High-Performance PCI RAID Applications and Solutions

In today's high-demand server environments, the loss of critical data due to a drive failure can translate into revenue loss. RAID (Redundant Array of Independent Disks) data storage reduces the chance of this kind of loss. RAID combines multiple inexpensive disk drives into an array of drives to deliver higher performance, capacity, and reliability than a single large drive. Data is distributed across the drives, which appear as a single logical device to the host computer (and to users). RAID storage is often implemented via the PCI (Peripheral Component Interconnect) bus, a common pathway for transferring information within computing and network devices. With PCI RAID, the RAID controller is located on a PCI card that is simply plugged into a server's PCI bus. PCI RAID cards that are available today offer a wide range of capabilities and features. Servers with PCI host-based RAID data storage and retrieval typically are dedicated to high-performance applications involving either large data transfers or a large number of sequential read/write transactions. Some examples include video servers, web servers, file servers, and servers dedicated to handling transaction processing. This paper identifies environments best suited to high-end PCI host-based RAID implementation. It also describes new advanced features, such as those found in the four-channel Adaptec SCSI RAID 5400S, a PCI controller that extends the benefits and capabilities of high-end PCI RAID. The paper also provides a comparative performance analysis of the Adaptec 5400S and the Mylex eXtremeRAID 2000, both comparably priced, four-channel, Ultra160 SCSI controllers designed for use in enterprise servers.

View Entire Paper | Previous Page | White Papers Search

If you found this page useful, bookmark and share it on: