Fault disk processing method and device

Abstract

The invention discloses a fault disk processing method and device, and relates to the technical field of computers. According to one specific embodiment, the method comprises the steps that state information of a disk in a data node is obtained, the state information comprises read-write frequency and disk busy degree, and the disk busy degree is used for indicating the proportion occupied by read-write operation in operation of the data node; determining a fault disk according to the read-write frequency, the disk busy degree and a read-write frequency threshold corresponding to the disk; and initiating a disk unloading command to the data node corresponding to the fault disk to unload the fault disk. According to the implementation mode, the faulty disk can be automatically recognized and unloaded, the read-write operation of other normal disks in the current data node is not influenced in the processing process of the faulty disk, the processing time of the faulty disk is shortened, the processing cost of the faulty disk is reduced, the read-write operation efficiency of the disk is improved, and the processing efficiency of the faulty disk is improved. And the disk utilization rate is improved.

Description

technical field [0001] The invention relates to the technical field of computers, in particular to a processing method and device for a faulty disk. Background technique [0002] The distributed file system provides data reading and writing operations through the disk under the data node (DataNode), which provides convenience for data storage and sharing. In order to ensure the efficiency of disk read and write operations, it is necessary to identify and execute disk kick operations in a timely manner, where disk kick refers to unloading or removing a specified disk from a data node. [0003] In the course of realizing the present invention, the inventor finds that there are at least the following problems in the prior art: [0004] 1. In the existing faulty disk processing method, the faulty disk is often found through the monitoring system or manual inspection, and the automatic identification and processing of the faulty disk cannot be realized, resulting in low processi...

AI Technical Summary

Problems solved by technology

[0004] 1. In the existing processing methods for faulty disks, faulty disks are often found through monitoring systems or manual inspections, which cannot automatically identify and process faulty disks, resulting in low processing efficiency and high processing costs for faulty disks;

[0005] 2. When the existing faulty disk is processed, it is necessary to suspend the read and write operations of all disks in the data node, and the entire processing cycle is long, so that the normal disk in the data node cannot work normally during the process of kicking the disk, resulting in reduced distribution. The read and write operation efficiency of each disk in the file system reduces the utilization rate of the disk

Images