1. 1 Core-Stateless Fair Queueing: Achieving Approximately Fair Bandwidth Allocations in High Speed Networks Ion Stoica,Scott Shenker, and Hui Zhang SIGCOMM’99, Vancouver, August 1999 Presented by Bob Kinicki

2. Advanced Computer Networks : CSFQ2 Outline Introduction CSFQ Architecture – Flow Arrival Rate – Link Fair Share Rate Estimation Many Simulations Conclusions

3. Advanced Computer Networks : CSFQ3 Introduction This paper brings forward the concept of “fair” allocation. The claim is that fair allocation inherently requires routers to maintain state and perform operations on a per flow basis. They present an architecture and a set of algorithms that is “approximately fair” while using FIFO queueing at internal routers.

4. Advanced Computer Networks : CSFQ4 An “Island” of Routers Edge Router Core Router Source Destination

5. Advanced Computer Networks : CSFQ5 Core-Stateless Fair Queueing Ingress edge routers compute per-flow rate estimates and insert these estimates as labels into each packet header. Labels are updated at each router based only on aggregate information. FIFO queueing with probabilistic dropping of packets on input is employed at core routers.

6. Advanced Computer Networks : CSFQ6 Edge – Core Router Architecture

7. Advanced Computer Networks : CSFQ7 Model Variables and Parameters Router with output link capacity C. r i (t) :: i th flows arrival rate α(t) :: fair share rate In the fluid flow model, incoming bits of flow i at a core router are dropped with probability Max (0, 1 - α(t) / r i (t) )

8. Advanced Computer Networks : CSFQ8 Flow Arrival Rate At each edge router, use exponential averaging to estimate the rate of a flow. For flow i, let l i k be the length of the k th packet. t i k be the arrival time of the k th packet. Then the estimated rate of flow i, r i is updated every time a new packet is received: r i new = (1-e -T/K )*L / T + e -T/K * r i old where T = T i k = t i k – t i k-1 L = l i k and K is a constant

9. Advanced Computer Networks : CSFQ9 Link Fair Rate Estimation Heuristic algorithm with aggregate state variables: alpha_hat :: fair share estimate Lambda_hat :: aggregate arrival rate estimate F_hat :: aggregate acceptance rate estimate

10. Advanced Computer Networks : CSFQ10 Algorithm Idea When packet arrives, Lambda_hat is updated using exponential averaging. If the packet is dropped, F_hat remains the same. If the packet is not dropped, F_hat is updated using exponential averaging. Whenever “epoch” switches congested state, update alpha_hat: alpha_hat new = alpha_hat old * C /F_hat

11. Advanced Computer Networks : CSFQ11 Algorithm Idea (cont.) Alpha_hat now feeds into next calculation of drop probability (p) as alpha: p = max ( 0, 1 – alpha / label )

12. Advanced Computer Networks : CSFQ12 CSFQ Pseudo -Code

13. Advanced Computer Networks : CSFQ13 Label Rewriting At core routers, outgoing rate is merely the minimum between the incoming rate and the fair rate, α. Hence, the packet label L can be rewritten by L new = min (L old, α )

14. Advanced Computer Networks : CSFQ14 Simulations Major effort of the paper is to compare CSFQ to four algorithms via ns-2 simulations. FIFO RED FRED (Flow Random Early Drop) DRR (Deficit Round Robin)

15. Advanced Computer Networks : CSFQ15 FRED (Flow Random Early Drop) Maintains per flow state in router. FRED preferentially drops a packet that has either: – Had many packets dropped in the past – A queue larger than the average queue size Main goal : Fairness FRED-2 guarantees to each flow a minimum number of buffers.

16. Advanced Computer Networks : CSFQ16 DRR (Deficit Round Robin) Represents an efficient implementation of WFQ. A sophisticated per-flow queueing algorithm. Scheme assumes that when router buffer is full the packet from the longest queue is dropped. Can be viewed as “best case” algorithm with respect to fairness.

17. Advanced Computer Networks : CSFQ17 Simulation Details Use TCP, UDP, RLM and On-Off traffic sources in separate simulations. Bottleneck link: 10 Mbps, 1ms latency, 64KB buffer RED, FRED min max thresholds: 16KB, 32KB Constants (K,, K c ) : all 100 ms. KαKα

18. Advanced Computer Networks : CSFQ18 A Single Congested Link First Experiment : 32 UDP flows – Each UDP flow is indexed from 0 to 31 with flow 0 sending at 0.3125 Mbps and each of the i subsequent flows sending (i+ 1) times its fair share of 0.3125 Mbps. Second Experiment : 1 UDP flow, 31 TCP flows – UDP flow sends at 10 Mbps – 31 TCP flows share a single 10 Mbps link.

19. Advanced Computer Networks : CSFQ19 Figure 3a: 32 UDP Flows Only CSFQ and DRR can contain UDP flows!!

20. Advanced Computer Networks : CSFQ20 Figure 3b : One UDP Flow, 31 TCP Flows Only CSFQ and DRR can contain Flow 0 – the only UDP flow!

21. Advanced Computer Networks : CSFQ21 A Single Congested Link Third Experiment Set : 31 simulations – Each simulation has a different N, N = 2 … 32. – One TCP and N-1 UDP flows with each UDP flow sending at twice fair share rate of 10/N Mbps.

22. Advanced Computer Networks : CSFQ22 Figure 4 : One TCP Flow, N-1 UDP Flows Normalized fair share throughput for TCP source DRR good for less than 22 flows. CSFQ better than DRR when a large number of flows. CSFQ beats FRED.

23. Advanced Computer Networks : CSFQ23 Multiple Congested Links Router UDP Sinks TCP/UDP-0 Sink TCP/UDP-0 Source UDP Sources 1 1-10 K1-K10 101120K10K1

24. Advanced Computer Networks : CSFQ24 Figure 6a : UDP source Fraction of UDP-0 traffic forwarded versus the number of congested links.

25. Advanced Computer Networks : CSFQ25 Figure 6b : TCP Source Fraction of TCP-0 traffic forwarded versus the number of congested links.

26. Advanced Computer Networks : CSFQ26 Receiver-driven Layered Multicast RLM is an adaptive scheme in which the source sends the information encoded in a number of layers. Each layer represents a diferent multicast group. Receivers join and leave multicast groups based on packet drop rates experienced.

27. Advanced Computer Networks : CSFQ27 Receiver-driven Layered Multicast Simulation of three RLM flows and one TCP flow. Fair share for each is 1 Mbps. Since router buffer set to 64 KB, K, K c, and are set to 250 ms. KαKα

28. Advanced Computer Networks : CSFQ28 Figure 7a : DRR

29. Advanced Computer Networks : CSFQ29 Figure 7b : CSFQ

30. Advanced Computer Networks : CSFQ30 Figure 7c : FRED

31. Advanced Computer Networks : CSFQ31 Figure 7d : RED

32. Advanced Computer Networks : CSFQ32 Figure 7e : FIFO

33. Advanced Computer Networks : CSFQ33 On-Off Flow Model One approach to modeling interactive, Web traffic :: OFF represents “think time” ON and OFF drawn from exponential distribution with means of 100 ms and 1900 ms respectively. During ON period source sends at 10 Mbps.

34. Advanced Computer Networks : CSFQ34 Table 1 : One On-Off Flow, 19 TCP Flows AlgorithmDeliveredDropped DRR6016157 CSFQ16805078 FRED17145044 RED53221436 FIFO54521306

35. Advanced Computer Networks : CSFQ35 Web Traffic A second approach to modeling Web traffic that uses Pareto Distribution to model the length of a TCP connection. In this simulation 60 TCP flows whose inter-arrivals are exponentially distributed with mean 0.05 ms and Pareto distribution that yields a mean connection length of 20,1 KB packets.

36. Advanced Computer Networks : CSFQ36 Table 2 : 60 Short TCP Flows, One UDP Flow Algorithm Mean Transfer Time for TCP Standard Deviation DRR2599 CSFQ62142 FRED40174 RED5921274 FIFO8401695

37. Advanced Computer Networks : CSFQ37 Table 3 : 19 TCP Flows, One UDP Flow with propagation delay of 100 ms. Algorithm Mean Throughput Standard Deviation DRR608064 CSFQ5761220 FRED4974190 RED62880 FIFO37869

38. Advanced Computer Networks : CSFQ38 Packet Relabeling Router Flow 2 Router Sink Flow 1 Sources Flow 3 Link 2 10 Mbps Link 1 10 Mbps

39. Advanced Computer Networks : CSFQ39 Table 4 : UDP and TCP with Packet Relabeling TrafficFlow 1Flow 2Flow 3 UDP3.363.323.28 TCP3.433.133.43

40. Advanced Computer Networks : CSFQ40 Unfriendly Flows Using TCP congestion control requires cooperation from other flows. Three types cooperation violators: – Unresponsive flows (e.g., Real Audio) – Not TCP-friendly flows – Flows that lie to cheat. This paper deals with unfriendly flows!!

41. Advanced Computer Networks : CSFQ41 Conclusions This paper presents Core Stateless Fair Queueing and offers many simulations to show how CSFQ provides better fairness than RED or FIFO. They mention issue of “large latencies”. This is the robust versus fragile flow issue from FRED paper. CSFQ ‘clobbers’ UDP flows!

42. Advanced Computer Networks : CSFQ42 Significance First paper to use hints from the edge of the subnet. Deals with UDP. Many algorithms do not. Makes a reasonable attempt to look at a variety of traffic types.

43. Advanced Computer Networks : CSFQ43 Problems/ Weaknesses “Epoch” is related to three constants in a way that can produce different results. How does one set K constants for a variety of situations. No discussion of algorithm “stability”

44. Advanced Computer Networks : CSFQ44 Acknowledgments Figures extracted from presentation by Nagaraj Shirali and Choong-Soo Lee in Spring 2002.