Reference Architecture

Intel Cluster Ready specification and Intel Cluster Checker tool

Developed in conjunction with Dell and other leading HPC vendors, the Intel Cluster Ready program helps simplify buying, building, deploying, and managing a high-performance computing (HPC) cluster. Intel Cluster Ready helps to ensure application and component interoperability from the moment you power up the cluster through the lifetime of the system.

  • Choose a certified Dell Intel Cluster Ready system to reduce the time and risk of selecting a collection of independent hardware components for your applications.
  • Select a Dell certified Intel Cluster Ready system for your registered Intel Cluster Ready applications so you can be confident the hardware and software components will work together, right out of the box.
  • Software tools such as Intel®  Cluster Checker help ensure that those components continue to work together, delivering a high level of quality and a low total cost of ownership over the course of the cluster's lifetime.

In collaboration with Dell, other OEMs, channel members, and ISVs, the Intel Cluster Ready program specifies a common basis for clusters. This helps ensure ISV applications written to run on one certified cluster can reliably run on another certified cluster; conversely, a certified cluster will support multiple Intel Cluster Ready ISV applications.

The program includes:

  • Specification - a common basis for building clusters and developing applications for HPC. The specification includes requirements for hardware, software, manageability, and functionality.
  • Certification - ensuring the cluster you buy is designed and built to specification
  • Tools - validating and testing the ongoing operation and performance of all cluster components
  • Labeling - making it easier to select interoperable hardware and software
  • Communications - ensuring best practices are well known and readily available

Intel Cluster Checker

Intel Cluster Checker is an essential software management tool that helps make sure system components continue to work together over the lifetime of the cluster. Included with all certified Intel Cluster Ready clusters, Intel Cluster Checker analyzes the cluster's configuration to make sure it remains within certification. Whether a software update is causing software conflicts or a cable has come loose, Intel Cluster Checker can identify the problem quickly and provide detailed diagnostic information. Use Intel Cluster Checker to help reduce the time spent troubleshooting and minimize the need for specialized support skills. Run Intel Cluster Checker regularly to help enhance system reliability and ensure optimal performance.

The Intel Cluster Checker tools provide a full range of tests, analyzing important aspects of cluster organization, functionality, and performance to help ensure consistent, systemic operations. Advanced tests, such as the HPCC suite, evaluate the performance of individual nodes, as well as performance of all compute nodes in the system. If a problem occurs, the Intel Cluster Checker will automatically provide a detailed per-component diagnostic report, including pass-fail status. This reporting helps greatly simplify problem isolation and resolution, allowing you to quickly address the problem at its source. The Intel Cluster Checker tool suite is extensible, letting users customize tests by specifying command and expected output, and even integrating additional test via plug-ins.

Intel Cluster Checker Features

  • Modular and configurable. While defaults are provided that work out-of-the-box, tests can also be tailored to fit specific needs.
  • "Smart" checking. Starts with basic node-level tests and builds complexity and comprehensiveness via dependencies to full cluster-wide checking.
  • Parallel execution across the cluster
  • Rapid diagnosis of issues
  • "Traffic light" dashboard output
  • Nearly 70 "wellness" modules

Tags: intel cluster checker, intel cluster, certified cluster, intel cluster ready, cluster checker