Twig: Multi-Agent Task Management for Colocated Latency-Critical Cloud Services
Authors:
- 1 February 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 167-179
Abstract
Many of the important services running on data centres are latency-critical, time-varying, and demand strict user satisfaction. Stringent tail-latency targets for colocated services and increasing system complexity make it challenging to reduce the power consumption of data centres. Data centres typically sacrifice server efficiency to maintain tail-latency targets resulting in an increased total cost of ownership. This paper introduces Twig, a scalable quality-of-service (QoS) aware task manager for latency-critical services co-located on a server system. Twig successfully leverages deep reinforcement learning to characterise tail latency using hardware performance counters and to drive energy-efficient task management decisions in data centres. We evaluate Twig on a typical data centre server managing four widely used latency-critical services. Our results show that Twig outperforms prior works in reducing energy usage by up to 38% while achieving up to 99% QoS guarantee for latency-critical services.Keywords
This publication has 41 references indexed in Scilit:
- Heracles2015
- Human-level control through deep reinforcement learningNature, 2015
- Towards energy proportionality for large-scale latency-critical workloadsACM SIGARCH Computer Architecture News, 2014
- Quasar2014
- QoS-Aware scheduling in heterogeneous datacenters with paragonACM Transactions on Computer Systems, 2013
- Whare-map2013
- Bubble-fluxACM SIGARCH Computer Architecture News, 2013
- KnightShift: Scaling the Energy Proportionality Wall through Server-Level Heterogeneity2012
- Addressing shared resource contention in multicore processors via schedulingACM SIGPLAN Notices, 2010
- Reinforcement Learning: An IntroductionIEEE Transactions on Neural Networks, 1998