Method for remote copying between multi-control shared memory systems

Abstract

The invention discloses a method for remote copying between multi-control shared memory systems. The method includes the following steps: a first node in a node cluster of a first multi-control memory system executes a remote copying service, and performs remote copying of data with a second multi-control memory system; a cluster resource manager pacemaker adds service resources iufs_sync corresponding to the remote copying service to cluster resource management; when a fault occurs in the first node, the cluster resource manager pacemaker automatically migrates the service resources iufs_sync from the first node to a second node which normally runs in the node cluster; and the second node executes the remote copying service corresponding to the service resources iufs_sync. The method realizes a guarantee for efficiency and continuous operation of the remote copying service, and eliminates a single-point fault.

Description

technical field [0001] The invention relates to the technical field of remote replication, in particular to a method for remote replication among multi-control shared storage systems. Background technique [0002] At present, remote replication is to copy product data to devices in remote locations for the purpose of data protection or data disaster recovery. For remote replication between multi-controller shared storage systems, considering that replication tasks may be performed on multiple nodes at the same time It will cause data inconsistency and the occupation of network bandwidth by running multiple replication tasks at the same time. The remote replication service is usually completed by a single node, which can be any node in the cluster system. If the node that is executing the replication task appears Downtime or network interruption will cause the remote replication service between systems to be abnormal, that is, the system single point of failure. At this time,...

AI Technical Summary

Problems solved by technology

[0002] At present, remote replication is to copy product data to devices in remote locations for the purpose of data protection or data disaster recovery. For remote replication between multi-controller shared storage systems, considering that replication tasks may be performed on multiple nodes at the same time It will cause data inconsistency and the occupation of network bandwidth by running multiple replication tasks at the same time. The remote replication service is usually completed by a single node, which can be any node in the cluster system. If the node that is executing the replication task appears Downtime or network interruption will cause the remote replication service between systems to be abnormal, that is, the system single point of failure. At this time, the remote replication in the multi-controller shared storage system cannot continue, and the remote replication is interrupted and cannot continue when the failure occurs The remote copy process, the efficiency of remote copy is affected

Images