You must have the BDR Administrator or Full Administrator role on both clusters to define a Peer relationship and perform all subsequent steps.

1. Log in to Cloudera Manager Admin Console on the master node of the backup cluster.
2. Click the Backup tab and select Peers from the menu.
3. On the Peers page, click Add Peers.
4. On the Add Peer page:
   1. Peer Name - Enter a meaningful name for the cluster that you want to back up, such as Production DB. This peer name becomes available in the next step, to be selected as the source for the replication.
   2. Peer URL - Enter the URL (including port number) for the Cloudera Manager Admin Console running on the master node of the cluster.
   3. Peer Admin Username - Enter the name of the administrator account for the cluster.
   4. Peer Admin Password - Enter the password for the administrator account.
   
   
   
   
   
5. Click Add Peer to save your settings, connect to the production cluster, and establish this peer relationship.

The Peers page re-displays, showing the Status column as Connected (note the green check-mark):

You can now create a schedule to replicate Hive files from production to the backup cluster.

From the Cloudera Manager Admin Console on the backup cluster:

1. Click the Backup tab and select Replication Schedules from the menu.
2. On the Replication Schedules page, select Create Schedule > Hive Replication.
3. On the Create Hive Replication page, click the General tab to display the default schedule options:
   1. Source - Make sure the Hive node selected in the drop-down is the production cluster (the cluster to be backed up).
   2. Destination - This is the cluster you are logged into, the backup cluster. Select the Hive node on the cluster.
   3. Databases - Select Replicate All to re-create all Hive databases from the production system to the backup. Or deselect Replicate All and enter specific database name and tables to back up select databases or tables only.
   4. Schedule - Immediate. For production environments, change this to Recurring and set an appropriate time-frame that can backup the selected dataset completely. For example, do not set an hourly schedule if it takes two hours to back up the dataset.
   5. Run As Username - Leave as Default.
   6. Scheduler Pool - Leave as Default.
4. Click Save Schedule.

The files are replicated from the source cluster to the backup cluster immediately.

  Note: When you configure a replication schedule to back up Hive data on a regular basis, make sure that the schedule allows for each backup to complete. For example, do not create a schedule to back up every hour if it takes two hours to complete a full backup.

When the process completes, the Replication Schedules page re-displays, showing a green check-mark and time-stamp in the Last Run column:

When you set up your own schedules in your actual production environment, the Next Run column will likely also contain a date and time according to your specifications for the schedule.

You can verify that data has been replicated by using Hive commands, the HDFS File Browser, or the Hue Web UI (shown below):

The Hive database is now on both the production and the backup clusters—the source and destination of the backup Replication Schedule, respectively.

At this point if the production cluster has a catastrophic data loss, you can use the backup replica to restore the database to the production cluster.

For example, assume that the us_fda_fea database was inadvertently deleted from the example production cluster as shown in the Hue Web UI:

Whenever you first discover an issue (data loss, corruption) with production data, immediately disable any existing backup replication schedules. Disabling the backup replication schedule prevents corrupt or missing data from being replicated over an existing backup replica is why it is the first step in the restore process detailed in the next set of steps.

At the Cloudera Manager Admin Console on the backup cluster:

1. Select Backup > Replication Schedules.
2. On the Replication Schedules page, select the schedule.
3. From the Actions drop-down menu, select Disable.

When the Replication Schedules pages refreshes, the word Disabled displays in the Next Run column for the schedule.

With the backup replication schedule temporarily disabled, move to the production cluster to create and run the replication schedule to restore the data as detailed in the remaining steps.

Log in to Cloudera Manager Admin Console on the master node of the production cluster.

1. Click the Backup tab and select Peers from the menu.
2. On the Peers page, click Add Peers button.
3. On the Add Peer page:
   1. Peer Name - Enter a meaningful name for the cluster from which to obtain the backup data.
   2. Peer URL - Enter the URL for the Cloudera Manager Admin Console (running on the master node of the cluster).
   3. Peer Admin Username - Enter the administrator user name for the backup cluster.

      
      

      
      
      

4. Click Add Peer to save your settings. The production cluster connects to the backup cluster, establishes the peer relationship, and tests the connection.

The Peers page redisplays and lists the peer name, URL, and shows its Status (Connected) as shown below:

From the Cloudera Manager Admin Console on the production cluster:

1. Click the Backup tab and select Replication Schedules from the menu.
2. On the Replication Schedules page, select Create Schedule > Hive Replication.
3. On the General settings tab of the Create Hive Replication page:
   1. Source - The backup cluster from which to pull the data.
   2. Destination - The production cluster that needs the data restored.
   3. Databases - Select Replicate All.
   4. Schedule - Immediate.
   5. Run As Username - Leave as Default.
   6. Scheduler Pool - Leave as Default.
     Important: Be sure that the source is the cluster where your backup is stored and the destination is the cluster containing lost or damaged data that you want to replace with the backup.
4. Click the Advanced tab:

   
   

   
   
   

5. Select Force Overwrite so that the backup cluster's metadata replaces the metadata on the production cluster. The assumption is that the production cluster's dataset has been corrupted.
     Important: The Force Overwrite setting can destroy tables or entries created after the backup completed. Do not use this setting unless you are certain that you want to overwrite the destination cluster with data from the source.
6. Click Save Schedule.

This schedule runs one time and restores your Hive databases. When the process completes, the Replication Schedules page displays the time-stamp and check-mark in the Last Run column for the schedule.

Immediately disable the Replication Schedule used for the restore as soon as it completes. From the Replication Schedules page:

1. Select the replication schedule that just completed.
2. From the Actions drop-down menu, select Disable.

The page refreshes and displays Disabled in the Next Run column.

Use the Hive command-line, the HDFS File Browser, or the Hue Web UI to verify successful data restore:

The restore process is complete. In a production environment, assuming the restored Hive database and tables are as you want them in a temporary path, you can re-configure the replication schedule to restore the data to the original path.

On the backup cluster, log in to the Cloudera Manager Admin Console.

1. Select Backup > Replication Schedules.
2. On the Replication Schedules page, select the schedule created at the beginning of this process.
3. From the Actions drop-down menu, select Enable.

The restore process is complete.

In actual production environments, create replication schedules that regularly back up your production clusters. To restore data, create replication schedules as shown in this tutorial.

Alternatively, you can define replication schedules in advance but leave them disabled. See How To Back Up and Restore HDFS Data Using Cloudera Enterprise BDR for details.

See Backup and Disaster Recovery and BDR Tutorials or more information about Cloudera Enterprise BDR.