"Pay bursts only once" does not hold for non-FIFO guaranteed rate nodes

We consider end-to-end delay bounds in a network of guaranteed rate (GR) nodes. We demonstrate that, contrary to what is generally believed, the existing end-to-end delay bounds apply only to GR nodes that are FIFO per flow. We show this by exhibiting a counter example. Then, we show that the proof of the existing bounds has a subtle, but important, dependency on the FIFO assumption, which was never noticed before. Finally, we give a tight delay bound that is valid in the non-FIFO case; it is noticeably higher that the existing one. In particular, the phenomenon known as ''pay bursts only once'' does not apply to non-FIFO nodes. These findings are important in the context of differentiated services. Indeed the existing bounds have been applied to cases where a flow (in the sense of the GR definition) is an aggregate of end-user microflows, and it is not generally true that a router is FIFO per aggregate; thus, the GR node model of a differentiated services router cannot always be assumed to be FIFO per flow.

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

[2]  Harrick M. Vin,et al.  Determining end-to-end delay bounds in heterogeneous networks , 1995, Multimedia Systems.

[3]  Zheng Wang,et al.  An Architecture for Differentiated Services , 1998, RFC.

[4]  Jean-Yves Le Boudec,et al.  Network Calculus: A Theory of Deterministic Queuing Systems for the Internet , 2001 .

[5]  Harrick M. Vin,et al.  Generalized guaranteed rate scheduling algorithms: a framework , 1997, TNET.

[6]  Jorge A. Cobb,et al.  End-to-end delay guarantees for multiple-channel schedulers , 2002, IEEE 2002 Tenth IEEE International Workshop on Quality of Service (Cat. No.02EX564).

[7]  Volker Sander,et al.  A parameter based admission control for differentiated services networks , 2004, Comput. Networks.

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

[9]  Luciano Lenzini,et al.  Delay bounds for FIFO aggregates: a case study , 2003, Comput. Commun..

[10]  Corneliu S. Pencea,et al.  BSFQ: bin sort fair queueing , 2002, Proceedings.Twenty-First Annual Joint Conference of the IEEE Computer and Communications Societies.

[11]  Banu Özden,et al.  Fair queuing for aggregated multiple links , 2001, SIGCOMM.

[12]  Kevin C. Almeroth,et al.  Proceedings of the 13th international workshop on Network and operating systems support for digital audio and video , 2003 .

[13]  David L. Black,et al.  An Architecture for Differentiated Service , 1998 .

[14]  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.

[15]  Craig Partridge,et al.  Packet reordering is not pathological network behavior , 1999, TNET.

[16]  George Varghese,et al.  Leap forward virtual clock: a new fair queuing scheme with guaranteed delays and throughput fairness , 1997, PODC '97.

[17]  Brahim Bensaou,et al.  Credit-based fair queueing (CBFQ): a simple and feasible scheduling algorithm for packet networks , 1997, IEEE ATM '97 Workshop Proceedings (Cat. No.97TH8316).

[18]  George Varghese,et al.  Leap forward virtual clock: a new fair queuing scheme with guaranteed delays and throughput fairness , 1997, Proceedings of INFOCOM '97.

[19]  Jean-Yves Le Boudec,et al.  Packet scale rate guarantee for non-FIFO nodes , 2002, Proceedings.Twenty-First Annual Joint Conference of the IEEE Computer and Communications Societies.

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