You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "lostinoverflow (JIRA)" <ji...@apache.org> on 2016/11/01 22:33:58 UTC
[jira] [Updated] (SPARK-18211) Spark SQL ignores split.size

     [ https://issues.apache.org/jira/browse/SPARK-18211?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

lostinoverflow updated SPARK-18211:
-----------------------------------
    Description: 
I expect that RDD and DataFrame will have the same number of partitions (worked in 1.6) but it looks like Spark SQL ignores Hadoop configuration.

{code}

import org.apache.spark.sql.SparkSession

object App {
  def main(args: Array[String]) {
    val spark = SparkSession
      .builder()
      .master("local[*]")
      .appName("split size")
      .getOrCreate()
    spark.sparkContext.hadoopConfiguration.setInt("mapred.min.split.size", args(0).toInt)
    spark.sparkContext.hadoopConfiguration.setInt("mapred.max.split.size", args(0).toInt)
    println(spark.sparkContext.textFile(args(1)).partitions.size)
    println(spark.read.textFile(args(1)).rdd.partitions.size)
    spark.stop()
  }
}

{code}

  was:
I expect that RDD and DataFrame will have the same number of partitions (worked in 1.6) but it looks like Spark SQL ignores Hadoop configuration.

import org.apache.spark.sql.SparkSession

object App {
  def main(args: Array[String]) {
    val spark = SparkSession
      .builder()
      .master("local[*]")
      .appName("split size")
      .getOrCreate()
    spark.sparkContext.hadoopConfiguration.setInt("mapred.min.split.size", args(0).toInt)
    spark.sparkContext.hadoopConfiguration.setInt("mapred.max.split.size", args(0).toInt)
    println(spark.sparkContext.textFile(args(1)).partitions.size)
    println(spark.read.textFile(args(1)).rdd.partitions.size)
    spark.stop()
  }
}


> Spark SQL ignores split.size
> ----------------------------
>
>                 Key: SPARK-18211
>                 URL: https://issues.apache.org/jira/browse/SPARK-18211
>             Project: Spark
>          Issue Type: Bug
>          Components: SQL
>    Affects Versions: 2.0.0
>            Reporter: lostinoverflow
>
> I expect that RDD and DataFrame will have the same number of partitions (worked in 1.6) but it looks like Spark SQL ignores Hadoop configuration.
> {code}
> import org.apache.spark.sql.SparkSession
> object App {
>   def main(args: Array[String]) {
>     val spark = SparkSession
>       .builder()
>       .master("local[*]")
>       .appName("split size")
>       .getOrCreate()
>     spark.sparkContext.hadoopConfiguration.setInt("mapred.min.split.size", args(0).toInt)
>     spark.sparkContext.hadoopConfiguration.setInt("mapred.max.split.size", args(0).toInt)
>     println(spark.sparkContext.textFile(args(1)).partitions.size)
>     println(spark.read.textFile(args(1)).rdd.partitions.size)
>     spark.stop()
>   }
> }
> {code}



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

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