Introduction

There can be situations when a Controller Cluster should be reverted to act as a Standalone Controller:

• In case of an architecture decision to continue with a Standalone Controller.
• In case of severe loss of cluster-related data, for example if journals of both a Controller instance and of the Cluster Watch Agent have not been consistently written to disk or are not available after a server crash or file system crash.

Converting a Controller Cluster to a Standalone Controller offers to re-instate the Cluster at any later point in time.

Revoking the Controller Cluster

Stopping the Controller Cluster

As a pre-requisite both active and standby Controller instances have to be terminated.

Reverting the Controller Journal

Users decide which Controller instance should become the Standalone Controller to continue operations.

• In most situations this will be the previously active Controller instance.
• Users should remove the journal of the previous standby Controller instance, precisely they should remove the contents of the Controller instance's state folder. This measure prevents a situation when later on the previous standby Controller instance will be started by chance and will invite the Standalone Controller instance to re-establish the cluster.

Reverting the Controller journal can be performed with the following command:

# reverting Controller journal for Unix with no running Controller instances
./controller_instance.sh revoke

# reverting Controller journal for Unix with a running Controller instance that is stopped and reverted
./controller_instance.sh stop --revoke

@rem reverting Controller journal for Unix with no running Controller instances
./controller_instance.cmd revoke

@rem reverting Controller journal for Unix with a running Controller instance that is stopped and reverted
.\controller_instance.cmd stop --revoke

Explanation:

• Running the above script will remove any cluster related items from the Controller instance's journal.
• This allows the Controller instance to be started as a Standalone instance.
  • Standalone Controllers
    • do not connect to a Cluster Watch Agent,
    • do not connect nor can be connected to/from a second Controller instance acting in a standby role.

Configuring the Standalone Controller

The Controller's administrative menu is invoked from JOC Cockpit as follows:

From the list of Controllers displayed users select the "Edit" action menu item for the respective Controller:

When editing the Controller configuration the following popup window is offered:

The initial radio buttons Standalone and Cluster determine the Controller type. Users can modify the Controller type to Standalone and enter the URL of the Controller instance that should be used as a Standalone Controller like this:

When submitting the changes the Controller will not be started. Therefore the Test Connection function cannot be used.

Starting the Standalone Controller

With the Controller type being reverted users can start the Standalone Controller instance from the command line like this:

# starting the Standalone Controller for Unix from the command line
./controller_instance.sh start

# starting the Standalone Controller for Unix from systemd
sudo systemctl start controller.service

@rem starting the Standalone Controller for Windows from the command line
.\controller_instance.cmd start

@rem starting the Standalone Controller Windows Service from the command line
.\controller_instance.cmd start-service

@rem alternatively the Standalone Controller can be started from the Windows Service Panel