IntroductionIt can also easily be seen that no other component follows this growth rate. Memory, RAM and storage are getting cheaper. However, what is not happening is that the performance of access time and resp decreases. increasing at an exponential rate. Looking specifically at magnetic disk technology, we see that disk density has improved by about 50% per year, almost quadrupling in three years. Access time has only improved by a third in 10 years. Super-fast processors and huge memories must be "powered" and a system is only as fast as its slowest component, currently the disk. In our analysis we will consider the advantages and disadvantages of currently available technologies and their impact on system performance and effectiveness. To narrow down this still very vast topic even further, we will focus our attention on standard Personal Computers. The reason is that 90% of the computers used in the world are of this type. Along the way we will try to demystify the difference between the interfaces currently used, EIDE (Enhanced Integrated Drive Electronics) and SCSI (Small Computer System Interface) and their cost-performance correlation. We will try to analyze the performance of different units through different benchmarks. The reason for using multiple benchmark programs is that performance bottlenecks may be easier to detect by comparing results from different benchmarks. Each benchmark tells part of the story, and together you can paint a more complete picture. The Art of Benchmarking Without a doubt, benchmarking is one of the most controversial topics in the computer industry. This is understandable, given the number of exaggerated performance claims that consumers are exposed to... half of the paper... mentioned in the introduction, the goal of this paper was to compare the performance of different disk drives using benchmarks . While we have focused our attention on the subsystem-level performance of the different drives, we have included results for the Winstone 97® benchmark suite. This was done to show the impact of disk drive performance on overall system performance. The reader should, however, exercise caution when reading Winstone 97® results. These results indicate the influence of the drive only if the benchmark was run on the same or identical system, except for the disk drive. This is because system-level performance is determined by many more factors than just the disk drive. The type of processor, amount of memory, operating system, system bus chipset, graphics accelerator and many others contribute to system performance.