.png){kind=icon}
返回
A Configurable Model-Based Reinforcement Learning Framework for Disaggregated Storage Systems
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2023.3244388.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
With the rapid growth of data-intensive jobs and the use of different hardware in storage, disaggregated storage architecture systems are being used to improve the operational cost efficiency of data centers. The hardware heterogeneity and mixed configurations of disaggregated storage systems, along with the diversity of workloads, often make it difficult for administrators to operate them optimally. In this work, we investigate model-based reinforcement learning (RL) schemes to develop automated system operations and maintain the storage performance across various system settings and workloads in self-managed storage systems. Specifically, we propose a novel configurable model structure in which a system environment is abstracted with a two-level hierarchy of storage devices and a platform and thus the environment can be reconfigured according to a given system specification. Using that novel model structure, we implement a configurable model-based RL framework CoMoRL by which RL agents are trained through model variants that represent a variety of storage system specifications; thus, their learned management policy can be highly robust to the diverse operation conditions of real-world storage systems. We evaluate our CoMoRL framework using a storage cluster that relies on NVMe-oF devices and demonstrate that the framework can be adapted to different scenarios such as volume placement scenarios with Kubernetes and primary affinity control scenarios with Ceph. The learned management policy outperforms an IOPS-based heuristic method and a model-based method by 0.7%similar to 5.1% and 11.8%similar to 29.7%, respectively, for various Kubernetes system specifications, and by 1.6%similar to 5.6% and 8.2%similar to 16.5%, respectively, for various Ceph system specifications, without requiring model and policy retraining. This zero-shot adaptation superiority of our framework makes it possible to realize RL-based self-managing storage systems in data centers with frequent system changes.
Keyword:
Model-based reinforcement learning
configurable model
meta learning
policy adaptation
data placement
disaggregated storage
heterogeneous storage
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Succinylated copper, zinc superoxide dismutase. A novel approach to the problem of active subunits琥珀酰化铜，锌超氧化物歧化酶。一种解决活性亚基问题的新方法.png)
Biochemistry
BiochemistryIF0
PREAI
分享收藏Antigen-Presenting Cells in Human Endometrium During the Menstrual Cycle Compared to Early Pregnancy
PREAI
分享收藏PRS: A Pattern-Directed Replication Scheme for Heterogeneous Object-Based StoragePRS: 一种面向异构对象存储的模式定向复制方案
OAAI
OAAI分享收藏Cognitive Predictors of Obsessive–Compulsive Symptoms in Adolescence: A Preliminary Investigation
PREAI
分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏
查看更多内容