Reduced Complexity Input Buffered Switches

Input-Output buffered crossbars are popular building blocks for scalable high-speed switching because they require minimum speed-up of memory bandwidth. Scaling the design of crossbar switches to large capacities is limited by technology issues such as the reconfiguration of high-speed fabrics or power consumption. In addition, these crossbar architechtures typically schedule and transfer in terms of fixed size envelopes. Thus when they are used in the context of IP networks where packets are of variable size, the incoming packets need to be fragmented into fixed size envelopes. This fragmentation can lead to, possibly large [1], loss of bandwidth and even instability. This paper proposes a new method for switching variable sized packets over a crossbar switch that i) allows maximum utilization of switch bandwidth and avoids the fragmentation effect, and ii) allows designers to use much larger envelopes for transfering data over the fabric and thus minimizes the reconfiguration frequency of the fabric. Reducing the scheduling frequency makes implementation of complex schedulers practical and enables us to build ultra-fast switches incorporating optical technology that can provide bandwidth and delay guarantees.

[1]  Jean C. Walrand,et al.  Achieving 100% throughput in an input-queued switch , 1996, Proceedings of IEEE INFOCOM '96. Conference on Computer Communications.

[2]  T. V. Lakshman,et al.  On adaptive bandwidth sharing with rate guarantees , 1998, Proceedings. IEEE INFOCOM '98, the Conference on Computer Communications. Seventeenth Annual Joint Conference of the IEEE Computer and Communications Societies. Gateway to the 21st Century (Cat. No.98.

[3]  Ashok V. Krishnamoorthy,et al.  Optoelectronic-VLSI: photonics integrated with VLSI circuits , 1998 .

[4]  Hui Zhang,et al.  Exact emulation of an output queueing switch by a combined input output queueing switch , 1998, 1998 Sixth International Workshop on Quality of Service (IWQoS'98) (Cat. No.98EX136).

[5]  Nsf Ncr,et al.  A Generalized Processor Sharing Approach to Flow Control in Integrated Services Networks: The Single Node Case* , 1991 .

[6]  A. Charny,et al.  Algorithms for providing bandwidth and delay guarantees in input-buffered crossbars with speedup , 1998, 1998 Sixth International Workshop on Quality of Service (IWQoS'98) (Cat. No.98EX136).

[7]  Rene L. Cruz,et al.  Service Burstiness and Dynamic Burstiness Measures: A Framework , 1992, J. High Speed Networks.

[8]  Nick McKeown,et al.  The iSLIP scheduling algorithm for input-queued switches , 1999, TNET.

[9]  Hui Zhang,et al.  WF/sup 2/Q: worst-case fair weighted fair queueing , 1996, Proceedings of IEEE INFOCOM '96. Conference on Computer Communications.

[10]  Lixia Zhang.  VirtualClock: A New Traffic Control Algorithm for Packet-Switched Networks , 1991, ACM Trans. Comput. Syst..

[11]  H. Storoy,et al.  Reconfigurable all-fiber all-optical cross-connect node using synthesized fiber Bragg gratings for both demultiplexing and switching , 1998 .

[12]  QueueingJon,et al.  WF 2 Q : Worst-case Fair Weighted Fair , 1996 .

[13]  Thomas E. Anderson,et al.  High-speed switch scheduling for local-area networks , 1993, TOCS.

[14]  Nick McKeown,et al.  The Tiny Tera: A Packet Switch Core , 1998, IEEE Micro.

[15]  Anujan Varma,et al.  Efficient fair queueing algorithms for packet-switched networks , 1998, TNET.

[16]  Abhay Parekh,et al.  A generalized processor sharing approach to flow control in integrated services networks-the single node case , 1992, [Proceedings] IEEE INFOCOM '92: The Conference on Computer Communications.

[17]  Nick McKeown,et al.  Matching output queueing with a combined input/output-queued switch , 1999, IEEE J. Sel. Areas Commun..

[18]  Leandros Tassiulas,et al.  Scheduling of Variable Size Packets in Input Queued Switches with Bandwidth and Delay Guarantees , 1999 .

[19]  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).

[20]  Hui Zhang,et al.  Hierarchical packet fair queueing algorithms , 1996, SIGCOMM '96.

[21]  Anujan Varma,et al.  Latency-rate servers: a general model for analysis of traffic scheduling algorithms , 1996, Proceedings of IEEE INFOCOM '96. Conference on Computer Communications.

[22]  Abhay Parekh,et al.  A generalized processor sharing approach to flow control in integrated services networks: the single-node case , 1993, TNET.

[23]  Lixia Zhang,et al.  VirtualClock: a new traffic control algorithm for packet-switched networks , 1991, TOCS.

[24]  Thomas L. Rodeheffer,et al.  Smooth Scheduling in a Cell-Based Switching Network , 1998 .

[25]  Anujan Varma,et al.  A general methodology for designing efficient traffic scheduling and shaping algorithms , 1997, Proceedings of INFOCOM '97.