On achievable service differentiation with token bucket marking for TCP

Abstract

The Differentiated services (diffserv) architecture has been proposed as a scalable solution for providing service differentiation among flows without any per-flow buffer management inside the core of the network. It has been advocated that it is feasible to provide service differentiation among a set of flows by choosing an appropriate “marking profile” for each flow. In this paper, we examine (i) whether it is possible to provide service differentiation among a set of TCP flows by choosing appropriate marking profiles for each flow, (ii) under what circumstances, the marking profiles are able to influence the service that a TCP flow receives, and, (iii) how to choose a correct profile to achieve a given service level. We derive a simple, and yet accurate, analytical model for determining the achieved rate of a TCP flow when edge-routers use “token bucket” packet marking and core-routers use active queue management for preferential packet dropping. From our study, we observe three important results: (i) the achieved rate is not proportional to the assured rate, (ii) it is not always possible to achieve the assured rate and, (iii) there exist ranges of values of the achieved rate for which token bucket parameters have no influence. We find that it is not easy to regulate the service level achieved by a TCP flow by solely setting the profile parameters. In addition, we derive conditions that determine when the bucket size influences the achieved rate, and rates that can be achieved and those that cannot. Our study provides insight for choosing appropriate token bucket parameters for the achievable rates.

Theories and models for Internet quality of service

“…Sahu et al [135] determine the parameters of a leaky-bucket marking necessary for guaranteeing a given rate, if at all possible. They reach similar conclusions as above such as that in the under-subscribed case, when the committed rate is small, the marking has no influence on the achieved rate.…”

Quality of service modeling and analysis for carrier ethernet

“…With rigorous simulations we show that our scheme converges to the optimal bucket size in most cases and this is achieved without any knowledge of parameters such as round trip time or level of aggregation of the tra¢ c being policed. Although TCP's interaction with a token bucket policer has been widely studied ( [70], [12], [40], [90]), the previous work has not achieved the con…guration of token bucket parameters independent of the tra¢ c pro…le.…”

Evaluating performance among different TCP flows in a differentiated services enabled network

“…It has been seen throughout a number of studies [e.g. 4,5,6,7,8] that it is difficult to guarantee requested throughput to the TCP flows in a such network. Most of these studies have concluded that the throughput attained by a customer is affected, not only by the marking strategies at the edge router, but by the presence of other flows in the same bottleneck link.…”

“…Sahu et al in [5] derived a simple analytical model for determining the achieved rate of a TCP flow when edge routers use token bucket marking and the core routers use active queue management for preferential packet dropping. As shown in [5], it is not feasible to achieve ideal service differentiation across a set of TCP with token bucket marking. In their study, they focused on a single TCP flow, i.e.…”