ACM Home Page
Please provide us with feedback. Feedback
Application performance pitfalls and TCP's Nagle algorithm
Full text PdfPdf (775 KB)
Source ACM SIGMETRICS Performance Evaluation Review archive
Volume 27 ,  Issue 4  (March 2000) table of contents
Pages: 36 - 44  
Year of Publication: 2000
ISSN:0163-5999
Authors
Greg Minshall  Siara Systems
Yasushi Saito  Department of Computer Science and Engineering, University of Washington
Jeffrey C. Mogul  Compaq Computer Corp. Western Research Lab., 250 University Ave., Palo Alto, CA
Ben Verghese  Compaq Computer Corp. Western Research Lab.
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 4,   Downloads (12 Months): 34,   Citation Count: 0
Additional Information:

abstract   index terms   collaborative colleagues   peer to peer  

Tools and Actions: Review this Article  
Save this Article to a Binder    Display Formats: BibTex  EndNote ACM Ref   
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/346000.346012
What is a DOI?

ABSTRACT

Performance improvements to networked applications can have unintended consequences. In a study of the performance of the Network News Transport Protocol (NNTP), the initial results suggested it would be useful to disable TCP's Nagle algorithm for this application. Doing so significantly improved latencies. However, closer observation revealed that with the Nagle algorithm disabled, the application was transmitting an order of magnitude more packets. We found that proper application buffer management significantly improves performance, but that the Nagle algorithm still slightly increases mean latency. We suggest that modifying the Nagle algorithm would eliminate this cost.


Collaborative Colleagues:
Greg Minshall: colleagues
Yasushi Saito: colleagues
Jeffrey C. Mogul: colleagues
Ben Verghese: colleagues

Peer to Peer - Readers of this Article have also read: