1998 ASR Home

Back

SCD ASR Index

Next

SCD Home

Maintaining the existing production supercomputer environment

During FY1998 the major changes in the SCD production supercomputer environment were:

• The installation of a new Cray J90se/24-1024 (chipeta) in the Community
• The installation of a new Silicon Graphics Cray Origin2000/128 (ute) in the CSL
• The transition of the HP SPP-2000/64 from an HPCC resource to the Community

During FY1998, SCD integrated new DSM systems into the existing parallel-vector supercomputer production environment and attempted to provide as seamless a computational environment for the CSL and Community users as possible. Though SCD introduced these two DSM computer systems, the Silicon Graphics Cray Origin2000 (ute) and HP SPP-2000 (sioux), into the CSL and Community environments, respectively, SCD is committed to continuing to provide support of production parallel-vector supercomputer systems at least through FY1999, and likely well beyond. Historically, it is these parallel-vector systems that have served the computational needs of NCAR and the atmospheric/oceanic sciences, and SCD will continue to support these systems to minimize the impact of the introduction of new computing architectures and systems.

At the end of FY1998, the "production computational environment" managed by SCD for NCAR includes five Cray supercomputers (a C90/16 (antero), a J90/20 (aztec), a J90/16 (paiute), and a pair of J90se/24 systems (ouray and chipeta) -- known generically as "Parallel Vector Processor" or PVP systems), Distributed Shared Memory supercomputers (the Silicon Graphics Cray Origin2000 (ute) and HP SPP-2000 (sioux)), the NCAR Mass Storage system, the HiPPI data communications fabric and networking facilities, the DataPark (a Silicon Graphics PowerChallenge XL (winterpark)), a test system (Silicon Graphics Cray Origin2000 (mouache)), fileservers, and the Visualization Lab. This environment's reliability is enhanced by the systems support, operational monitoring, and user services activities provided by SCD staff.

One of the most important aspects of SCD's attention to maintaining the existing production supercomputer environments is to provide 7x24 operation and service. This attention is reflected in the following tables, which show average system performance and utilization for FY1998:

Where "GFLOPS" is the average number of floating point operations per second (in billions) during the measuring period; "Utilz'n" is the average user utilization of the system (system downtime counts against utilization); "User" is the percent of uptime occupied in performing computation for user processes; "Idle" is the percent of uptime spent idle; "System" is the percent of uptime consumed in system overhead; "WaitIO" is the percent of uptime spent awaiting I/O completion; "IOfs" is the percent of the WaitIO time spent in performing user filesystem I/O; and "IOswp" is the percent of the WaitIO time spent in performing process swapping/paging.

Where "GFLOPS" is the average number of floating point operations per second (in billions) during the measuring period; "Utilz'n" is the average user utilization of the system (system downtime counts against utilization); "User" is the percent of uptime occupied in performing computation for user processes; "Idle" is the percent of uptime spent idle; "System" is the percent of uptime consumed in system overhead; "WaitIO" is the percent of uptime spent awaiting I/O completion; "IOfs" is the percent of the WaitIO time spent in performing user filesystem I/O; and "IOswp" is the percent of the WaitIO time spent in performing process swapping/paging.

Where "GFLOPS" is the average number of floating point operations per second (in billions) during the measuring period; "Utilz'n" is the average user utilization of the system (system downtime counts against utilization); "User" is the percent of uptime occupied in performing computation for user processes; "Idle" is the percent of uptime spent idle; "System" is the percent of uptime consumed in system overhead; "WaitIO" is the percent of uptime spent awaiting I/O completion; "IOfs" is the percent of the WaitIO time spent in performing user filesystem I/O; and "IOswp" is the percent of the WaitIO time spent in performing process swapping/paging.

Key maintenance activities

• Maintain supercomputer operating systems:
  The Cray systems were upgraded to the latest release of UNICOS (10.0.0) during the spring of 1998. SCD intends to stay apprised of major software releases from Silicon Graphics/Cray Research and carefully schedule upgrades to the production system and product set software based on judged stability of those upgrades in the NCAR production environment.

• Maintain stability and reliability of systems:
  One of the most significant attributes of the NCAR computational environment is its overall stability and reliability. For instance, the NCAR Mass Storage System has a reputation for reliability, and SCD has in the last year deployed a number of high-availability fileserver systems. This reliability and stability does not come easily; it stems from a combination of choosing reliable, stable vendor products and using proven, fail-safe system administration and maintenance techniques. SCD will continue to focus on ensuring, in whatever ways possible, highly stable and reliable systems and systems operations.

• Maintain batch subsystems and job scheduling:
  SCD continued to maintain the existing NQE batch subsystem as the common batch interface within the NCAR computational environment and enhanced its Batch Priority Scheduler (BPS). In addition, SCD implemented a new queue structure for the DSM systems in FY1998. More information appears in the Unified Queuing System report.

• Year 2000 compliance and testing:
  During FY1998, SCD engaged itself in a significant effort to ensure that all mission-critical resources maintained by SCD are Year-2000 compliant. The most significant objective is to ensure that all production systems are unaffected by the transition into the next century. SCD has been working with its major systems vendors to upgrade production systems' operating systems and product set software to Year-2000-compliant versions. In addition, SCD plans to perform testing of Year-2000 compliance of those systems and SCD-developed software and subsystems. More information appears in the Year 2000 planning and testing report.

• System monitoring:
  Over the years, SCD has developed a large number of system monitoring procedures, techniques, and tools. SCD continued to enhance and utilize its collective experience to maintain the stability of the existing production systems through this proactive monitoring. In addition, SCD continued to enhance its monitoring tools, techniques, and procedures, and SCD automated a number of procedures for detecting system failure or trouble. This automation, at the end of FY1998, was being integrated with commercial alphanumeric paging technology to provide more rapid alert mechanisms to SCD operations and systems staff and thus reduce the amount of time that systems are unavailable to the NCAR user community when they do fail.

• High-speed communications:
  SCD has deployed a high-speed HiPPI data communications "fabric" within the NCAR computer center; in addition, more traditional networking capabilities, including ATM, FDDI, and Ethernet technologies, have become the mainstay for connectivity between computational systems at NCAR and its divisions and remote departments. All of these systems are routinely monitored and maintained. SCD will continue to provide these stable, high-speed communications interfaces and enhance them with new technologies as those technologies prove their reliability and stability within our environment. Furthermore, as SCD enhances its computational capabilities, it will maintain and enhance its high-bandwidth connections between the NCAR MSS and the supercomputers to ensure that the systems are balanced and capable of satisfying the loads imposed by the growing need for both computational and storage capacities. In addition, during FY1998 SCD began evaluating new high-speed data and communications technologies, such as Fibre Channel and Gigabit Ethernet, as replacements for older, less-supported technologies. SCD hopes that this evaluation can lead to the adoption of these new technologies into our production environment -- but only after their reliability is proven.

• DataPark system:
  SCD maintained and enhanced the NCAR DataPark system. We believe this system will provide a new paradigm for computational data analysis as well as serving to provide lower latency access to large-capacity mass storage. More information on the DataPark and SCD's plans appears in the NCAR DataPark report.

• Visualization Lab:
  The SCD Visualization Lab capabilities are leading NCAR and atmospheric sciences into a new, revolutionary period in scientific computing. SCD maintained and enhanced, through new high-performance hardware and innovative tools, its Visualization Lab capabilities during FY1998. More information appears in the Visualization Laboratory report.

• NCAR DataVision:
  SCD maintained and enhanced NCAR Graphics during FY1998, and plans to continue collaborative development of its successor NCAR DataVision product. More information on SCD's plans are contained in the DataVision report.

• Consultation and user services:
  SCD maintained and improved responsiveness to user needs through FY1998, including augmentation of services provided by the SCD Consulting Office and Computer Production staff. More information appears in the Technical support services and the Operational procedures and infrastructure reports.