gbraccialli

hadoop jar /usr/hdp/current/hadoop-mapreduce-client/hadoop-mapreduce-examples.jar teragen 10000000000 /tmp/teragenout
hadoop jar /usr/hdp/current/hadoop-mapreduce-client/hadoop-mapreduce-examples.jar terasort -D mapred.reduce.tasks=170 -D mapred.job.queue.name=ds /tmp/teragenout /tmp/terasortout

hadoop jar /usr/hdp/current/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient.jar TestDFSIO -D dfs.replication=1 -D -write -nrFiles 100 -fileSize 5000
hadoop jar /usr/hdp/current/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient.jar TestDFSIO -D dfs.replication=3 -D -write -nrFiles 100 -fileSize 5000
hadoop jar /usr/hdp/current/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient.jar TestDFSIO -D dfs.replication=1 -D -write -nrFiles 200 -fileSize 5000
hadoop jar /usr/hdp/current/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient.jar TestDFSIO -D dfs.replication=1 -D -write -nrFiles 600 -fileSize 2000
hadoop jar /usr/hdp/current/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient.jar 

gbraccialli

case class Test (typet: String, value: Int)
val test = List(Test("B", 99), Test("B", 2), Test("B", 35), Test("A", 6), Test("A", 3))
val rdd = sc.parallelize(test)
val df = rdd.toDF

var i = 0
var previous = ""
def udf_buffer(in: String): Option[Int] = 
{
  if (in.equals(previous))

gbraccialli

val jdbcDF = spark.read.format("jdbc").options( 
  Map(
  "driver" -> "org.postgresql.Driver",
  "url" -> "jdbc:postgresql://localhost/?user=postgres&password=postgres",
  "dbtable" -> "nifi_test"
  )
).load()
  
jdbcDF.show

gbraccialli

import org.apache.spark.sql.SQLContext
import org.apache.spark.util.LongAccumulator
import org.apache.spark.sql.types._
import org.apache.spark.sql._
import org.apache.avro.Schema
import com.databricks.spark.avro._
import scala.collection.JavaConversions._
import scala.util.matching.Regex
import java.io.File

gbraccialli

git add *
git commit -m "changes..."
git push

git checkout v1.1
git pull

git remote set-url origin https://[email protected]

git config credential.helper store

gbraccialli

case class Person (name: String, age: Int)

val df = sc.parallelize(List(Person("Guilherme", 35), Person("Isabela", 6), Person("Daniel", 3))).toDF


def wordsLengthScala(a: Any): Array[Int] = {
  a match {
     case s: String => {s.split(" ").map(s => s.length)}
     case i: Integer => {Array(i)}
  } 

gbraccialli

yum install mysql-connector-java mysql-server

mysql -u root
create database metastore;
CREATE USER 'metastore'@'%' IDENTIFIED BY 'metastore';
CREATE USER 'metastore'@'localhost' IDENTIFIED BY 'metastore';
GRANT ALL PRIVILEGES ON metastore.* TO 'metastore'@'%';
GRANT ALL PRIVILEGES ON metastore.* TO 'metastore'@'localhost';

gbraccialli

git clone https://github.com/databricks/spark-sql-perf.git
cd spark-sql-perf
sbt assembly

git clone https://github.com/davies/tpcds-kit
sudo yum groupinstall "Development Tools"
cd tpcds-kit/tools
cp Makefile.suite Makefile
make

gbraccialli

yarn-site.xml
yarn.resourcemanager.scheduler.monitor.enable=true
yarn.resourcemanager.monitor.capacity.preemption.max_ignored_over_capacity=0.01
yarn.resourcemanager.monitor.capacity.preemption.max_wait_before_kill=1000
yarn.resourcemanager.monitor.capacity.preemption.monitoring_interval=1000
yarn.resourcemanager.monitor.capacity.preemption.natural_termination_factor=1
yarn.resourcemanager.monitor.capacity.preemption.total_preemption_per_round=1
yarn.resourcemanager.scheduler.monitor.policies=org.apache.hadoop.yarn.server.resourcemanager.monitor.capacity.ProportionalCapacityPreemptionPolicy

capacity-scheduler.xml

gbraccialli

spark.hadoop.fs.s3a.experimental.input.fadvise random
spark.hadoop.fs.s3a.readahead.range 67108864
spark.hadoop.fs.s3a.connection.maximum 200
spark.hadoop.fs.s3a.connection.establish.timeout 2000000
spark.hadoop.fs.s3a.connection.timeout      2000000