How are you adding com.rr.data.Visit to spark? With --jars? It is
possible we are using the wrong classloader. Could you open a JIRA?
On Thu, Jun 18, 2015 at 2:56 PM, Chad Urso McDaniel <cha...@gmail.com>
wrote:
> We are seeing class exceptions when converting to a DataFrame.
> Anyone out there with some suggestions on what is going on?
>
> Our original intention was to use a HiveContext to write ORC and we say
> the error there and have narrowed it down.
>
> This is an example of our code:
> ---
> def saveVisitsAsOrcFile(sqlContext: SQLContext, rdd: RDD[Visit],
> outputDir: String) {
> // works!: println("rdd count: " + rdd.map(_.clicks.size).sum)
>
> import sqlContext.implicits._
> // scala.ScalaReflectionException: class com.rr.data.Visit
> print("rdd.toDF.count:" + rdd
> .toDF()
> .count())
> ---
> This runs locally, but when using spark-submit with 1.4 we get:
>
>
> Exception in thread "main" scala.ScalaReflectionException: class
> com.rr.data.Visit in JavaMirror with
> sun.misc.Launcher$AppClassLoader@5c647e05 of type class
> sun.misc.Launcher$AppClassLoader with classpath
> [file:/home/candiru/tewfik/,file:/home/candiru/tewfik/spark-1.4.0-bin-tewfik-spark/conf/,file:/home/candiru/tewfik/spark-1.4.0-bin-tewfik-spark/lib/spark-assembly-1.4.0-hadoop2.0.0-mr1-cdh4.2.0.jar,file:/home/candiru/tewfik/spark-1.4.0-bin-tewfik-spark/lib/datanucleus-api-jdo-3.2.6.jar,file:/home/candiru/tewfik/spark-1.4.0-bin-tewfik-spark/lib/datanucleus-core-3.2.10.jar,file:/home/candiru/tewfik/spark-1.4.0-bin-tewfik-spark/lib/datanucleus-rdbms-3.2.9.jar]
> and parent being sun.misc.Launcher$ExtClassLoader@1c79d093 of type class
> sun.misc.Launcher$ExtClassLoader with classpath
> [file:/usr/java/jdk1.8.0_05/jre/lib/ext/cldrdata.jar,file:/usr/java/jdk1.8.0_05/jre/lib/ext/dnsns.jar,file:/usr/java/jdk1.8.0_05/jre/lib/ext/jfxrt.jar,file:/usr/java/jdk1.8.0_05/jre/lib/ext/localedata.jar,file:/usr/java/jdk1.8.0_05/jre/lib/ext/nashorn.jar,file:/usr/java/jdk1.8.0_05/jre/lib/ext/sunec.jar,file:/usr/java/jdk1.8.0_05/jre/lib/ext/sunjce_provider.jar,file:/usr/java/jdk1.8.0_05/jre/lib/ext/sunpkcs11.jar,file:/usr/java/jdk1.8.0_05/jre/lib/ext/zipfs.jar]
> and parent being primordial classloader with boot classpath
> [/usr/java/jdk1.8.0_05/jre/lib/resources.jar:/usr/java/jdk1.8.0_05/jre/lib/rt.jar:/usr/java/jdk1.8.0_05/jre/lib/sunrsasign.jar:/usr/java/jdk1.8.0_05/jre/lib/jsse.jar:/usr/java/jdk1.8.0_05/jre/lib/jce.jar:/usr/java/jdk1.8.0_05/jre/lib/charsets.jar:/usr/java/jdk1.8.0_05/jre/lib/jfr.jar:/usr/java/jdk1.8.0_05/jre/classes]
> not found.
> at
> scala.reflect.internal.Mirrors$RootsBase.staticClass(Mirrors.scala:123)
> at
> scala.reflect.internal.Mirrors$RootsBase.staticClass(Mirrors.scala:22)
> at
> com.rr.data.visits.orc.OrcReadWrite$$typecreator2$1.apply(OrcReadWrite.scala:36)
> at
> scala.reflect.api.TypeTags$WeakTypeTagImpl.tpe$lzycompute(TypeTags.scala:232)
> at
> scala.reflect.api.TypeTags$WeakTypeTagImpl.tpe(TypeTags.scala:232)
> at
> org.apache.spark.sql.catalyst.ScalaReflection$class.localTypeOf(ScalaReflection.scala:71)
> at
> org.apache.spark.sql.catalyst.ScalaReflection$class.schemaFor(ScalaReflection.scala:59)
> at
> org.apache.spark.sql.catalyst.ScalaReflection$.schemaFor(ScalaReflection.scala:28)
> at
> org.apache.spark.sql.SQLContext.createDataFrame(SQLContext.scala:410)
> at
> org.apache.spark.sql.SQLContext$implicits$.rddToDataFrameHolder(SQLContext.scala:335)
> at
> com.rr.data.visits.orc.OrcReadWrite$.saveVisitsAsOrcFile(OrcReadWrite.scala:36)
> at
> com.rr.data.visits.VisitSequencerRunner$.main(VisitSequencerRunner.scala:43)
> at
> com.rr.data.visits.VisitSequencerRunner.main(VisitSequencerRunner.scala)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:483)
> at
> org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:664)
> at
> org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:169)
> at
> org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:192)
> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:111)
> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
>
>
