Affinity-aware Serverless Function Scheduling

TL;DR

This paper introduces aAPP, a language extension for affinity-aware scheduling in serverless platforms, demonstrating improved performance for affinity-dependent functions without added overhead in other scenarios.

Contribution

It presents aAPP, a novel declarative language extension that enables affinity-aware scheduling in FaaS platforms, validated through a prototype on Apache OpenWhisk.

Findings

aAPP improves performance in affinity-aware scenarios

No noticeable overhead in affinity-unaware scenarios

Prototype implementation on Apache OpenWhisk validates approach

Abstract

Functions-as-a-Service (FaaS) is a Serverless Cloud paradigm where a platform manages the scheduling (e.g., resource allocation, runtime environments) of stateless functions. Recent work proposed using domain-specific languages to express per-function policies, e.g., policies that enforce the allocation on nodes that enjoy lower latencies to databases and services used by the function. Here, we focus on affinity-aware scenarios, i.e., where, for performance and functional requirements, the allocation of a function depends on the presence/absence of other functions on nodes. We present aAPP, an extension of a declarative, platform-agnostic language that captures affinity-aware scheduling at the FaaS level. We implement an aAPP-based prototype on Apache OpenWhisk. Besides proving that a FaaS platform can capture affinity awareness using aAPP and improve performance in affinity-aware scenarios, we use our prototype to show that aAPP imposes no noticeable overhead in scenarios without affinity constraints.