A data storage method and disk array

Abstract

The invention discloses a data storage method. The method comprises the steps that when write failure information returned by disks for cache data is received, a disk controller judges whether the time during which faults occurs in the disks is smaller than a preset first time threshold or not; if the time is smaller than the preset first time threshold, the disk controller keeps a state of a disk array unchanged and returns failure information to array caches, wherein the failure information is used for enabling the array caches to continuously store the cache data and resend the cache data to the disk controller according to a preset cache refreshing policy. During a disk fault time period, the disk controller repeatedly sends the failure information to the array caches, so the cache data can be repeatedly written into the disks, and after the disks are returned to normal, the cache data can be successfully stored in the disks. The disk array failure resulting from a large number of transient disk false medium errors is avoided, and monitoring video data is guaranteed to be stored continuously, completely and accurately.

Description

technical field [0001] The present invention relates to the field of communication technology, in particular to a data storage method, and in particular to a disk array. Background technique [0002] In the prior art, a storage server can manage a large number of disks through a SAS (Serial Attached SCSI, serial SCSI technology) controller. For example, in addition to a group of disks managed by the storage server itself, multi-level disk cabinets can be cascaded through SAS cables to manage all these disks, and are used to create arrays and provide services to the outside world. [0003] In actual application, it is found that since the stability and reliability of the underlying processing of the SAS controller and disk are uncontrollable, once a problem occurs, it will have a great impact on the upper storage software. In particular, in the application of the monitoring environment, due to comprehensive factors such as SAS controllers and disk links, a large number of di...

AI Technical Summary

Problems solved by technology

[0008] For such fake and short-lived large number of disk media errors at the bottom layer, the RAID software will deal with them according to the array level, but there will be a high probability that the command will fail to return, causing the array to become a failure state

In the monitoring environment, the monitoring video will not be able to continue to be stored, and the monitoring video will be lost, which will bring serious losses to the user.

Images