Before you can run the Hive metastore with a remote MySQL database, you must install the MySQL JDBC driver, set up the initial database schema, and configure the MySQL user account for the Hive user.

For instructions on installing the MySQL JDBC driver, see Installing the MySQL JDBC Driver.

Configure MySQL to use a strong password and to start at boot. Note that in the following procedure, your current root password is blank. Press the Enter key when you're prompted for the root password.

To set the MySQL root password:

$ sudo /usr/bin/mysql_secure_installation
[...]
Enter current password for root (enter for none):
OK, successfully used password, moving on...
[...]
Set root password? [Y/n] y
New password:
Re-enter new password:
Remove anonymous users? [Y/n] Y
[...]
Disallow root login remotely? [Y/n] N
[...]
Remove test database and access to it [Y/n] Y
[...]
Reload privilege tables now? [Y/n] Y
All done!

To make sure the MySQL server starts at boot:

• On RHEL systems:

$ sudo /sbin/chkconfig mysqld on
$ sudo /sbin/chkconfig --list mysqld
mysqld          0:off   1:off   2:on    3:on    4:on    5:on    6:off

• On SLES systems:

$ sudo chkconfig --add mysql

• On Debian/Ubuntu systems:

$ sudo chkconfig mysql on

The instructions in this section assume you are using Remote mode, and that the MySQL database is installed on a separate host from the metastore service, which is running on a host named metastorehost in the example.

  Note: If the metastore service will run on the host where the database is installed, replace 'metastorehost' in the CREATE USER example with 'localhost'. Similarly, the value of javax.jdo.option.ConnectionURL in /etc/hive/conf/hive-site.xml (discussed in the next step) must be jdbc:mysql://localhost/metastore. For more information on adding MySQL users, see http://dev.mysql.com/doc/refman/5.5/en/adding-users.html.

Create the initial database schema. Cloudera recommends using the Hive schema tool to do this.

If for some reason you decide not to use the schema tool, you can use the hive-schema-n.n.n.mysql.sql file instead; that file is located in the /usr/lib/hive/scripts/metastore/upgrade/mysql/ directory. (n.n.n is the current Hive version, for example 1.1.0.) Proceed as follows if you decide to use hive-schema-n.n.n.mysql.sql.

Example using hive-schema-n.n.nmysql.sql

  Note: Do this only if you are not using the Hive schema tool.

$ mysql -u root -p
Enter password:
mysql> CREATE DATABASE metastore;
mysql> USE metastore;
mysql> SOURCE /usr/lib/hive/scripts/metastore/upgrade/mysql/hive-schema-n.n.n.mysql.sql;

You also need a MySQL user account for Hive to use to access the metastore. It is very important to prevent this user account from creating or altering tables in the metastore database schema.

  Important: To prevent users from inadvertently corrupting the metastore schema when they use lower or higher versions of Hive, set the hive.metastore.schema.verification property to true in /usr/lib/hive/conf/hive-site.xml on the metastore host.

Example

mysql> CREATE USER 'hive'@'metastorehost' IDENTIFIED BY 'mypassword';
...
mysql> REVOKE ALL PRIVILEGES, GRANT OPTION FROM 'hive'@'metastorehost';
mysql> GRANT ALL PRIVILEGES ON metastore.* TO 'hive'@'metastorehost';
mysql> FLUSH PRIVILEGES;
mysql> quit;

This step shows the configuration properties you need to set in hive-site.xml (/usr/lib/hive/conf/hive-site.xml) to configure the metastore service to communicate with the MySQL database, and provides sample settings. Though you can use the same hive-site.xml on all hosts (client, metastore, HiveServer2), hive.metastore.uris is the only property that must be configured on all of them; the others are used only on the metastore host.

Given a MySQL database running on myhost and the user account hive with the password mypassword, set the configuration as follows (overwriting any existing values).

  Note: The hive.metastore.local property is no longer supported (as of Hive 0.10); setting hive.metastore.uris is sufficient to indicate that you are using a remote metastore.

<property>
  <name>javax.jdo.option.ConnectionURL</name>
  <value>jdbc:mysql://myhost/metastore</value>
  <description>the URL of the MySQL database</description>
</property>

<property>
  <name>javax.jdo.option.ConnectionDriverName</name>
  <value>com.mysql.jdbc.Driver</value>
</property>

<property>
  <name>javax.jdo.option.ConnectionUserName</name>
  <value>hive</value>
</property>

<property>
  <name>javax.jdo.option.ConnectionPassword</name>
  <value>mypassword</value>
</property>

<property>
  <name>datanucleus.autoCreateSchema</name>
  <value>false</value>
</property>

<property>
  <name>datanucleus.fixedDatastore</name>
  <value>true</value>
</property>

<property>
  <name>datanucleus.autoStartMechanism</name> 
  <value>SchemaTable</value>
</property> 

<property>
  <name>hive.metastore.uris</name>
  <value>thrift://<n.n.n.n>:9083</value>
  <description>IP address (or fully-qualified domain name) and port of the metastore host</description>
</property>

<property>
<name>hive.metastore.schema.verification</name>
<value>true</value>
</property>

To install PostgreSQL on a RHEL system:

$ sudo yum install postgresql-server

To install PostgreSQL on a SLES system:

$ sudo zypper install postgresql-server

To install PostgreSQL on a Debian/Ubuntu system:

$ sudo apt-get install postgresql

After using the command to install PostgreSQL, you may need to respond to prompts to confirm that you do want to complete the installation. In order to finish installation on RHEL compatible systems, you need to initialize the database. Please note that this operation is not needed on Ubuntu and SLES systems as it's done automatically on first start:

To initialize database files on RHEL compatible systems

$ sudo service postgresql initdb

To ensure that your PostgreSQL server will be accessible over the network, you need to do some additional configuration.

First you need to edit the postgresql.conf file. Set the listen_addresses property to *, to make sure that the PostgreSQL server starts listening on all your network interfaces. Also make sure that the standard_conforming_strings property is set to off.

You can check that you have the correct values as follows:

On Red-Hat-compatible systems:

$ sudo cat /var/lib/pgsql/data/postgresql.conf  | grep -e listen -e standard_conforming_strings
listen_addresses = '*'
standard_conforming_strings = off

On SLES systems:

$ sudo cat /var/lib/pgsql/data/postgresql.conf  | grep -e listen -e standard_conforming_strings
listen_addresses = '*'
standard_conforming_strings = off

On Ubuntu and Debian systems:

$ cat /etc/postgresql/9.1/main/postgresql.conf | grep -e listen -e standard_conforming_strings
listen_addresses = '*'
standard_conforming_strings = off

You also need to configure authentication for your network in pg_hba.conf. You need to make sure that the PostgreSQL user that you will create later in this procedure will have access to the server from a remote host. To do this, add a new line into pg_hba.con that has the following information:

host    <database>         <user>         <network address>         <mask>               md5

The following example allows all users to connect from all hosts to all your databases:

host    all         all         0.0.0.0         0.0.0.0               md5

  Note: This configuration is applicable only for a network listener. Using this configuration does not open all your databases to the entire world; the user must still supply a password to authenticate himself, and privilege restrictions configured in PostgreSQL will still be applied.

After completing the installation and configuration, you can start the database server:

Start PostgreSQL Server

$ sudo service postgresql start

Use chkconfig utility to ensure that your PostgreSQL server will start at a boot time. For example:

chkconfig postgresql on

You can use the chkconfig utility to verify that PostgreSQL server will be started at boot time, for example:

chkconfig --list postgresql

Before you can run the Hive metastore with a remote PostgreSQL database, you must configure a JDBC driver to the remote PostgreSQL database, set up the initial database schema, and configure the PostgreSQL user account for the Hive user.

To install the PostgreSQL JDBC Driver on a RHEL 6 system:

On the Hive metastore server host, install postgresql-jdbc package and create symbolic link to the /usr/lib/hive/lib/ directory. For example:

$ sudo yum install postgresql-jdbc
$ ln -s /usr/share/java/postgresql-jdbc.jar /usr/lib/hive/lib/postgresql-jdbc.jar

To install the PostgreSQL JDBC Driver on a SLES system:

On the Hive metastore server host, install postgresql-jdbc and symbolically link the file into the /usr/lib/hive/lib/ directory.

$ sudo zypper install postgresql-jdbc
$ ln -s /usr/share/java/postgresql-jdbc.jar
/usr/lib/hive/lib/postgresql-jdbc.jar

To install the PostgreSQL JDBC Driver on a Debian/Ubuntu system:

On the Hive metastore server host, install libpostgresql-jdbc-java and symbolically link the file into the /usr/lib/hive/lib/ directory.

$ sudo apt-get install libpostgresql-jdbc-java
$ ln -s /usr/share/java/postgresql-jdbc4.jar /usr/lib/hive/lib/postgresql-jdbc4.jar

Proceed as in the following example, using the appropriate script in /usr/lib/hive/scripts/metastore/upgrade/postgres/ n.n.n is the current Hive version, for example 1.1.0:

$ sudo -u postgres psql
postgres=# CREATE USER hiveuser WITH PASSWORD 'mypassword';
postgres=# CREATE DATABASE metastore;
postgres=# \c metastore;
You are now connected to database 'metastore'.
postgres=# \i /usr/lib/hive/scripts/metastore/upgrade/postgres/hive-schema-n.n.n.postgres.sql
SET
SET
...

Now you need to grant permission for all metastore tables to user hiveuser. PostgreSQL does not have statements to grant the permissions for all tables at once; you'll need to grant the permissions one table at a time. You could automate the task with the following SQL script:

  Note: If you are running these commands interactively and are still in the Postgres session initiated at the beginning of this step, you do not need to repeat sudo -u postgres psql.

bash# sudo -u postgres psql
metastore=# \c metastore
metastore=# \pset tuples_only on
metastore=# \o /tmp/grant-privs
metastore=#   SELECT 'GRANT SELECT,INSERT,UPDATE,DELETE ON "'  || schemaname || '". "' ||tablename ||'" TO hiveuser ;'
metastore-#   FROM pg_tables
metastore-#   WHERE tableowner = CURRENT_USER and schemaname = 'public';
metastore=# \o
metastore=# \pset tuples_only off
metastore=# \i /tmp/grant-privs

You can verify the connection from the machine where you'll be running the metastore service as follows:

psql -h myhost -U hiveuser -d metastore
metastore=#

This step shows the configuration properties you need to set in hive-site.xml (/usr/lib/hive/conf/hive-site.xml) to configure the metastore service to communicate with the PostgreSQL database. Though you can use the same hive-site.xml on all hosts (client, metastore, HiveServer2), hive.metastore.uris is the only property that must be configured on all of them; the others are used only on the metastore host.

Given a PostgreSQL database running on host myhost under the user account hive with the password mypassword, you would set configuration properties as follows.

  Note:

• The instructions in this section assume you are using Remote mode, and that the PostgreSQL database is installed on a separate host from the metastore server.

• The hive.metastore.local property is no longer supported as of Hive 0.10; setting hive.metastore.uris is sufficient to indicate that you are using a remote metastore.

<property>
  <name>javax.jdo.option.ConnectionURL</name>
  <value>jdbc:postgresql://myhost/metastore</value>
</property>
 
<property>
  <name>javax.jdo.option.ConnectionDriverName</name>
  <value>org.postgresql.Driver</value>
</property>
 
<property>
  <name>javax.jdo.option.ConnectionUserName</name>
  <value>hiveuser</value>
</property>
 
<property>
  <name>javax.jdo.option.ConnectionPassword</name>
  <value>mypassword</value>
</property>
 
<property>
  <name>datanucleus.autoCreateSchema</name>
  <value>false</value>
</property>

<property>
  <name>hive.metastore.uris</name>
  <value>thrift://<n.n.n.n>:9083</value>
  <description>IP address (or fully-qualified domain name) and port of the metastore host</description>
</property>

<property>
<name>hive.metastore.schema.verification</name>
<value>true</value>
</property>

$ hive –e “show tables;”

  Note: This will take a while the first time.