Cluster management
An HPC cluster needs to have all the qualities you would expect from an effective production system: it must be available and capable of delivering the best performance under normal working conditions, with a varied and fluctuating workload, multiple users and multiple applications. This means the choice of cluster management suite is crucial, and has a real impact on the effective availability rate of the computing environment. At the same time, users should be able to concentrate on their own applications, rather than spend their time on administering the cluster.
Bull HPC solutions offer a choice between Bull Advanced Server - Bull’s comprehensive HPC Software Suite for Linux environments - and Microsoft® Windows® Server 2008.
Linux 
Windows HPCS
Linux 
Bull Advanced Server (BAS) is delivered with the Bull NovaScale Cluster 400-L (Intel® Xeon®-based) and Bull NovaScale Cluster 3000 (Intel® Itanium®2-based) Series.
Bull Advanced Server is based on a standard RedHat Linux distribution combined with a number of Open Source applications to take advantage of the best from the Open Systems community. This combined with technology from Bull and its partners, results in a powerful and complete solution for the development, execution and management of parallel and serial applications simultaneously.
Centralized cluster administration
The Bull HPC Software Suite enables the entire configuration to be controlled and administered – including the platform and interconnect network – as a single system. It features functions for software deployment on the servers, resource controls and monitoring from a centralized control workstation. Users are provided with a classic task management interface to manage the execution of their workload on the cluster.
The environment uses the very best Open Source and industry standard software, and incorporates all the improvements made by Bull, particularly to ensure that the various administration tools work effectively together and operate well on very large clusters. All the functionality has been fully integrated to ensure simple, high-performance operation of Bull NovaScale Clusters from a single point of control – the administration node – with a high level of security.
|
|
|
Microsoft® Windows® HPC Server 2008
Bull, as a Microsoft Gold Partner, supports Microsoft Windows HPC Server 2008. The Bull NovaScale Cluster 400-W range is designed especially for Windows and is delivered with Windows HPCS pre-installed, to provide an easy to use, scalable HPC infrastructure.
Microsoft Windows HPC Server 2008 (HPCS), the next generation of high performance computing, provides enterprise-class tools, performance, and scalability for a highly productive HPC environment. HPCS provides a complete and integrated cluster environment including the operating system, a Job Scheduler, Message Passing Interface v2 (MPI2) support, and cluster management and monitoring components. Built on Windows Server® 2008 64-bit technology, HPCS can efficiently scale to thousands of processing cores and includes a management console that helps proactively monitor and maintain system health and stability. Job scheduling interoperability and flexibility enables integration between Windows and Linux-based HPC platforms, and supports batch and service-oriented architecture (SOA) workloads. Enhanced productivity, scalable performance, and ease of use are some of the features that make Windows HPC Server 2008 best-of-breed for Windows environments.
Windows HPC Server 2008 can help shorten user time-to-insight for HPC workloads through easier deployment and management. By using the existing Windows-based information technology (IT) infrastructure, HPCS simplifies management, security, and storage for the cluster, and provides seamless access from the desktop.
HPCS includes improved provisioning based on the Windows Server 2008 Windows Deployment Services technology, a faster Microsoft Message Passing Interface (MS-MPI) that includes new NetworkDirect support, an advanced Job Scheduler, and a new management interface built on the Microsoft® System Center 2007 user interface (UI), which has support for Windows PowerShell™ as a preferred scripting interface.
HPCS uses the failover clustering capabilities of Windows Server 2008 Enterprise and of Microsoft® SQL Server® to provide high availability and redundancy of the head node in your HPC cluster.
| |
|
