分布式存储系统数据块管理方法、系统、设备及储存介质

By introducing placement groups to manage data blocks, the problems of metadata servers becoming a bottleneck and hash mapping limitations are solved, enabling more efficient data block location management and system expansion.

CN116737080BActive Publication Date: 2026-07-17TOYOU FEIJI ELECTRONICS

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
TOYOU FEIJI ELECTRONICS
Filing Date
2023-06-29
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

In existing distributed storage systems, metadata servers become a bottleneck, limiting system size and scalability, and hash mapping methods restrict the flexibility of data block distribution and storage balance.

Method used

Data blocks are managed using placement groups (PGs). Data blocks are allocated to placement groups through a metadata service, and placement group information is cached on the client side, reducing the load and interaction of the metadata service and enabling flexible storage resource management.

Benefits of technology

It enhances the scalability of distributed storage systems, reduces the load on metadata services, and improves storage resource utilization and the flexibility of data block location management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116737080B_ABST
    Figure CN116737080B_ABST
Patent Text Reader

Abstract

本发明公开了一种分布式存储系统数据块管理方法、系统、设备及储存介质,所述方法包括:将数据块分配到预设的归置组;将所述归置组存储到预设的数据块服务,并在所述归置组与所述数据块服务之间建立映射关系;基于元数据服务管理所述归置组与所述数据块服务之间的映射关系,并在客户端在启动时从所述元数据服务获取最新的所述归置组的信息和其对应的所述数据块服务信息。通过本公开的处理方案,可以高效灵活地管理数据块在集群中存储位置。
Need to check novelty before this filing date? Find Prior Art