The standard benchmark for NFS file server performance, SPEC SFS (also known as LADDIS), measures performance in terms of both throughput---the aggregate amount of data a file server can move across the network per unit of time---and response time---the time required to service an individual client request. NetBench, the most commonly used file server benchmark for the CIFS (or SMB) protocol measures only throughput. Network Appliance believes response time is as important a performance metric as throughput, especially in the highly interactive environment typical of CIFS networks, since throughput offers little solace to a user waiting to access a file. This paper documents the methodology and tools developed to measure response time during a NetBench run. While cumbersome and primitive, useful data has been produced, demonstrating that the fundamental idea is sound. SPEC SFS has had a noticeable effect on vendors of NFS file servers, motivating them to improve response time from an a...

Abstract — This paper introduces a new benchmark tool,

Abstract not found

www.spec.org Copyright (c) 2001 by Standard Performance Evaluation Corporation (SPEC) All rights reserved SPEC and SFS are registered trademarks of the Standard Performance Evaluation Corporation NFS is a registered trademark of Sun Microsystems, Inc. 1 SFS 3.0

This paper provides two contributions to the study of highperformance Web servers. First, it outlines the optimizations necessary to build efficient and scalable Web servers and illustrates how we've applied some of these optimizations to create JAWS. JAWS is a high-performance Web server that is explicitly designed to alleviate overheads incurred by existing Web servers on high-speed networks. It consistently outperforms existing Web servers (such as Apache, Java Server, PHTTPD, Zeus, and Netscape Enterprise) over 155 Mbps ATM networks on UNIX platforms. Second, this paper describes how we have customized JAWS to leverage advanced features of Windows NT for multiprocessor hardware over ATM. The Windows NT features used in JAWS include asynchronous mechanisms for connection establishment and data transfer. Our previous benchmarking studies demonstrate that once the overhead of disk I/O is reduced to a negligible constant factor (e.g., via memory caches), the primary determinants of We...

ies. The Innocenti Digests are produced by the Centre to provide reliable and accessible information on specific child rights issues. This issue of the Innocenti Digest was prepared principally by Maggie Black, Consultant to the UNICEF Innocenti Research Centre, with the assistance of researchers Victoria Haeri, Consultant, and Nicolette Moodie, Consultant, UNICEF New York. With special thanks to Nafis Sadik, Executive Director, UNFPA. The Centre is particularly grateful to the Forum on Marriage and the Rights of Women and Girls for its support throughout the preparation of this Digest, and to the many UNICEF Country Offices who provided information and advice. Grateful thanks are also due to Srilakshmi Gururaja and Marilen Danguilen of UNICEF New York, Flora Sibander-Mulder of UNICEF Abidjan and Oscar Sikes of UNFPA. This Digest has also benefited from the input of international experts who attended the Consultation on Early Marriage held at the UNICEF Innocenti Research Centre in Oct

In this report, we describe the collection of file system traces from three different environments. By using the auditing system to collect traces on client machines, we are able to get detailed traces with minimal kernel changes. We then present results of traffic analysis on the traces, contrasting them with those from previous studies. Based on these results, we argue that file systems must optimize disk layout for good read performance.

As the scale and complexity of VLSI circuits increase, Electronic Design Automation (EDA) tools become much more sophisticated and are held to increasing standards of quality. Newgeneration EDA tools must work correctly on a wider range of inputs, have more internal states, take more effort to develop, and offer fertile ground for programming mistakes. Ensuring quality of a commercial tool in realistic design flows requires rigorous simulation, non-trivial computational resources, accurate reporting of results and insightful analysis. However, time-to-market pressures encourage EDA engineers and chip designers to look elsewhere. Thus, the recent availability of cheap Linux clusters and grids shifts the bottleneck from hardware to logistical tasks, i.e., the speedy collection, reporting and analysis of empirical results. To be practically feasible, such tasks must be automated; they leverage high-performance computing to improve EDA tools. In this work we outline a possible infrastructure solution, called bX, explore relevant use models and describe our computational experience. In a specific application, we use bX to automatically build Pareto curves required for accurate performance analysis of randomized algorithms.

The Network File System (NFS) utilizes a stateless protocol between clients and servers; the major advantage of this statelessness is that NFS crash recovery is very easy. However, the protocol requires that data modification operations such as write be fully committed to stable storage before replying to the client. The cost of this is significant in terms of response latency and server CPU and I/O loading. This paper describes a write gathering technique that exploits the fact that there are often several write requests for the same file presented to the server at about the same time. With this technique the data portions of these writes are combined and a single metadata update is done that applies to them all. No replies are sent to the client until after this metadata update has been fully committed, thus the NFS crash recovery design is not violated. This technique can be used in most NFS server implementations and requires no client modifications. 1.

The majority of sexually active adolescent girls in developing countries are married. This statement may come as a surprise to many in the reproductive health field because so much attention has been focused on sexual activity among unmarried adolescents. While striving to meet the needs of all adolescents, we must recognize that married adolescent girls represent a particularly vulnerable—and largely invisible— population. For example, they are highly vulnerable to significant reproductive health problems, including pregnancy-related morbidity and mortality, sexually transmitted infections (STIs), including HIV infection, as well as non-sexually transmitted reproductive tract infections (RTIs). They suffer disadvantages in other areas as well— for example, they are less likely than unmarried girls to complete their education. Yet, despite their large numbers, elevated risks, and many unmet needs, married adolescent girls have rarely been the target of programmatic efforts. Data in developing countries quantify the proportion of females who marry as adolescents. This proportion varies by region and country, but is high across the board— for example, in the mid-1990s the percentage of women aged 25–29 who married before