San Implementation

1216 Words3 Pages

SAN implementation over Gigabit Ethernet

A Storage Area Network is virtualized storage.

A storage area network (SAN) is a dedicated, centrally managed, secure information infrastructure, which enables any-to-any interconnection of servers and storage systems.
A SAN can be configured to provide a nearly infinite pool of storage that you can grow and move between servers as they need it. The storage can be added to and removed without requiring the server to be rebooted. The services provided by the server continue to operate without interruption.
The primary purpose for implementing a SAN is to provide a large storage pool that multiple hosts could access. Common storage configurations involve direct attachment of storage to a host. This storage is only available for use by that host. If there were another host that needed storage, you would need to buy additional storage to install on that host. The host with excess capacity would not be able to share its storage with another host.
In a SAN, all networked devices share storage capacity as peer resources; they are not the exclusive property of any one server. You can use a SAN to connect servers to storage, Servers to each other, and storage to storage through hubs or switches. A SAN carries only I/O traffic between servers and doesn’t carry any general-purpose traffic such as e-mail. Storage area networks remove data traffic, like backup processes, from the production network giving IT managers a strategic way to improve system performance and application availability.
As SAN technology develops, it is growing beyond the use of any one kind of technology. A SAN can be configured to use a number of protocols such as IP or Fibre Channel over a network medium like Ethernet or ATM. FC over Ethernet supports up to 1.06 Mbps. Emerging standards that are still being defined include Gigabyte System Network(GSN) which promises full-duplex 6.4 Mbps over a 40 meter copper cable.
Storage area networks improve data access. Using Fibre Channel connections, SANs provide the high-speed network communications and distance needed by remote workstations and servers to easily access shared data storage pools. IT managers can more easily centralize management of their storage systems and consolidate backups, increasing overall system efficiency. The increased distances provided by Fibre Channel technology make it easier to ...

... middle of paper ...

... all of your different hosts and handle the conversion and routing of data between the servers and their virtual disks.

The phrase SAN implementation over Gigabit Ethernet is a misnomer. You are using FC or SCSI disks at all times. The SAN is implemented using the common Fibre Channel or SCSI technology. The hosts however would use a variety of methods to attach to the storage pool. The usual connection methods try to avoid introducing bottlenecks between the server and the storage pool. If you combine the different links from the servers together over a 1000Base switch, you would make better use of the available bandwidth to the storage.
Using Gigabit Ethernet in this way makes for an excellent low-cost connection to storage resources. Since many customers already have a Ethernet network in place the additional cost of the GSN capable switch is the only additional cost. Once the switch is attached to the SAN, the benefits of a SAN solution can be pushed out to more client computers in the company.

Bibliography

http://www.zdnet.com/eweek/reviews/1201/01gig.html#Reference

http://www.iol.unh.edu/consortiums/ge/index.html

http://www.cisco.com/warp/public/729/gigabit/index.shtml

More about San Implementation

Open Document