This paper describes our experiences, from a software perspective, with the OSIRIS network adaptor. It first identifies the problems we encountered while programming OSIRIS and optimizing network performance, and outlines how we either addressed them in the software, or had to modify the hardware. It then describes the opportunities provided by OSIRIS that we were able to exploit in the host operating system (OS); opportunities that suggested techniques for making the OS more effective in delivering network data to application programs. The most novel of these techniques, called application device channels, gives application programs running in user space direct access to the adaptor. The paper concludes with the lessons drawn from this work, which we believe will benefit the designers of future network adaptors. 1 Introduction With the emergence of high-speed network facilities, several research efforts are focusing on the design and implementation of network adaptors [5, 2, 3, 16, 2...

This paper describes a new host interface architecture for high-speed networks operating at 800 of Mbit/second or higher rates. The architecture is targeted to achieve several 100s of Mbit/second application-to-application performance for a wide range of host architectures. The architecture achieves the goal by providing a streamlined execution environment for the entire path between host application and network interface. In particular, a "Communication Accelerator Block" (CAB) is used to minimize data copies, reduce host interrupts, support DMA and hardware checksumming, and control network access. This host architecture is applicable to a large class of hosts with high-speed I/O busses. Two implementations for the 800 Mbit/second HIPPI network are under development. One is for a distributed-memory supercomputer (iWarp) and the other is for a high-performance workstation (DECstation 5000). We describe and justify both implementations. Keyword Codes: B.4.1; C.2.1 Keywords: Data Commun...

Abstract: The emergence of fast, cheap embedded processors presents the opportunity for processing to occur on the network adapter. We are investigating how a system design incorporating such an intelligent network adapter can be used for applications that benefit from being tightly integrated with the network subsystem. We are developing a safe, extensible operating system, called SPINE, which enables applications to compute directly on the network adapter. We demonstrate the feasibility of our approach with two applications: a video client and an Internet Protocol router. As a result of our system structure, image data is transferred only once over the I/O bus and places no load on the host CPU to display video at aggregate rates exceeding 100 Mbps. Similarly, the IP router can forward roughly 10,000 packets per second on each network adapter, while placing no load on the host CPU. Based on our experiences, we describe three hardware features useful for improving performance. Finally, we conclude that offloading work to the network adapter can make sense, even using current embedded processor technology. 1

This paper looks at the I/O bottleneck in operating systems, with particular focus on high-speed networking. We start by identifying the causes of this bottleneck, which are rooted in a mismatch of operating system behavior with the performance characteristics of modern computer hardware. Then, traditional approaches to supporting I/O in operating systems are re-evaluated in light of current hardware performance tradeoffs. This re-evaluation gives rise to a set of novel techniques that eliminate the I/O bottleneck. The root cause of the OS I/O bottleneck is that speed improvements of main memory have lagged behind those of the central processing unit (CPU) and I/O devices during the past decade [6]. In state-of-the-art computer systems, the bandwidth of main memory is orders of magnitude lower than the bandwidth of the CPU, and the bandwidths of the fastest I/O devices approach that of main memory

Security and privacy are growing concerns in the Internet community, due to the Internet's rapid growth and the desire to conduct business over it safely. This desire has led to the advent of several proposals for security standards, such as secure IP, secure HTTP, and the Secure Socket Layer. All of these standards propose using cryptographic protocols such as DES and RSA. Thus, the need to use encryption protocols is increasing. Shared-memory multiprocessors make attractive server platforms, for example as secure World-Wide Web servers. These machines are becoming more common, as shown by recent vendor introductions of platforms such as SGI's Challenge, Sun's SPARCCenter, and DEC's AlphaServer. The spread of these machines is due both to their relative ease of programming and their good price/performance. This paper is an experimental performance study that examines how encryption protocol performance can be improved by using parallelism. We show linear speedup for several different ...

This paper is focused on an efficient protocol implementation based on flexible user protocol interface (UPI) configurable for different service options and protocol processing architectures. The XTPL implementation discussed in this paper is developed based on the BERKOM eXpress Transfer Protocol (XTP) Lite version for HP 9000 / 7x Series using HP-UX 9.0 operating system. This implementation supports the dynamical configuration of user protocol interfaces intended to provide different objectives: - optimization of the user data copy operations (use of the "single copy archtecture") - selectable QoS options for application layer framing, reliability and checksumming. Performance analyses are included to show the flexible use of user protocol interfaces, in particular the reliable single and dual copy interface, dependent on the application traffic of the connections. Keywords: User Protocol Interface, Application Programming Interface (API), Application Layer Framing, Single Copy....

This licentiate thesis presents a method for using a high performance network based on circuit switching as a new link level technology for the Internet. The network is called Dynamic synchronous Transfer Mode, DTM, which provides a service based on simplex multirate channels. DTM uses resource reservation and synchronous switching, which gives good real-time support. These features make DTM well suited for applications that generate a mix of video, audio and file transfer traffic. Such applications require network services providing high capacity and timely delivery of data. The DTM protocol suite spans from the medium access control up to the network level, and the thesis shows how DTM's protocol suite can be brought together with the protocols used within the Internet, i.e., the TCP/IP suite. In addition, a programming interface is presented, which gives applications direct access to the services provided by DTM. The thesis describes a protocol architecture, which ha...

Digital video services, scientific visualization and other multimedia applications require delivery of high network throughput to end user applications. In this paper we identify bottlenecks in the data path between high-speed networks and applications. Using performance of multimedia applications as a metric, the effectiveness of solutions to reduce network, operating system, and user bottlenecks is explored experimentally. Key words: Multimedia, networking, operating systems, performance, TCP/IP. 1. Introduction The past few years have seen development of applications with high bandwidth requirements such as medical image transfer, video conferencing, scientific process simulation, and visualization. Popular local area networks such as Ethernet and Token Ring (4 Mbit/s and 16 Mbit/s) are incapable of providing the bandwidth needed by these multimedia applications. New network technologies such as Fiber Distributed Data Interface (FDDI), Fast Ethernet (100BASET) , and Asynchronous ...

Networked information systems have seen explosive growth in the last few years, and are transforming society both economically and socially. The information available via the global information infrastructure is growing rapidly, dramatically increasing the performance requirements for large scale information servers. Example services include digital libraries, video-on-demand, World-Wide Web and highperformance file systems. In this dissertation, we investigate performance issues that affect networking support for high-performance servers. We focus on three research issues: ffl Parallelism Using Packets. The first part of this dissertation identifies performance issues of network protocol processing on shared-memory multiprocess...