NSDI '23 - Unlocking unallocated cloud capacity for long, uninterruptible workloads

Unlocking unallocated cloud capacity for long, uninterruptible workloads

Anup Agarwal, Carnegie Mellon University; Shadi Noghabi, Microsoft Research; Íñigo Goiri, Azure Systems Research; Srinivasan Seshan, Carnegie Mellon University; Anirudh Badam, Microsoft Research

Cloud providers auction off unallocated resources at a low cost to avoid keeping hardware idle. One such mechanism is Harvest VMs (HVMs). These VMs grow and shrink as the unallocated resources in a server change. While HVMs are larger in size and less prone to eviction compared to other …

auction azure carnegie mellon carnegie mellon university cloud cost hardware idle low microsoft research resources systems university workloads