codel
play

CoDel present by Van Jacobson to the IETF-84 Transport Area Open - PowerPoint PPT Presentation

Feb 18, 2023 •203 likes •577 views

Kathie Nichols CoDel present by Van Jacobson to the IETF-84 Transport Area Open Meeting 30 July 2012 Vancouver, Canada 2 3 Sender Receiver 4 Sender Receiver 5 Sender Receiver Queue forms at a bottleneck Theres probably

  1. Kathie Nichols’ CoDel present by Van Jacobson to the IETF-84 Transport Area Open Meeting 30 July 2012 Vancouver, Canada

  2. 2

  3. 3

  4. Sender Receiver 4

  5. Sender Receiver 5

  6. Sender Receiver • Queue forms at a bottleneck • There’s probably just one bottleneck (each flow sees exactly one) ➡ Choices: can move the queue (by making a new bottleneck) or control it. 5

  7. Good Queue / Bad Queue Queue length Time 6

  8. Good Queue / Bad Queue Queue length Time Queue length Time 6

  9. Good Queue / Bad Queue • Good queue goes Queue length away in an RTT, bad queue hangs around. ➡ queue length min() over a sliding window Time measures bad queue ... Queue length ➡ ... as long as window is at least an RTT wide. Time 7

  10. Good Queue / Bad Queue • Good queue goes Queue length away in an RTT, bad queue hangs around. ➡ tracking min() in a sliding window gives Time bad queue ... Queue length ➡ ... as long as window is at least an RTT wide. Time 8

  11. Good Queue / Bad Queue • Good queue goes Queue length away in an RTT, bad queue hangs around. ➡ tracking min() in a sliding window gives Time bad queue ... Queue length ➡ ... as long as window is at least an RTT wide. Time 8

  12. How big is the queue? • Can measure size in bytes – interesting if worried about overflow – requires output bandwidth to compute delay • Can measure packet’s sojourn time – direct measure of delay – easy (no enque/deque coupling so works with any packet pipeline). 9

  13. Sojourn Time • Works with time-varying output bandwidth (e.g., wireless and shared links) • Better behaved than queue length – no high frequency phase noise • Includes everything that affects packet so works for multi-queue links 10

  14. 6 5 Two views of a Queue 4 Q delay (ms.) 3 2 1 Top graph is sojourn time, 0 24.5 25.0 25.5 26.0 bottom is queue size. Time (sec.) 6 5 4 Q size (ms.) 3 (one ftp + web traffic; 2 10Mbps bottleneck; 1 80ms RTT; TCP Reno) 11 0

  15. 6 5 Two views of a Queue 4 Q delay (ms.) 3 2 1 Top graph is sojourn time, 0 24.5 25.0 25.5 26.0 bottom is queue size. Time (sec.) 6 5 4 Q size (ms.) 3 (one ftp + web traffic; 2 10Mbps bottleneck; 1 80ms RTT; TCP Reno) 11 0

  16. 2.0 Two views of a Queue 1.5 Q delay (ms.) 1.0 0.5 0.0 Top graph is sojourn time, 25.00 25.05 25.10 25.15 25.20 bottom is queue size. Time (sec.) 2.5 2.0 1.5 Q size (ms.) (one ftp + web traffic; 1.0 10Mbps bottleneck; 0.5 80ms RTT; TCP Reno) 12 0.0

  17. Multi-Queue behavior 13

  18. Controlling Queue a) Measure what you’ve got b) Decide what you want c) If (a) isn’t (b), move it toward (b) 14

  19. Controlling Queue - Estimator a) Measure what you’ve got - Setpoint b) Decide what you want - Control loop c) If (a) isn’t (b), move it toward (b) 15

  20. How much ‘bad’ queue do we want? • Can’t let the link go idle (need one or two MTU of backlog) • More than this will give higher utilization at low degree of multiplexing (1-3 bulk xfers) at the cost of higher delay • Can the trade-off be quantified? 16

  21. Utilization vs. Target for a single Reno TCP 100 95 Bottleneck Link Utilization (% of max) 90 85 80 75 0 20 40 60 80 100 Target (% of RTT) 17

  22. Power vs. Target for a Reno TCP 1.00 0.95 0.90 Average Power (Xput/Delay) 0.85 0.80 0.75 0.70 0 20 40 60 80 100 Target (as % of RTT) 18

  23. Power vs. Target for a Reno TCP 1.00 0.95 0.90 Average Power (Xput/Delay) 0.85 0.80 0.75 0.70 0 20 40 60 80 100 Target (as % of RTT) 18

  24. Power vs. Target for a Reno TCP 1.00 0.99 0.98 Average Power (Xput/Delay) 0.97 0.96 0.95 0.94 0.93 0 5 10 15 20 25 30 Target (as % of RTT) 19

  25. Power vs. Target for a Reno TCP 1.00 0.99 0.98 Average Power (Xput/Delay) 0.97 0.96 0.95 0.94 0.93 0 5 10 15 20 25 30 Target (as % of RTT) 19

  26. 20

  27. • Setpoint target of 5% of nominal RTT (5ms for 100ms RTT) yields substantial utilization improvement for small added delay. 20

  28. • Setpoint target of 5% of nominal RTT (5ms for 100ms RTT) yields substantial utilization improvement for small added delay. • Result holds independent of bandwidth and congestion control algorithm (tested with Reno, Cubic & Westwood). 20

  29. • Setpoint target of 5% of nominal RTT (5ms for 100ms RTT) yields substantial utilization improvement for small added delay. • Result holds independent of bandwidth and congestion control algorithm (tested with Reno, Cubic & Westwood). ➡ CoDel has no free parameters: running- min window width determined by worst- case expected RTT and target is a fixed fraction of same RTT. 20

  30. Algorithm & Control Law (see I-D, CACM paper and Linux kernels >= 3.5) 21

  31. Eric Dumazet has combined CoDel with a simple SFQ (256-1024 buckets with RR service discipline). Cost in state & cycles is small and improvement is big. • provides isolation - protects low rate CBR and web for a better user experience. Makes IW1 0 concerns a non-issue. • gets rid of bottleneck bi-directional traffic problems (‘ack-compression’ burstiness) • improves flow mixing for better network performance (reduce HoL blocking) ➡ Since we’re adding code, add fqcodel, not codel. 22

  32. Where are we? • thanks to Jim Gettys and the ACM, have dead-tree publication to protect ideas • un-encumbered code (BSD/GPL dual-license) available for ns2, ns3 & linux • in both simulation and real deployment, CoDel does no harm – it either does nothing or reduces delay without affecting xput. 23

  33. What needs to be done • Still looking at parts of the algorithm but changes likely to be 2nd order. • Would like to see CoDel on both ends of every home/small-office access link but: - We need to know more about how traffic behaves on particular bottlenecks (wi-fi, 3G cellular, cable modem) - There are system issues with deployment 24

  34. Deployment Issues Cable Home RTR/AP Headend Modem Gateway 25

  35. Deployment Issues Cable Home RTR/AP Headend Modem Gateway Protocol Device Linux Device stack Driver kernel 26

  36. Deployment Issues Cable Home RTR/AP Headend Modem Gateway Protocol Device Linux Device stack Driver kernel Phone 3G ? RAN SGSN Cellphone CPU Modem 27

  37. Our thanks to: • Jim Gettys • CoDel early experimenters, particularly Dave Taht • Eric Dumazet • ACM Queue • Eben Moglen 28

More recommend