4th USENIX Conference on File and Storage TechnologiesAbstract
Pp. 309322 of the Proceedings
I/O System Performance Debugging
Using Model-driven Anomaly Characterization
Kai Shen, Ming Zhong, and Chuanpeng Li, University of Rochester
Abstract
It is challenging to identify performance problems and
pinpoint their root causes in complex systems, especially
when the system supports wide ranges of workloads
and when performance problems only materialize under
particular workload conditions. This paper proposes
a model-driven anomaly characterization approach and
uses it to discover operating system performance bugs
when supporting disk I/O-intensive online servers. We
construct a whole-system I/O throughput model as the
reference of expected performance and we use statistical
clustering and characterization of performance anomalies
to guide debugging. Unlike previous performance
debugging methods offering detailed statistics at specific
execution settings, our approach focuses on comprehensive
anomaly characterization over wide ranges of workload
conditions and system configurations.
Our approach helps us quickly identify four performance
bugs in the I/O system of the recent Linux 2.6.10
kernel (one in the file system prefetching, two in the
anticipatory I/O scheduler, and one in the elevator I/O
scheduler). Our experiments with twoWeb server benchmarks,
a trace-driven index searching server, and the
TPC-C database benchmark show that the corrected kernel
improves system throughput by up to five-fold compared
with the original kernel (averaging 6%, 32%, 39%,
and 16% for the four server workloads).
- View the full text of this paper in HTML and PDF.
Until December 2006, you will need your USENIX membership identification in order to access the full papers. The Proceedings are published as a collective work, © 2005 by the USENIX Association. All Rights Reserved. Rights to individual papers remain with the author or the author's employer. Permission is granted for the noncommercial reproduction of the complete work for educational or research purposes. USENIX acknowledges all trademarks within this paper.
- If you need the latest Adobe Acrobat Reader, you can download it from Adobe's site.
|