Appraising the delay accuracy in browser-based network measurement

Conducting network measurement in a web browser (e.g., speedtest and Netalyzr) enables end users to understand their network and application performance. However, very little is known about the (in)accuracy of the various methods used in these tools. In this paper, we evaluate the accuracy of ten HTTP-based and TCP socket-based methods for measuring the round-trip time (RTT) with the five most popular browsers on Linux and Windows. Our measurement results show that the delay overheads incurred in most of the HTTP-based methods are too large to ignore. Moreover, the overheads incurred by some methods (such as Flash GET and POST) vary significantly across different browsers and systems, making it very difficult to calibrate. The socket-based methods, on the other hand, incur much smaller overhead.Another interesting and important finding is that Date.getTime(), a typical timing API in Java, does not provide the millisecond resolution assumed by many measurement tools on some OSes (e.g., Windows 7). This results in a serious under-estimation of RTT. On the other hand, some tools over-estimate the RTT by including the TCP handshaking phase.

[1]  Matthew J. Zekauskas,et al.  A Round-trip Delay Metric for IPPM , 1999, RFC.

[2]  Vern Paxson,et al.  IPPM Metrics for Measuring Connectivity , 1999, RFC.

[3]  Mikel Izal,et al.  The European Traffic Observatory Measurement Infrastructure (ETOMIC): a testbed for universal active and passive measurements , 2005, First International Conference on Testbeds and Research Infrastructures for the DEvelopment of NeTworks and COMmunities.

[4]  Nick Feamster,et al.  Broadband internet performance: a view from the gateway , 2011, SIGCOMM.

[5]  Gurjit Singh Butalia,et al.  Secure web browsing over long-delay broadband networks - Recommendations for Web Browsers , 2004, e-Business and Telecommunication Networks.

[6]  Boris Nechaev,et al.  Netalyzr: illuminating the edge network , 2010, IMC '10.

[7]  Feng Qian,et al.  An in-depth study of LTE: effect of network protocol and application behavior on performance , 2013, SIGCOMM.

[8]  Jeffrey Pang,et al.  Can you GET me now?: estimating the time-to-first-byte of HTTP transactions with passive measurements , 2012, IMC '12.

[9]  Matthew J. Zekauskas,et al.  A One-way Packet Loss Metric for IPPM , 1999, RFC.

[10]  Mark Claypool,et al.  How's My Network? A Java Approach to Home Network Measurement , 2009, 2009 Proceedings of 18th International Conference on Computer Communications and Networks.

[11]  Matthew J. Zekauskas,et al.  A One-way Delay Metric for IPPM , 1999, RFC.

[12]  Renata Teixeira,et al.  Fathom: a browser-based network measurement platform , 2012, Internet Measurement Conference.

[13]  Balachander Krishnamurthy,et al.  Dasu: Pushing Experiments to the Internet's Edge , 2013, NSDI.

[14]  Chandra Krintz,et al.  Using JavaNws to compare C and Java TCP‐Socket performance , 2001, Concurr. Comput. Pract. Exp..

[15]  Mark Claypool,et al.  JavaScript and Flash Overhead in the Web Browser Sandbox , 2010 .

[16]  Krishna P. Gummadi,et al.  King: estimating latency between arbitrary internet end hosts , 2002, IMW '02.

[17]  Jaideep Chandrashekar,et al.  HostView: annotating end-host performance measurements with user feedback , 2011, SIGMETRICS Perform. Evaluation Rev..

[18]  Vern Paxson,et al.  Framework for IP Performance Metrics , 1998, RFC.

[19]  Cheng Huang,et al.  Estimating the performance of hypothetical cloud service deployments: A measurement-based approach , 2011, 2011 Proceedings IEEE INFOCOM.