The present invention provides a storage system capable of having a large-scale configuration for maintaining a write access response speed and reliability upon an occurrence of a failed cache and its control method. Plural clusters that control a disk drive connected thereto and have a cache memory are connected to one another through a cross coupling network, and write data in the cache memory of another cluster is mutually made redundant in the cache memories in two clusters that jointly use the same disk drive. When a failure occurs in the cache memory, the cluster that uses the disk drive jointly with the cluster having the cache memory in which the failure occurs performs processing for getting access to the disk drive performed by the cluster having the cache memory in which the failure occurs, and the other normally-operated cluster is caused to perform to only make redundant the write data in the cache memory in its cluster.

 
Web www.patentalert.com

< Method, system, and program for improved throughput in remote mirroring systems

< Systems and methods for striped storage migration

> Method for transaction command ordering in a remote data replication system

> Nonvolatile semiconductor memory device and method for providing security for the same

~ 00237