1. 1/18 Evaluating Potential Routing Diversity for Internet Failure Recovery *Chengchen Hu, + Kai Chen, + Yan Chen, *Bin Liu *Tsinghua University, + Northwestern University

2. 2/18 Internet Emergency  Emergencies or disasters can lead to substantial Internet disruption  Earthquakes,  Storms,  Terrorist incident: 9.11 event

3. 3/18 Example: Taiwan earthquake incident  Large earthquakes hit Luzon Strait, south of Taiwan on 26 December 2006  Only two of nine cross-sea cables not affected  All cables reported repaired as of February 14, 2007  Long-term network interruption from Asia to USA Page 3

4. 4/18 How reliable the Internet is?  BGP resilience is limited [Wu, CoNEXT’07]  32% ASes are vulnerable to a single critical customer- provider link cut  93.7% Tier-1 ISP’s single-homed customers are lost due to Tier-1 depeering  Internet is not as reliable as people expected!  Our question: can we find more resources to increase the Internet reliability under Internet emergency?

5. 5/18 Outline  Background and Motivation  Basic Idea  Simulation Study  Conclusion

6. 6/18 Basic Idea  Internet eXchange Points (IXPs)  Co-location where multiple ASes exchange their traffic  Participant ASes in an IXP may not be connected via BGP  Internet valley-free routing policy  AS relationships: customer-provider, peering, sibling  Peering relationship won’t allow one peer to carry the traffic from the other peer to its provider  Mentioned in [Wu, CoNEXT’07], without evaluation  How much can we gain from these two potential resources, i.e., IXP and PR?

7. 7/18 Dataset  Most complete AS topology  BGP data + P2P traceroute  120K AS links with relationships  http://aqualab.cs.northwestern.edu/projects/SidewalkEnd s.html [Chen et al, CoNEXT’09]  IXP data  PCH + Peeringdb + Euro-IX (~200 IXPs)  3468 participant ASes

8. 8/18 Failure Models  Tier-1 depeering  Cogent and Level3 depeering  Tier-1 provider-customer link teardown  Reported in NANOG  Mixed types of link breakdown  9.11 event, Taiwan Earthquakes,

9. 9/18 Evaluation Metrics  Recovery Ratio  # of recovered AS pairs versus total # of affected AS pairs  Path Diversity  # of increased link-disjoint AS paths between affected AS pairs  Shifted Path  # of link-disjoint AS paths shifted onto a normal link after we use IXP or PR resources

10. 10/18 Results: Tier-1 Depeering  36 experiments for 9 Tier-1 ASes  Recovery ratio

11. 11/18 Results: Tier-1 Depeering  Path diversity

12. 12/18 Results: Tier-1 Depeering  Shifted path  Different # of shifted AS paths for different links  In average, 3.75 ~ 17.2 for all experiments

13. 13/18 Conclusion  A first work to evaluate potential routing diversity with the most complete AS map  40%-80% of disconnected AS pairs can be recovered via IXP and PR  Point out a new venue for Internet emergency recovery

14. 14/18 Thanks, Q&A

15. 15/18 Backup

16. 16/18 Results: Tier-1 provider-customer links teardown  Recovery ratio  Path diversity  4.64 for 10 Tier-1 provider-customer links teardown  4.54 for 20 Tier-1 provider-customer links teardown

17. 17/18 Results: Mixed types of links breakdown  Focus on Taiwan earthquake, 9 big victim ASes  Recovery ratio

18. 18/18 Results: Mixed types of links breakdown  Path diversity