THE EFFECT OF TRAFFIC SHAPING IN EFFICIENTLY PROVIDING END-TO-END PERFORMANCE GUARANTEES

This paper reports new results concerning the capabilities of a family of service disciplines aimed at providing per-connection end-to-end d elay (and throughput) guarantees in high-speed networks. This family c onsists of the class of rate-controlled service disciplines, in which traffic from a connection is reshaped to conform to specific traffic c haracteristics, at every hop on its path. When used together with a sc heduling policy at each node, this reshaping enables the network to pr ovide end-to-end delay guarantees to individual connections. The main advantages of this family of service disciplines are their implementat ion simplicity and flexibility. On the other hand, because the delay g uarantees provided are based on summing worst case delays at each node , it has also been argued that the resulting bounds are very conservat ive which may more than offset the benefits. In particular, other serv ice disciplines such as those based on Fair Queueing or Generalized Pr ocessor Sharing (GPS), have been shown to provide much tighter delay b ounds. As a result, these disciplines, although more complex from an i mplementation point-of-view, have been considered for the purpose of p roviding end-to-end guarantees in high-speed networks. In this paper, we show that through ''proper'' selection of the reshaping to which we subject the traffic of a connection, the penalty incurred by computin g end-to-end delay bounds based on worst cases at each node can be all eviated. Specifically, we show how rate-controlled service disciplines can be designed to outperform the Rate Proportional Processor Sharing (RPPS) service discipline. Based on these findings, we believe that r ate-controlled service disciplines provide a very powerful and practic al solution to the problem of providing end-to-end guarantees in high- speed networks.