Exploiting Wide-Area Resource Elasticity With Fine-Grained Orchestration for Serverless Analytics
- 4 November 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Networking
- Vol. 33 (1) , 398-413
Abstract
With the flourishing of global services, low-latency analytics on large-volume geo-distributed data has been a regular requirement for application decision-making. Serverless computing, with its rapid function start-up and lightweight deployment, provides a compelling way for geo-distributed analytics. However, existing research focuses on elastic resource scaling at the stage granularity, struggling to heterogeneous resource demands across component functions in wide-area settings . The neglect potentially results in the cost inefficiency and Service Level Objective (SLO) violations. In this paper, we advocate for fine-grained function orchestration to exploit wide-area resource elasticity . We thereby present Demeter , a fine-grained function orchestrator that saves job execution costs for geo-distributed serverless analytics while ensuring SLO compliance. By learning from volatile and bursty environments, Demeter jointly makes per-function placement and resource allocation decisions using a well-optimized multi-agent reinforcement learning algorithm with a pruning mechanism. It prevent the irreparable performance loss by function congestion control. Ultimately, we implement Demeter and evaluate it with the realistic workloads. Experimental results reveal that Demeter outperforms the baselines by up to 46.6% on cost, while reducing SLO violation by over 23.7% and bringing it to below 15%.Keywords
Funding Information
- National Natural Science Foundation of China (62472028, 62172038)
- Beijing Natural Science Foundation (4232033)
- National Key Research and Development Program of China (2023YFB3107300)
- Yunnan provincial major science and technology special plan project (202302AD080003)
- National Natural Science Foundation of China (62372045, 62072040)
- Horizon Europe CODECO project (101092696)
- Horizon Europe COVER project (101086228)
This publication has 33 references indexed in Scilit:
- Demeter: Fine-grained Function Orchestration for Geo-distributed Serverless Analytics2024
- Stateful Serverless Application Placement in MEC With Function and State DependenciesIEEE Transactions on Computers, 2023
- Astrea:Auto-Serverless Analytics Towards Cost-Efficiency and QoS-AwarenessIEEE Transactions on Parallel and Distributed Systems, 2022
- StepConf: SLO-Aware Dynamic Resource Configuration for Serverless Function Workflows2022
- GOFS: Geo-distributed Scheduling in OpenFaaS2021
- Network Cost-Aware Geo-Distributed Data Analytics SystemIEEE Transactions on Parallel and Distributed Systems, 2021
- GlobalFlow: A Cross-Region Orchestration Service for Serverless Computing Services2019
- Optimizing cost for geo-distributed storage systems in online social networksJournal of Computational Science, 2018
- Scheduling Jobs across Geo-Distributed Datacenters with Max-Min FairnessIEEE Transactions on Network Science and Engineering, 2018
- Low Latency Geo-distributed Data AnalyticsACM SIGCOMM Computer Communication Review, 2015