Check out the new USENIX Web site.
 1998 USENIX Annual Technical Conference - June 15-19, 1998 - Marriott Hotel, New Orleans, Louisiana
Jump to Conference Home Page Jump to Registration Information
Table of Contents
M1   System and Network Performance Tuning
Hal Stern, Sun Microsystems

Who should attend: Novice and advanced UNIX system and network administrators, UNIX developers concerned about network performance impacts. A basic understanding of the UNIX system facilities and network environments is assumed.

We will explore procedures and techniques for tuning systems, networks and application code. Starting from the single system view, we will examine how the virtual memory system, the I/O system, and filesystem can be measured and optimized. We'll extend the single host view to include Network File System tuning and performance strategies. Detailed treatment of networking performance problems, including network design and media choices will lead to examples of network capacity planning. Application issues, such as system call optimization, memory usage and monitoring, code profiling, real-time programming, and techniques for controlling response time will be addressed. Many examples will be given, along with guidelines for capacity planning and customized monitoring based of your workloads and traffic patterns. Question and analysis periods for particular situations will be provided.

-    Performance Tuning Strategies
*    Practical goals
*    Monitoring intervals
*    Useful statistics
*    Tools, tools, tools
-    Server Tuning
*    Filesystem and disk tuning
*    Memory consumption and swap space
*    System resource monitoring
-    NFS Performance Tuning
*    NFS server constraints
*    NFS client improvements
*    NFS over WANs
*    Automounter and other tricks
-    Network Performance, Design, and Capacity Planning
*    Locating bottlenecks
*    Demand management
*    Media Choices & Protocols
*    Network Topologies: bridges, switches and routers
*    Throughput and latency considerations
*    Modeling resource usage
-    Application Tuning
*    System resource usage
*    Memory Allocation
*    Code profiling
*    Job scheduling and queueing
*    Real-time issues
*    Managing response time

Hal Stern  is a Distinguished Systems Engineer with Sun Microsystems Computer Company, where he focuses on high-end server technology, operations management, networking, performance tuning, and information systems architecture. Hal has been a UNIX administrator and user for more than 10 years. Before joining Sun, he developed molecular modeling software for a Boston area start-up company and was on the research staff at Princeton University. He is the author of Managing NFS & NIS and the author of several articles on application performance and network design.

Program at-a-Glance - Tutorials - Technical Program - Registration -
Birds-of-a-Feather - Conference Activities - Hotel & Travel Info - Conference Home
Conference Index
Events Calendar