A method, device and storage medium for releasing cache space

Abstract

The invention discloses a method for releasing a cache space, comprising the steps of: detecting the use frequency of data in the cache space allocated to users; integrating the data whose use frequency is less than a threshold into a first cache unit in the cache space in; lock the first cache unit; determine whether the transmission bandwidth corresponding to the user drops within a preset time period; The data in the unit is migrated to the mechanical hard disk, and the cache space is released. The invention also discloses a computer device and a readable storage medium. The scheme of the present invention integrates the data that users use less frequently in the cache space into a separate cache unit, and locks the cache unit, and at the same time detects whether the user efficiency is affected. If there is no impact, after a period of time, the locked The cache unit is released to maximize the utilization of cache resources.

Description

technical field [0001] The invention relates to the field of storage, in particular to a method, device and storage medium for releasing a cache space. Background technique [0002] As a new supercomputing method and service model, cloud computing is data-centric and is a data-intensive supercomputing. Cloud computing provides different business-level services for different user needs, divided into infrastructure, namely Services, platform as a service, software as a service, provide these services to multiple customers, that is, multiple users, among which infrastructure as a service (Iass) provides hardware infrastructure as a measurable server to customers. [0003] In the existing technology, such as figure 1 As shown, a multi-user cache system is designed based on the Iass layer, which requires fast transmission and processing. In order to solve the limitation of IO bandwidth in traditional architecture transmission, the IO bandwidth can be improved by caching accelera...

AI Technical Summary

Problems solved by technology

[0003] In the existing technology, such as figure 1 As shown, a multi-user cache system is designed based on the Iass layer, which requires fast transmission and processing. In order to solve the limitation of IO bandwidth in traditional architecture transmission, the IO bandwidth can be improved by caching acceleration, and the PMC RAID card maxcache is used. The technology configures SSD storage as a cache of traditional mechanical storage to store hot data. However, when users apply for resources, there will be errors in estimating the size of the cache space. During use, the following two scenarios will appear: redundant cache space and insufficient cache space , so it will cause low utilization of cache space and cannot be maximized

Images