By Sam Rossoff. The Red Police Controlling High- Bandwidth Flows at the Congested Router By Ratul Mahajan Sally Floyd and David Wetherall.

Slides:



Advertisements
Similar presentations
Balaji Prabhakar Active queue management and bandwidth partitioning algorithms Balaji Prabhakar Departments of EE and CS Stanford University
Advertisements

RED-PD: RED with Preferential Dropping Ratul Mahajan Sally Floyd David Wetherall.
Computer Networking Lecture 20 – Queue Management and QoS.
RED Enhancement Algorithms By Alina Naimark. Presented Approaches Flow Random Early Drop - FRED By Dong Lin and Robert Morris Sabilized Random Early Drop.
WHITE – Achieving Fair Bandwidth Allocation with Priority Dropping Based on Round Trip Time Name : Choong-Soo Lee Advisors : Mark Claypool, Robert Kinicki.
CSIT560 Internet Infrastructure: Switches and Routers Active Queue Management Presented By: Gary Po, Henry Hui and Kenny Chong.
Transport Layer3-1 TCP AIMD multiplicative decrease: cut CongWin in half after loss event additive increase: increase CongWin by 1 MSS every RTT in the.
Congestion Control: TCP & DC-TCP Swarun Kumar With Slides From: Prof. Katabi, Alizadeh et al.
CS 268: Lecture 8 Router Support for Congestion Control Ion Stoica Computer Science Division Department of Electrical Engineering and Computer Sciences.
CS 4700 / CS 5700 Network Fundamentals Lecture 12: Router-Aided Congestion Control (Drop it like it’s hot) Revised 3/18/13.
5/17/20151 Adaptive RED: An Algorithm for Increasing the Robustness of RED’s Active Queue Management or How I learned to stop worrying and love RED Presented.
TFRC for Voice: the VoIP Variant Sally Floyd, Eddie Kohler. March 2005, presentation to AVT draft-ietf-dccp-tfrc-voip-01.txt.
Ion Stoica, Scott Shenker, and Hui Zhang SIGCOMM’98, Vancouver, August 1998 subsequently IEEE/ACM Transactions on Networking 11(1), 2003, pp Presented.
Max Min Fairness How define fairness? “ Any session is entitled to as much network use as is any other ” ….unless some sessions can use more without hurting.
XCP: Congestion Control for High Bandwidth-Delay Product Network Dina Katabi, Mark Handley and Charlie Rohrs Presented by Ao-Jan Su.
1 Core-Stateless Fair Queueing: A Scalable Architecture to Approximate Fair Bandwidth Allocations in High Speed Networks Core-Stateless Fair Queueing:
Controlling High- Bandwidth Flows at the Congested Router Ratul Mahajan, Sally Floyd, David Wetherall AT&T Center for Internet Research at ICSI (ACIRI)
EE689 Lecture 5 Review of last lecture More on HPF RED.
15-744: Computer Networking L-11 Queue Management.
1 Random Early Detection Gateways for Congestion Avoidance Sally Floyd and Van Jacobson, IEEE Transactions on Networking, Vol.1, No. 4, (Aug 1993), pp
1 Core-Stateless Fair Queueing: Achieving Approximately Fair Bandwidth Allocations in High Speed Networks Ion Stoica,Scott Shenker, and Hui Zhang SIGCOMM’99,
Stochastic Fair Traffic Management for Efficient and Robust IP Networking Jae Chung Airvana Inc. Chelmsford, MA Mark Claypool, Robert Kinicki WPI.
1 Emulating AQM from End Hosts Presenters: Syed Zaidi Ivor Rodrigues.
Active Queue Management Rong Pan Cisco System EE384y Spring Quarter 2006.
Random Early Detection Gateways for Congestion Avoidance
1 Core-Stateless Fair Queueing: Achieving Approximately Fair Bandwidth Allocations in High Speed Networks Ion Stoica,Scott Shenker, and Hui Zhang SIGCOMM’99,
Promoting the Use of End-to-End Congestion Control & Random Early Detection of Network Congestion.
Congestion Control for High Bandwidth-delay Product Networks Dina Katabi, Mark Handley, Charlie Rohrs.
Core Stateless Fair Queueing Stoica, Shanker and Zhang - SIGCOMM 98 Rigorous fair Queueing requires per flow state: too costly in high speed core routers.
UCB Improvements in Core-Stateless Fair Queueing (CSFQ) Ling Huang U.C. Berkeley cml.me.berkeley.edu/~hlion.
Advanced Computer Networks : RED 1 Random Early Detection Gateways for Congestion Avoidance Sally Floyd and Van Jacobson, IEEE Transactions on Networking,
Core Stateless Fair Queueing Stoica, Shanker and Zhang - SIGCOMM 98 Fair Queueing requires per flow state: too costly in high speed core routers Yet, some.
1 Queue Management Hamed Khanmirza Principles of Networking University of Tehran.
Bandwidth partitioning (jointly with R. Pan, C. Psounis, C. Nair, B. Yang, L. Breslau and S. Shenker)
ACN: CSFQ1 CSFQ Core-Stateless Fair Queueing Presented by Nagaraj Shirali Choong-Soo Lee ACN: CSFQ1.
Link Scheduling & Queuing COS 461: Computer Networks
CS 268: Computer Networking L-6 Router Congestion Control.
Advance Computer Networking L-6 TCP & Routers Acknowledgments: Lecture slides are from the graduate level Computer Networks course thought by Srinivasan.
ACN: RED paper1 Random Early Detection Gateways for Congestion Avoidance Sally Floyd and Van Jacobson, IEEE Transactions on Networking, Vol.1, No. 4, (Aug.
Congestion Control - Supplementary Slides are adapted on Jean Walrand’s Slides.
TFRC for Voice: the VoIP Variant Sally Floyd, Eddie Kohler. August 2005 draft-ietf-dccp-tfrc-voip-02.txt Slides:
Presented by: Peng Wang EE Department University of Delaware A Probabilistic Approach for Achieving Fair Bandwidth Allocation in CSFQ.
1 Congestion Control Computer Networks. 2 Where are we?
Stochastic Fair Blue: A Queue Management Algorithm for Enforcing Fairness W. Feng, D. Kandlur, D. Saha, and K. Shin Presented by King-Shan Lui.
Queueing and Active Queue Management Aditya Akella 02/26/2007.
The Impact of Active Queue Management on Multimedia Congestion Control Wu-chi Feng Ohio State University.
9.7 Other Congestion Related Issues Outline Queuing Discipline Avoiding Congestion.
Packet Scheduling and Buffer Management Switches S.Keshav: “ An Engineering Approach to Networking”
15744 Course Project1 Evaluation of Queue Management Algorithms Ningning Hu, Liu Ren, Jichuan Chang 30 April 2001.
TFRC for Voice: the VoIP Variant Sally Floyd, Eddie Kohler. March draft-ietf-dccp-tfrc-voip-01.txt
Promoting the Use of End-to-End Congestion Control in the Internet Sally Floyd and Kevin Fall IEEE-ACAM Transactions on Networking, 馬儀蔓.
Thoughts on the Evolution of TCP in the Internet (version 2) Sally Floyd ICIR Wednesday Lunch March 17,
We used ns-2 network simulator [5] to evaluate RED-DT and compare its performance to RED [1], FRED [2], LQD [3], and CHOKe [4]. All simulation scenarios.
1 Core-Stateless Fair Queueing: A Scalable Architecture to Approximate Fair Bandwidth Allocations in High Speed Networks Core-Stateless Fair Queueing:
© Janice Regan, CMPT 128, CMPT 371 Data Communications and Networking Congestion Control 0.
Congestion Avoidance Created by M Bateman, A Ruddle & C Allison As part of the TCP View project.
1 Sheer volume and dynamic nature of video stresses network resources PIE: A lightweight latency control to address the buffer problem issue Rong Pan,
CS492B Project #2 TCP Tutorial # Jin Hyun Ju.
Univ. of TehranIntroduction to Computer Network1 An Introduction Computer Networks An Introduction to Computer Networks University of Tehran Dept. of EE.
Corelite Architecture: Achieving Rated Weight Fairness
CS 268: Computer Networking
Topics discussed in this section:
Johns Hopkins university
Router-Assisted Congestion Control
TFRC for Voice: VoIP Variant and Faster Restart.
Core-Stateless Fair Queueing: A Scalable Architecture to Approximate Fair Bandwidth Allocations in High Speed Networks Ion Stoica, Scott Shenker, and Hui.
Advance Computer Networking
EE 122: Router Support for Congestion Control: RED and Fair Queueing
Max Min Fairness How define fairness?
Adaptive RED: An Algorithm for Increasing the Robustness of RED’s Active Queue Management or How I learned to stop worrying and love RED Presented by:
Presentation transcript:

By Sam Rossoff

The Red Police Controlling High- Bandwidth Flows at the Congested Router By Ratul Mahajan Sally Floyd and David Wetherall

By Sam Rossoff Networking 101 ● Modern routers use a simple FIFO queue ● When a router runs out of room to store packets new packets are dropped from the end of the queue Internet | | | | | | | | | | | | | Router Destination

By Sam Rossoff Pushy Flows ● Because a router's bandwidth is fixed, if a single flow is very large it will hog up all the room on the queue ● Solution: Restrict the bandwidth of large flows

By Sam Rossoff Try Try Again ● Previous approaches break up into two categories ● Continuum: (SFQ, FIFO, etc) ● Scheduling: (CSFQ, FRED, RED, etc)

By Sam Rossoff Schedules and You ● CHOKe – Find a packet at random, compare to incoming packet and nuke both if same flow. – Limited performance: ● When there are too many high ● With high UDP flows ● CSFQ: Core Stateless Fair Queuing – Estimates packets fair share and drops based on rate estimate and fair share – Requires: ● Core “island” of routers ● Extra field in packet header

By Sam Rossoff The Design ● We really only need to worry about the big flows

By Sam Rossoff On Beyond Zebra ● This works because: – A Fraction of the flows make up most of the bandwidth – Predictable effect on the traffic going through the router

By Sam Rossoff The SEC Algorithm  Use the RED drop history  To identify flows that are sending more than ƒ ( r, p ), the reference TCP flow’s rate ( RTT r and packet drop rate p ). And thus dropping more than once in CL( r,p ) seconds.

By Sam Rossoff Epoch's are Fun  Congestion epoch length  Maintaining the packet drop history over K x CL ( R, p ) seconds  Partitioning the history into M lists  RED-PD identifies flows with losses in at least K of M lists  K = 3, M = 5, r = 40 ms and p = 1%

By Sam Rossoff But, Does it work? Flow 1:.1mbps Flow 2:.5 mbps Flow i: Rate(i-1) +.5mbps Identifying: g x f(R, p)

By Sam Rossoff I'm Going to Go with Yes ● RED-FD responds based on the drop rate. ● Few drops and flows run wild 1 CBR flow and 9 TCP flows The CBR flow starts with a rate of 0.25 Mbps, increases it to 4 Mbps at t=50s, and decreases it back to 0.25 Mbps at t=250s. The RTT of the TCP flows ranged from 30 to 70 ms.

By Sam Rossoff And Other Fun Facts on Cereal Boxes ● For flows identified as unresponsive, RED-PD increases the drop probability more quickly. ● Memory Required is only: ● RED-PD targets flows dropped from either itself, RED, or overflow ● Nets of these routers have faster response times and are more effecient.

By Sam Rossoff RED-PD Protects the Innocent ● Even works when there are a few flows of enormous bandwidth coming in. Flow 10: 5mbps Flow 11: 3mbps Flow 12: 1mbps

By Sam Rossoff Which is Why I Think I Would Make a Good President Now for my opponent who is a poopoo head