Are you looking for a reliable software solution with enterprise-level security to manage your growing cluster installations while meeting the needs of increasing number of users? The HPE Performance Cluster Manager delivers a fully integrated system management solution for Linux®-based high-performance computing (HPC) clusters scaling up to 100,000 nodes. The software enables fast system setup from bare-metal, comprehensive hardware monitoring and management, image management and software updates as well as power management. The HPE Performance Cluster Manager reduces the time and resources spent administering HPC systems - lowering total cost of ownership, increasing productivity and providing a better return on hardware investments.
What's new
- Support for HPE HPC systems: HPE Apollo, HPE SGI 8600, HPE ProLiant DL servers and HPE Moonshot.
Features
Provision Your Cluster Fast and Maintain Production
HPE Performance Cluster Manager can quickly provision a Linux operating system on a cluster with thousands of nodes from bare metal -- typically within an hour.
Hardware components in the cluster including those added to the cluster later on are automatically discovered and configured without requiring system shut down.
System administrators and end-user functionalities are kept separate and authenticated system configuration information is stored in a central repository. Those are just some examples of software features helping to reduce exposure of your HPC system to security breaches.
Comprehensive System Monitoring and Management
The HPE Performance Cluster Manager collects metrics from the hardware system, environmental, performance and power sources and allows administrators to view the data in a graphic user interface (GUI), web browser or a command line interface (CLI).
System administrators can broadcast management commands to any selected set of nodes (provision, reboot, shut down, power off, etc.) from the management console or via CLI.
System alerts resulting from continuous system monitoring are displayed in the management console and emailed to the system administrator. The alerts include corresponding reactions, allowing users to add automated responses to important events.
To maintain consistent configurations, users can execute one command across any selected set of nodes and immediately see differences or inconsistencies.
Out-of-band management protocols supported include Redfish, IPMI, and SNMP allowing integration with other hardware and software tools.
Software Updates Accommodate a Wide Range of Requirements
HPE Performance Cluster Manager does not require system to be rebooted after provisioning. Provisioning is not disrupted by network communication interruptions and supports automatic retries without requiring system administrator intervention.
HPE Performance Cluster Manager provides flexibility by enabling users to install different versions of Linux operating systems across the whole cluster or on selected nodes on-demand for variety of different workloads.
Comprehensive image management enables users to build and maintain a software image repository to easily establish, switch, or restore your software environments as needed. Version control allows software changes to roll forward or backward as required and keeps track of changes for accountability.
Lowering Operating Costs with Advanced Power Management
HPE Performance Cluster Manager offers tools for accurate measurement and prediction of power usage for better capacity planning.
