The origins of network server latency & the myth of connection scheduling
Pages 424 - 425
Abstract
We investigate the origins of server-induced latency to understand how to improve latency optimization techniques. Using the Flash Web server [4], we analyze latency behavior under various loads. Despite latency profiles that suggest standard queuing delays, we find that most latency actually originates from negative interactions between the application and the locking and blocking mechanisms in the kernel. Modifying the server and kernel to avoid these problems yields both qualitative and quantitative changes in the latency profiles -- latency drops by more than an order of magnitude, and the effective service discipline also improves.We find our modifications also mitigate service burstiness in the application, reducing the event queue lengths dramatically and eliminating any benefit from application-level connection scheduling. We identify one remaining source of unfairness, related to competition in the networking stack. We show that adjusting the TCP congestion window size addresses this problem, reducing latency by an additional factor of three.
References
[1]
M. Crovella, R. Frangioso, and M. Harchol-Balter. Connection scheduling in web servers. In Proc. of the 2nd USENIX Symp. on Internet Technologies and Systems (USITS'99), Boulder, CO, Oct. 1999.
[2]
M. Harchol-Balter, B. Schroeder, M. Agrawal, and N. Bansal. Size-based scheduling to improve web performance. ACM Transactions on Computer Systems, 21(2):207--233, May 2003.
[3]
J. Larus and M. Parkes. Using cohort-scheduling to enhance server performance. In USENIX 2002 Annual Technical Conference, pages 103--114, Monterey, CA, June 2002.
[4]
V. S. Pai, P. Druschel, and W. Zwaenepoel. Flash: An efficient and portable web server. In USENIX 1999 Annual Technical Conference, pages 199--212, Monterey, CA, June 1999.
[5]
Y. Ruan and V. S. Pai. The origins of network server latency & the myth of connection scheduling. Technical Report TR-694-04, Princeton University, 2004.
[6]
M. Welsh, D. E. Culler, and E. A. Brewer. SEDA: An architecture for well-conditioned, scalable Internet services. In Proc. of the 18th ACM Symp. on Operating System Principles, pages 230--243, Chateau Lake Louise, Banff, Canada, Oct. 2001.
Index Terms
- The origins of network server latency & the myth of connection scheduling
Recommendations
The origins of network server latency & the myth of connection scheduling
SIGMETRICS '04/Performance '04: Proceedings of the joint international conference on Measurement and modeling of computer systemsWe investigate the origins of server-induced latency to understand how to improve latency optimization techniques. Using the Flash Web server [4], we analyze latency behavior under various loads. Despite latency profiles that suggest standard queuing ...
Fine-grained latency and loss measurements in the presence of reordering
SIGMETRICS '11: Proceedings of the ACM SIGMETRICS joint international conference on Measurement and modeling of computer systemsModern trading and cluster applications require microsecond latencies and almost no losses in data centers. This paper introduces an algorithm called FineComb that can estimate fine-grain end-to-end loss and latency measurements between edge routers in ...
Fine-grained latency and loss measurements in the presence of reordering
Performance evaluation reviewModern trading and cluster applications require microsecond latencies and almost no losses in data centers. This paper introduces an algorithm called FineComb that can estimate fine-grain end-to-end loss and latency measurements between edge routers in ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
June 2004450 pagesISBN:1581138733DOI:10.1145/1005686- General Chair:
- E. G. Coffman,
- Program Chairs:
- Zhen Liu,
- Arif Merchant
Copyright © 2004 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 01 June 2004
Published in SIGMETRICS Volume 32, Issue 1
Check for updates
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- View Citations3Total Citations
- 339Total Downloads
- Downloads (Last 12 months)4
- Downloads (Last 6 weeks)0
Reflects downloads up to 18 Nov 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in