Random early detection gateways for congestion avoidance

The authors present random early detection (RED) gateways for congestion avoidance in packet-switched networks. The gateway detects incipient congestion by computing the average queue size. The gateway could notify connections of congestion either by dropping packets arriving at the gateway or by setting a bit in packet headers. When the average queue size exceeds a present threshold, the gateway drops or marks each arriving packet with a certain probability, where the exact probability is a function of the average queue size. RED gateways keep the average queue size low while allowing occasional bursts of packets in the queue. During congestion, the probability that the gateway notifies a particular connection to reduce its window is roughly proportional to that connection's share of the bandwidth through the gateway. RED gateways are designed to accompany a transport-layer congestion control protocol such as TCP. The RED gateway has no bias against bursty traffic and avoids the global synchronization of many connections decreasing their window at the same time. Simulations of a TCP/IP network are used to illustrate the performance of RED gateways. >

[1]  Micha Hofri,et al.  Probabilistic Analysis of Algorithms , 1987, Texts and Monographs in Computer Science.

[2]  Jon Postel,et al.  Something a Host Could Do with Source Quench: The Source Quench Introduced Delay (SQuID) , 1987, RFC.

[3]  Jon Crowcroft,et al.  A new congestion control scheme: slow start and search (Tri-S) , 1991, CCRV.

[4]  Van Jacobson,et al.  Traffic phase effects in packet-switched gateways , 1991, CCRV.

[5]  Debasis Mitra,et al.  Dynamic Adaptive Windows for High Speed Data Networks with Multiple Paths and Propagation Delays , 1993, Comput. Networks ISDN Syst..

[6]  Jon Postel,et al.  Internet Control Message Protocol , 1981, RFC.

[7]  David G. Carta,et al.  Two fast implementations of the “minimal standard” random number generator , 1990, CACM.

[8]  Partho Pratim Mishra,et al.  A hop by hop rate-based congestion control scheme , 1992, SIGCOMM 1992.

[9]  Andrew Harvey,et al.  Forecasting, Structural Time Series Models and the Kalman Filter , 1990 .

[10]  Ashok K. Agrawala,et al.  DTP: An Efficient Transport Protocol , 1992, NETWORKS.

[11]  D. Mitra,et al.  Dynamic adaptive windows for high speed data networks: theory and simulations , 1990, SIGCOMM 1990.

[12]  Yechiam Yemini,et al.  Nest: A Network Simulation and Prototyping Tool , 1988, USENIX Winter.

[13]  David Clark,et al.  Supporting Real-Time Applications in an Integrated Services Packet Network: Architecture and Mechanism , 1992, SIGCOMM.

[14]  Peter C. Young,et al.  Recursive Estimation and Time Series Analysis , 1984 .

[15]  Sally Floyd,et al.  The synchronization of periodic routing messages , 1993, SIGCOMM 1993.

[16]  Sally Floyd,et al.  Issues in Flexible Resource Manage-ment for Datagram Networks , 1992 .

[17]  David Tipper,et al.  The performance of adaptive window flow controls in a dynamic load environment , 1990, Proceedings. IEEE INFOCOM '90: Ninth Annual Joint Conference of the IEEE Computer and Communications Societies@m_The Multiple Facets of Integration.

[18]  V. Jacobson,et al.  Congestion avoidance and control , 1988, CCRV.

[19]  Srinivasan Keshav,et al.  REAL: A Network Simulator , 1988 .

[20]  Jon Crowcroft,et al.  Eliminating periodic packet losses in the 4.3-Tahoe BSD TCP congestion control algorithm , 1992, CCRV.

[21]  L. P. Kok,et al.  Table erratum: A table of series and products [Prentice-Hall, Englewood Cliffs, N.J., 1975] by E. R. Hansen , 1986 .

[22]  Scott Shenker,et al.  Observations on the dynamics of a congestion control algorithm: the effects of two-way traffic , 1991, SIGCOMM '91.

[23]  Debasis Mitra,et al.  Dynamic adaptive windows for high speed data networks: theory and simulations , 1990, SIGCOMM '90.

[24]  Peter C. Young,et al.  Recursive Estimation and Time-Series Analysis: An Introduction , 1984 .

[25]  Israel Cidon,et al.  Congestion control for high speed packet switched networks , 1990, Proceedings. IEEE INFOCOM '90: Ninth Annual Joint Conference of the IEEE Computer and Communications Societies@m_The Multiple Facets of Integration.

[26]  K. K. Ramakrishnan,et al.  Gateway Congestion Control Survey , 1991, RFC.

[27]  Sally Floyd,et al.  Connections with multiple congested gateways in packet-switched networks part 1: one-way traffic , 1991, CCRV.

[28]  W. Hoeffding.  Probability Inequalities for sums of Bounded Random Variables , 1963 .

[29]  Lixia Zhang,et al.  A new architecture for packet switching network protocols , 1989 .

[30]  Srinivasan Keshav.  A control-theoretic approach to flow control , 1991, SIGCOMM 1991.

[31]  Raj Jain,et al.  A delay-based approach for congestion avoidance in interconnected heterogeneous computer networks , 1989, CCRV.

[32]  Eman Salaheddin Hashem,et al.  Analysis of Random Drop for Gateway Congestion Control , 1989 .

[33]  K. K. Ramakrishnan,et al.  A binary feedback scheme for congestion avoidance in computer networks with a connectionless network layer , 1988, SIGCOMM '88.

[34]  E. Hansen.  A Table of Series and Products , 1977 .

[35]  Van Jacobson,et al.  The synchronization of periodic routing messages , 1994, TNET.

[36]  KeshavSrinivasan.  A control-theoretic approach to flow control , 1991 .

[37]  Raj Jain,et al.  Myths about Congestion Management in High Speed Networks , 1992, INDC.

[38]  R. Jain.  Congestion control in computer networks: issues and trends , 1990, IEEE Network.

[39]  Van Jacobson,et al.  The synchronization of periodic routing messages , 1993, SIGCOMM '93.

[40]  A. Romanow.  TCP over ATM with Congestion: Some Performance Results , 1993, Proceedings of the 6th IEEE Workshop on Local and Metropolitan Area Networks.

[41]  K. K. Ramakrishnan,et al.  A binary feedback scheme for congestion avoidance in computer networks with a connectionless network layer , 1995, CCRV.