /Users/andrewdavidson/workSpace/spark/spark-1.6.0-bin-hadoop2.6/python/pyspark/sql/readwriter.py
> in load(self, path, format, schema, **options) 137 return
> self._df(self._jreader.load(path)) 138 else:--> 139
> return self._df(self._jreader.load()) 140 141 @since(1.4)
> /Users/andrewdavidson/workSpace/spark/spark-1.6.0-bin-hadoop2.6/python/lib/py4j-0.9-src.zip/py4j/java_gateway.py
> in __call__(self, *args) 811 answer =
> self.gateway_client.send_command(command) 812 return_value =
> get_return_value(--> 813 answer, self.gateway_client,
> self.target_id, self.name) 814 815 for temp_arg in temp_args:
> /Users/andrewdavidson/workSpace/spark/spark-1.6.0-bin-hadoop2.6/python/pyspark/sql/utils.py
> in deco(*a, **kw) 43 def deco(*a, **kw): 44 try:---> 45
> return f(*a, **kw) 46 except
> py4j.protocol.Py4JJavaError as e: 47 s =
> e.java_exception.toString()
> /Users/andrewdavidson/workSpace/spark/spark-1.6.0-bin-hadoop2.6/python/lib/py4j-0.9-src.zip/py4j/protocol.py
> in get_return_value(answer, gateway_client, target_id, name) 306
> raise Py4JJavaError( 307 "An error occurred
> while calling {0}{1}{2}.\n".--> 308 format(target_id,
> ".", name), value) 309 else: 310 raise
> Py4JError(
> Py4JJavaError: An error occurred while calling o280.load.
> : java.io.IOException: Failed to open native connection to Cassandra at
> {192.168.1.126}:9042
> at
> com.datastax.spark.connector.cql.CassandraConnector$.com$datastax$spark$connector$cql$CassandraConnector$$createSession(CassandraConnector.scala:162)
> at
> com.datastax.spark.connector.cql.CassandraConnector$$anonfun$2.apply(CassandraConnector.scala:148)
> at
> com.datastax.spark.connector.cql.CassandraConnector$$anonfun$2.apply(CassandraConnector.scala:148)
> at
> com.datastax.spark.connector.cql.RefCountedCache.createNewValueAndKeys(RefCountedCache.scala:31)
> at
> com.datastax.spark.connector.cql.RefCountedCache.acquire(RefCountedCache.scala:56)
> at
> com.datastax.spark.connector.cql.CassandraConnector.openSession(CassandraConnector.scala:81)
> at
> com.datastax.spark.connector.cql.CassandraConnector.withSessionDo(CassandraConnector.scala:109)
> at
> com.datastax.spark.connector.rdd.partitioner.CassandraRDDPartitioner$.getTokenFactory(CassandraRDDPartitioner.scala:184)
> at
> org.apache.spark.sql.cassandra.CassandraSourceRelation$.apply(CassandraSourceRelation.scala:267)
> at
> org.apache.spark.sql.cassandra.DefaultSource.createRelation(DefaultSource.scala:57)
> at
> org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:158)
> at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:119)
> 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:497)
> 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: com.datastax.driver.core.exceptions.NoHostAvailableException: All
> host(s) tried for query failed (tried: /192.168.1.126:9042
> (com.datastax.driver.core.exceptions.TransportException: [/192.168.1.126]
> Cannot connect))
> at
> com.datastax.driver.core.ControlConnection.reconnectInternal(ControlConnection.java:231)
> at
> com.datastax.driver.core.ControlConnection.connect(ControlConnection.java:77)
> at com.datastax.driver.core.Cluster$Manager.init(Cluster.java:1414)
> at com.datastax.driver.core.Cluster.getMetadata(Cluster.java:393)
> at
> com.datastax.spark.connector.cql.CassandraConnector$.com$datastax$spark$connector$cql$CassandraConnector$$createSession(CassandraConnector.scala:155)
> ... 22 more
>
>
>
