1 views collected around this technical thread.
This article details Bilibili's offline big‑data cluster challenges, the mixed‑deployment architecture that combines offline and online resources, the Amiya service's over‑commit and eviction mechanisms, performance optimizations, monitoring strategies, and future plans to further improve resource utilization and scheduling.
This article examines Borg’s strategies for efficient machine utilization, fine‑grained resource allocation, and isolation—including cell compaction, resource reclamation, and performance isolation—provides experimental results and comparisons, and distills lessons learned to inform the design of cloud‑native systems such as Kubernetes.
The article reviews Google’s Borg paper, highlighting how Borg distinguishes production and non‑production tasks, manages jobs and containers, improves utilization through mixed‑workload scheduling, enforces isolation via overload and over‑commitment controls, and compares Borg’s approach to other cluster managers.