In this paper, we design and implement a data disaster recovery system based on storage-virtualization. The data disaster
recovery system implements its function through the collaboration of multiple sites in wide-area scope. Each site is an
independent data center and data disaster recovery unit. The construction of each site is based on storage-virtualization
gateway which is a storage-virtualization platform supporting storage multi-protocol. Therefore, through storagevirtualization
gateway's implementation of data replication, failure detection, service switch/takeover among the
multiple sites, data disaster recovery could be implemented.
According to both the Fibre Channel (FC) Storage Area Network (SAN) switch and Fabric Application Interface Standard
(FAIS) mechanism, an iSCSI storage controller is put forward and based upon it, an internet Small Computer
System Interface (iSCSI) SAN construction strategy for disaster recovery (DR) is proposed and some multiple
sites replication models and a closed queue performance analysis method are also discussed in this paper.
The iSCSI storage controller lies in the fabric level of the networked storage infrastructure, and it can be used
to connect to both the hybrid storage applications and storage subsystems, besides, it can provide virtualized
storage environment and support logical volume access control, and by cooperating with the remote peerparts,
a disaster recovery storage system can be built on the basis of the data replication, block-level
snapshot and Internet Protocol (IP) take-over functions.