<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>question Spark-submit not working on cloudera yarn in Archives of Support Questions (Read Only)</title>
    <link>https://community.cloudera.com/t5/Archives-of-Support-Questions/Spark-submit-not-working-on-cloudera-yarn/m-p/23900#M4686</link>
    <description>&lt;P&gt;Hi ,&lt;BR /&gt;I am running my spark program on yarn. but i am getting below endless message on console.&lt;/P&gt;&lt;P&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp;15/01/22 01:12:13 INFO cluster.YarnClientSchedulerBackend: Application report from ASM:&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp;appMasterRpcPort: -1&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp;appStartTime: 1421868378949&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp;yarnAppState: ACCEPTED&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;I am using&amp;nbsp;Cloudera 5.2 &amp;nbsp;and setting&amp;nbsp;&lt;SPAN&gt;HADOOP_CONF_DIR&amp;nbsp;&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;export HADOOP_CONF_DIR="/etc/hadoop/conf"&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Running using below command. Please suggest me if I am missing any configuration&lt;/P&gt;&lt;P&gt;spark-submit --master yarn --class alu.ausdc.analitics.sparkEx.ParallelizeEx sparkanalitics-1.jar&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;ParallelizeEx.java:&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;package alu.ausdc.analitics.sparkEx;&lt;/P&gt;&lt;P&gt;import java.util.Arrays;&lt;/P&gt;&lt;P&gt;import org.apache.spark.Accumulator;&lt;BR /&gt;import org.apache.spark.SparkConf;&lt;BR /&gt;import org.apache.spark.api.java.JavaRDD;&lt;BR /&gt;import org.apache.spark.api.java.JavaSparkContext;&lt;BR /&gt;import org.apache.spark.api.java.function.Function;&lt;BR /&gt;import org.apache.spark.api.java.function.Function2;&lt;/P&gt;&lt;P&gt;/**&lt;BR /&gt;* @author sangalar&lt;BR /&gt;*&lt;BR /&gt;*/&lt;BR /&gt;public class ParallelizeEx {&lt;/P&gt;&lt;P&gt;public static void main(String[] args) {&lt;BR /&gt;SparkConf conf = new SparkConf().setAppName("ParallelizeEx")/*.setMaster("local")*/;&lt;BR /&gt;JavaSparkContext sc = new JavaSparkContext(conf);&lt;BR /&gt;JavaRDD&amp;lt;String&amp;gt; lines = sc.parallelize(Arrays.asList("pandas", "i like pandas"));&lt;BR /&gt;&lt;BR /&gt;System.out.println("No. lines: "+lines.count());//2&lt;BR /&gt;&lt;BR /&gt;final Accumulator&amp;lt;Integer&amp;gt; i=sc.accumulator(0);&lt;BR /&gt;&lt;BR /&gt;JavaRDD&amp;lt;Integer&amp;gt; line = lines&lt;BR /&gt;.map(new Function&amp;lt;String, Integer&amp;gt;() {&lt;BR /&gt;public Integer call(String s) {&lt;BR /&gt;i.add(1);&lt;BR /&gt;return s.split(" ").length;&lt;BR /&gt;&lt;BR /&gt;}&lt;BR /&gt;});&lt;BR /&gt;&lt;BR /&gt;int totalWords=line.reduce(new Function2&amp;lt;Integer, Integer, Integer&amp;gt;() {&lt;BR /&gt;&lt;BR /&gt;public Integer call(Integer arg0, Integer arg1) throws Exception {&lt;BR /&gt;// TODO Auto-generated method stub&lt;BR /&gt;return arg0+arg1;&lt;BR /&gt;}&lt;BR /&gt;});&lt;BR /&gt;&lt;BR /&gt;System.out.println("totalWords: "+ totalWords);&lt;BR /&gt;&lt;BR /&gt;}&lt;BR /&gt;}&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;thanks,&lt;/P&gt;&lt;P&gt;Shekhar Reddy.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Fri, 16 Sep 2022 09:19:55 GMT</pubDate>
    <dc:creator>shekharreddy</dc:creator>
    <dc:date>2022-09-16T09:19:55Z</dc:date>
    <item>
      <title>Spark-submit not working on cloudera yarn</title>
      <link>https://community.cloudera.com/t5/Archives-of-Support-Questions/Spark-submit-not-working-on-cloudera-yarn/m-p/23900#M4686</link>
      <description>&lt;P&gt;Hi ,&lt;BR /&gt;I am running my spark program on yarn. but i am getting below endless message on console.&lt;/P&gt;&lt;P&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp;15/01/22 01:12:13 INFO cluster.YarnClientSchedulerBackend: Application report from ASM:&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp;appMasterRpcPort: -1&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp;appStartTime: 1421868378949&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp;yarnAppState: ACCEPTED&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;I am using&amp;nbsp;Cloudera 5.2 &amp;nbsp;and setting&amp;nbsp;&lt;SPAN&gt;HADOOP_CONF_DIR&amp;nbsp;&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;export HADOOP_CONF_DIR="/etc/hadoop/conf"&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Running using below command. Please suggest me if I am missing any configuration&lt;/P&gt;&lt;P&gt;spark-submit --master yarn --class alu.ausdc.analitics.sparkEx.ParallelizeEx sparkanalitics-1.jar&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;ParallelizeEx.java:&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;package alu.ausdc.analitics.sparkEx;&lt;/P&gt;&lt;P&gt;import java.util.Arrays;&lt;/P&gt;&lt;P&gt;import org.apache.spark.Accumulator;&lt;BR /&gt;import org.apache.spark.SparkConf;&lt;BR /&gt;import org.apache.spark.api.java.JavaRDD;&lt;BR /&gt;import org.apache.spark.api.java.JavaSparkContext;&lt;BR /&gt;import org.apache.spark.api.java.function.Function;&lt;BR /&gt;import org.apache.spark.api.java.function.Function2;&lt;/P&gt;&lt;P&gt;/**&lt;BR /&gt;* @author sangalar&lt;BR /&gt;*&lt;BR /&gt;*/&lt;BR /&gt;public class ParallelizeEx {&lt;/P&gt;&lt;P&gt;public static void main(String[] args) {&lt;BR /&gt;SparkConf conf = new SparkConf().setAppName("ParallelizeEx")/*.setMaster("local")*/;&lt;BR /&gt;JavaSparkContext sc = new JavaSparkContext(conf);&lt;BR /&gt;JavaRDD&amp;lt;String&amp;gt; lines = sc.parallelize(Arrays.asList("pandas", "i like pandas"));&lt;BR /&gt;&lt;BR /&gt;System.out.println("No. lines: "+lines.count());//2&lt;BR /&gt;&lt;BR /&gt;final Accumulator&amp;lt;Integer&amp;gt; i=sc.accumulator(0);&lt;BR /&gt;&lt;BR /&gt;JavaRDD&amp;lt;Integer&amp;gt; line = lines&lt;BR /&gt;.map(new Function&amp;lt;String, Integer&amp;gt;() {&lt;BR /&gt;public Integer call(String s) {&lt;BR /&gt;i.add(1);&lt;BR /&gt;return s.split(" ").length;&lt;BR /&gt;&lt;BR /&gt;}&lt;BR /&gt;});&lt;BR /&gt;&lt;BR /&gt;int totalWords=line.reduce(new Function2&amp;lt;Integer, Integer, Integer&amp;gt;() {&lt;BR /&gt;&lt;BR /&gt;public Integer call(Integer arg0, Integer arg1) throws Exception {&lt;BR /&gt;// TODO Auto-generated method stub&lt;BR /&gt;return arg0+arg1;&lt;BR /&gt;}&lt;BR /&gt;});&lt;BR /&gt;&lt;BR /&gt;System.out.println("totalWords: "+ totalWords);&lt;BR /&gt;&lt;BR /&gt;}&lt;BR /&gt;}&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;thanks,&lt;/P&gt;&lt;P&gt;Shekhar Reddy.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Fri, 16 Sep 2022 09:19:55 GMT</pubDate>
      <guid>https://community.cloudera.com/t5/Archives-of-Support-Questions/Spark-submit-not-working-on-cloudera-yarn/m-p/23900#M4686</guid>
      <dc:creator>shekharreddy</dc:creator>
      <dc:date>2022-09-16T09:19:55Z</dc:date>
    </item>
    <item>
      <title>Re: Spark-submit not working on cloudera yarn</title>
      <link>https://community.cloudera.com/t5/Archives-of-Support-Questions/Spark-submit-not-working-on-cloudera-yarn/m-p/23943#M4687</link>
      <description>&lt;P&gt;I fixed this issue by setting yarn.nodemanager.resource.memory-mb &amp;nbsp;to 8 GB&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;-Shekhar Reddy&lt;/P&gt;</description>
      <pubDate>Thu, 22 Jan 2015 10:44:38 GMT</pubDate>
      <guid>https://community.cloudera.com/t5/Archives-of-Support-Questions/Spark-submit-not-working-on-cloudera-yarn/m-p/23943#M4687</guid>
      <dc:creator>shekharreddy</dc:creator>
      <dc:date>2015-01-22T10:44:38Z</dc:date>
    </item>
  </channel>
</rss>

