Revealing Utilization at Internet Interconnection Points
Revealing Utilization at Internet Interconnection Points
复制标题
揭示互联网互连点的利用率
DOI：
--
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
N. Feamster
中科院分区：
文献类型：
--
作者：
N. Feamster
最近的互联网互连争端引发了人们对开发收集和收集关于互联点使用情况的数据的方法越来越感兴趣。由Deepfield Networks开发的一种机制允许互联网服务提供商(ISP)使用网络流量统计收集和汇总使用信息，该统计在互联网工程任务组中标准化为IPFIX。这份报告(1)概述了Deepfield Networks用来衡量内容提供商和互联网服务提供商之间的各种互连链路或内容与互联网服务提供商之间的流量流经的链路的利用率的方法；以及(2)调查了七家参与的互联网服务提供商--光明之家网络公司、康卡斯特公司、考克斯公司、Mediacom公司、Midco公司、Suddenlink公司和时代华纳有线公司--提供的五个月的互联网利用数据--它们的接入网络约占美国所有宽带用户的50%。然后，我们讨论测量功能的基本操作，包括收集和汇总流量统计数据(即IPFIX记录)，对这些汇总测量可以产生准确结论的场景进行评估，以及与收集相关的注意事项。我们评估了流量统计用于测量使用率的能力，并讨论了该方法的能力和限制。我们讨论了互联网服务提供商在向我们提供数据时使用的聚合技术以及我们在公开数据之前应用的聚合技术。数据集包括每个参与的互联网服务提供商约97%的付费对等、免结算对等和互联网服务提供商付费中转链路。对数据的初步分析表明，许多互连都有大量的空闲容量，这些空闲容量既存在于每个地区的所有互联网服务提供商之间，也存在于任何单个互联网服务提供商的总和中，并且在高峰期间，所有互连的总利用率约为50%。
Recent Internet interconnection disputes have sparked an increased interest in developing methods for gathering and collecting data about utilization at interconnection points. One mechanism, developed by DeepField Networks, allows Internet service providers (ISPs) to gather and aggregate utilization information using network flow statistics, standardized in the Internet Engineering Task Force as IPFIX. This report (1) provides an overview of the method that DeepField Networks is using to measure the utilization of various interconnection links between content providers and ISPs or links over which traffic between content and ISPs flow; and (2) surveys the findings from five months of Internet utilization data provided by seven participating ISPs — Bright House Networks, Comcast, Cox, Mediacom, Midco, Suddenlink, and Time Warner Cable — whose access networks represent about 50% of all U.S. broadband subscribers.We first discuss the problem of interconnection and utilization at interconnection points. We then discuss the basic operation of the measurement capabilities, including the collection and aggregation of traffic flow statistics (i.e., IPFIX records), providing an assessment of the scenarios where these aggregate measurements can yield accurate conclusions, as well as caveats associated with their collection. We assess the capabilities of flow statistics for measuring utilization, and we discuss the capabilities and limitations of the approach the aggregation techniques that the ISPs use both in providing data to us, and that we apply before making the data public.The dataset includes about 97% of the paid peering, settlement-free peering, and ISP-paid transit links of each of the participating ISPs. Initial analysis of the data — which comprises more than 1,000 link groups, representing the diverse and substitutable available routes — suggests that many interconnects have significant spare capacity, that this spare capacity exists both across ISPs in each region and in aggregate for any individual ISP, and that the aggregate utilization across interconnects is roughly 50% during peak periods.