General
Multiple JobScheduler can built a cluster.
All JobScheduler of a cluster must have the same Id and must use the same database.
Furthermore, each JobScheduler of a cluster must start with one of the following cluster options
- -exclusive
- -exclusive -backup
- -distributed-orders
Look at http://www.sos-berlin.com/doc/en/scheduler.doc/command_line.xml for more information about JobScheduler start options
JobScheduler Cluster
All JobScheduler of this cluster have the start option -exclusive.
After you have start all JobScheduler of this cluster only the first one is active.
The other JobScheduler are waiting for activation.
We assume that all JobScheduler of the cluster have the same configuration (Jobs, Job Chains, Orders, etc.)
If you terminate the active JobScheduler then one of the other will go active automatically and knows all states, i.e. wether the Jobs or Job Chains are stopped or not, Job Chain Nodes are stopped, skipped or not, Orders are suspended or not and on which step they are.
JobScheduler Backup Cluster
Here we have a primary JobScheduler which has the start option -exclusive.
All other Backup JobScheduler have the start option -exclusive -backup -backup-precedence=n where n is a number.
The option -backup-precedence is optional and the number n defines the order in which another JobScheduler goes active when necessary.
After you have start all JobScheduler of this cluster only the primary JobScheduler is active.
We assume that all JobScheduler of the cluster have the same configuration (Jobs, Job Chains, Orders, etc.)
A Backup JobScheduler of this cluster doesn't start when you have terminate the primary JobScheduler in a normal way.
But when you abort the primary JobScheduler or its process is killed (e.g. the Server has crashed) then the (next) Backup JobScheduler goes active and knows all states, i.e. wether the Jobs or Job Chains are stopped or not, Job Chain Nodes are stopped, skipped or not, Orders are suspended or not and on which step they are.
If a Backup JobScheduler is active and the primary JobScheduler is restarted then you must terminate the Backup JobScheduler to reactivate the primary.
See also http://www.sos-berlin.com/doc/en/scheduler.doc/backupscheduler.xml
JobScheduler Load Balancing Cluster (Distributed Orders)
All JobScheduler of this cluster have the start option -distributed-orders.
After you have start all JobScheduler of this cluster then all are active.
Each JobScheduler of this cluster handle its Jobs alone except Orders of Job Chains which are configured as distributed.
See also http://www.sos-berlin.com/doc/en/scheduler.doc/distributed_orders.xml and http://www.sos-berlin.com/doc/en/scheduler.doc/xml/job_chain.xml#attribute_distributed
How can I set the cluster start option
During the installer you can choose cluster options.
For later configuration you must edit the file ./user_bin/jobscheduler_environment_variables.(sh|cmd).
Example: ./user_bin/jobscheduler_environment_variables.sh on Unix
SCHEDULER_CLUSTER_OPTIONS=-exclusive
Example: ./user_bin/jobscheduler_environment_variables.cmd on Windows
SET SCHEDULER_CLUSTER_OPTIONS=-exclusive
See also http://www.sos-berlin.com/doc/en/scheduler_installation.pdf
Cluster tab in JOC
If you open JOC of a JobScheduler which is member of a cluster then a Cluster tab is displayed.
Here you see a list of all cluster members.
Example: Backup Cluster
