Abstract
In this paper, we look at web caching as a means to cut Internet access costs. We specifically look at caching of HTTPS traffic which has thus far not received much attention. We first look at client side caching on smartphones in mobile web scenarios to evaluate the potential for bandwidth savings. Our analysis based on user logs reveals that app traffic dominates browser traffic at 82.7% and HTTPS traffic dominates HTTP traffic at 82.3%. There is around 15% redundancy in this traffic, however much of this redundancy does not lend itself to practical savings since app logic or server cache configurations cannot be controlled.
Given the negative result of above approach, we shifted our attention to infrastructure side caching (wired) in an organizational setting. Analysis of our logs indicate that HTTPS accounts for 91.6% of all considered traffic and YouTube accounts for 82% of this HTTPS traffic. We found that there is some amount of redundancy in this traffic and hence potential for bandwidth savings. However proxying HTTPS traffic is challenging given that the proxy has to act as a man in the middle of a secure transaction. To circumvent this problem, we propose a new architecture that serves only insensitive HTTPS traffic from the proxy. We validate the feasibility of this approach via an implementation. A trace driven simulation shows that one can realize bandwidth savings of between 13–17% with our architecture.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
In the smartphone logs, the redundancy in HTTPS was also less than HTTP, but the analysis there was based on content not URL. That was the nature of HTTPS traffic in smartphone logs, which seems to differ from desktop logs.
References
Charles Proxy. http://www.charlesproxy.com
Qian, F., et al.: Web caching on smartphones: ideal vs. reality. In: MobiSys 2012 (2012)
Lymberopoulos, D., et al.: PocketWeb: instant web browsing for mobile devices. In: ASPLOS 2012 (2012)
Wang, Z., et al.: How far can client-only solutions go for mobile browser speed? In: WWW 2012 (2012)
Zhang, Y., Tan, C., Qun, L.: CacheKeeper: a system-wide web caching service for smartphones. In: UbiComp 2013 (2013)
Sherry, J., et al.: Making middleboxes someone else’s problem: network processing as a cloud service. In: SIGCOMM 2012 (2012)
Lan, C., et al.: Embark: securely outsourcing middleboxes to the cloud. In: NSDI 2016 (2016)
Zink, M., et al.: Characteristics of YouTube network traffic at a campus network measurements, models, and implications. Comput. Netw. 53(4), 501–514 (2009)
Guillemin, F., et al.: Experimental analysis of caching efficiency for YouTube traffic in an ISP network. In: Teletraffic Congress (ITC) (2013)
Lothar, B., et al.: Analyzing caching benefits for YouTube traffic in edge networks—a measurement-based evaluation. In: NOMS (2012)
Naylor, D., et al.: The Cost of the “S” in HTTPS. In: CONEXT 2014 (2014)
Woo, S., et al.: Comparison of caching strategies in modern cellular backhaul networks. In: MobiSys 2013 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Gupta, P., Patel, M., Chebrolu, K. (2017). Cutting Internet Access Costs Through HTTPS Caching: A Measurement Study. In: Kaafar, M., Uhlig, S., Amann, J. (eds) Passive and Active Measurement. PAM 2017. Lecture Notes in Computer Science(), vol 10176. Springer, Cham. https://doi.org/10.1007/978-3-319-54328-4_20
Download citation
DOI: https://doi.org/10.1007/978-3-319-54328-4_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-54327-7
Online ISBN: 978-3-319-54328-4
eBook Packages: Computer ScienceComputer Science (R0)