Continuous-action reinforcement learning for memory allocation in virtualized servers
Visualitza/Obre
10.1007/978-3-030-34356-9_2
Inclou dades d'ús des de 2022
Cita com:
hdl:2117/187687
Tipus de documentText en actes de congrés
Data publicació2019
EditorSpringer
Condicions d'accésAccés obert
Tots els drets reservats. Aquesta obra està protegida pels drets de propietat intel·lectual i
industrial corresponents. Sense perjudici de les exempcions legals existents, queda prohibida la seva
reproducció, distribució, comunicació pública o transformació sense l'autorització del titular dels drets
ProjecteEUROSERVER - Green Computing Node for European micro-servers (EC-FP7-610456)
COMPUTACION DE ALTAS PRESTACIONES VII (MINECO-TIN2015-65316-P)
EuroEXA - Co-designed Innovation and System for Resilient Exascale Computing in Europe: From Applications to Silicon (EC-H2020-754337)
BARCELONA SUPERCOMPUTING CENTER - CENTRO. NACIONAL DE SUPERCOMPUTACION (MINECO-SEV-2015-0493)
COMPUTACION DE ALTAS PRESTACIONES VII (MINECO-TIN2015-65316-P)
EuroEXA - Co-designed Innovation and System for Resilient Exascale Computing in Europe: From Applications to Silicon (EC-H2020-754337)
BARCELONA SUPERCOMPUTING CENTER - CENTRO. NACIONAL DE SUPERCOMPUTACION (MINECO-SEV-2015-0493)
Abstract
In a virtualized computing server (node) with multiple Virtual Machines (VMs), it is necessary to dynamically allocate memory among the VMs. In many cases, this is done only considering the memory demand of each VM without having a node-wide view. There are many solutions for the dynamic memory allocation problem, some of which use machine learning in some form.
This paper introduces CAVMem (Continuous-Action Algorithm for Virtualized Memory Management), a proof-of-concept mechanism for a decentralized dynamic memory allocation solution in virtualized nodes that applies a continuous-action reinforcement learning (RL) algorithm called Deep Deterministic Policy Gradient (DDPG). CAVMem with DDPG is compared with other RL algorithms such as Q-Learning (QL) and Deep Q-Learning (DQL) in an environment that models a virtualized node.
In order to obtain linear scaling and be able to dynamically add and remove VMs, CAVMem has one agent per VM connected via a lightweight coordination mechanism. The agents learn how much memory to bid for or return, in a given state, so that each VM obtains a fair level of performance subject to the available memory resources. Our results show that CAVMem with DDPG performs better than QL and a static allocation case, but it is competitive with DQL. However, CAVMem incurs significant less training overheads than DQL, making the continuous-action approach a more cost-effective solution.
CitacióGarrido, L.; Nishtala, R.; Carpenter, P. Continuous-action reinforcement learning for memory allocation in virtualized servers. A: International Conference on High Performance Computing. "High Performance Computing, ISC High Performance 2019 International Workshops: Frankfurt, Germany, June 16-20, 2019: revised selected papers". Berlín: Springer, 2019, p. 13-24.
ISBN978-3-030-34356-9
Versió de l'editorhttps://link.springer.com/chapter/10.1007/978-3-030-34356-9_2
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
Garrido et al.pdf | 1,149Mb | Visualitza/Obre |