Historical reporting products provide an excellent overview of past performance, but do you know how your clusters are performing right now?

Platform RTM, a product in the Platform Manage suite, is an operational dashboard for Platform LSF that provides comprehensive reports for day-to-day administration activities in single and multiple Platform LSF clusters environment. It provides timely information on the current status of your High Performance Computing (HPC) environment to help system administrators improve decision-making, reduce costs and increase service levels.

Platform RTM automatically collects job and host metrics in a non-intrusive manner and uses a centralized web-based portal to provide visibility on workload and resource usage from clusters, hosts, users, queues, down to the individual job level. With the Cacti plug-in architecture and graphing templates, Platform RTM has the flexibility to support customization for most site specific reporting needs at both application and host level.

Platform RTM Datasheet: Report, Track, and Monitor Platform LSF® Clusters

How you can benefit from Platform RTM:

• Ensure efficient operations of one or more compute clusters and maintain an optimal policy set for high utilization and high throughput
• Increase user service level by quickly diagnosing and identifying issues
• Proactively manage Platform LSF clusters by understanding user workload
• Protect long-term investment with flexible customization tools for adding site-specific monitoring and reporting capabilities
• Understand types of workload and resource usage trends and patterns over time

Selected facts about Platform RTM:

• Comprehensive WLM Dashboard – administrators can monitor more clusters with less effort, validate that Platform LSF policies are set effectively, and make proactive adjustments
  • Intuitive user interface means minimal or no training is required
• Based on Industry Standards – equipped with out-of-the-box tools based on Open Source Industry Standards in high performance data logging and graphing
  • Cacti RRDTool (Round Robin Database Tool) provides a solid foundation for efficient and low-maintenance logging and graphing, so you can take advantage of industry best practice immediately
• Flexible & Extensible – extend and customize Platform RTM to cover site specific monitoring and reporting requirements to protect your investment for the long-term  
  • Access OOB graph templates covering the WLM metrics, and a large collection of templates covering hardware devices and applications
  • Cacti plug-in architecture allows Platform to provide enhancements such as event triggers and alerts, monitoring for parallel jobs, job control and remote execution, reducing the need for multiple monitoring tools
• Cost Effective – Cheaper to buy than to build
  • Proven scalability to 1000+ hosts deployed in multiple clusters
  • Eliminates the need for “compile-build-install” with pre-configuration for quick deployment into existing cluster environment