Failure processing method and system for multi-controller storage system

Abstract

The embodiment of the invention provides a failure processing method and system for a multi-controller storage system, wherein the method comprises following steps of sending an abnormal termination signal to the slave MCC (multi-controller communication) module in a slave controller when the slave controller transmits data to a master controller, and if an HA module detects that the master controller is in downtime; invoking the slave IOM module in the slave controller to stop transmitting the data after the MCC module receives the abnormal termination information; returning data failed to be written and transmitted to the slave IOM module; adding the data failed to be written and transmitted in the upper layer of a blocking queue by the slave IOM module; and blocking data which is not sent by an SCST module, wherein the SCST module sends the data in the blocking queue according to a preset sequence at intervals of preset time until the data in the blocking queue is written in a rear end disk by the master controller. According to the method and the system, the integrity of the written data and the stability of the multi-controller storage system are ensured, and relatively high data writing efficiency is realized.

Description

technical field [0001] The invention relates to the technical field of fault processing, in particular to a fault processing method and system for a multi-controller storage system. Background technique [0002] At present, in a multi-controller storage system, when the SCST module (host interface layer module) writes data to the back-end disk through the slave controller, it is necessary for the slave controller to first write the data sent by the SCST module to the The data that needs to be written to the back-end disk is sent to the main controller, and then the main controller writes the data that needs to be written to the back-end disk. However, in the current multi-controller storage system, if the master controller goes down during the process of sending data from the controller to it, the data transmission process on the master controller will be terminated due to the downtime, resulting in the need to write The imported data cannot continue to be written to the ba...

AI Technical Summary

Problems solved by technology

[0004] In view of this, an embodiment of the present invention provides a fault handling method and system for a multi-controller storage system to solve the problem of communication between master and slave controllers among multiple controllers by setting a timeout waiting processing mechanism in the prior art The problem may destroy the integrity of the written data and the stability of the multi-controller storage system. At the same time, it will cause too long waiting time and affect the data writing efficiency.

Images