Author: Paul Griffith
Adaptec, Inc.
Why Choose SAS?
The topmost factor in choosing a storage subsystem for enterprise system development is reliability. Maintaining user access to valuable data reduces total IT costs and increases user productivity. Serial Attached SCSI, a serial bus architecture, has emerged to deliver higher levels of reliability than parallel SCSI for mission-critical, transactional applications that must be online around the clock with no data loss.
To ensure continuous data access when a disk drive fails, multiple initiators have long been used in enterprise computing to provide disk drive access to multiple hosts and host bus adapters or both – an approach that doesn’t work well in parallel technology configurations because doing so produces single points of failure that can block access to a device and ultimately to critical data.
A developer benefits from utilizing serial bus architectures that overcome this shortcoming in reliability by supporting a network of dedicated point-to-point device connections and eliminating the single point of failure. The connections also provide full bandwidth to each storage device to boost system performance. By contrast, multi-drop parallel bus architectures share total bandwidth among devices.
SAS Disk Drive Reliability Advantages
SAS topologies offer many different redundant pathways through multiple controllers and expanders to the disk drives to deliver the highest levels of reliability. SAS disk drives feature dual porting to provide redundant data paths, so they can be used to build high-availability systems with no single points of failure. Dual-ported SAS disks can connect to multiple expanders and controllers via a high-speed interconnect, providing a secondary redundant disk access path in case one connection fails. SAS disk drives provide additional system resilience via Self-Monitoring, Analysis and Reporting Technology (SMART) capability, optimized sequential addressing features, SCSI protocol native data integrity and error event handling capability.
SAS increases fault tolerance by using expanders to connect multiple devices to multiple initiators, which maintain concurrent operation to many devices. Commands can be sent down one link and data returned on another in a separate connection to further increase fault tolerance.
SAS expanders, in combination with dual-port SAS drives and SATA drives with two-port adapters, simplify the design of redundant systems for maximum fault tolerance. A new class of 2.5-inch SAS disk drives with dual porting enables fully fault-tolerant designs in new technically challenging, higher compute-density applications. (Dual-ported SAS drives in the standard 3.5-inch form factor are also available.) These highly scalable and reliable connections enable enterprise-level topologies that support multi-node clustering for automatic failover or load balancing vital for high-availability mission-critical applications. (See Figure 1)
Figure 1: Redundant SAS controllers enable fully fault tolerant designs
Conclusion
Today, most data centers use parallel storage technology like SCSI, but IT managers are looking to new serial technologies such as SAS for greater reliability. SAS combines point-to-point connections, expanders, dual porting and other capabilities to enable the design of highly fault-tolerant designs with redundant pathways.
