1. On the Interaction between Dynamic Routing in the Native and Overlay Layers INFOCOM 2006 Srinivasan Seetharaman Mostafa Ammar College of Computing Georgia Institute of Technology

2. 2 INFOCOM 2006 Infrastructure overlay networks offer better services by deploying intelligent routing schemes. Uncoordinated dynamic routing in the two layers lead to many problems. We focus on the effect of native link failures, as they trigger each layer to reroute independently Dual Rerouting Inter-Layer Interaction Problem

3. 3 INFOCOM 2006 Temporal Dynamics Consider a native link failure in CE Only one overlay link is affected. The native path AE is rerouted over F (ACE → ACFDE) Native Failure Overlay recovery: 8 Overlay rerouting: 4 Original: 2 Native Rerouting: 2 Time ∞ Native Recovery Native Repair Cost A B C D F E H I G A E I G 3 2 3 2 + OVERLAY NATIVE 4

4. 4 INFOCOM 2006 1. Overlap of functionality between layers causing large number of route flaps (oscillations) 2. Unawareness of other layer’s decisions leading to resource overloading, multiple simultaneous failures a low success rate in rerouting sub-optimal paths after rerouting 3. Lack of flexibility and control Downside to Dual Rerouting

5. 5 INFOCOM 2006 Problem Statement I Assume the two ends of each link (native & overlay) use a keepAlive protocol for link verification. 3 keepAlive messages lost  Failure Understand the effects of different parameters on the rerouting performance.  KeepAlive-time: Time between two keepAlive messages  Hold-time: Time window to declare link as down  Overlay link cost scheme (Ex: Native hops, Overlay hops)

6. 6 INFOCOM 2006 Performance Metrics 1. Hit-time: Time taken for traffic to be recovered. = Detection time+Convergence time+Device time (depends on timers) (protocol specific)(Negligible) 2. Success rate of recovery Success rate of a layer = Number of paths recovered Number of failed overlay paths 3. Number of route flaps Average route flaps = Number of route flaps Number of failed overlay paths 4. Peak & Stabilized inflation (before repair) Path cost inflation = Path cost after rerouting Path cost before failure

7. 7 INFOCOM 2006 Temporal Dynamics Native Failure Overlay recovery: 8 Overlay rerouting: 4 Original: 2 Native Rerouting: 2 Time Hit time ∞ Native Recovery Native Repair Cost Overlay path AE Overlay detects first 100% success rate 3 route flaps Peak inflation = 8/2 Stabilized inflation = 4/2

8. 8 INFOCOM 2006 Performance Evaluation – ns2 Using GT-ITM, we randomly generate: 25 topologies = (5 overlay network) x (5 native network) Two scenarios 1. Inspect intra-domain failures in single-domain native network 2. Inspect inter-domain failures in multi-domain native network In each scenario, tabulate failure recovery statistics of all overlay paths by breaking one native link at a time

9. 9 INFOCOM 2006 Effect of Routing Parameters Observations: By varying the overlay keepAlive-time, hold-time and cost scheme, we observe: hold-time  hit time  (only until overlay hold-time < native hold-time) hold-time  # route flaps  hold-time  sub-optimality  keepAlive-time  hit-time  hold-time

10. 10 INFOCOM 2006 Conclusion I Dual rerouting can be made optimal by adopting the following recommendations: Overlay hold-time very close to the native hold-time. Overlay keepAlive-time that is half that of the hold- time as it leads to an earlier detection.

11. 11 INFOCOM 2006 Problem Statement II Main observation from previous simulations: “Native-rerouting yields the optimal path, albeit a bit later” Make the overlay layer aware of this observation and give higher precedence to native rerouting attempts  Improve overlay routing performance by adjusting the overlay layer functioning

12. 12 INFOCOM 2006 Three Levels of Layer Awareness 1. No awareness Dual rerouting 2. Awareness of native layer’s existence: Probabilistically Suppressed Overlay Rerouting (PSOR): Suppress overlay rerouting attempt with probability ‘p’ Deferred Overlay Rerouting (DOR): Delay overlay recovery by time ‘d’

13. 13 INFOCOM 2006 3. Awareness of native layer’s parameters: Follow-on Suppressed Overlay Rerouting (FSOR) If follow-on time < threshold ‘f’, then suppress overlay rerouting Three Levels of Layer Awareness (contd.) Time Overlay layer detects failure Native layer detects failure Failure Follow-on time

14. 14 INFOCOM 2006 Effect of Adjusting Overlay All three schemes are simple and offer significant control over the tradeoffs between hit-time and the other metrics. PSOR: Least number of route flaps Least peak inflation DSOR and FSOR behave similarly (FSOR has slightly better hit-time): Better success rate Lower stabilized inflation

15. 15 INFOCOM 2006 Conclusion II By appropriately tuning  keepAlive-time  hold-time  suppression probability  delay  follow-on threshold …we can improve results for:  Hit-time  # Route flaps  Path cost inflation  Stabilization time  Success rate

16. 16 INFOCOM 2006 Problem Statement III Main observation from previous simulations: “It is not possible to improve all metrics simultaneously. Hence, performance is still bounded!” As overlay applications proliferate, the native layer should gradually evolve to suit them  Improve overlay routing performance by adjusting the native layer functioning

17. 17 INFOCOM 2006 Tuning the Native keepAlive-time We adopt a non-invasive procedure to advance the native layer rerouting Tuning of the native layer keepAlive-time Constraints: Tuning should not generate any extra overhead Effective detection time should be same

18. 18 INFOCOM 2006 Consider the following scenarios for tuning. Scenario B is vanilla Dual rerouting Scenario A is the layer-aware overlay rerouting scheme Scenario C is the tuning we recommend here Tuning the Native keepAlive-time (contd.)

19. 19 INFOCOM 2006 Conclusions III Native layer tuning we proposed achieves the best performance in all our metrics

20. 20 INFOCOM 2006 Summary We propose means to mitigate the problems associated in the inter-layer interaction We explore two directions: 1. Adjusting the overlay layer functioning 2. Adjusting the native layer functioning