Maxtor D540X-4K manual Latency time and thus increases data throughput

Basic Principles of Operation

￿￿￿￿￿￿￿2GTHQTOCPEGIn a drive without￿$GPGHKVUDisCache, there is a delay during sequential reads because of the rotational latency, even if the disk actuator already is positioned at the desired cylinder. DisCache eliminates this rotational latency time (7.14 ms on average) when requested data resides in the cache.

Moreover, the disk must often service requests from multiple processes in a multitasking or multiuser environment. In these instances, while each process might request data sequentially, the disk drive must share time among all these processes. In most disk drives, the heads must move from one location to another. With DisCache, even if another process interrupts, the drive continues to access the data sequentially from its high-speed memory. In handling multiple processes, DisCache achieves its most impressive performance gains, saving both seek and latency time when desired data resides in the cache.

The cache can be flexibly divided into several segments under program control. Each segment contains one cache entry. A cache entry consists of the requested read data plus its corresponding prefetch data.

The requested read data takes up a certain amount of space in the cache segment. Hence, the corresponding prefetch data can essentially occupy the rest of the space within the segment. The other factors determining prefetch size are the maximum and minimum prefetch. The drive’s prefetch algorithm dynamically controls the actual prefetch value based on the current demand, with the consideration of overhead to subsequent commands.

￿￿￿￿￿￿GCFHead￿CPFand￿%[NKPFGTcylinder skewing￿5MGYKPIin the Maxtor D540X-4K AT hard disk drives minimize

￿*latency time and thus increases data throughput.

GCFHead￿5MGYKPIskewing reduces the latency time that results when the drive must switch read/ write heads to access sequential data. A head skew is employed such that the next logical sector of data to be accessed will be under the read/write head once the head switch is made, and the data is ready to be accessed. Thus, when sequential data is on the same cylinder but on a different disk surface, a head switch is needed but not a seek. Since the sequential head-switch time is well defined on the Maxtor D540X-4K drives, the sector addresses can be optimally positioned across track boundaries to minimize the latency time during a head switch. See Table 5-2.

￿￿￿￿￿￿￿%[NKPFGTCylinder￿5MGYKPIskewing is also used to minimize the latency time associated with a single- cylinder seek. The next logical sector of data that crosses a cylinder boundary is positioned on the drive such that after a single-cylinder seek is performed, and when the drive is ready to continue accessing data, the sector to be accessed is positioned directly under the read/write head. Therefore, the cylinder skew takes place between the last sector of data on the last head of a cylinder, and the first sector of data on the first head of the next cylinder. Since single-cylinder seeks are well defined on the Maxtor D540X-4K drives, the sector addresses can be optimally positioned across cylinder boundaries to minimize the latency time associated with a single-cylinder seek. See Table 5-2.

Maxtor D540X-4K 20.4/40.0/60.0/80.0 GB AT 5-11