Vagrantfile for Pivotal HD 1.0.1 CE + HAWQ 1.1.0-8 Defines the type of VMs required and how to configure and provision those machines * pcc_provision.sh - Provisioning is applied only to the pcc VM. It follows the PHD_10_Guid.pdf instruction to install PCC on the pcc VM and PHD on the phd[1..3] VMs. Annotations in the script can provide addition…

pcc_provision.sh

#!/bin/bash
 
# All configuration and installation  steps applied here follow the PHD installation guide: 
# http://bitcast-a.v1.o1.sjc1.bitgravity.com/greenplum/pivotal-docs/PHD_10_Guide.pdf
# 
# Note: The default pwd is /home/vagrant. 
#
# Note: By default, Vagrant shares your project directory (that is the one with the Vagrantfile) 
#       to the /vagrant directory in your guest VMs. 
# 
# Note: 'root' is the default user. You can not change the root user in the script. "$sudo su - gpadmin" will not work!
#       Use the inline syntax instead: "$su - -c "some command" gpadmin".
 
# Sets the cluster name to be used in PCC (Pivotal Control Center)
CLUSTER_NAME=PHD_C1
 
# List of Hadoop services to be deployed with this installation.
# Note: Hive is disabled because phd2 and ph3 VMs are configured with just 1GB of memory (Vagrantfile)! To enable Hive 
# increase the memory of the VMs to 2GB at least (edit Vagrantfile) and then add 'hive' to the $SERVICES variable.
# Alternativly if you don't have enough physical memory then you can remove one VM (phd3 for example) and increase the memory
# of the remaining VMs. For this you need to remove phd3 definition from the Vagrangfile and from the $MASTER_AND_SLAVES list.
SERVICES=hdfs,yarn,pig,zookeeper,hbase,gpxf,hawq
 
# Sets the dns name of the VM used as Master node for all Hadoop services (e.g. namenode, hawq master, jobtracker ...)
# Note: Master node is not an Admin node (where PCC runs). By convention the Admin node is the pcc.localdomain. 
MASTER_NODE=phd1.localdomain
 
# By default the HAWQ master is collocated with the other master services.
HAWQ_MASTER=$MASTER_NODE
 
# List of all Pivotal HD nodes in the cluster (including the master node)
MASTER_AND_SLAVES=$MASTER_NODE,phd2.localdomain,phd3.localdomain
 
# By default all nodes will be used as Hawq segment hosts. Edit the $HAWQ_SEGMENT_HOSTS variable to change this setup.  
HAWQ_SEGMENT_HOSTS=$MASTER_AND_SLAVES
 
# Client node defaults to the MASTER node 
CLIENT_NODE=$MASTER_NODE
 
# Root password required for creating gpadmin users on the cluster nodes. 
# (By default Vagrant creates 'vagrant' root user on every VM. The password is 'vagrant' - used below)
ROOT_PASSWORD=vagrant
 
# Non-empty password to be used for the gpadmin user. Required by the PHD installation. 
GPADMIN_PASSWORD=gpadmin
 
echo "********************************************************************************"
echo "*               Prepare PCC (Pivotal Control Center)  Perquisites               "
echo "********************************************************************************"
 
# If missing try to download the Oracle JDK6 installation binary. 
if [ ! -f /vagrant/jdk-6u45-linux-x64-rpm.bin ];
then
   cd /vagrant; wget --cookies=off --header "Cookie: gpw_e24=http%3A%2F%2Fwww.oracle.com" "http://download.oracle.com/otn-pub/java/jdk/6u45-b06/jdk-6u45-linux-x64-rpm.bin"; cd ~
fi
 
# Ensure that all installation packages are available in the same folder where  the 'vagrant up' is executed.
[ ! -f /vagrant/jdk-6u45-linux-x64-rpm.bin ] && ( echo "Can not find jdk-6u45-linux-x64-rpm.bin in the vagrant startup directory"; exit 1 )
[ ! -f /vagrant/PCC-2.0.1.84.121.163.x86_64.tar.gz ] && ( echo "Can not find PCC-2.0.1.84.121.163.x86_64.tar.gz in the vagrant startup directory"; exit 1 )
[ ! -f /vagrant/PHD-1.0.1.0-19.tar.gz ] && ( echo "Can not find PHD-1.0.1.0-19.tar.gz in the vagrant startup directory"; exit 1 )
# <HAWQ> If PADS (e.g. HAWQ) is not available locally, download it from the public distribution.
if [ ! -f /vagrant/PADS-1.1.0-8.tar.gz ];
then
  cd /vagrant; wget http://bitcast-a.v1.o1.sjc1.bitgravity.com/greenplum/pivotal-sw/PADS-1.1.0-8.tar.gz; cd ~
fi
# </HAWQ>
 
# Disable security.
sestatus; chkconfig iptables off; service iptables stop; service iptables status
 
# Install required packages.
yum -y install httpd mod_ssl postgresql postgresql-devel postgresql-server compat-readline5 createrepo sigar nc expect
 
# Install Oracle Java 6 on PCC (e.g Admin) node.
cp /vagrant/jdk-6u45-linux-x64-rpm.bin .; chmod a+x ./jdk-6u45-linux-x64-rpm.bin; sudo ./jdk-6u45-linux-x64-rpm.bin; java -version
 
echo "********************************************************************************"
echo "*                 Install PCC (Pivotal Control Center)                          "
echo "********************************************************************************"
 
service commander stop
 
# Copy, uncompress and enter the PCC package folder
tar --no-same-owner -xzvf /vagrant/PCC-2.0.1.84.121.163.x86_64.tar.gz --directory /home/vagrant/; cd /home/vagrant/PCC-2.0.1.84
 
# Install PCC as root using root's login shell (Note: will not work without the '-' option)
su - -c "cd /home/vagrant/PCC-2.0.1.84; ./install" root
 
echo "********************************************************************************"
echo "*                 Prepare Hosts for Cluster: $CLUSTER_NAME                   "
echo "********************************************************************************"
 
# Add Sun Java JDK RPM installer binary (jdk-6u45-linux-x64-rpm.bin). Will be installed on all cluster hosts automatically.
# The JDK rpm file need to have execute permission. If the JDK version you have downloaded is only available as a .rpm file 
# (not as a Linux binary installer .bin file) you need to install the JDK by hand on all cluster nodes.
su - -c "cp /vagrant/jdk-6u45-linux-x64-rpm.bin .; chmod a+x ./jdk-6u45-linux-x64-rpm.bin" gpadmin
 
echo "Import PHD & PADS packages into the PCC local yum repository ..."
 
# (Required) For installing PHD
su - -c "tar -xzf /vagrant/PHD-1.0.1.0-19.tar.gz --directory ~; icm_client import -p ./PHD-1.0.1.0-19" gpadmin
 
# <<HAQW>>
# Import HAWQ packages in the local yum repo
su - -c "tar -xzf /vagrant/PADS-1.1.0-8.tar.gz --directory ~; icm_client import -p ./PADS-1.1.0-8" gpadmin
# <</HAWQ>> 
 
# (Optional) Import DataLoader and UUS installation packages
#su - -c "tar -xzf /vagrant/PHDTools-1.0.1-19.tar.gz --directory ~; icm_client import -p ./PHDTools-1.0.1-19" gpadmin
 
# Create a hostfile (HostFile.txt) that contains the hostnames of all cluster nodes (except pcc) separated by newlines.
# Important: The hostfile should contain all nodes within your cluster EXCEPT the Admin node (e.g. except pcc.localdomain).
su - -c "echo $MASTER_AND_SLAVES  | tr , '\n' > /home/gpadmin/HostFile.txt" gpadmin
 
echo "Prepare cluster hosts"
 
# Preparing the Cluster Nodes for Pivotal HD
# Note: preparehosts expects user inputs like root and gpadmin passwords. The 'expect' tool is used to emulate this user interaction. 
cat > /home/gpadmin/preparehosts.exp <<EOF
#!/usr/bin/expect -f
 
set timeout 100
 
spawn icm_client  preparehosts --hostfile=./HostFile.txt --java=jdk-6u45-linux-x64-rpm.bin --ntp --selinuxoff --iptablesoff
 
expect "Please enter the root user's password. This is required for creating gpadmin users on the cluster nodes:"
send -- "$ROOT_PASSWORD\r"
expect "Please enter a non-empty password to be used for the gpadmin user:"
send -- "$GPADMIN_PASSWORD\r"
send -- "\r"
expect eof
EOF
 
chown gpadmin:gpadmin /home/gpadmin/preparehosts.exp; chmod a+x /home/gpadmin/preparehosts.exp
 
# Prepare all PHD hosts
su - -c "expect -f /home/gpadmin/preparehosts.exp" gpadmin
 
# <<HAWQ>> 
echo "Prepare HAWQ hosts"
 
# Set vm.overcommit_memory to 1 to prevent OOM and other VM issues. 
sed -i 's/vm.overcommit_memory = 2/vm.overcommit_memory = 1/g' /usr/lib/gphd/gphdmgr/hawq_sys_config/sysctl.conf
 
 
# Prepare all Hawq hosts. Asumes that HAWQ is deployed on all hosts. 
su - -c "icm_client prepare-hawq-hosts -f ./HostFile.txt -g /usr/lib/gphd/gphdmgr/hawq_sys_config/" gpadmin
# <</HAWQ>> 
 
 
# Verify that all hosts are prepared for installation
su - -c "icm_client scanhosts -f ./HostFile.txt" gpadmin
 
echo "********************************************************************************"
echo "*                 Deploy Cluster: $CLUSTER_NAME                    "
echo "********************************************************************************"
 
# Cluster is deployed as gpadmin user!
 
# Pivotal HD manager deploys clusters using input from the cluster configuration directory. This cluster 
# configuration directory contains files that describes the topology and configuration for the cluster and the 
# installation procedure.
 
# Fetch the default Cluster Configuration Templates. 
su - -c "icm_client fetch-template -o ~/ClusterConfigDir" gpadmin
 
# Use the following convention to assign cluster hosts to Hadoop service roles. All changes are 
# applied to the ~/ClusterConfigDir/clusterConfig.xml file, generated in the previous step. 
# Note: By default HAWQ_MASTER=MASTER_NODE, CLIENT_NODE=MASTER_NODE and HAWQ_SEGMENT_HOSTS=MASTER_AND_SLAVES
# ---------------------------------------------------------------------------------------------------------
#      Hosts        |                       Services
# ---------------------------------------------------------------------------------------------------------
# MASTER_NODE       | client, namenode, secondarynameonde, yarn-resourcemanager, mapreduce-historyserver, 
#                   | hbase-master,hive-server,hive-metastore,hawq-master,hawq-standbymaste,hawq-segment,
#                   | gpxf-agent
#                   |
# MASTER_AND_SLAVES | datanode,yarn-nodemanager,zookeeper-server,hbase-regionserver,hawq-segment,gpxf-agent 
# ---------------------------------------------------------------------------------------------------------

# Apply the mapping convention (above) to the default clusterConfig.xml.
sed -i "\
s/<clusterName>.*<\/clusterName>/<clusterName>$CLUSTER_NAME<\/clusterName>/g;\
s/<services>.*<\/services>/<services>$SERVICES<\/services>/g;\
s/<client>.*<\/client>/<client>$CLIENT_NODE<\/client>/g;\
s/<namenode>.*<\/namenode>/<namenode>$MASTER_NODE<\/namenode>/g;\
s/<datanode>.*<\/datanode>/<datanode>$MASTER_AND_SLAVES<\/datanode>/g;\
s/<secondarynamenode>.*<\/secondarynamenode>/<secondarynamenode>$MASTER_NODE<\/secondarynamenode>/g;\
s/<yarn-resourcemanager>.*<\/yarn-resourcemanager>/<yarn-resourcemanager>$MASTER_NODE<\/yarn-resourcemanager>/g;\
s/<yarn-nodemanager>.*<\/yarn-nodemanager>/<yarn-nodemanager>$MASTER_AND_SLAVES<\/yarn-nodemanager>/g;\
s/<mapreduce-historyserver>.*<\/mapreduce-historyserver>/<mapreduce-historyserver>$MASTER_NODE<\/mapreduce-historyserver>/g;\
s/<zookeeper-server>.*<\/zookeeper-server>/<zookeeper-server>$MASTER_AND_SLAVES<\/zookeeper-server>/g;\
s/<hbase-master>.*<\/hbase-master>/<hbase-master>$MASTER_NODE<\/hbase-master>/g;\
s/<hbase-regionserver>.*<\/hbase-regionserver>/<hbase-regionserver>$MASTER_AND_SLAVES<\/hbase-regionserver>/g;\
s/<hive-server>.*<\/hive-server>/<hive-server>$MASTER_NODE<\/hive-server>/g;\
s/<hive-metastore>.*<\/hive-metastore>/<hive-metastore>$MASTER_NODE<\/hive-metastore>/g;\
s/<hawq-master>.*<\/hawq-master>/<hawq-master>$HAWQ_MASTER<\/hawq-master>/g;\
s/<hawq-standbymaster>.*<\/hawq-standbymaster>/<hawq-standbymaster>$HAWQ_MASTER<\/hawq-standbymaster>/g;\
s/<hawq-segment>.*<\/hawq-segment>/<hawq-segment>$HAWQ_SEGMENT_HOSTS<\/hawq-segment>/g;" /home/gpadmin/ClusterConfigDir/clusterConfig.xml
 
# Use ICM to perform the deploy
su - -c "icm_client deploy -c ~/ClusterConfigDir" gpadmin
 
echo "********************************************************************************"
echo "*                    HAWQ - post deploy configuration                   "
echo "********************************************************************************"
# <<HAWQ>> 
su - -c "echo $HAWQ_SEGMENT_HOSTS  | tr , '\n' > /home/gpadmin/HAWQ_Segment_Hosts.txt" gpadmin
 
su - -c "\
scp /home/gpadmin/HAWQ_Segment_Hosts.txt gpadmin@$HAWQ_MASTER:/home/gpadmin/HAWQ_Segment_Hosts.txt;\
ssh gpadmin@$HAWQ_MASTER 'source /usr/local/hawq/greenplum_path.sh;\
/usr/local/hawq/bin/gpssh-exkeys -f /home/gpadmin/HAWQ_Segment_Hosts.txt -p $GPADMIN_PASSWORD'" gpadmin
# <</HAWQ>>
 
echo "********************************************************************************"
echo "*                 Start Cluster: $CLUSTER_NAME                                  "
echo "********************************************************************************"
 
su - -c "icm_client start -l $CLUSTER_NAME" gpadmin
 
echo "********************************************************************************"
echo "*                       Initialise HAWQ   									  "
echo "********************************************************************************"
# <<HAWQ>> 
su - -c "ssh gpadmin@$HAWQ_MASTER '/etc/init.d/hawq init'" gpadmin;
# <</HAWQ>>

Vagrantfile

# -*- mode: ruby -*-
# vi: set ft=ruby :

# Vagrantfile API/syntax version. Don't touch unless you know what you're doing!
VAGRANTFILE_API_VERSION = "2"

# Embedded provisioning script common for all cluster hosts and PCC.
$phd_provision_script = <<SCRIPT
#!/bin/bash

# Install the packages required for all cluster and admin nodes 
yum -y install postgresql-devel nc expect ed ntp

# Set timezone and run NTP (set to Europe - Amsterdam time).
/etc/init.d/ntpd stop; mv /etc/localtime /etc/localtime.bak; ln -s /usr/share/zoneinfo/Europe/Amsterdam /etc/localtime; /etc/init.d/ntpd start

cat > /etc/hosts <<EOF 
127.0.0.1     localhost.localdomain    localhost
::1           localhost6.localdomain6  localhost6
 
10.211.55.100 pcc.localdomain  pcc
10.211.55.101 phd1.localdomain phd1
10.211.55.102 phd2.localdomain phd2
10.211.55.103 phd3.localdomain phd3

EOF

SCRIPT

Vagrant.configure(VAGRANTFILE_API_VERSION) do |config|

  config.vm.define :phd1 do |phd1|
   phd1.vm.box = "CentOS-6.2-x86_64"
   phd1.vm.provider :virtualbox do |v|
    v.name = "phd1"
    v.customize ["modifyvm", :id, "--memory", "2048"]
   end
   phd1.vm.provider "vmware_fusion" do |v|
    v.name = "phd1"
    v.vmx["memsize"]  = "2048"
   end         
   phd1.vm.hostname = "phd1.localdomain"
   phd1.vm.network :private_network, ip: "10.211.55.101"
   phd1.vm.provision :shell, :inline => $phd_provision_script
  end

  config.vm.define :phd2 do |phd2|
   phd2.vm.box = "CentOS-6.2-x86_64"
   phd2.vm.provider :virtualbox do |v|
    v.name = "phd2"
    v.customize ["modifyvm", :id, "--memory", "1024"]
   end
   phd2.vm.provider "vmware_fusion" do |v|
    v.name = "phd2"
    v.vmx["memsize"]  = "1024"
   end       
   phd2.vm.hostname = "phd2.localdomain"
   phd2.vm.network :private_network, ip: "10.211.55.102"
   phd2.vm.provision :shell, :inline => $phd_provision_script
  end

  config.vm.define :phd3 do |phd3|
   phd3.vm.box = "CentOS-6.2-x86_64"
   phd3.vm.provider :virtualbox do |v|
    v.name = "phd3"
    v.customize ["modifyvm", :id, "--memory", "1024"]
   end
   phd3.vm.provider "vmware_fusion" do |v|
    v.name = "phd3"
    v.vmx["memsize"]  = "1024"
   end       
   phd3.vm.hostname = "phd3.localdomain"
   phd3.vm.network :private_network, ip: "10.211.55.103"
   phd3.vm.provision :shell, :inline => $phd_provision_script
  end

  config.vm.define :pcc do |pcc|
   pcc.vm.box = "CentOS-6.2-x86_64"
   pcc.vm.provider :virtualbox do |v|
    v.name = "pcc"
    v.customize ["modifyvm", :id, "--memory", "352"]
   end
   pcc.vm.provider "vmware_fusion" do |v|
    v.name = "pcc"
    v.vmx["memsize"]  = "352"
   end  
   pcc.vm.hostname = "pcc.localdomain"
   pcc.vm.network :private_network, ip: "10.211.55.100"
   pcc.vm.network :forwarded_port, guest: 5000, host: 5000
   pcc.vm.provision :shell, :inline => $phd_provision_script
   pcc.vm.provision :shell, :path => "pcc_provision.sh"
  end
end