CIMdata PLM Industry Summary Online Archive

26 February 2013

Product News

Altair Expands Capabilities for Cluster Management with PBS Professional Connector for HP Insight CMU

Altair today announced availability of a connector that more deeply integrates its leading workload management product, PBS Professional, with the HP Insight Cluster Management Utility (CMU) for cluster lifecycle management.

Altair has accomplished this integration using a "connector" that furnishes seamless integration and provides the administrator an interface to automate 80 percent or more of the administrator's tasks. The CMU PBS Professional Connector simplifies cluster deployment and automates the most common tasks for managing a PBS Professional cluster via CMU.

"With the CMU PBS Professional Connector, cluster administrators have a much easier way to monitor and manage cluster nodes and jobs," said Bill Nitzberg, chief technology officer for PBS Works at Altair. This important integration automates the most common cluster administration tasks so system administrators can spend as much time as possible on higher-value aspects of managing their HPC resources." 

The HP Insight CMU is an efficient and robust hyperscale framework for cluster lifecycle management and offers a suite of tools for large Linux clusters such as those found in high performance computing (HPC) environments.  A simple graphical user interface (GUI) enables an "at-a-glance" view of the entire cluster across multiple metrics, provides frictionless scalable remote management and analysis, and allows rapid provisioning of software to all the nodes of the system.  Insight CMU makes the management of a cluster more user friendly, efficient, and error free than if it were being managed by scripts, or on a node-by-node basis. 

"High performance computing environments need a unique set of management tools that offer ultra-scalability and simplicity," said Scott Misage, director, Hyperscale Computing, HP.  "The CMU PBS Professional Connector augments the benefits of HP Insight with an easy- to-use approach for managing cluster workloads that is easy to access, efficient and error-free."

Features of the CMU PBS Professional Connector include:

  • Dynamic creation of node groups in the CMU GUI when jobs are executed, so administrators and users easily can see utilization and performance metrics related to all nodes where a certain job is running
  • Dynamic OS provisioning based on workload in queues, with automatic GUI updates, so PBS Professional can comprehend all existing OS images that can be provisioned on nodes
  • Integrated PBS menus in CMU GUI for registering nodes, onlining/offlining (or "draining") nodes, enabling OS provisioning, deleting jobs and much more
  • Easy access to data on jobs and reservations, including which jobs are running, suspended or check-pointed on nodes
  • Automatic network topology configuration so PBS can optimally place jobs on appropriate network entities
  • Maintenance mode support allowing administrators to move "bad" nodes into maintenance mode for troubleshooting without competing with users' jobs
  • One-click access to online resources, including PBS Professional documentation, user forums and support

Using the HP Insight CMU with the CMU PBS Professional Connector simplifies management of clusters by automating numerous manual tasks and providing easier access to important utilization and performance metrics, as well as improved access to job data. The CMU PBS Professional Connector optimizes job placement via automatic topology configuration and provides one-click access to support resources, such as PBS Professional user forums and documentation. The Connector is simple to install and easily extensible for site-specific customizations.

The CMU PBS Professional Connector can be downloaded here: www.pbsworks.com/cmupbsconnector/

Become a member of the CIMdata PLM Community to receive your daily PLM news and much more.

Tell us what you think of the CIMdata Newsletter. Send your feedback.

CIMdata is committed to your privacy. Your personal information will never be sold or shared outside of CIMdata without your express permission.

Subscribe