Cambridge researchers developed Latency-Aware Group Scheduling (LAGS), a modified Linux kernel scheduler that increases Kubernetes cluster capacity by 10-20%. Unlike the Completely Fair Scheduler (CFS), which prioritizes fairness by rotating tasks equally, LAGS prioritizes completing shorter tasks first to reduce context

5m read time From cloudnativenow.com
Post cover image
Table of contents
CFS is Not Always ‘Fair’Kubernetes Workloads Hit DifferentAn Adjustment to the SchedulerA Multi-Core Scheduling ProblemNext Steps for a New SchedulerRelated

Sort: