Operations Selecting and Implementing the PBS Scheduler on a SGI Onyx 2/Origin2000 Sandra Bittner In the Mathematics and Computer Science Division at Argonne, the demand for resources on the Onyx 2 exceeds the resources available for consumption. To distribute these scarce resources effectively, we need a scheduling and resource management package with multiple capabilities. In particular, it must accept standard interactive user logins, allow batch jobs, backfill the system based on available resources, and permit system activities such as accounting to proceed without interruption. The package must include a mechanism to treat the graphic pipes as a schedulable resource. Also required is the ability to create advance reservations, offer dedicated system modes for large resource runs and benchmarking, and track the resources consumed for each job run. Furthermore, our users want to be able to obtain repeatable timing results on job runs. And, of course, package costs must be carefully considered. We explored several options, including NQE and various third-party products, before settling on the PBS scheduler. Installation and Administration of Software on a CRAY SV1 SuperCluster from the SWS Scott Grabow With the introduction of the CRAY SV1 SuperCluster the installation process for initial and upgrade installations has been updated to provide a level of flexibility and consistency for sites that have a CRAY SV1 SuperCluster system. This paper will outline the two processes available to perform each installation and address some administration issues when working with SV1-8 and larger SuperClusters. Improvements in SGI's Electronic Support Lori Leanne Parris and Vernon Clemons Join SGI for an update on our Electronic Support and Services roadmap and planned improvements in this area. Learn of our exciting plans to optimize your electronic support and services experience. This session will be interactive and we encourage you to share your feedback with us. IRIX/Windows NT Interoperability Hank Shiffman No man is an island, entire of itself. Similarly, computing systems need to interact, to share information, to cooperate in helping users do their jobs. We'll discuss the range of challenges involved in integrating IRIX and Windows systems into one environment, a variety of solutions to these challenges and ways to satisfy the differing concerns of application users, developers and system administrators. Workload Management: NQE/LSF Status and Plans Jack Thompson and Brian MacDonald SGI is working with Platform Computing to incorporate key Network Queuing Environment (NQE) Features into Platform's Load Sharing Facility (LSF). Platform and SGI will jointly present the status of LSF for IRIX, UNICOS, and UNICOS/mk and discuss upcoming features in LSF 4.0. SV1 SuperCluster System Resiliency Mike Wolf Clustering of computer systems brings unique challenges for resiliency. This paper discusses those challenges, and what SGI is doing to address them. While the features discussed in this paper apply to any shared GigaRing channel environment, this paper will focus on the Cray SV1 SuperCluster system. Table of Contents | Author Index | CUG Home Page | Home (Title Page)