干旱区生态环境知识资源中心(Arid): Oasis: Controlling Data Migration in Expansion of Object-based Storage Systems

Arid

DOI	10.1145/3568424
	Oasis: Controlling Data Migration in Expansion of Object-based Storage Systems
	Zhang, Yiming; Wang, Li; Gai, Shun; Ke, Qiwen; Li, Wenhao; Song, Zhenlong; Xue, Guangtao; Shu, Jiwu
通讯作者	Zhang, YM
来源期刊	ACM TRANSACTIONS ON STORAGE
ISSN	1553-3077
EISSN	1553-3093
出版年	2023
卷号	19 期号:1
英文摘要	Object-based storage systems have been widely used for various scenarios such as file storage, block storage, blob (e.g., large videos) storage, and so on, where the data is placed among a large number of object storage devices (OSDs). Data placement is critical for the scalability of decentralized object-based storage systems. The state-of-the-art CRUSH placement method is a decentralized algorithm that deterministically places object replicas onto storage devices without relying on a central directory. While enjoying the benefits of decentralization such as high scalability, robustness, and performance, CRUSH-based storage systems suffer from uncontrolled data migration when expanding the capacity of the storage clusters (i.e., adding new OSDs), which is determined by the nature of CRUSH and will cause significant performance degradation when the expansion is nontrivial. This article presents MapX, a novel extension to CRUSH that uses an extra time-dimension mapping (from object creation times to cluster expansion times) for controlling data migration after cluster expansions. Each expansion is viewed as a new layer of the CRUSH map represented by a virtual node beneath the CRUSH root. MapX controls the mapping from objects onto layers by manipulating the timestamps of the intermediate placement groups (PGs). MapX is applicable to a large variety of object-based storage scenarios where object timestamps can be maintained as higher-level metadata. We have applied MapX to the state-of-the-art Ceph-RBD (RADOS Block Device) to implement a migration-controllable, decentralized object-based block store (called Oasis). Oasis extends the RBD metadata structure to maintain and retrieve approximate object creation times (for migration control) at the granularity of expansion layers. Experimental results show that the MapX-based Oasis block store outperforms the CRUSH-based Ceph-RBD (which is busy in migrating objects after expansions) by 3.17x similar to 4.31x in tail latency, and 76.3% (respectively, 83.8%) in IOPS for reads (respectively, writes).
英文关键词	Object storage cluster expansion datamigration data placement CRUSH block storage system
类型	Article
语种	英语
收录类别	SCI-E
WOS记录号	WOS:000939530200002
WOS关键词	PERFORMANCE ; SERVICE ; OVERLAY ; CHORD
WOS类目	Computer Science, Hardware & Architecture ; Computer Science, Software Engineering
WOS研究方向	Computer Science
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/394930
推荐引用方式 GB/T 7714	Zhang, Yiming,Wang, Li,Gai, Shun,et al. Oasis: Controlling Data Migration in Expansion of Object-based Storage Systems[J],2023,19(1).
APA	Zhang, Yiming.,Wang, Li.,Gai, Shun.,Ke, Qiwen.,Li, Wenhao.,...&Shu, Jiwu.(2023).Oasis: Controlling Data Migration in Expansion of Object-based Storage Systems.ACM TRANSACTIONS ON STORAGE,19(1).
MLA	Zhang, Yiming,et al."Oasis: Controlling Data Migration in Expansion of Object-based Storage Systems".ACM TRANSACTIONS ON STORAGE 19.1(2023).