Advanced cluster management made easy

Workload Management

Bright Cluster Manager™ offers a choice of workload management systems, also known as queuing systems or queueing systems. A number of supported workload managers are integrated into Bright Cluster Manager and manageable through the cluster management GUI.

Integrated Workload Managers

The following workload management systemsqueuing systems or queueing systems are integrated in Bright Cluster Manager:

1. TORQUE Resource Manager — TORQUE (Terascale Open-Source Resource and QUEue Manager) is an open source, distributed resource manager originally based on OpenPBS. It has limited scheduling intelligence built in, which is why it is usually used in combination with the Maui Cluster Scheduler.
2. Maui Cluster Scheduler — Maui is a powerful open source job scheduler which can provide scheduling intelligence to TORQUE.
3. Grid Engine — Grid Engine is a powerful workload managerqueuing systems or queueing systems which includes both queuing and scheduling functionality.

We can optionally install and configure alternative workload managersqueuings systems or queueing systems with Bright Cluster Manager, such as Moab, LSF, PBS Pro, SLURM and LoadLeveler.

Workload Management Features

Both Grid Engine and Torque/Maui offer at least the following features:

1. Fairness policies — define what a cluster owner considers as a fair use of available resources.
2. Advanced reservation — guarantees the availability of a set of resources at a particular time.
3. Job priority policies and configurations — determines in which order jobs should be run to achieve some pre-defined fair-share policy.
4. Quality of Services (QoS) support — allows jobs, users or groups to receive special treatment based on privileges and fairness policies.
5. Multi-attribute fairshare — allows historical resource utilization information to be incorporated into job feasibility and priority decisions.
6. Configurable node allocation policies — allow a site to specify how available resources should be allocated to each job.
7. Multiple configurable backfill policies — allows a scheduler to make better use of available resources by running jobs out of order.
8. System diagnostic support — provides commands for diagnosing system behavior.
9. Allocation manager support and interface — manages resource allocations where a resource allocation grants a job the right to use a particular amount of resources (also known as allocation bank or CPU bank).
10. Resource utilization tracking and statistics — provides extensive accounting facilities which allow resource usage to be tracked by resources (i.e., compute nodes), jobs, users, and other objects.
11. Non-intrusive 'Test' modes — conducts scheduling cycles for testing as it would if running in normal or production mode, but without actually starting or modifying jobs.

Integration with the Cluster Management GUI

Through the GUI it is possible to view and manipulate jobs, and to configure the workload manager without having to learn its specific configuration commands or files. This screenshot shows the jobs currently running on the cluster. The blue buttons at the bottom are common commands for manipulating jobs.

Through the GUI it is possible to view and manipulate jobs, and to configure the workload manager without having to learn its specific configuration commands or files.

The cluster management GUI offers a single and consistent interface to all available cluster management functionalities. This includes the workload manager. Through the GUI it is possible to view and manipulate jobs, and to configure the workload managerqueuing system or queueing system without having to learn its specific configuration commands or files.

The following commands are available in the GUI for queues:

1. Add — add a new queue.
2. Remove — remove the selected queue.
3. Modify — modify various properties of the selected queue.

The following commands are available in the GUI for jobs:

1. Show — show detailed properties of the selected job.
2. Remove — remove the selected job from the queue.
3. Hold — put the selected job on hold.
4. Release — release the selected job that was previously put on hold.
5. Suspend — suspend the selected job.
6. Resume — resume the selected job that was previously suspended.