Data caching method and device, server and caching medium

By dividing the cache list into multi-level segmented lists and caching data based on the number of accesses and the cache space status, the problem of low cache hit rate in existing technologies is solved, thereby improving the caching efficiency and service quality of RAID cards.

CN117251481BActive Publication Date: 2025-12-12INSPUR SUZHOU INTELLIGENT TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202311234640.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-09-22
Publication Date
2025-12-12
Estimated Expiration
2043-09-22

AI Technical Summary

Technical Problem

In existing technologies, caching methods based on the last access time of data result in a large amount of random data within the linked list, affecting the overall hit rate of the caching system and reducing the service quality of the RAID card.

Method used

The cache list is divided into multi-level segmented linked lists. The target data is cached into the corresponding segmented linked list according to the access frequency range. The access frequency of the target data is determined by using historical access information. The remaining state of the cache space is considered when caching, and data is inserted or replaced reasonably.

Benefits of technology

It improves cache hit rate, extends the residence time of frequently accessed data in the cache, and enhances the service quality and access performance of the RAID card.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117251481B_ABST
    Figure CN117251481B_ABST
Patent Text Reader

Abstract

The application relates to the technical field of data caching, and discloses a data caching method and device, a server and a caching medium. The data caching method comprises the following steps: acquiring the current access frequency of target data currently accessed; determining a target segmented linked list for caching the target data from continuous multi-level segmented linked lists based on the current access frequency, wherein different segmented linked lists correspond to different access frequency intervals, and each segmented linked list is arranged in a specified order according to the corresponding access frequency interval; if there is no idle caching space in the target segmented linked list, then caching the target data based on the caching space remaining state of a first segmented linked list, wherein the first segmented linked list is adjacent to the target segmented linked list, and the numerical range of the access frequency interval corresponding to the first segmented linked list is greater than the numerical range of the access frequency interval corresponding to the target segmented linked list. The application can reduce the probability of frequently accessed data being flushed out of the cache linked list, thereby improving the cache hit rate and the service quality.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Cache management method and device

    CN104077242A

  • Data replacement method of hierarchical storage system

    CN111427969A