1 / 20

Understanding TCP Dynamics in an Integrated Services Internet

Understanding TCP Dynamics in an Integrated Services Internet. Wu-chang Feng, Dilip Kandlur, Debanjan Saha, and Kang Shin. Motivation. Many TCP-based applications can take advantage of guarantees in the network Majority of these applications don’t require strict delay bound guarantees

cmarlow
Download Presentation

Understanding TCP Dynamics in an Integrated Services Internet

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. Understanding TCP Dynamics in an Integrated Services Internet Wu-chang Feng, Dilip Kandlur, Debanjan Saha, and Kang Shin NOSSDAV '97

  2. Motivation • Many TCP-based applications can take advantage of guarantees in the network • Majority of these applications don’t require strict delay bound guarantees • Examples • Non-interactive audio and video • Data streaming applications • Elastic applications (ftp, http) NOSSDAV '97

  3. Controlled-load Service • IETF defined service which provides more flexible guarantees to applications than Guaranteed Service • Application provides TSpec • Compliant traffic receives service similar to that in an “unloaded” network • Non-compliant traffic is treated as best-effort NOSSDAV '97

  4. Question Can TCP-based applications take advantage of a network which provides controlled-load service? NOSSDAV '97

  5. System Model • Source • Compliance check done at the source using a token bucket filter derived from TSpec • Compliant packets sent marked • Non-compliant packets sent unmarked • Network • Enhanced Random Early Detection (ERED) NOSSDAV '97

  6. Source Model Sending source TCP Send Compliance Check Network NOSSDAV '97

  7. Network support • RED queues • Random early packet dropping for congestion avoidance • Keep queue lengths small • Avoid synchronization • Remove biases against bursty traffic NOSSDAV '97

  8. Enhanced RED queues (ERED) • Same as RED, but marked packets have a much lower drop probability than unmarked packets • Single queue implementation • Retains FIFO ordering • Does not require per-flow information in the data forwarding path NOSSDAV '97

  9. Example scenario • Reserved connections should get reserved rate and a share of the excess bandwidth • 3 sources with 1Mbs, 2Mbs and 4Mbs policed with token buckets of depth 50ms • 3 best-effort sources • 80KB ERED queues at each router • Simulated using ns-1.1 S D 10Mb 10Mb 10Mb 10Mb 45Mb NOSSDAV '97

  10. TCP with reservations NOSSDAV '97

  11. Problem • TCP uses acknowledgement based triggers to send data • Well-known problem of ACK compression which can cause gaps in ACK stream • Transmission credits build up in token bucket as TCP waits for an ACK • Credits overflow and are lost NOSSDAV '97

  12. TCP losing tokens S D NOSSDAV '97

  13. TCP timer modification After every acknowledgement if (room under cwnd and awnd) if (tokens available > packet size) send packet marked else send packet unmarked After every timer expiry reset timer if (room under awnd) if (tokens available > packet size) send packet marked NOSSDAV '97

  14. TCP timer modification NOSSDAV '97

  15. TCP timer modification NOSSDAV '97

  16. Rate-adaptive windowing Normal Windowing Window Size Time Rate Adaptive Windowing Window Size Time NOSSDAV '97

  17. TCP windowing modification After every new acknowledgement if (cwnd < ssthresh) cwnd = cwnd + (cwnd-rwnd)/cwnd elsecwnd = cwnd + 1/cwnd Upon detection of loss from DUPACKs cwnd = rwnd + (cwnd-rwnd)/2 + ndup ssthresh = rwnd + (cwnd-rwnd)/2 Upon RTO cwnd = rwnd + 1 ssthresh = rwnd + (cwnd-rwnd)/2 NOSSDAV '97

  18. TCP w/ timer and window mods NOSSDAV '97

  19. Additional Experiments • Performance when a subset or when no network routers support service differentiation • Integration into a more elaborate packet scheduling and/or link scheduling experiments • Influence on pricing • Reservations vs. adaptation NOSSDAV '97

  20. Summary • TCP’s ack-clocking and windowing algorithm limit its performance in an integrated services environment • Fine-grained timer and rate-adaptive windowing can solve this problem • Extended version and simulation results at http://www.eecs.umich.edu/~wuchang/ered/ TCP Brooklyn? NOSSDAV '97 (We don’t play chess all day)

More Related