Distributed Autonomous Storage Resource Aggregation Method with Unified Namespace

Abstract

The invention provides a dispersed autonomous storage resource aggregation method with a unified name space, comprising the following steps: firstly, mounting physical resources on a stand-alone filesystem, providing mapping from a logic path to an actual address, and realizing aggregation of the physical storage resources; and then deploying a parallel storage cluster on the physical server deployed with the stand-alone file system, providing conversion mapping from a storage cluster read-write request to a stand-alone file system read-write request, and realizing aggregation of local storage resources; and finally, designing a name space mapping and file distribution algorithm on the constructed storage cluster, establishing a global name space, realizing global resource aggregation, and forming a unified storage space. A plurality of management nodes are deployed in order to realize high availability of a wide area storage resource aggregation architecture, a plurality of global metadata copies are maintained and managed, and a synchronization algorithm is adopted to maintain the consistency among the plurality of global metadata copies. The plurality of management nodes adopta peer-to-peer structure, so that load balancing and high availability are realized.

Description

Technical field: [0001] The invention discloses a decentralized autonomous storage resource aggregation method with a unified name space, relates to challenges faced by wide-area high-performance computing, and belongs to the technical field of computers. Background technique: [0002] At present, in the national high-performance computing environment, storage resources are widely dispersed and isolated and autonomous. Large-scale computing applications urgently need to aggregate and disperse storage resources to form a virtual data space, provide a unified resource access path, and support the unified management and application of decentralized autonomous storage resources. access. In the research field of wide-area storage resource aggregation methods, many scholars have carried out a lot of research, and summarized the following categories: wide-area storage resource aggregation methods for Internet applications, wide-area storage resource aggregation methods for distribu...

AI Technical Summary

Problems solved by technology

[0011] The main purpose of the invention is to provide a decentralized and autonomous storage resource aggregation method with a unified name space. Aiming at the problem that storage resources are scattered in a high-performance computing environment and cannot fully exert the aggregation effect, a decentralized and autonomous storage resource based on a unified name space is established. The aggregation method, based on the underlying rich resource management layer, establishes the top-level global thin resource management layer, and combines the physical location positioning service to realize the mapping conversion between the top-level unified naming and the bottom-level heterogeneous naming; for a single management node, it leads to a wide-area storage resource aggregation architecture High-availability issues, build multiple global metadata copies, and use synchronization algorithms to maintain consistency between multiple metadata copies to achieve high availability of wide-area storage resource aggregation architecture

Images