Download now Free registration required
Benchmarking is critical when evaluating performance, but is especially difficult for file and storage systems. Complex interactions between I/O devices, caches, kernel daemons, and other OS components result in behavior that is rather difficult to analyze. Moreover, systems have different features and optimizations, so no single benchmark is always suitable. The large variety of workloads that these systems experience in the real world also adds to this difficulty. In this paper, the authors survey 415 file system and storage benchmarks from 106 recent papers. They found that most popular benchmarks are flawed and many research papers do not provide a clear indication of true performance. They provide guidelines that they hope will improve future performance evaluations.
- Format: PDF
- Size: 545.9 KB