Some of the material in is restricted to members of the community. By logging in, you may be able to gain additional access to certain collections or items. If you have questions about access or logging in, please use the form on the Contact Page.
As storage device performance increases, the lifespan of an I/O request becomes throttled more-so by data path traversal than physical disk access. Even though many computer performance analysis tools exist, a surprisingly small amount of research has been published documenting bottlenecks throughout the Linux storage stack. What research has been published focuses on results found through tracing, glossing over how the traces were performed. This work details my process of developing a refined tracing method, what that method is, and how the research can be applied to measure I/O latency at any layer of the Linux storage stack. Sample results are given after examining the filesystem layer, the block layer, and the memory management system. Among these three components of the storage stack, the filesystem layer is responsible for the longest duration of an I/O request's lifespan.
