ClusterVision has a dedicated cluster production and implementation infrastructure that allows for a rapid, trouble free deployment and support of cluster solutions at your premises. Our production infrastructure includes professional project management, quality control procedures, a production line specifically designed for high-end servers, and extensive hardware burn-in procedures.
Small to medium size projects are assigned a Project Engineer who acts as Project Manager. The Project Manager is responsible for the successful implementation of the project, from the moment the sales team hands over the project to the purchasing and engineering teams. The Project Manager supervises the hardware and software engineers, monitors overall progress , and keeps the customer informed of progress. Large projects are managed by a dedicated team of project managers, project engineers and purchasing and logistics experts.
A cluster deployment project includes various phases and milestones, including order receipt and confirmation, project and production planning, site survey, detailed network and rack designs, transport planning, installation, configuration, burn-in testing, handover, training, etc.
Clusters are complex products which only work to full satisfaction if all hardware and software components work together as a whole. Therefore, we subject our production process to the highest quality standards. For example, each individual component of every server in a cluster receives a unique ID which links the serial number of that component to the unique ID of the associated server in our support database.
This allows us to track each individual component or batch of components and analyse and diagnose problems efficiently. The ability to analyse batch problems can be particularly useful with components such as hard disks and memory modules.
ClusterVision runs a dedicated production facility, specifically designed for high-end servers, workstations and server racks. Our production facility is subject to the highest standards of quality control and health and safety regulations. Our emphasis on the importance of a high-quality production line is based on our long experience in working with high-end server hardware. A high quality production line allows us to build and test a wide range of servers, workstations, server racks and other hardware in high volume, while eliminating production errors and identifying faulty components.
Our production facility has the space and infrastructure to build complete clusters in server racks. This allows us to fully test the final solution and eliminate production errors, faulty hardware components and hardware/software incompatibilities before shipment.
Most servers we ship will be running Linux once in production
- Linux is more stable than most other operating system, so if something fails you can be sure that the hardware is to blame;
- Linux is capable of pushing hardware to its maximum capabilities;
- Linux produces more comprehensive error messages then other operating systems when hardware fails.
Our burn-in procedure includes for example the following tests:
- Stress testing the memory with ECC switched off in the BIOS. Having ECC switched off ensures that memory faults are not covered up the by the ECC mechanism
- Stress testing hard disks, raw writes and reads, checking for bad blocks
- CPU heat test, specifically stressing the CPU to produce maximum heat in the CPU.
- Overall heat and stability test: running several tests at the same time in order to produce maximum heat inside the chassis
- Warm start test: restarting the server several times directly after the heat test
- Cold start test: restarting the server several times directly when cold
- Consistency test: running several calculations and comparing the results and timings with reference results and timings