Disk array reconstruction task scheduling method and device, equipment and storage medium

Abstract

The invention discloses a disk array reconstruction task scheduling method and device, equipment and a storage medium. The method comprises the following steps: counting real-time performance indexes of a current disk array; the real-time performance index is a performance index represented by the number of currently executed first user read-write tasks; based on the real-time performance index and a preset performance index, whether the reconstruction task speed of the disk array needs to be adjusted currently is judged, so that a corresponding judgment result is obtained; the preset performance index is a performance index represented by the number of second user read-write tasks expected to be executed; and performing corresponding adjustment on the current reconstruction task speed of the disk array based on the judgment result and a preset reconstruction task scheduling rule. According to the method, the adaptive speed adjustment of the reconstruction task is carried out based on the real-time performance index and the preset performance index of the disk array, so that the performance requirement of a user for reading and writing the task is adapted, the configuration process is simplified, and the operation efficiency of a storage server system is further improved.

Description

technical field [0001] The invention relates to the technical field of computer storage, in particular to a disk array reconfiguration task scheduling method, device, equipment and storage medium. Background technique [0002] At present, in order to maintain its high availability so as not to stop the business when the hardware fails, the existing storage system mostly adopts hardware redundancy, that is, the same RAID (Redundant Arrays of Independent Disks, disk array) is placed on the run on two nodes. When the controllers on the two nodes are running normally, they process different services to maintain performance; if the controller on one node fails, the controller on the other node will take over the failure of the controller. business. [0003] Moreover, when the existing storage system is configured with RAID5 or RAID6 to run, the storage system supports recovering accidentally lost data through redundant data, and executes some tasks that need to be reconfigured ...

AI Technical Summary

Problems solved by technology

[0007] In view of this, the purpose of the present invention is to provide a disk array reconstruction task scheduling method, device, equipment, and storage medium, which can adapt to the performance requirements of user read and write tasks, and schedule background reconstruction tasks based on real-time performance indicators. This simplifies the configuration process, further improves the operating efficiency of the storage server system, and solves the problem of difficulty in setting the target value in the scenario of uneven performance during the execution of the reconstruction task.

Images