1 / 38

Testing TCP Westwood+ over Transatlantic Links at 10 Gigabit/Second rate

Testing TCP Westwood+ over Transatlantic Links at 10 Gigabit/Second rate. Giuseppe Racanelli Summer student at CERN IT DIVISION. Saverio Mascolo Dipartimento di Elettrotecnica ed Elettronica Politecnico di Bari Via Orabona 4, Bari, Italy. PFLDNET 05, Feb. 3, 2005, Lyon. Motivation.

yestin
Download Presentation

Testing TCP Westwood+ over Transatlantic Links at 10 Gigabit/Second rate

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Testing TCP Westwood+ over Transatlantic Links at 10 Gigabit/Second rate Giuseppe Racanelli Summer student at CERN IT DIVISION Saverio Mascolo Dipartimento di Elettrotecnica ed Elettronica Politecnico di Bari Via Orabona 4, Bari, Italy PFLDNET 05, Feb. 3, 2005, Lyon

  2. Motivation • Recent introduction of 10 Gigabit Routers and 10 Gigabit Ethernet cards makes of great importance the issue of designing and testing new protocols capable of efficient utilization of 10 gigabit Internet paths Saverio Mascolo – PFLDNET’05

  3. Outline • Brief summary of problems of TCP over Gigabit nets • Brief description of Westwood+ TCP • Performance evaluation of Westwood+ over the DataTAG at CERN IT division Saverio Mascolo – PFLDNET’05

  4. Standard TCP troughput • The long-term throughput T of standard TCP can be approximated as • which sets a fundamental limitation for the TCP Saverio Mascolo – PFLDNET’05

  5. In other terms… • To fill a high speed path with bandwidth B it is necessary to open a congestion window Saverio Mascolo – PFLDNET’05

  6. Required packet loss • which requires a packet loss probability • i.e., to obtain full link utilization, a lower and lower p is required with increasing B. Saverio Mascolo – PFLDNET’05

  7. From S. Floyd draft on HS-TCP • A Standard TCP connection with 1500-byte packets and a 100 ms round-trip time would require an average congestion window of 83,333 segments to achieve a steady-state throughput of 10 Gbps in the presence of a packet drop rate of at most one loss event every 5,000,000 packets. The average packet drop rate of at most 2*10^-10, which is needed for full link utilization in this scenario, corresponds to a bit error rate of at most 2*10^-14 , which is unrealistic for current networks. Saverio Mascolo – PFLDNET’05

  8. Reasons to investigate Westwood+ • For these considerations, the main idea of Westwood+, which consists of shrinking the control windows after congestion by taking into account an estimate of the available bandwidth, is valuable of investigation in the context of very high speed networks. Saverio Mascolo – PFLDNET’05

  9. WESTWOOD+ TCP • key ideaof Westwood+: • use the stream of ack packets to get an e2e estimateof the available bandwidth to be used for setting cwnd and ssthreshafter congestion (whereas standard TCP implements a “blind” by half window decrease) Saverio Mascolo – PFLDNET’05

  10. TCP Westwood+ cwnd Adaptive decrease cwnd=ssthr=BWE*RTTmin Congestion Avoidance ssthresh Timeout BWE*RTTmin time Slow start Westwood Adaptive decrease vs (New) Reno blind by ½ window shrinking Saverio Mascolo – PFLDNET’05

  11. E2E bandwidth estimation • The rate of returning ACKS is exploited to estimate the “best-effort” available bandwidth packets packets SENDER RECEIVER Network Filter Bandwidth estimate ACKs ACKs

  12. Warning… • ACKs reach the TCP sender compressed • Bandwidth samples contain high frequency components that cannot be filtered out by a discrete-time filter due to aliasing Saverio Mascolo – PFLDNET’05

  13. An anti-aliasing filter in packet networks Antialiased samples Saverio Mascolo – PFLDNET’05

  14. We are currently using the standard exponential filter Saverio Mascolo – PFLDNET’05

  15. Summary on bandwidth estimate • Westwood TCP: one bandwidth sample computed for each ACK (Mobicom 01)=>> Bandwdith overestiamte (when ACK compression) • Westwood+ TCP: one bandwidth sample for each RTT (see ACM CCR, April 04) Saverio Mascolo – PFLDNET’05

  16. Known Advantages of Westwood+ TCP • higher throughput over wireless links because losses due to unreliable links do not provoke overshrinking of the congestion window • Improved fairness wrt to Reno (Reno throughput is proportional to 1/RTT whereas Westwood throughput is proportional to 1/sqrt(RTT) )

  17. Pseudo code of Westwood+ • a) On ACK reception: -cwnd is increased accordingly to the Reno algorithm; -an estimate BWE of the available bandwdith is computed; • b) When 3 DUPACKs are received: ssthresh =max(2, (BWE* RTTmin) / seg_size); cwnd = ssthresh;  • c) When coarse timeout expires: ssthresh = max(2,(BWE* RTTmin) / seg_size); cwnd = 1; Saverio Mascolo – PFLDNET’05

  18. Experimental testbed Saverio Mascolo – PFLDNET’05

  19. Single Stream Tests • congestion window and slow start threshold of a single TCP NewReno stream over a 10Gbps. At t=180s, due to a loss,cwnd reduces from 2.5*10^8 bytes to 2.7*10^7 bytes and the TCP enters the congestion avoidance phase. Saverio Mascolo – PFLDNET’05

  20. Instantaneous and mean throughput of NewReno TCP • it is around 1.8Gbps, which is less than one fifth of the channel capacity. Saverio Mascolo – PFLDNET’05

  21. cwnd and ssthresh dynamics obtained in the same scenario using Westwood+ TCP • cwnd after congestion reduces from 2.5*10^8 bytes to 2.3*10^8 bytes, which is remarkably larger than the corresponding value obtained using New Reno. Saverio Mascolo – PFLDNET’05

  22. Instantaneous and mean throughput of Westwood+ TCP • the achieved throughput is now around 7 Gbps Saverio Mascolo – PFLDNET’05

  23. Cwnd and ssthresh of Westwood+ TCP • an UDP stream at 5Gbps is injected for few seconds; the slow start threshold is set to 3.5*10^7 bytes after congestion and, again, it takes a long time for the TCP in congestion phase to grab all the bandwidth available after the UDP is turned off. Saverio Mascolo – PFLDNET’05

  24. Throughput of Westwood+ • UDP active for a while: around one tenth of the available bandwidth (i.e. 1.2 Gbps) is achieved. Saverio Mascolo – PFLDNET’05

  25. TCP Westwood+ with a modified probing phase à la Scalable TCP ·   on ACK reception; If ssthresh < = cwnd < window_threshold cwnd=cwnd+1/cwnd; If cwnd> window_threshold cwnd=cwnd+0.04 By increasing cwnd of 0.04 on every ack reception, cwnd increases of one twenty-fifth per RTT, i.e., the growth is greater with larger windows. Saverio Mascolo – PFLDNET’05

  26. cwnd and ssthresh of Westwood+ TCP using the modified congestion avoidance • UDP active for a while Saverio Mascolo – PFLDNET’05

  27. Westwood+ TCP using a modified probing phase • In this case, even though the setting of the threshold is below the network capacity, the congestion window quickly increases and provides good results in terms of average throughput, which jumps to 6.2 Gbps Saverio Mascolo – PFLDNET’05

  28. Multiple Stream Tests • The testbed is the10Gbps connection going from Geneva to Chicago, wherethe link between the Cisco router 7606 at Geneva and the Extreme router s01gva is at 1 Gbps link. • To investigate fairness in bandwidth utilization we consider 3 flows sharing the bottleneck. Saverio Mascolo – PFLDNET’05

  29. Cwnd of 3 NewReno flows New Reno flows exhibit the classic “sawtooth” oscillatorybehaviour of the cwnddue to the by half window reduction. Saverio Mascolo – PFLDNET’05

  30. Cwnd of 3 Westwood+ flows • REMARK: oscillation free behavior (the congestion window is kept around the same value of 5*10^06 byte during all the test) Saverio Mascolo – PFLDNET’05

  31. Throughput - 3 New Reno flows • the average per-connection throughput in the case of New Reno is 270 Mbps Saverio Mascolo – PFLDNET’05

  32. Throughput - 3 Westwood+ streams • the average per-connection throughput in the case of Westwood+ is 320 Mbps. Saverio Mascolo – PFLDNET’05

  33. Fairness • To provide a mathematical evaluation of the fairness, we plot the dynamics of the Jain fairness index defined as below: where bi(t) is the instantaneous throughput of the ith connection and M is the number of connections sharing the bottleneck. The Jain fairness index belongs to the interval [0,1] and increases with fairness up to the value of one. Saverio Mascolo – PFLDNET’05

  34. Jain Fairness Index of 3 NewReno flows Saverio Mascolo – PFLDNET’05

  35. Jain Fairness Index of 3 Westwood+ flows Saverio Mascolo – PFLDNET’05

  36. Conclusions Saverio Mascolo – PFLDNET’05 The setting of the cwnd and ssthresh a là Westwood provides improvement in throughput and fairness wrt NewReno TCP also in the context of gigabit networks. We plan to make much more experiments We plan to blend the Westwood+ features with more aggresive probing phases such as the ones of Scalable TCP or HS-TCP

  37. ACKNOWLEDGMENTS Saverio Mascolo – PFLDNET’05 We thank Olivier Martin at the IT division of CERN and all the CS group, namely: Sylvain Ravot, Paolo Moroni, Edoardo Martelli and Dan Nae (from Caltech) for their great support and for allowing us to collect measurements reported in this paper.

  38. Thanks for the attention and Questions? Saverio Mascolo – PFLDNET’05

More Related