Hi all,
I wrote below spark code to extract data from SQL server using spark
SQLContext.read.format with several different options , question does by
default sqlContext.read load function run in parallel does it use all the
available cores available ? when I am saving the output to a file it is
getting saved as one file does it mean the code used single core in my
machine ?
My Code:-
package com.kali.db
/**
* Created by kalit_000 on 06/12/2015.
*/
import org.apache.spark.SparkConf
import org.apache.log4j.Logger
import org.apache.log4j.Level
import org.apache.spark._
import org.apache.spark.rdd.{JdbcRDD, RDD}
import org.apache.spark.sql.DataFrame
import org.springframework.context.support.ClassPathXmlApplicationContext
case class
SparkSqlValueClass(driver:String,url:String,username:String,password:String,sql:String,table:String,opdelimeter:String)
object SparkSqlSelectSpring {
def main (args: Array[String]) {
Logger.getLogger("org").setLevel(Level.WARN)
Logger.getLogger("akka").setLevel(Level.WARN)
val conf = new
SparkConf().setMaster("local[*]").setAppName("SparkSqlConfigurable").set("spark.hadoop.validateOutputSpecs",
"false")
val sc = new SparkContext(conf)
def opfile(value:DataFrame,delimeter:String):RDD[String]=
{
value.map(x =>
x.toString.replace("[","").replace("]","").replace(",",delimeter))
}
//read the application context file
val ctx = new ClassPathXmlApplicationContext("sparksql.xml")
val DBinfo =
ctx.getBean("SparkSQLInst").asInstanceOf[SparkSqlValueClass]
val driver = DBinfo.driver
val url = DBinfo.url
val username = DBinfo.username
val password = DBinfo.password
val query = DBinfo.sql
val sqlquery = DBinfo.sql
val table = DBinfo.table
val opdelimeter=DBinfo.opdelimeter
println("DB Driver:-%s".format(driver))
println("DB Url:-%s".format(url))
println("Username:-%s".format(username))
println("Password:-%s".format(password))
println("Query:-%s".format(query))
println("Table:-%s".format(table))
println("Opdelimeter:-%s".format(opdelimeter))
try {
val sqlContext = new org.apache.spark.sql.SQLContext(sc)
val df = sqlContext.read.format("jdbc").options(Map("url" ->
url,"dbtable" -> table,"driver" -> driver)).load()
df.registerTempTable(table)
val OP=sqlContext.sql(query)
opfile(OP,opdelimeter).saveAsTextFile("C:\\Users\\kalit_000\\Desktop\\typesafe\\scaladbop\\op.txt")
} catch {
case e: Exception => e.printStackTrace
}
sc.stop()
}
}
Spring Bean:-
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE beans PUBLIC "-//SPRING//DTD BEAN//EN"
"http://www.springframework.org/dtd/spring-beans.dtd">
<beans>
<bean id="queryProps"
class="org.springframework.beans.factory.config.PropertiesFactoryBean">
</bean>
<bean id="SparkSQLInst" class="com.kali.db.SparkSqlValueClass">
<constructor-arg value="com.microsoft.sqlserver.jdbc.SQLServerDriver" />
<constructor-arg
value="jdbc:sqlserver://localhost;user=admin;password=oracle;database=AdventureWorks2014"
/>
<constructor-arg value="admin" />
<constructor-arg value="oracle" />
<constructor-arg value="select
CustomerID,StoreID,TerritoryID,AccountNumber,ModifiedDate from customer
limit 10" />
<constructor-arg value="customer" />
<constructor-arg value="~" />
</bean>
</beans>
Thanks
Sri
--
View this message in context:
http://apache-spark-user-list.1001560.n3.nabble.com/Spark-sql-data-frames-do-they-run-in-parallel-by-default-tp25604.html
Sent from the Apache Spark User List mailing list archive at Nabble.com.
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
