Assessing Affinity Between Users and CDN Sites - Traffic Monitoring and Analysis
Conference Papers Year : 2015

Assessing Affinity Between Users and CDN Sites

Xun Fan
  • Function : Author
  • PersonId : 995513
Ethan Katz-Bassett
  • Function : Author
  • PersonId : 995514
John Heidemann
  • Function : Author
  • PersonId : 995515

Abstract

Large web services employ CDNs to improve user performance. CDNs improve performance by serving users from nearby Front-End (FE) Clusters. They also spread users across FE Clusters when one is overloaded or unavailable and others have unused capacity. Our paper is the first to study the dynamics of the user-to-FE Cluster mapping for Google and Akamai from a large range of client prefixes. We measure how 32,000 prefixes associate with FE Clusters in their CDNs every 15 minutes for more than a month. We study geographic and latency effects of mapping changes, showing that 50–70 % of prefixes switch between FE Clusters that are very distant from each other (more than 1,000 km), and that these shifts sometimes (28–40 % of the time) result in large latency shifts (100 ms or more). Most prefixes see large latencies only briefly, but a few (2–5 %) see high latency much of the time. We also find that many prefixes are directed to several countries over the course of a month, complicating questions of jurisdiction.
Fichier principal
Vignette du fichier
336978_1_En_7_Chapter.pdf (438.13 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01411186 , version 1 (07-12-2016)

Licence

Identifiers

Cite

Xun Fan, Ethan Katz-Bassett, John Heidemann. Assessing Affinity Between Users and CDN Sites. 7th Workshop on Traffic Monitoring and Analysis (TMA), Apr 2015, Barcelona, Spain. pp.95-110, ⟨10.1007/978-3-319-17172-2_7⟩. ⟨hal-01411186⟩
83 View
114 Download

Altmetric

Share

More