With the ubiquity of storage area network (SAN) devices, many specialized data management applications and hardware solutions are now emerging to exploit SAN infrastructure. Implementations of LAN-free backup are becoming more common and emerging trends such as server-free data transfer (Extended SCSI Third Party Copy) have received significant mind share. A current question revolves around the functional benefits of LAN-free versus server-free backup implementations using a SAN. This white paper will distinguish between the two methodologies, while explaining the ANSI standards behind both, to clarify the current functional reality of both implementations.
LAN-free data transfer allows a server to perform a backup over a Fiber Channel interface. The data moves from the SAN attached disk, through the application server and directly to a SAN attached storage device. This methodology takes full advantage of the Fiber Channel conduit and provides maximum throughput of 100 MB/second. As compared to traditional LAN backups, LAN-free backups provide substantial performance gains for large volume backup requirements. Meta-data packets containing information about the backed up data, travel across the LAN in this configuration, with minimal impact to LAN bandwidth.
Server-free backup takes LAN-free one step further, by lowering the involvement of the application server and reducing the amount of CPU, memory, and I/O consumption during the backup process. Conceptually, the data moves directly from the server's disk to a 'data mover' router, through the SAN to a SAN attached storage device. This methodology also takes full advantage of the Fibre Channel conduit and provides maximum throughput of 100 MB/second. This is made possible by Extended Copy commands along with a data management application to manage the data once it is moved to another device. First, the logical data is mapped to the physical block location. This is done through two steps: snapshot and logical disk object mapping. First, the snapshot image establishes a point in time reference for when the data is being backed up. The applications are quiesced to perform this process. After the server snapshot is made, the logical file names are linked to the actual physical blocks of data. The data is then moved across the SAN using Extended Copy command set. [Reference 4] The key advantage to server-free backup is the reduction of workload on the application server. For mission critical (24x7 availability) application servers, this technology will provide a great advancement for data management methods.
This was first published in March 2002