Drafting behind Akamai (travelocity-based detouring)

Su, Ao-Jan; Choffnes, David; Kuzmanovic, Aleksandar; Bustamante, Fabián E.

doi:10.1145/1151659.1159962

Cited by 84 publications

(23 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DNS' Time-To-Live (TTL) value defines how frequently a client should query DNS system to get current IP addresses of a hostname. On the one hand, in DNS-driven systems, large TTL can lead to slow response to changes of network or server conditions [27]. On the other hand, small TTL may put unnecessarily high load on the DNS system.…”

Section: Slow Load Balancingmentioning

confidence: 99%

“…The question then becomes which TTL Akamai sets for their streaming service. While we answer this question in the next section, our key hypothesis is that if the redirections at time scales of several tens of seconds are applied, as used in the case of web [27], that might generate severe vulnerabilities in the case of live streaming.…”

Section: Slow Load Balancingmentioning

confidence: 99%

See 1 more Smart Citation

Thinning akamai

Kuzmanovic

2008

Proceedings of the 8th ACM SIGCOMM Conference on Internet Measurement

Self Cite

View full text Add to dashboard Cite

Global-scale Content Distribution Networks (CDNs), such as Akamai, distribute thousands of servers worldwide providing a highly reliable service to their customers. Not only has reliability been one of the main design goals for such systems -they are engineered to operate under severe and constantly changing number of server failures occurring at all times. Consequently, in addition to being resilient to component or network outages, CDNs are inherently considered resilient to denial-of-service (DoS) attacks as well.In this paper, we focus on Akamai's (audio and video) streaming service and demonstrate that the current system design is highly vulnerable to intentional service degradations. We show that (i) the discrepancy among streaming flows' lifetimes and DNS redirection timescales, (ii) the lack of isolation among customers and services, (e.g., video on demand vs. live streaming), (iii) a highly transparent system design, (iv) a strong bias in the stream popularity, and (v) minimal clients' tolerance for low-quality viewing experiences, are all factors that make intentional service degradations highly feasible. We demonstrate that it is possible to impact arbitrary customers' streams in arbitrary network regions: not only by targeting appropriate points at the streaming network's edge, but by effectively provoking resource bottlenecks at a much higher level in Akamai's multicast hierarchy. We provide countermeasures to help avoid such vulnerabilities and discuss how lessons learned from this research could be applied to improve DoS-resiliency of large-scale distributed and networked systems in general.

show abstract

Section: Slow Load Balancingmentioning

confidence: 99%

Section: Slow Load Balancingmentioning

confidence: 99%

Thinning akamai

Kuzmanovic

2008

Proceedings of the 8th ACM SIGCOMM Conference on Internet Measurement

Self Cite

View full text Add to dashboard Cite

show abstract

“…Dasu also provides support for Internet experiments that require synchronized client operation (e.g., [32] and [33]). For coarse-level synchronization, Dasu clients include a cron-like probe-scheduler that allows the scheduling of measurements for future execution.…”

Section: H Synchronizationmentioning

confidence: 99%

A Measurement Experimentation Platform at the Internet's Edge

Sánchez¹,

Otto²,

Bischof³

et al. 2015

IEEE/ACM Trans. Networking

Self Cite

View full text Add to dashboard Cite

Poor visibility into the network hampers progress in a number of important research areas, from network troubleshooting to Internet topology and performance mapping. This persistent, well-known problem has served as motivation for numerous proposals to build or extend existing Internet measurement platforms by recruiting larger, more diverse vantage points. Capturing the edge of the network, however, remains an elusive goal. We argue that at its root the problem is one of incentives. Today's measurement platforms build on the assumption that the goals of experimenters and those hosting the platform are the same. As much of the Internet growth occurs in residential broadband networks, this assumption no longer holds. We present a measurement experimentation platform that reaches the network edge by explicitly aligning the objectives of the experimenters with those of the users hosting the platform. Dasu-our current prototype-is designed to support both network measurement experimentation and broadband characterization. Dasu has been publicly available since July 2010 and has been installed by over 100 000 users with a heterogeneous set of connections spreading across 2431 autonomous systems (ASs) and 166 countries. We discuss some of the challenges we faced building and using a platform for the Internet's edge, describe its design and implementation, and illustrate the unique perspective its current deployment brings to Internet measurement.

show abstract

“…In many cases, the cache server with the minimum latency to the requesting user is selected [33], and the selected cache server delivers the content item to the requesting user if it exists in its cache storage, i.e., cache hit. Otherwise, the cache server obtains this content item from the origin server, stores it in its storage, and delivers it to the requesting user [28].…”

Section: A Amount Of Inter-as Trafficmentioning

confidence: 99%

“…Content m is delivered from the cache server of AS x if there exists a copy of content m in any cache servers of AS x, i.e., in the case of cache hit, or content m is delivered from the origin server if no cache servers of AS x keeps content m, i.e., in the case of cache miss [33]. Therefore, the cache servers of AS x are used only for the users accommodated by AS x. L k AS x does not cache content whose origin servers connect with AS x, and the ratio of origin servers accommodated in each AS x is W k /N k as mentioned in Section III-C2.…”

Section: A Amount Of Inter-as Trafficmentioning

confidence: 99%

Analyzing Impact of Introducing CCN on Profit of ISPs

Kamiyama

2015

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

Content centric networking (CCN) has attracted a great deal of attention as a network that can efficiently deliver content. In CCN, content is delivered using the content name, instead of the host IP address, from cache memory implemented at routers. The nodes sending content are not explicitly indicated, and content is delivered from routers that have copies of content on the routes where the Interest packets are transmitted. Therefore, as a result of introducing CCN in ISP networks, the pattern of traffic exchanges among ISPs will change considerably. Customer ISPs normally pay a transit fee to transit ISPs based on the traffic volume transmitted on the transit links. Therefore, the introduction of CCN by ISPs will affect the profit of ISPs. CCN is introduced and operated by ISPs based on their business judgment, so it is important to estimate how CCN affects ISP profit to investigate the likelihood of CCN spreading among many ISPs. In this paper, we formalize the profit of ISPs when implementing CCN, assuming a hierarchical topology of ISPs in three levels and show that introducing CCN increases the profit of layer 2 and 3 ISPs, whereas introducing CCN decreases the profit of layer 1 ISPs. We also clarify that the effect of introducing CCN for the profit of ISPs is more remarkable as the cache capacity or the bias of content popularity increases.

show abstract

Drafting behind Akamai (travelocity-based detouring)

Cited by 84 publications

References 21 publications

Thinning akamai

Thinning akamai

A Measurement Experimentation Platform at the Internet's Edge

Analyzing Impact of Introducing CCN on Profit of ISPs

Contact Info

Product

Resources

About