What’s New with Auto-Scaler in Bright Cluster Manager 9.1


By Robert Stober | April 01, 2021 |



Bright Cluster Manager includes a feature called Auto Scaler that dynamically scales HPC workload management (WLM) and Kubernetes clusters based on workload demand, subject to configured policies. Auto Scaler is the engine that drives the hybrid cloud. It can repurpose and/or re-image on-prem and edge nodes and it can automatically extend the cluster to the cloud. 

Essentially, Bright Auto Scaler can be thought of as a top-level meta-scheduler that takes care of assigning resources to workload management systems.

Bright Cluster Manager 9.1 includes enhancements to auto-scaling that improve performance, provide more granular control, and improved ease of use. Enhancements include:

  • Faster reallocation and repurposing of nodes that share a common software image
  • The ability to control and prioritize which cluster resources can be used by different jobs
  • The ability to leverage priorities and job resource requirements from workload managers to determine node allocations
  • Easier setup of auto-scaling via a wizard

These new features will provide better control over prioritizing workload.

With Bright Cluster Manager’s auto-scaling capability, organizations can create a flexible and dynamic high-performance computing infrastructure that spans from edge-to-core-to-cloud and can adapt to changing needs of both users and the organization. For example, repurposing a node can be done automatically based on workload within seconds. Auto Scaler will also do a better job of looking for special resources that a job has requested. We've also added a setup wizard that will make it easier to configure Auto Scaler to meet your needs.

As a result of these enhancements, computing resources can be redirected and aggregated to support high-priority jobs when needed, and virtual resources from the public cloud or VMware can be added and subtracted to meet outlier demands when needed.

Bright’s auto-scaling capability eliminates silos in high-performance infrastructure, increases and optimizes overall compute utilization and improves and accelerates responsiveness to end user’s needs. 

To learn more about our auto-scaling enhancements, please watch this demo or get in touch.