I'm using GCP and I have one datacenter in "asia-south1" and another one in "us-west1". I have provided a list of IP address of my nodes under spark.cassandra.connection.host as follows;
spark.cassandra.connection.host 100.220.0.100,10.210.0.21,100.140.0.62
When I try to run a Spark job from PySpark Shell, I'm getting the following exception
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/opt/spark/python/pyspark/sql/readwriter.py", line 172, in load
return self._df(self._jreader.load())
File "/opt/spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py", line 1257, in __call__
File "/opt/spark/python/pyspark/sql/utils.py", line 63, in deco
return f(*a, **kw)
File "/opt/spark/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py", line 328, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o44.load.
: java.io.IOException: Failed to open native connection to Cassandra at {100.220.0.100,10.210.0.21,100.140.0.62}:9042
at com.datastax.spark.connector.cql.CassandraConnector$.com$datastax$spark$connector$cql$CassandraConnector$$createSession(CassandraConnector.scala:168)
at com.datastax.spark.connector.cql.CassandraConnector$$anonfun$8.apply(CassandraConnector.scala:154)
at com.datastax.spark.connector.cql.CassandraConnector$$anonfun$8.apply(CassandraConnector.scala:154)
at com.datastax.spark.connector.cql.RefCountedCache.createNewValueAndKeys(RefCountedCache.scala:32)
at com.datastax.spark.connector.cql.RefCountedCache.syncAcquire(RefCountedCache.scala:69)
at com.datastax.spark.connector.cql.RefCountedCache.acquire(RefCountedCache.scala:57)
at com.datastax.spark.connector.cql.CassandraConnector.openSession(CassandraConnector.scala:79)
at com.datastax.spark.connector.cql.CassandraConnector.withSessionDo(CassandraConnector.scala:111)
at com.datastax.spark.connector.rdd.partitioner.dht.TokenFactory$.forSystemLocalPartitioner(TokenFactory.scala:98)
at org.apache.spark.sql.cassandra.CassandraSourceRelation$.apply(CassandraSourceRelation.scala:272)
at org.apache.spark.sql.cassandra.DefaultSource.createRelation(DefaultSource.scala:56)
at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:318)
at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:223)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:211)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:167)
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:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.lang.IllegalArgumentException: requirement failed: Contact points contain multiple data centers: us-west1, asia-south1
at scala.Predef$.require(Predef.scala:224)
at com.datastax.spark.connector.cql.LocalNodeFirstLoadBalancingPolicy$.determineDataCenter(LocalNodeFirstLoadBalancingPolicy.scala:145)
at com.datastax.spark.connector.cql.LocalNodeFirstLoadBalancingPolicy$$anonfun$init$1.apply(LocalNodeFirstLoadBalancingPolicy.scala:39)
at com.datastax.spark.connector.cql.LocalNodeFirstLoadBalancingPolicy$$anonfun$init$1.apply(LocalNodeFirstLoadBalancingPolicy.scala:39)
at scala.Option.getOrElse(Option.scala:121)
at com.datastax.spark.connector.cql.LocalNodeFirstLoadBalancingPolicy.init(LocalNodeFirstLoadBalancingPolicy.scala:39)
at com.datastax.driver.core.Cluster$Manager.init(Cluster.java:1510)
at com.datastax.driver.core.Cluster.getMetadata(Cluster.java:399)
at com.datastax.spark.connector.cql.CassandraConnector$.com$datastax$spark$connector$cql$CassandraConnector$$createSession(CassandraConnector.scala:161)
... 25 more
As a workaround, I removed the node in "asia-south1" from the `spark.cassandra.connection.host` list and then it works without no issue. I'm just wondering how to handle this issue.
