I've got a Cassandra 2.1.1 + Spark 1.1.0 cluster running. I'm using
sbt-assembly to create a uber jar to submit to the stand alone master. I'm
using the hadoop 1 prebuilt binaries for Spark. As soon as I try to do
sc.CassandraTable(...) I get an error that's likely to be a Guava versioning
issue. I'm using the Spark Cassandra connector v 1.1.0-rc2 which just came out,
though the issue was in rc1 as well. I can't see the cassandra connector using
Guava directly, so I guess it's a dependency for some other thing that the
cassandra spark connector is using. Does anybody have a workaround for this?
The sbt file and the exception are given below.
Regards,
Ashic.
sbt file:
import sbt._
import Keys._
import sbtassembly.Plugin._
import AssemblyKeys._
assemblySettings
name := "foo"
version := "0.1.0"
scalaVersion := "2.10.4"
libraryDependencies ++= Seq (
"org.apache.spark" %% "spark-core" % "1.1.0" % "provided",
"org.apache.spark" %% "spark-sql" % "1.1.0" % "provided",
"com.datastax.spark" %% "spark-cassandra-connector" % "1.1.0-rc2"
withSources() withJavadoc(),
"org.specs2" %% "specs2" % "2.4" % "test" withSources()
)
//allow provided for run
run in Compile <<= Defaults.runTask(fullClasspath in Compile, mainClass in
(Compile, run), runner in (Compile, run))
mergeStrategy in assembly := {
case PathList("META-INF", xs @ _*) =>
(xs map {_.toLowerCase}) match {
case ("manifest.mf" :: Nil) | ("index.list" :: Nil) | ("dependencies" ::
Nil) => MergeStrategy.discard
case _ => MergeStrategy.discard
}
case _ => MergeStrategy.first
}
resolvers += "Akka Repository" at "http://repo.akka.io/releases/";
test in assembly := {}
Exception:
14/11/24 14:20:11 INFO client.AppClient$ClientActor: Executor updated:
app-20141124142008-0001/0 is now RUNNING
Exception in thread "main" java.lang.NoSuchMethodError:
com.google.common.collect.Sets.newConcurrentHashSet()Ljava/util/Set;
at
com.datastax.driver.core.Cluster$ConnectionReaper.<init>(Cluster.java:2065)
at com.datastax.driver.core.Cluster$Manager.<init>(Cluster.java:1163)
at com.datastax.driver.core.Cluster$Manager.<init>(Cluster.java:1110)
at com.datastax.driver.core.Cluster.<init>(Cluster.java:118)
at com.datastax.driver.core.Cluster.<init>(Cluster.java:105)
at com.datastax.driver.core.Cluster.buildFrom(Cluster.java:174)
at com.datastax.driver.core.Cluster$Builder.build(Cluster.java:1075)
at
com.datastax.spark.connector.cql.DefaultConnectionFactory$.createCluster(CassandraConnectionFactory.scala:81)
at
com.datastax.spark.connector.cql.CassandraConnector$.com$datastax$spark$connector$cql$CassandraConnector$$createSession(CassandraConnector.scala:165)
at
com.datastax.spark.connector.cql.CassandraConnector$$anonfun$2.apply(CassandraConnector.scala:160)
at
com.datastax.spark.connector.cql.CassandraConnector$$anonfun$2.apply(CassandraConnector.scala:160)
at
com.datastax.spark.connector.cql.RefCountedCache.createNewValueAndKeys(RefCountedCache.scala:36)
at
com.datastax.spark.connector.cql.RefCountedCache.acquire(RefCountedCache.scala:61)
at
com.datastax.spark.connector.cql.CassandraConnector.openSession(CassandraConnector.scala:71)
at
com.datastax.spark.connector.cql.CassandraConnector.withSessionDo(CassandraConnector.scala:97)
at
com.datastax.spark.connector.cql.CassandraConnector.withClusterDo(CassandraConnector.scala:108)
at
com.datastax.spark.connector.cql.Schema$.fromCassandra(Schema.scala:134)
at
com.datastax.spark.connector.rdd.CassandraRDD.tableDef$lzycompute(CassandraRDD.scala:227)
at
com.datastax.spark.connector.rdd.CassandraRDD.tableDef(CassandraRDD.scala:226)
at
com.datastax.spark.connector.rdd.CassandraRDD.verify$lzycompute(CassandraRDD.scala:266)
at
com.datastax.spark.connector.rdd.CassandraRDD.verify(CassandraRDD.scala:263)
at
com.datastax.spark.connector.rdd.CassandraRDD.getPartitions(CassandraRDD.scala:292)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:202)
at org.apache.spark.rdd.MappedRDD.getPartitions(MappedRDD.scala:28)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:202)
at org.apache.spark.rdd.MappedRDD.getPartitions(MappedRDD.scala:28)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:202)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1135)
at org.apache.spark.rdd.RDD.foreachPartition(RDD.scala:767)
at Main$.main(Main.scala:33)
at Main.main(Main.scala)
