Faster and Cheaper Serverless Computing on Harvested Resources

TLDR

Serverless computing is popular for its ease of programming, rapid elasticity, and fine‑grained billing, but its cost remains tied to the underlying VMs, prompting interest in using discounted spare resources to lower expenses. The authors employ Harvest VMs, which opportunistically consume unallocated CPU cores and may be evicted, and address the resulting challenges of VM evictions and fluctuating resources when running a serverless platform.

Abstract

Serverless computing is becoming increasingly popular due to its ease of programming, fast elasticity, and fine-grained billing. However, the serverless provider still needs to provision, manage, and pay the IaaS provider for the virtual machines (VMs) hosting its platform. This ties the cost of the serverless platform to the cost of the underlying VMs. One way to significantly reduce cost is to use spare resources, which cloud providers rent at a massive discount. Harvest VMs offer such cheap resources: they grow and shrink to harvest all the unallocated CPU cores in their host servers, but may be evicted to make room for more expensive VMs. Thus, using Harvest VMs to run the serverless platform comes with two main challenges that must be carefully managed: VM evictions and dynamically varying resources in each VM.