I/O Latency in the Linux Storage Stack
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 bot...
| Other Authors: | |
|---|---|
| Format: | Others |
| Language: | English English |
| Published: |
Florida State University
|
| Subjects: | |
| Online Access: | http://purl.flvc.org/fsu/fd/FSU_FALL2017_Stephens_fsu_0071N_14270 |
| Summary: | 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. === A Thesis submitted to the Department of Computer Science in partial fulfillment of the requirements for the
degree of Master of Science. === Fall Semester 2017. === November 15, 2017. === IO, Latency, Linux, Stack, Storage === Includes bibliographical references. === An-I Andy Wang, Professor Directing Thesis; Zhi Wang, Committee Member; David Whalley, Committee
Member. |
|---|