TCP suffers from known problems in constrained environments such as satellite and wireless networks. And the problems grow more severe as networks grow increasingly integrated and diverse, where local optimization fail to suffice. One established method for dealing with these problems involves subdividing, or splitting the end-to-end TCP connection into a number of sub-connections. In this paper, we take an indepth look at the buffer requirements for "split connections". After briefly introducing the mechanics of a split connection, we proceed to identify a simple analytic model describing the behavior of the split connection and develop a number of design "rules of thumb" based on our analysis. We compare the results of simulations with the model and measure the efficacy of our design constraints, finding them to improve both the stability and performance of splitting. Finally, we discover that when used properly, oversubscribing, i.e., advertising non-existent space, may greatly reduce the required per-connection buffer-space in some situations.

Several satellite systems currently in operation or under development claim to support broadband Internet applications. In these scenarios, transmission control protocol (TCP) plays a critical role. Unfortunately, when used with satellite links, TCP suffers from a number of well-known performance problems, especially for higher data rates and high altitude satellites with longer delays. In response to these difficulties, the satellite and Internet research communities have developed a large gamut of solutions ranging from architectural modifications to changes in the TCP protocol. Among these, one approach requiring minimal modifications involves splitting the TCP connection in two or more segments with one segment connecting terrestrial nodes across the satellite network. In this paper, we consider an evolution of this idea: placing a TCP proxy on board the satellite that further subdivides the end-to-end connection into separate TCP connections between ground and space. We focus upon the efficient use of buffer resources on board the satellite, while at the same time enhancing TCP performance. We evaluate two TCP protocol versions, TCP NewReno and TCP Westwood. We consider various geosynchronous earth orbit satellite scenarios, with and without the split proxy, and with different channel error conditions (random errors, shadowing, etc.). Using simulation, we show that an on-board proxy provides a number of distinct advantages and can enhance throughput up to threefold for both TCP New Reno and TCP Westwood, in some scenarios, with relatively modest on-board buffering requirements. The main contributions of this paper are: the on-board split proxy concept, the buffer management strategy, the use of a realistic "urban shadowing" model in the evaluation, and the extensive comparison of the recently announced TCP Westwood with the traditional TCP New Reno.

This paper investigates the use of advanced communication services in grid environments. Such services can include augmented communication semantics (e.g., filtering), collective operations, content-based and policy-based routing, and managing communication scope to manage feasibility. These services could be implemented and deployed in a variety of ways, such as a traditional network of servers, or as a middleware forwarding and routing layer, or even in an active network. In any of these approaches, topology-awareness can play a major role in their performance and scalability. As a case study, we demonstrate here a communication service to support time management in distributed simulations that is managed using a grid computing toolkit. We also present emulation and simulation results to demonstrate the scalability that topology-awareness enables for services such as time management. Since the design space for communication services offers so many possibilities and alternatives, we argue for the definition of proper high-level models and APIs such that the underlying implementations and scope of deployment can be developed and improved with minimal impact on applications.

High errors and high delays create well-known problems with TCP. One established approach to solve this problem involves dividing TCP connections into segments, or splitting the connection. This paper takes this approach one step further by exploring the use of a TCP proxy on board a satellite for the purpose of enhancing end-to-end TCP performance. We show that this approach yields a number of important advantages, especially for small, mobile terminals, multi-segment systems, and multicast applications. As part of this architecture, we introduce a method of TCP backpressure using the advertised window, which optimizes memory usage on the satellite. Using simulation, we demonstrate that performance may improve by as much as three-fold.

In grid computing environments, network bandwidth discovery and allocation is a serious issue.Before their applications are running, grid users will need to choose hosts based on available bandwidth.Running applications may need to adapt to a changing set of hosts.Hence, a tool is needed for monitoring network performance that is integral to the grid environment.To address this need, Gloperf was developed as part of the Globus grid computing toolkit.Gloperf is designed for ease of deployment and makes simple, end-to-end TCP measurements requiring no special host permissions.Scalability is addressed by a hierarchy of measurements based on group membership and by limiting overhead to a small, acceptable, fixed percentage of the available bandwidth.Since this fixed overhead may push host-pair revisit time into the tens-of-hours, we also quantitatively examine the "trajectory" of the cost-error trade-off for measurement frequency.