An evaluation of TCP splice benefits in web proxy servers

This study is the first to evaluate the performance benefits of using the recently proposed TCP Splice kernel service in Web proxy servers. Previous studies show that splicing client and server TCP connections in the IP layer improves the throughput of proxy servers like firewalls and content routers by reducing the data transfer overheads. In a Web proxy server, data transfer overheads represent a relatively large fraction of the request processing overheads, in particular when content is not cacheable or the proxy cache is memory-based. The study is conducted with a socket-level implementation of TCP Splice. Compared to IP-level implementations, socket-level implementations make possible the splicing of connections with different TCP characteristics, and improve response times by reducing recovery delay after a packet loss. The experimental evaluation is focused on HTTP request types for which the proxy can fully exploit the TCP Splice service, which are the requests for non-cacheabl.content and SSL tunneling. The experimental testbed includes an emulated WAN environment and benchmark applications for HTTP/1.0 Web client, Web server, and Web proxy running on AIX RS/6000 machines. Our experiments demonstrate that TCP Splice enables reductions in CPU utilization of 10-43% of the CPU, depending on file sizes and request rates. Larger relative reductions are observed when tunneling SSL connections, in particular for small file transfers. Response times are also reduced by up to 1.8sec.

[1]  Chengjie Liu,et al.  Maintaining strong cache consistency in the World-Wide Web , 1997, Proceedings of 17th International Conference on Distributed Computing Systems.

[2]  Jeffrey S. Chase,et al.  End system optimizations for high-speed TCP , 2001, IEEE Commun. Mag..

[3]  Anja Feldmann,et al.  Performance of Web proxy caching in heterogeneous bandwidth environments , 1999, IEEE INFOCOM '99. Conference on Computer Communications. Proceedings. Eighteenth Annual Joint Conference of the IEEE Computer and Communications Societies. The Future is Now (Cat. No.99CH36320).

[4]  Daniel M. Dias,et al.  High-Performance Web Site Design Techniques , 2000, IEEE Internet Comput..

[5]  D.A. Menasce,et al.  Scaling for e-business , 2000, Proceedings 8th International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (Cat. No.PR00728).

[6]  Craig E. Wills,et al.  N for the price of 1: bundling web objects for more efficient content delivery , 2001, WWW '01.

[7]  David A. Maltz,et al.  TCP Splice for application layer proxy performance , 1999, J. High Speed Networks.

[8]  Sandy Irani,et al.  Cost-Aware WWW Proxy Caching Algorithms , 1997, USENIX Symposium on Internet Technologies and Systems.

[9]  Evangelos P. Markatos,et al.  Secondary Storage Management for Web Proxies , 1999, USENIX Symposium on Internet Technologies and Systems.

[10]  Sampath Rangarajan,et al.  On the Performance of TCP Splicing for URL-Aware Redirection , 1999, USENIX Symposium on Internet Technologies and Systems.

[11]  Craig E. Wills,et al.  N for the Price of 1: Bundling Web Objects for More Eecient Content Delivery 1 , 2000 .

[12]  David A. Maltz,et al.  MSOCKS: an architecture for transport layer mobility , 1998, Proceedings. IEEE INFOCOM '98, the Conference on Computer Communications. Seventeenth Annual Joint Conference of the IEEE Computer and Communications Societies. Gateway to the 21st Century (Cat. No.98.

[13]  Peter Druschel,et al.  Measuring the capacity of a Web server under realistic loads , 1999, World Wide Web.

[14]  Christopher Allen,et al.  The TLS Protocol Version 1.0 , 1999, RFC.

[15]  RubensteinDan,et al.  Detecting shared congestion of flows via end-to-end measurement , 2002 .

[16]  Willy Zwaenepoel,et al.  IO-Lite: a unified I/O buffering and caching system , 1999, TOCS.

[17]  Peter,et al.  Io-lite: a Uniied I/o Buuering and Caching System , 1997 .

[18]  Guerney D. H. Hunt,et al.  Network Dispatcher: A Connection Router for Scalable Internet Services , 1998, Comput. Networks.

[19]  Michael Dahlin,et al.  Engineering server-driven consistency for large scale dynamic Web services , 2001, WWW '01.

[20]  Vern Paxson.  End-to-end internet packet dynamics , 1999, TNET.

[21]  Azer Bestavros,et al.  Popularity-aware greedy dual-size Web proxy caching algorithms , 2000, Proceedings 20th IEEE International Conference on Distributed Computing Systems.

[22]  John H. Hartman,et al.  Optimizing TCP forwarder performance , 2000, TNET.

[23]  Vern Paxson,et al.  End-to-end Internet packet dynamics , 1997, SIGCOMM '97.

[24]  Donald F. Towsley,et al.  Detecting shared congestion of flows via end-to-end measurement , 2000, SIGMETRICS '00.

[25]  Srinivasan Seshan,et al.  Improving TCP/IP performance over wireless networks , 1995, MobiCom '95.

[26]  Srinivasan Seshan,et al.  The effects of wide-area conditions on WWW server performance , 2001, SIGMETRICS '01.