QoS-Aware Resource Management for Multi-phase Serverless Workflows with Aquatope

Multi-stage serverless applications, i.e., workflows with many computation and I/O stages, are becoming increasingly representative of FaaS platforms. Despite their advantages in terms of fine-grained scalability and modular development, these applications are subject to suboptimal performance, resource inefficiency, and high costs to a larger degree than previous simple serverless functions. We present Aquatope, a QoS-and-uncertainty-aware resource scheduler for end-to-end serverless workflows that takes into account the inherent uncertainty present in FaaS platforms, and im-provesperformancepredictabilityandresourceefficiency.Aquatope usesasetofscalableandvalidatedBayesianmodelstocreatepre-warmedcontainersaheadoffunctioninvocations,andtoallocate appropriateresourcesatfunctiongranularitytomeetacomplex workflow’send-to-endQoS,whileminimizingresourcecost.Across adiversesetofanalyticsandinteractivemulti-stageserverlesswork-loads,Aquatopesignificantlyoutperformspriorsystems,reducing QoSviolationsby5 × , and cost by 34% on average and up to 52% compared to other QoS-meeting methods.