Abstract
The present disclosure provides systems and methods for using a unique identifier (or hash thereof) to determine where a workload should be scheduled, while also ensuring that failover events cause the minimum theoretical disruption. Additionally using the priority ordering of less-preferred (offline) nodes to determine the next-most-preferred node. This reduces the amount of randomness required to prioritize a workloads’ nodes while maintaining a fair distribution.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Anonymous, "Fair Hash Distribution with Minimum Failover Disruption", Technical Disclosure Commons, (April 25, 2022)
https://www.tdcommons.org/dpubs_series/5090