Open AccessPerformance optimization method for distributed storage system based on hybrid storage device
Author(s) -
Chen-han Wu
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1856/1/012001
Subject(s) - computer science , computer data storage , distributed data store , converged storage , information repository , file system , storage area network , throughput , big data , object storage , distributed computing , data access , database , operating system , wireless
In the era of big data and artificial intelligence, the storage data of data centers is growing rapidly. Big data storage systems with high-performance computing require high-speed data access and greater storage capacity. However, traditional storage technology based on hard disk media (HDDs) has been difficult to meet the current demand for high-performance storage, solid state drives (SSDs)’ cost will be a lot for storing massive amounts of data. Therefore, in response to the above problems, this paper proposes a hierarchical hybrid storage technology for distributed file system, including an adaptive file migration strategy and client caching mechanism. Through experimental verification, the proposed technology fully combines the high I/O throughput characteristics of SSDs and the large capacity characteristics of disks, thereby providing a cost-effective high-performance distributed storage solution, and when processing real-time data, it has higher access performance.