Scheduling to Minimize theWorst-Case Loss Rate

We study link scheduling in networks with small router buffers, with the goal of minimizing the guaranteed packet loss rate bound for each ingress-egress traffic aggregate (connection). Given a link scheduling algorithm (a service discipline and a packet drop policy), the guaranteed loss rate for a connection is the loss rate under worst-case routing and bandwidth allocations for competing traffic. Under simplifying assumptions, we show that a local min-max fairness property with respect to apportioning loss events among the connections sharing each link, and a condition on the correlation of scheduling decisions at different links are two necessary and (together) sufficient conditions for optimality in the minimization problem. Based on these conditions, we introduce a randomized link-scheduling algorithm called rolling priority where packet scheduling at each link relies exclusively on local information. We show that RP satisfies both conditions and is therefore optimal.

[1]  Guido Appenzeller,et al.  Sizing router buffers , 2004, SIGCOMM '04.

[2]  Mor Harchol-Balter,et al.  Bounding delays in packet-routing networks , 1995, STOC '95.

[3]  Mohamed G. Gouda,et al.  Time-shift scheduling—fair scheduling of flows in high-speed networks , 1998, TNET.

[4]  Allan Borodin,et al.  Adversarial queuing theory , 2001, JACM.

[5]  Cheng-Shang Chang,et al.  Performance guarantees in communication networks , 2000, Eur. Trans. Telecommun..

[6]  Tim Roughgarden,et al.  Routers with Very Small Buffers , 2006, Proceedings IEEE INFOCOM 2006. 25TH IEEE International Conference on Computer Communications.

[7]  Van Jacobson,et al.  Random early detection gateways for congestion avoidance , 1993, TNET.

[8]  Keith W. Ross,et al.  A framework for guaranteeing statistical QoS , 2002, TNET.

[9]  Rami G. Melhem,et al.  Analysis of a transmission scheduling algorithm for supporting bandwidth guarantees in bufferless networks , 2006, PERV.

[10]  Eyal Gordon,et al.  Competitive weighted throughput analysis of greedy protocols on DAGs , 2005, PODC '05.

[11]  Marco Ajmone Marsan,et al.  Joint optimal scheduling and routing for maximum network throughput , 2005, INFOCOM 2005.

[12]  Edward W. Knightly,et al.  Coordinated multihop scheduling: a framework for end-to-end services , 2002, TNET.

[13]  Abhay Parekh,et al.  A generalized processor sharing approach to flow control in integrated services networks-the multiple node case , 1993, IEEE INFOCOM '93 The Conference on Computer Communications, Proceedings.

[14]  Nick McKeown,et al.  Making router buffers much smaller , 2005, CCRV.

[15]  N. McKeown,et al.  Buffer sizing in all-optical packet switches , 2006, 2006 Optical Fiber Communication Conference and the National Fiber Optic Engineers Conference.

[16]  Rafail Ostrovsky,et al.  Dynamic routing on networks with fixed-size buffers , 2003, SODA '03.

[17]  Christophe Diot,et al.  Reasons not to deploy RED , 1999, 1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354).

[18]  Rami G. Melhem,et al.  Node delay assignment strategies to support end-to-end delay requirements in heterogeneous networks , 2004, IEEE/ACM Transactions on Networking.

[19]  Cheng-Shang Chang,et al.  Constructions of optical FIFO queues , 2006, IEEE Transactions on Information Theory.

[20]  Jorma T. Virtamo,et al.  The superposition of periodic cell arrival streams in an ATM multiplexer , 1991, IEEE Trans. Commun..

[21]  27th International Conference on Distributed Computing Systems Workshops (ICDCS 2007 Workshops), June 25-29, 2007, Toronto, Ontario, Canada , 2007, ICDCS Workshops.

[22]  Nick McKeown,et al.  Matching output queueing with a combined input output queued switch , 1999, IEEE INFOCOM '99. Conference on Computer Communications. Proceedings. Eighteenth Annual Joint Conference of the IEEE Computer and Communications Societies. The Future is Now (Cat. No.99CH36320).

[23]  Hao Jiang,et al.  Buffer sizing for congested Internet links , 2005, Proceedings IEEE 24th Annual Joint Conference of the IEEE Computer and Communications Societies..

[24]  Rami G. Melhem,et al.  Supporting Loss Guarantees in Buffer-Limited Networks , 2006, 200614th IEEE International Workshop on Quality of Service.

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

[26]  Matthew Andrews,et al.  Instability of FIFO in session-oriented networks , 2000, SODA '00.