Intermittent Failures of joinWithCassandraTable / RepartitionByCassandraReplica Tests
Description
19:30:49 com.datastax.driver.core.exceptions.InvalidQueryException: Invalid null value for partition key part key
19:30:49 at com.datastax.driver.core.exceptions.InvalidQueryException.copy(InvalidQueryException.java:35)
19:30:49 at com.datastax.driver.core.DefaultResultSetFuture.extractCauseFromExecutionException(DefaultResultSetFuture.java:289)
19:30:49 at com.datastax.driver.core.DefaultResultSetFuture.getUninterruptibly(DefaultResultSetFuture.java:205)
19:30:49 at com.datastax.driver.core.AbstractSession.execute(AbstractSession.java:52)
19:30:49 at sun.reflect.GeneratedMethodAccessor2.invoke(Unknown Source)
19:30:49 at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
19:30:49 at java.lang.reflect.Method.invoke(Method.java:606)
19:30:49 at com.datastax.spark.connector.cql.SessionProxy.invoke(SessionProxy.scala:33)
19:30:49 at com.sun.proxy.$Proxy12.execute(Unknown Source)
19:30:49 at com.datastax.spark.connector.rdd.CassandraJoinRDD$$anonfun$fetchIterator$1.apply(CassandraJoinRDD.scala:233)
19:30:49 at com.datastax.spark.connector.rdd.CassandraJoinRDD$$anonfun$fetchIterator$1.apply(CassandraJoinRDD.scala:231)
19:30:49 at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:396)
19:30:49 at com.datastax.spark.connector.util.CountingIterator.hasNext(CountingIterator.scala:12)
19:30:49 at scala.collection.Iterator$class.foreach(Iterator.scala:750)
19:30:49 at com.datastax.spark.connector.util.CountingIterator.foreach(CountingIterator.scala:4)
19:30:49 at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:59)
19:30:49 at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:104)
19:30:49 at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:48)
19:30:49 at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:295)
19:30:49 at com.datastax.spark.connector.util.CountingIterator.to(CountingIterator.scala:4)
19:30:49 at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:287)
19:30:49 at com.datastax.spark.connector.util.CountingIterator.toBuffer(CountingIterator.scala:4)
19:30:49 at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:274)
19:30:49 at com.datastax.spark.connector.util.CountingIterator.toArray(CountingIterator.scala:4)
19:30:49 at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885)
19:30:49 at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885)
19:30:49 at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765)
19:30:49 at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765)
19:30:49 at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63)
19:30:49 at org.apache.spark.scheduler.Task.run(Task.scala:70)
19:30:49 at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
19:30:49 at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
19:30:49 at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
19:30:49 at java.lang.Thread.run(Thread.java:744)
This came up on jenkins for a doc only change PR. We've also seen jenkins intermittently fail the actor streaming job which uses the same api.
19:30:49 com.datastax.driver.core.exceptions.InvalidQueryException: Invalid null value for partition key part key 19:30:49 at com.datastax.driver.core.exceptions.InvalidQueryException.copy(InvalidQueryException.java:35) 19:30:49 at com.datastax.driver.core.DefaultResultSetFuture.extractCauseFromExecutionException(DefaultResultSetFuture.java:289) 19:30:49 at com.datastax.driver.core.DefaultResultSetFuture.getUninterruptibly(DefaultResultSetFuture.java:205) 19:30:49 at com.datastax.driver.core.AbstractSession.execute(AbstractSession.java:52) 19:30:49 at sun.reflect.GeneratedMethodAccessor2.invoke(Unknown Source) 19:30:49 at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) 19:30:49 at java.lang.reflect.Method.invoke(Method.java:606) 19:30:49 at com.datastax.spark.connector.cql.SessionProxy.invoke(SessionProxy.scala:33) 19:30:49 at com.sun.proxy.$Proxy12.execute(Unknown Source) 19:30:49 at com.datastax.spark.connector.rdd.CassandraJoinRDD$$anonfun$fetchIterator$1.apply(CassandraJoinRDD.scala:233) 19:30:49 at com.datastax.spark.connector.rdd.CassandraJoinRDD$$anonfun$fetchIterator$1.apply(CassandraJoinRDD.scala:231) 19:30:49 at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:396) 19:30:49 at com.datastax.spark.connector.util.CountingIterator.hasNext(CountingIterator.scala:12) 19:30:49 at scala.collection.Iterator$class.foreach(Iterator.scala:750) 19:30:49 at com.datastax.spark.connector.util.CountingIterator.foreach(CountingIterator.scala:4) 19:30:49 at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:59) 19:30:49 at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:104) 19:30:49 at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:48) 19:30:49 at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:295) 19:30:49 at com.datastax.spark.connector.util.CountingIterator.to(CountingIterator.scala:4) 19:30:49 at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:287) 19:30:49 at com.datastax.spark.connector.util.CountingIterator.toBuffer(CountingIterator.scala:4) 19:30:49 at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:274) 19:30:49 at com.datastax.spark.connector.util.CountingIterator.toArray(CountingIterator.scala:4) 19:30:49 at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885) 19:30:49 at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885) 19:30:49 at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765) 19:30:49 at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765) 19:30:49 at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63) 19:30:49 at org.apache.spark.scheduler.Task.run(Task.scala:70) 19:30:49 at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213) 19:30:49 at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) 19:30:49 at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) 19:30:49 at java.lang.Thread.run(Thread.java:744)
This came up on jenkins for a doc only change PR. We've also seen jenkins intermittently fail the actor streaming job which uses the same api.