Service-aware multi-queue node memory management system and method in cloud memory pool

By introducing service-aware multi-queue node memory management system and high-bandwidth parallel data exchange subsystem into the cloud memory pool, the cloud memory pool system is solved, and efficient memory resource utilization and data access efficiency are improved.

CN119728775AActive Publication Date: 2025-03-28SHANGHAI JIAOTONG UNIV
6 Cites 0 Cited by

Patent Information

Application Number
CN202411917607.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-24
Publication Date
2025-03-28
Estimated Expiration
2044-12-24

AI Technical Summary

Technical Problem

The existing cloud memory pool system is not aware of the access characteristics of application data, resulting in low management efficiency and is composed of only a single storage medium, resulting in excessive hardware costs.

Method used

A service-aware multi-queue node memory management system in cloud memory pool is proposed. Data access characteristics are pre-analyzed through the memory service offline analysis module, a hierarchical storage structure is constructed, and data offloading and prefetching is carried out through a high-bandwidth parallel data exchange subsystem to realize differentiated management and efficient data access.

Benefits of technology

Through service-aware memory management and high-bandwidth parallel data exchange, data access efficiency in cloud memory pools is improved, memory resource usage is reduced, memory resource utilization efficiency is improved, memory resource utilization is improved, and hardware costs are reduced.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a service-aware multi-queue node memory management system and method in a cloud memory pool, and the system comprises a memory service offline analysis module, a service-aware memory node management module and a high-bandwidth parallel data exchange subsystem, endowing a data unloading label to the memory service; the service-aware memory node management module constructs hierarchical storage, adds a data unloading label to the data entering the cloud memory pool according to the data unloading label of the service, performs differentiated management on the data according to the data unloading label, and controls unloading of the data; and the high-bandwidth parallel data exchange subsystem is used for data unloading I / O of data in the memory nodes. According to the method, a multi-level memory storage structure supporting high-parallel high-bandwidth data exchange is constructed, the memory is expanded by cloud storage to reduce the use of memory resources, the data characteristics of cloud memory services are analyzed, differentiated management of service data in a cloud memory pool is realized, the overall access efficiency of data is improved, the occupation of memory resources is further reduced, and the user experience is improved. The data center memory resource efficiency is improved.
Need to check novelty before this filing date? Find Prior Art