Borg Paper (2015)

Back to Key Papers to Read

“Large-Scale Cluster Management at Google with Borg” (2015) — Verma et al.

Describes Borg, Google’s cluster manager that runs hundreds of thousands of jobs across multiple clusters. Key ideas: declarative job specification, efficient bin-packing, priority and preemption, allocs (resource reservations). Directly inspired the design of Kubernetes. Published a decade after Borg was already in production.


google-internal papers borg #2015