Krysha: Cost-Efficient Resource Orchestration for Geo-Distributed Serverless Microservices
Yuqiu Zhang, Hans-Arno Jacobsen
Abstract
The convergence of microservice architectures and serverless computing promises an elastic and cost-efficient model for modern cloud applications that often span multiple geo-distributed regions. However, prevailing serverless orchestrators that prioritize resource utilization or simple cold-start mitigation often prove suboptimal concerning SLO compliance and cost-efficiency in this emerging use case. In this paper, we present Krysha, an adaptive orchestration framework that jointly optimizes function scheduling and resource allocation for geo-distributed serverless microservices. Krysha employs a novel bi-level scheduling strategy: global-level early-binding to regions for fast function dispersion, coupled with regional-level late-binding to compute nodes for optimized resource use and cost. Moreover, Krysha achieves fine-grained resource allocation by decoupling CPU and memory provisioning and applying in-place vertical scaling on individual function instances. These capabilities are guided by a comprehensive cost model and practical online optimization techniques. Our extensive evaluation shows that Krysha can achieve up to 74.7% cost savings in scaled deployments compared to state-of-the-art alternatives while maintaining SLO requirements.
Ask Lune
Know where this paper stands in minutes, not an afternoon.
Lune can read the top-tier papers that cite it and the ones closest to it, and tells you what it claims, what came after and where it falls short, each point cited to the paper it comes from. No skimming, no AI slop.
Related papers
- SPES: Towards Optimizing Performance-Resource Trade-Off for Serverless FunctionsCheryl Lee, Zhouruixin Zhu, Tianyi Yang, Yintong Huo et al.ICDE 2024 · 13 citations
- Demeter: Fine-grained Function Orchestration for Geo-distributed Serverless AnalyticsXiaofei Yue, Song Yang, Liehuang Zhu, Stojan Trajanovski et al.INFOCOM 2024 · 13 citations
- StepConf: SLO-Aware Dynamic Resource Configuration for Serverless Function WorkflowsZhaojie Wen, Yishuo Wang, Fangming LiuINFOCOM 2022 · 72 citations
- Unifying serverless and microservice workloads with SigmaOSAriel Szekely, Adam Belay, Robert Morris, M. Frans KaashoekSOSP 2024 · 11 citations
- SPRIGHT: extracting the server from serverless computing! high-performance eBPF-based event-driven, shared-memory processingShixiong Qi, Leslie Monis, Ziteng Zeng, Ian-Chin Wang et al.SIGCOMM 2022 · 85 citations
