Chapter 5. HETEROGENEOUS DISK PLATFORM SM SERVERS

To achieve the high bandwidth and massive storage required for multi-user SM servers, disk drives are commonly combined into disk arrays to support many simultaneous I/O requests, as described in Chapter 3. Such large-scale systems potentially suffer from two limitations that might introduce heterogeneity into their storage disk array. First, disks are mechanical devices that can fail. We will introduce the fault characteristics of disks and fault-tolerance techniques in Chapter 6. Because the technological trend for magnetic disk drives is one of annual increase in both performance and storage capacity (40% to 60% annually), it is usually more cost-effective to replace a failed disk with a new model (there is a 50% to 100% annual decrease in storage cost [83]). Moreover, in the fast-paced disk industry, the corresponding model may be unavailable because it was discontinued by the manufacturer. Second, if the disk array needs to be expanded due to increased demand of either bandwidth or storage capacity, it is usually most cost-effective to add current-generation disks. Hence, a SM server should manage these heterogeneous resources intelligently in order to maximize their utilization and to guarantee jitter-free video and audio rendering.

Only a few multi-disk designs and implementations to display SM from heterogeneous storage systems have been reported in the research literature. They can broadly be classified into two groups: (1) designs that partition a heterogeneous storage system into multiple, homogeneous subservers, and (2) designs that present a virtual homogeneous view on top of the physical heterogeneity. We will consider the two groups in turn, in Section 5.1 and in Section 5.2. Subsequently, in Section 5.3, we extend our discussion to multizone disk drives. Finally, in Section 5.4, we present our conclusions.