Region Load Balancing 


Region Load Balancing manages the distribution of compute and storage resources across multiple cloud service provider (CSP) regions based on resource availability and region health data and is available to all users. In addition to the default load balancing, customers can specify additional region preferences, which helps minimize wait time and execution failure due to capacity constraints or ongoing issues with CSP data centers.

Each CSP region’s available capacity and current health state have major impacts on job waiting time and success rate. If capacity runs low, then a job will have to wait a long time before resources become available, or could even lose hardware after the execution starts. 

If a region is suffering operational issues, such as degraded hardware or networking overload, then the job’s execution performance and success rate will suffer as well. Region Load Balancing helps customers avoid those potential problems by sending jobs to CSP regions that have sufficient capacity and low error rate.

If a job or desktop is launched with an HPS attached, that HPS must always be already running and have its own region that the HPS cluster resides in. With region load balancing, the job or desktop using the HPS will be restricted to only run in the region that the HPS is already running in.

Using Region Load Balancing

By default, Rescale platforms specify a set of regions that compute can be distributed to. Additionally, Rescale platforms leverage dynamically calculated Capacity Health Scores to rank regions that can be selected to run compute.

Some customers may need to use specific regions. For example, customers may have license servers in a specific region or customers may have large workloads that require additional regions. In this case, customers can configure their own region preferences. The preferences can be set at user level, workspace level, or partner level. Rescale will give priority to customers preferences.

If a customer has specific compliance such as ITAR, that customer must use a specific region, such as US gov regions. In this case, customers should set the compliance level so that Region Load Balancing will not dynamically route compute to non-compliant regions.

How to enable Region Load Balancing

If you’d like to configure region load balancing for your organization, please reach out to Rescale Support.