Jork Zijlstra created SPARK-19628:
-------------------------------------

             Summary: Duplicate Spark jobs in 2.1.0
                 Key: SPARK-19628
                 URL: https://issues.apache.org/jira/browse/SPARK-19628
             Project: Spark
          Issue Type: Bug
          Components: Spark Core
    Affects Versions: 2.1.0
            Reporter: Jork Zijlstra
             Fix For: 2.0.1
         Attachments: spark2.0.1.png, spark2.1.0.png

After upgrading to Spark 2.1.0 we noticed that they are duplicate jobs 
executed. Going back to Spark 2.0.1 they are gone again

{code}
import org.apache.spark.sql._

object DoubleJobs {
  def main(args: Array[String]) {

    System.setProperty("hadoop.home.dir", "/tmp");

    val sparkSession: SparkSession = SparkSession.builder
      .master("local[4]")
      .appName("spark session example")
      .config("spark.driver.maxResultSize", "6G")
      .config("spark.sql.orc.filterPushdown", true)
      .config("spark.sql.hive.metastorePartitionPruning", true)
      .getOrCreate()

    sparkSession.sqlContext.setConf("spark.sql.orc.filterPushdown", "true")

    val paths = Seq(
      ""//some orc source
    )

    def dataFrame(path: String): DataFrame = {
      sparkSession.read.orc(path)
    }

    paths.foreach(path => {
      dataFrame(path).show(20)
    })
  }
}
{code}



--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org

Reply via email to