AI helps you reading Science

AI generates interpretation videos

AI extracts and analyses the key points of the paper to generate videos automatically


pub
Go Generating

AI Traceability

AI parses the academic lineage of this thesis


Master Reading Tree
Generate MRT

AI Insight

AI extracts a summary of this paper


Weibo:
We conducted the first systematic measurement study to quantify the existence of path exploration and slow convergence in the global Internet routing system

Quantifying path exploration in the internet

Proceedings of the 8th ACM SIGCOMM conference on Internet measurement, no. 2 (2009): 269-282

Cited: 115|Views79
EI

Abstract

A number of previous measurement studies [10, 12, 17] have shown the existence of path exploration and slow convergence in the global Internet routing system, and a number of protocol enhancements have been proposed to remedy the problem [21, 15, 4, 20, 5]. However all the previous measurements were conducted over a small number of testin...More

Code:

Data:

0
Introduction
  • The Border Gateway Protocol (BGP) is the routing protocol used in the global Internet.
  • In response to path failures or routing policy changes, some BGP routers may try a number of transient paths before selecting a new best path or declaring unreachability to a destination.
  • In a typical route failure event, some BGP routers can spend up to several minutes exploring a large number of alternate paths before declaring a destination unreachable
Highlights
  • The Border Gateway Protocol (BGP) is the routing protocol used in the global Internet
  • A number of previous analytical and measurement studies have shown the existence of Border Gateway Protocol path exploration and slow convergence in the operational Internet routing system, which can potentially lead to severe performance problems in data delivery [10, 12, 17]
  • Our results show that route fail-over events, where the paths move from shorter or more preferred ones to longer or less preferred ones, has much shorter convergence time than route failure events, where the destinations become unreachable
  • We conducted the first systematic measurement study to quantify the existence of path exploration and slow convergence in the global Internet routing system
  • We first developed a new path ranking method based on the usage time of each path and validated its effectiveness using data from controlled experiments with beacon prefixes. we applied our path ranking method to Border Gateway Protocol updates of all the prefixes in the global routing table and classified each observed routing event into three classes: Path Change, Path Disturbance, and Same Path
  • There is a wide existence of path exploration and slow convergence in the global routing system, the significance of the problem can vary considerably depending on the locations of both the origin ASes and the observation routers in the routing system hierarchy
Methods
  • Previous measurement results on BGP slow convergence were obtained through controlled experiments.
  • In these experiments, a small number of “beacon” prefixes are periodically announced and withdrawn by their origin ASes at fixed time intervals [1, 2], and the resulting routing updates are collected at remote monitoring routers and analyzed.
  • One cannot assess the overall Internet routing performance from observing the small number of existing beacon prefixes
Results
  • As one can see from the figure, in about 50% of the cases the three different T values result in the same number of events, and in more than 80% of the cases the results from using the different T values differ by at most 2 events.
  • The authors' result shows that using length for path ranking gives only about 60% accuracy, and usage time can give more than 95% accuracy
Conclusion
  • The authors conducted the first systematic measurement study to quantify the existence of path exploration and slow convergence in the global Internet routing system.
  • The authors applied the path ranking method to BGP updates of all the prefixes in the global routing table and classified each observed routing event into three classes: Path Change, Path Disturbance, and Same Path.
  • There is a wide existence of path exploration and slow convergence in the global routing system, the significance of the problem can vary considerably depending on the locations of both the origin ASes and the observation routers in the routing system hierarchy.
  • Routers in tier-1 ISPs observe less path exploration and shorter convergence delays than routers in edge ASes, and prefixes originated from tier-1 ISPs experience much less slow convergence than those originated from edge ASes
Tables
  • Table1: Event Statistics similar number of Tdown events, but there are also a few outliers that observe either too many or too few Tdown events. Too many Tdown events can be due to failures that are close to monitors and partition the monitors from the rest of the Internet, or underestimation of the relative timeout T used to cluster updates. Too few Tdown events can be due to missing data during monitor downtime, or overestimation of the relative timeout T . In order to keep consistency among all monitors, we decided to exclude the head and tail of the distribution, reducing the data set to 32 monitors
  • Table2: Median of duration of Tdown events observed and originated in different tiers
  • Table3: Tdown Events by Origin AS
Download tables as Excel
Related work
  • Empirical Linear Fit

    Days of January 2006

    No of events No of prefixes originated No of events per prefix

    Core 3,011 14,367

    Middle 34,514 81,988

    Edge 78,149 122,877

    There are two types of BGP update characterization work in the literature: passive measurements [13, 14, 11, 26, 3, 16, 23, 27, 7], and active measurements [10, 12, 17]. The work presented in this paper belongs to the first category. We conducted a systematic measurement to classify routing instability events and quantify path exploration for all the prefixes in the Internet. Our measurement also showed the impact of AS’s tier level on the extent of path explorations.

    Existing measurements of path exploration and slow convergence have all been based on active measurements [10, 12, 17], where controlled events were injected into the Internet from a small number of beacon sites. These measurement results demonstrated the existence of BGP path exploration and slow convergence, but did not show to what extent they exist on the Internet under real operational conditions. In contrast, in this paper we classify routing events of all prefixes, as opposed to a small number of beacon sites, into different categories, and for each category we provide measurement results on the updates per event and event durations. Given we examine the updates from multiple peers for all the prefixes in the global routing table, we are able to identify the impact of AS tier levels on path exploration. Regarding the relation between the tier levels of origin ASes, our results agree with previous active measurement work [12] (using a small number of beacon sites) that prefixes originated from tier-1 ASes tend to experience less slow convergence compared to prefixes originated from lower tier ASes. Moreover, our results also showed that, for the same prefix, routers of different AS tiers observe different degree of slow convergence, with tier-1 ASes seeing much less than lower tier ASes.
Funding
  • †Computer Science Department, University of California, Los Angeles. ‡Computer Science Department, University of Arizona. §ATT Labs Research. ∗This material is based upon work supported by the Defense Advanced Research Projects Agency (DARPA) under Contract No N66001-04-1-8926 and by National Science Foundation (NSF) under Contract No ANI-0221453
Reference
  • PSG Beacon List. Available from: http://www.psg.com/∼zmao/BGPBeacon.html [cited 05/11/2006].
    Findings
  • RIPE Beacon List. Available from: http://www.ripe.net/ris/docs/beaconlist.html [cited 05/11/2006].
    Findings
  • D. Andersen, N. Feamster, S. Bauer, and H. Balakrishnan. Topology inference from bgp routing dynamics. In ACM SIGCOMM Internet Measurement Workshop (IMW), 2002.
    Google ScholarLocate open access versionFindings
  • A. Bremler-Barr, Y. Afek, and S. Schwarz. Improved bgp convergence via ghost flushing. In Proc. of IEEE INFOCOM, 2003.
    Google ScholarLocate open access versionFindings
  • J. Chandrashekar, Z. Duan, Z.-L. Zhang, and J. Krasky. Limiting path exploration in path vector protocols. In Proc. of IEEE INFOCOM, March 2005.
    Google ScholarLocate open access versionFindings
  • D. Chang, R. Govindan, and J. Heidemann. The temporal and topological characteristics of BGP path changes. In Proc. of the Int’l Conf. on Network Protocols (ICNP), November 2003.
    Google ScholarLocate open access versionFindings
  • A. Feldmann, O. Maennel, Z. M. Mao, A. Berger, and B. Maggs. Locating internet routing instabilities. In Proc. of ACM SIGCOMM, 2004.
    Google ScholarLocate open access versionFindings
  • L. Gao. On inferring autonomous system relationships in the Internet. ACM/IEEE Transactions on Networking, 9(6):733–745, 2001.
    Google ScholarLocate open access versionFindings
  • T. G. Griffin and B. J. Premore. An experimental analysis of bgp convergence time. In Proc. of the Int’l Conf. on Network Protocols (ICNP), 2001.
    Google ScholarLocate open access versionFindings
  • C. Labovitz, A. Ahuja, A. Abose, and F. Jahanian. Delayed Internet routing convergence. IEEE/ACM Transactions on Networking, 9(3):293 – 306, June 2001.
    Google ScholarLocate open access versionFindings
  • C. Labovitz, A. Ahuja, and F. Jahanian. Experimental study of Internet stability and wide-area network failures. In Proceedings of FTCS99, June 1999.
    Google ScholarLocate open access versionFindings
  • C. Labovitz, A. Ahuja, R. Wattenhofer, and S. Venkatachary. The impact of Internet policy and topology on delayed routing convergence. In Proc. of IEEE INFOCOM, April 2001.
    Google ScholarLocate open access versionFindings
  • C. Labovitz, G. Malan, and F. Jahanian. Internet Routing Instability. In Proc. of ACM SIGCOMM, September 1997.
    Google ScholarLocate open access versionFindings
  • C. Labovitz, R. Malan, and F. Jahanian. Origins of Internet routing instability. In Proc. of IEEE INFOCOM, 1999.
    Google ScholarLocate open access versionFindings
  • J. Luo, J. Xie, R. Hao, and X. Li. An approach to accelerate convergence for path vector protocol. In Proc. of IEEE Globecom, November 2002.
    Google ScholarLocate open access versionFindings
  • O. Maennel and A. Feldmann. Realistic BGP traffic for test labs. In Proc. of ACM SIGCOMM, 2002.
    Google ScholarLocate open access versionFindings
  • Z. M. Mao, R. Bush, T. Griffin, and M. Roughan. BGP beacons. In ACM SIGCOMM Internet Measurement Conference (IMC), 2003.
    Google ScholarLocate open access versionFindings
  • A. Markopoulou, G. Iannaccone, S. Bhattacharyya, C.-N. Chuah, and C. Diot. Characterization of failures in an IP backbone. In IEEE Infocom, Hong Kong, 2004.
    Google ScholarLocate open access versionFindings
  • D. Pei,, B. Zhang, D. Massey, and L. Zhang. An analysis of path-vector routing protocol convergence algorithms. Computer Networks, 50(3):398 – 421, 2006.
    Google ScholarLocate open access versionFindings
  • D. Pei, M. Azuma, D. Massey, and L. Zhang. BGP-RCN: Improving BGP convergence through root cause notification. Computer Networks, 48(2):175–194, June 2005.
    Google ScholarLocate open access versionFindings
  • D. Pei, X. Zhao, L. Wang, D. Massey, A. Mankin, S. F. Wu, and L. Zhang. Improving bgp convergence through consistency assertions. In Proc. of IEEE INFOCOM, 2002.
    Google ScholarLocate open access versionFindings
  • Y. Rekhter, T. Li, and S. Hares. Border Gateway Protocol 4. RFC 4271, Internet Engineering Task Force, January 2006.
    Google ScholarFindings
  • J. Rexford, J. Wang, Z. Xiao, and Y. Zhang. BGP routing stability of popular destinations. In ACM SIGCOMM Internet Measurement Workshop (IMW), 2002.
    Google ScholarLocate open access versionFindings
  • The RIPE Routing Information Services. http://www.ris.ripe.net.
    Findings
  • The RouteViews project. http://www.routeviews.org/.
    Findings
  • L. Wang, X. Zhao, D. Pei, R. Bush, D. Massey, A. Mankin, S. F. Wu, and L. Zhang. Observation and analysis of BGP behavior under stress. In ACM SIGCOMM Internet Measurement Workshop (IMW), 2002.
    Google ScholarLocate open access versionFindings
  • J. Wu, Z. M. Mao, J. Rexford, and J. Wang. Finding a needle in a haystack: Pinpointing significant BGP routing changes in an IP network. In Symposium on Networked System Design and Implementation (NSDI), May 2005.
    Google ScholarLocate open access versionFindings
  • J. Xia and L. Gao. On the evaluation of AS relationship inferences. In Proc. of IEEE GLOBECOM, December 2004.
    Google ScholarLocate open access versionFindings
  • B. Zhang, V. Kambhampati, M. Lad, D. Massey, and L. Zhang. Identifying BGP Routing Table Transfers. In ACM SIGCOMM Mining the Network Data (MineNet) Workshop, August 2005.
    Google ScholarLocate open access versionFindings
  • B. Zhang, R. Liu, D. Massey, and L. Zhang. Collecting the internet as-level topology. ACM SIGCOMM Computer Communications Review (CCR), 35(1):53–62, January 2005.
    Google ScholarLocate open access versionFindings
0
Your rating :

No Ratings

Tags
Comments
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn