Passive, Streaming Inference of TCP Connection Structure for Network Server Management
We have developed a means of understanding the performance of servers in a network based on a real-time analysis of passively measured network traffic. TCP and IP headers are continuously collected and processed in a streaming fashion to first reveal the application-layer structure of all client/server dialogs ongoing in the network. Next, the representation of these dialogs are further processed to extract performance data such as response times of request-response exchanges for all servers. These data are then compared against archived historical distributions for each server to detect performance anomalies. Once found, these anomalies can be reported to server administrators for investigation.
Our method uncovers nontrivial performance anomalies in arbitrary servers with no instrumentation of the server nor even knowledge of the server’s function or configuration. Moreover, the entire process is completely transparent to servers and clients. We present the design of the tools used to perform this analysis, as well as a case study of the use of this method to uncover a significant performance anomaly in a UNC web portal.
KeywordsResponse Time Distribution Request Size Performance Anomaly Packet Capture Connection Vector
Unable to display preview. Download preview PDF.
- 1.Feldmann, A.: BLT: Bi-Layer Tracing of HTTP and TCP/IP. In: Proc. of WWW-9 (2000)Google Scholar
- 2.Olshefski, D.P., Nieh, J., Nahum, E.: ksniffer: determining the remote client perceived response time from live packet streams. In: Proc. OSDI, pp. 333–346 (2004)Google Scholar
- 3.Olshefski, D., Nieh, J.: Understanding the management of client perceived response time. In: ACM SIGMETRICS Performance Evaluation Review, pp. 240–251 (2006)Google Scholar
- 4.Smith, F., Hernández-Campos, F., Jeffay, K.: What TCP/IP Protocol Headers Can Tell Us About the Web. In: Proceedings of ACM SIGMETRICS 2001 (2001)Google Scholar
- 6.Hernández-Campos, F.: Generation and Validation of Empirically-Derived TCP Application Workloads. Ph.D. dissertation, Dept. of Computer Science, UNC Chapel Hill (2006)Google Scholar
- 7.Hernández-Campos, F., Jeffay, K., Smith, F.: Modeling and Generation of TCP Application Workloads. In: Proc. IEEE Int’l Conf. on Broadband Communications, Networks, and Systems (September 2007)Google Scholar
- 8.Broadhurst, R.E.: Compact Appearance in Object Populations Using Quantile Function Based Distribution Families. Ph.D. dissertation, Dept. of Computer Science, UNC Chapel Hill (2008)Google Scholar