This paper discusses the use of link-sharing mechanisms in packet networks and presents algorithms for hierarchical link-sharing. Hierarchical link-sharing allows multiple agencies, protocol families, or traflic types to share the bandwidth on a tink in a controlled fashion. Link-sharing and real-time services both require resource management mechanisms at the gateway. Rather than requiring a gateway to implement separate mechanisms for link-sharing and real-time services, the approach in this paper is to view link-sharing and real-time service requirements as simultaneous, and in some respect complementary, constraints at a gateway that can be implemented with a unified set of mechanisms. White it is not possible to completely predict the requirements that might evolve in the Internet over the next decade, we argue that controlled link-sharing is an essential component that can provide gateways with the flexibility to

A number of proposals for supporting IP over ATM are under discussion in the networking community including: LAN emulation, classical IP over ATM, routing over large clouds, and multiprotocol over ATM. Each of these proposals hides the real network topology from the IP layer by treating the data link layer as a large, opaque, network cloud. We argue that this leads to complexity, inefficiency and duplication of functionality in the resulting network. We propose an alternative in which we discard the connection oriented nature of ATM and integrate fast ATM hardware directly with IP, preserving the connectionless nature of IP. We use "soft" state in the ATM hardware to cache the IP forwarding decision. This enables further traffic on the same IP flow to be switched by the ATM hardware rather than forwarded by IP software. We claim that this approach combines the simplicity, scalability, and robustness of IP with the speed, capacity, and multiservice traffic capabilities of ATM. 1. Introd...

In this paper, we introduce a new operating system abstraction called reservation domains, and describe its implementation in Eclipse, an experimental operating system that provides a testbed for Quality of Service (QoS) support for applications. Reservation domains enable explicit control over the provisioning of system resources among applications in order to achieve desired levels of predictable performance. In general, each reservation domain is assigned a certain fraction of each resource (e.g., 25% CPU, 50% disk I/O, etc.). Eclipse implements reservation-domain scheduling of multiple resources. It currently supports CPU and disk and physical memory (working set size) scheduling. Eclipse implements a new scheduling algorithm, Move-to-Rear List Scheduling (MTR-LS), that provides a cumulative service guarantee, in addition to fairness and delay bounds. Cumulative service guarantee is necessary for ensuring predictable aggregate throughput for applications that require multiple res...

Future internetworks will include large numbers of portable devices moving among small wireless cells. We propose a hierarchical mobility management scheme for such networks. Our scheme exploits locality in user mobility to restrict handoff processing to the vicinity of a mobile node. It thus reduces handoff latency and the load on the internetwork. Our design is based on the Internet Protocol (IP) and is compatible with the Mobile IP standard. We also present experimental results for the lowest level of the hierarchy. We implemented our local handoff mechanism on Unix-based portable computers and base stations, and measured its performance on a WaveLAN network. These measurements show that our handoffs are fast enough to avoid noticeable disruptions in interactive voice traffic. For example, our handoff protocol completes less than 10 milliseconds after a mobile node initiates it. Our mechanism also recovers from packet losses suffered during the transition from one cell to another. T...

Application-specific safe message handlers (ASHs) are designed to provide applications with hardware-level network performance. ASHs are user-written code fragments that safely and efficiently execute in the kernel in response to message arrival. ASHs can direct message transfers (thereby eliminating copies) and send messages (thereby reducing send-response latency). In addition, the ASH system provides support for dynamic integrated layer processing (thereby eliminating duplicate message traversals) and dynamic protocol composition (thereby supporting modularity). ASHs provide this high degree of flexibility while still providing network performance as good as, or (if they exploit application-specific knowledge) even better than, hard-wired in-kernel implementations. A combination of user-level microbenchmarks and end-to-end system measurements using TCP demonstrate the benefits of the ASH system.

Introduction Future internetworks will include networks of small wireless cells populated by large numbers of portable devices. Laptop computers and cellular telephones have proven their utility, while continuing advances in miniaturization promise increasingly functional portable devices. Networks of small wireless cells offer high aggregate bandwidth, support low-powered mobile transceivers, and provide accurate location information. In these networks, users will often carry devices across cell boundaries in the midst of data transfers. A handoff mechanism is needed to maintain connectivity as devices move, while minimizing disruption to ongoing transfers. This mechanism should exhibit low latency, incur little or no data loss, and scale to a large internetwork. The Mobile IP standard [22] specifies a general handoff protocol for the Internet, but does not fully meet these goals. Mobile IP can handle both local-area and wide-area movement in both wired and w

The differentiated services (diffserv) architecture defines a new framework for the support of quality of service (QoS) in IP-based networks. In this paper, we focus on the mechanisms used to implement the Expedited Forwarding (EF) Per-Hop Behavior (PHB). We analyze these mechanisms with respect to two main QoS parameters: Delay and delay variation.

: This paper analyzes the efficiency of various high performance implementation techniques for the communication system of UNIX workstations. Using an Open System implies that a certain compatibility level is required from the protocol, user interface, and implementation framework. These constraints limit the opportunities to design a high performance communication system. We have designed an experimental platform around the TCP/IP protocol suite, using the STREAMS environment. A BSD TCP/IP stack and a classic STREAMS based TCP/IP stack serve as reference implementations for performance comparisons. We explain why the efficiency of some high performance implementation techniques we applied to this platform is limited. The impacts of the hardware architecture, of the operating system, and of the communication stack architecture on performances are analyzed. It is shown that the efficiency of data transmission would benefit from more simplicity and more synchronism in the communication e...

This paper is about the evolution of the Internet from a simple data network into a true multiservice network that can support the emerging multimedia applications and their protocols with appropriate performance and costs. The real-time delivery and specific bandwidth requirements of these multimedia applications have created a need for an Integrated Services Internet in which traditional best-effort datagram delivery can coexist with additional enhanced Quality of Service (QoS) delivery classes. The Integrated Services Internet will be able to commit to meet bandwidth, packet loss and delay specifications for individual data flows by using the Resource ReSerVation Protocol (RSVP), together with appropriate packet forward scheduling policies. Keywords Controlled-Load Service Data Flow Guaranteed Service Integrated Services (IS) One Pass with Advertising (OPWA) Quality of Service (QOS) ReSerVation setup Protocol (RSVP) Real Time Protocol (RTP) Random Early Detection (RED) Multicast ...

Abstract not found