Install Hadoop with HDP 2.2 on CentOS 6.5

Hadoop Hortonworks

Masters-- HDFS NameNode, YARN ResourceManager (ApplicationsManager + Scheduler), and HBase Master
Slaves-- HDFS DataNodes, YARN NodeManagers, and HBase RegionServers (Worker Nodes co-deployed)
ZooKeeper -- to manage HBase cluster

HA -- NameNode + Secondary NameNode 或者NameNode HA (Active + Standby)，推荐后者

分区考虑，不要使用LVM
root -- > 100G

/tmp -- >100G (run job失败的话请查看此目录空间)

swap -- 2倍系统内存

Master node:
RAID 10, dual Ethernet cards, dual power supplies, etc.

Slave node:
1. RAID is not necessary

2. HDFS分区, not using LVM
/etc/fstab -- ext3/ext4    defaults,noatime
挂载到/grid/[0-n] (one partition per disk)

HDP 2.2 and Ambari 1.7 repo

http://public-repo-1.hortonworks.com/HDP/centos6/2.x/GA/2.2.0.0/hdp.repo

http://public-repo-1.hortonworks.com/ambari/centos6/1.x/updates/1.7.0/ambari.repo

yum -y install yum-utils

yum repolist

reposync -r HDP-2.2.0.0

reposync -r HDP-UTILS-1.1.0.20

reposync -r Updates-ambari-1.7.0  

on all cluster nodes and ambari server:

cat << EOF > /etc/yum.repos.d/iso.repo
[iso]
name=iso
baseurl=http://mirrors.aliyun.com/centos/6.5/os/x86_64/

enable=1
gpgcheck=0
EOF

vi /etc/hosts to add all hosts FQDN, like below:

192.168.1.19    ambari.local
192.168.1.20    master1.local # HDFS NameNode

192.168.1.21    master2.local # YARN ResourceManager

192.168.1.22    slave1.local
192.168.1.23    slave2.local

192.168.1.24    slave3.local

192.168.1.25    client.local

vi /etc/sysconfig/network to set FQDN

yum -y install ntp

service ntpd start; chkconfig ntpd on

disable firewall and selinux:

service iptables stop
chkconfig iptables off; chkconfig ip6tables off

setenforce 0
sed -i 's,SELINUX=enforcing,SELINUX=disabled,g' /etc/selinux/config

yum -y install openssh-clients wget unzip

rpm -Uvh http://mirrors.aliyun.com/centos/6.5/updates/x86_64/Packages/openssl-1.0.1e-16.el6_5.15.x86_64.rpm

rpm -ivh jdk-7u67-linux-x64.rpm

echo 'export JAVA_HOME=/usr/java/default' >> /etc/profile

echo 'export PATH=$JAVA_HOME/bin:$PATH' >> /etc/profile

source /etc/profile

just on all cluster nodes:

disable ipv6 and kernel parameters tuning
echo "net.ipv6.conf.all.disable_ipv6 = 1" >> /etc/sysctl.conf

echo "vm.swappiness = 0" >> /etc/sysctl.conf

echo 'net.ipv4.tcp_retries2 = 2' >> /etc/sysctl.conf
echo 'vm.overcommit_memory = 1' >> /etc/sysctl.conf
echo "fs.file-max = 6815744" >> /etc/sysctl.conf
echo "fs.aio-max-nr = 1048576" >> /etc/sysctl.conf
echo "net.core.rmem_default = 262144" >> /etc/sysctl.conf
echo "net.core.wmem_default = 262144" >> /etc/sysctl.conf
echo "net.core.rmem_max = 16777216" >> /etc/sysctl.conf
echo "net.core.wmem_max = 16777216" >> /etc/sysctl.conf
echo "net.ipv4.tcp_rmem = 4096 262144 16777216" >> /etc/sysctl.conf
echo "net.ipv4.tcp_wmem = 4096 262144 16777216" >> /etc/sysctl.conf

only on ResourceManager and JobHistory Server
echo "net.core.somaxconn = 1000" >> /etc/sysctl.conf

sysctl -p

vi /etc/security/limits.conf
*         soft    core         unlimited
*         hard    core         unlimited
*         soft    nofile       65536
*         hard    nofile       65536
*         soft    nproc        unlimited
*         hard    nproc        unlimited
*         soft    memlock      unlimited
*         hard    memlock      unlimited

echo "echo never > /sys/kernel/mm/redhat_transparent_hugepage/enabled" >> /etc/rc.local
echo "echo never > /sys/kernel/mm/redhat_transparent_hugepage/defrag" >> /etc/rc.local
echo "echo no > /sys/kernel/mm/redhat_transparent_hugepage/khugepaged/defrag" >> /etc/rc.local

vi /etc/grub.conf
add "elevator=deadline"(no quotes) at the end of kernel line

reboot to take effect

Just on ambari server:

ssh-keygen -q -t rsa -f ~/.ssh/id_rsa -C '' -N ''

vi ~/.ssh/config

StrictHostKeyChecking no

ssh-copy-id master1.local

ssh-copy-id master2.local

ssh-copy-id slave1.local

ssh-copy-id slave2.local

ssh-copy-id slave3.local

yum -y install mysql-server httpd

vi /etc/my.cnf

[mysqld]
default_storage_engine=InnoDB
innodb_file_per_table=1

service mysqld start; chkconfig mysqld on

mysql_secure_installation

vi /etc/yum.repos.d/ambari.repo
[ambari]
name=ambari
baseurl=http://192.168.1.19/ambari
enable=1
gpgcheck=0

mkdir /hdp; mount /dev/cdrom /hdp

ln -s /hdp/ambari/ /var/www/html/ambari

ln -s /hdp/hdp /var/www/html/hdp

service httpd start; chkconfig httpd on

For ambari/hive/oozie database:

yum -y install ambari-server

mysql -uroot -p
create database ambari;
GRANT ALL PRIVILEGES ON *.* TO 'ambari'@'localhost' IDENTIFIED BY 'ambari' WITH GRANT OPTION;
GRANT ALL PRIVILEGES ON *.* TO 'ambari'@'%' IDENTIFIED BY 'ambari' WITH GRANT OPTION;

flush privileges;
use ambari;
source /var/lib/ambari-server/resources/Ambari-DDL-MySQL-CREATE.sql;

create database hive;
GRANT ALL PRIVILEGES ON *.* TO 'hive'@'localhost' IDENTIFIED BY 'hive' WITH GRANT OPTION;
GRANT ALL PRIVILEGES ON *.* TO 'hive'@'%' IDENTIFIED BY 'hive' WITH GRANT OPTION;
flush privileges;

create database oozie;
GRANT ALL PRIVILEGES ON *.* TO 'oozie'@'localhost' IDENTIFIED BY 'oozie' WITH GRANT OPTION;
GRANT ALL PRIVILEGES ON *.* TO 'oozie'@'%' IDENTIFIED BY 'oozie' WITH GRANT OPTION;
flush privileges;

Install mysql jdbc connector:

tar zxf mysql-connector-java-5.1.33.tar.gz
mkdir /usr/share/java
cp mysql-connector-java-5.1.33/mysql-connector-java-5.1.33-bin.jar /usr/share/java/mysql-connector-java.jar

ambari-server setup --jdbc-db=mysql --jdbc-driver=/usr/share/java/mysql-connector-java.jar

ambari-server setup -j /usr/java/default

Enter advanced database configuration [y/n] (n)? y

choose to use mysql, enter 3

ambari-server start

http://{your.ambari.server}:8080

default user name/password: admin/admin

使用Pi Estimator验证测试：

sudo -u hdfs hadoop jar /usr/hdp/version-number/hadoop-mapreduce/hadoop-mapreduce-examples.jar pi 10 1000

关机的正确步骤：

1. stop all service in Ambari Web UI (if there is no response for stopping, service ambari-server restart, then try again)

2. poweroff hosts

Enable HA for NameNode and ResourceManager

HUE installation:

we will install HUE on client node:

The Hive client configuration (hive-site.xml file) needs to be populated on the host to run Hue. In the beeswax section of hue.ini configure:

hive_conf_dir=/etc/hive/conf

Configure HDP
1. Modify the core-site.xml
2. Modify the webhcat-site.xml file
3. Modify the oozie-site.xml file

yum -y install hue

vi /etc/hue/conf/hue.ini
[desktop]
time_zone=Asia/Shanghai

[hadoop]
[[hdfs_clusters]]

    [[[default]]]
      fs_defaultfs=hdfs://fqdn.namenode.host:8020
      webhdfs_url=http://fqdn.namenode.host:50070/webhdfs/v1/

[[yarn_clusters]]

    [[[default]]]
      resourcemanager_api_url=http://fqdn.resourcemanager.host:8088
      resourcemanager_rpc_url=http://fqdn.resourcemanager.host:8050
      proxy_api_url=http://fqdn.resourcemanager.host:8088
      history_server_api_url=http://fqdn.historyserver.host:19888
      node_manager_api_url=http://fqdn.resourcemanager.host:8042

[liboozie]
       oozie_url=http://fqdn.oozieserver.host:11000/oozie

[beeswax]
       hive_server_host=fqdn.hiveserver.host

[hcatalog]
  templeton_url=http://fqdn.webhcatserver.host:50111/templeton/v1/

service hue start

http://hue.server:8000

Configuring Hue for MySQL Database
mysql -uroot -p
create database hue;
GRANT ALL PRIVILEGES ON *.* TO 'hue'@'localhost' IDENTIFIED BY 'hue' WITH GRANT OPTION;
GRANT ALL PRIVILEGES ON *.* TO 'hue'@'%' IDENTIFIED BY 'hue' WITH GRANT OPTION;
flush privileges;

service hue stop

vi /etc/hue/conf/hue.ini
[[database]]
engine=mysql
host=fqdn.mysqlserver.host
port=3306
user=hue
password=hue
name=hue

/usr/lib/hue/build/env/bin/hue syncdb --noinput
service hue start

This is just for hadoop tarball:

disable firewall and selinux
rpm -ivh jdk-7u67-linux-x64.rpm
yum -y install wget rsync unzip openssh-clients

ssh-keygen -q -t rsa -f ~/.ssh/id_rsa -C '' -N ''

vi ~/.ssh/config

StrictHostKeyChecking no

ssh-copy-id localhost

cd /usr/local/
tar xvf /root/hadoop-2.5.1.tar.gz
ln -s hadoop-2.5.1 hadoop

vi ~/.bashrc
export JAVA_HOME=/usr/java/default
export HADOOP_HOME=/usr/local/hadoop
export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin

. ~/.bashrc

vi $HADOOP_HOME/etc/hadoop/hadoop-env.sh
export JAVA_HOME=/usr/java/default

export HADOOP_CONF_DIR=${HADOOP_CONF_DIR:-"/usr/local/hadoop"}

Web Interface:

hadoop namenode: 50070
hadoop secondarynode: 50090
hadoop yarn ResourceManager: 8088

hadoop yarn NodeManager: 8042
hadoop MapReduce JobHistory Server: 19888