1. A Comparison of Application-Level and Router-Assisted Hierarchical Schemes for Reliable Multicast Pavlin Radoslavov Christos Papadopoulos Ramesh Govindan Deborah Estrin Reviewer: Jing Lu, Qian Wan CS770x

2. Outline Introduction –ALH: RMTP –RAH: LMS Metric Space Analysis Using k-ARY Trees Simulation Results Conclusion

3. IP Multicast Send packet from a source to the members of a multicast group. –Class D IP addresses (250 million) –IGMP & MOSPF –Best-effort packet forwarding Applications: multimedia, teleconferencing, distributed computing, etc.

4. Reliable IP Multicast Scalability issues: –Implosion: redundant messages triggered by packet loss –Exposure: redundant retransmissions to receivers who haven't experienced loss Long recovery latency Hierarchical data recovery schemes: –ALH (Application-Level Hierarchical): End systems assist in hierarchy creation and maintainance. RMTP –RAH (Router-Assisted Hierarchical): Routers assistance LMS

5. RMTP Data Recovery Static hierarchical scheme –Designated Receivers (DRs) are chosen statically –A receiver dynamically chooses a closest DR as its Ack and retransmission processor –A DR collects Nack from its local group members and retransmits packet within the group using unicast/multicast –A DR emits its own Nack to its parent DR in the upper hierarchy –Sender deals with Nacks from DRs at the top level hierarchy

6. ALH Data Recovery sender R1 R3 R2 R4 Rx1 Rx7 Rx8 Rx3Rx4Rx5Rx6 Rx2 Optimal Hierarchy

7. ALH Data Recovery sender R1 R3 R2 R4 Rx1 Rx7 Rx8 Rx3Rx4Rx5Rx6 Rx2 Optimal Hierarchy

8. ALH Data Recovery sender R1 R3 R2 R4 Rx1 Rx7 Rx8 Rx3Rx4Rx5Rx6 Rx2 Sub-optimal Hierarchy

9. ALH Data Recovery sender R1 R3 R2 R4 Rx1 Rx7 Rx8 Rx3Rx4Rx5Rx6 Rx2 Sub-optimal Hierarchy

10. Heuristic Dynamic Hierarchy Creation in ALH Each receiver obtains distance info to each other Dynamically create the hierarchy from bottom-up: –Initially all receivers are eligible to become parents –A fraction (frac pc ) of receivers with the smallest sum of distances becomes parents. –Receivers that are not elected choose the closest parent as its parent. –Repeat the selection process among receivers chosen from the previous iteration until the number of receivers left <= 1/frac pc, so their parent is the sender itself.

11. LMS Data Recovery LMS extends router forwarding Enhance routers to: –Replier selection –Forward Nacks to replier and discover root of loss subtree –Perform DMCAST

12. LMS Replier Selection Router state per-source tree: –Upstream link –List of downstream links –Replier link id sender R1 R3 R2 R4 Rx1 Rx7 Rx8 Rx3Rx4Rx5Rx6 Rx2

13. LMS Nack Forwarding LMS router handles Nacks [1]

14. LMS DMCAST DMCAST: –Replier encapsulates a multicast packet into a unicast packet and sends to the turning-point router –LMS router decapsulates and multicasts it on the specified link interfaces

15. LMS Enhanced Two-Step DMCAST Nack from a downstream replier specifies reply should be unicast back to it rather than to its turning point Replier then performs DMCAST when necessary

16. Summary of ALH and RAH ALHRAH Automatic creation of data recovery hierarchy End-to-end mechanism and heuristic algorithm Router selects the closest downstream receiver as replier RetransmissionParent unicasts/multicasts recovery data to its group members Replier unicasts recovery data to turning-point router, router multicasts it directly on specified links RAH is finer-grained with many more “internal nodes” RAH is more congruent to the underlying multicast tree RAH doesn’t have explicit group concept, so it is easily adaptive to membership change; membership maintenance cost is minimal

17. Metric Space Data Recovery Latency Receiver Exposure Data Traffic Overhead Control Traffic Overhead

18. Data Recovery Latency sender R1 R3 R2 R4 Rx1 Rx7 Rx8 Rx3Rx4Rx5Rx6 Rx2 Loss RcvslatRTT Rx268 Rx3810 Rx4810 Rx5810 Rx6810 NormLat0.79

19. Receiver Exposure sender R1 R3 R2 R4 Rx1 Rx7 Rx8 Rx3Rx4Rx5Rx6 Rx2 Loss RcvsExposure Rx20 Rx30 Rx40 Rx50 Rx60 NormExp0

20. Data Traffic Overhead sender R1 R3 R2 R4 Rx1 Rx7 Rx8 Rx3Rx4Rx5Rx6 Rx2 Loss RcvsDataSubtree Rx238 Rx3, Rx4, Rx5, Rx6 7 NormData Overhead 1.25

21. Control Traffic Overhead sender R1 R3 R2 R4 Rx1 Rx7 Rx8 Rx3Rx4Rx5Rx6 Rx2 Loss RcvsControlSubtree Rx238 Rx33 Rx43 Rx53 Rx63 NormLat1.875

22. Analysis using k-ARY Tree Purpose: − Gain initial understanding of the scalability of the ALH and RAH schemes Parameters: − k, L − q: fraction of leaf nodes that are receivers is 1/k q-1 Assumptions: − Each parent (ALH) has k-1 children. − Single link loss and average per link-loss across all links

23. Analysis using k-ARY Tree ALH RAH

24. Control Overhead Analysis L = 10

25. Data Overhead Analysis L = 10 RAH is slightly better than ALH In some cases, RAH replier multicast data to all receivers within a subtree ALH has to perform multiple multicasts within local groups

26. Data Recovery Latency Analysis

27. L = 10