TeraOS incorporates a broad sensor network with a highly scalable monitoring framework to read these sensors in near real time. TeraOS correlates the returned metrics and provides health status and alerts on major components, as well as a time-series performance analysis. Without all-inclusive hardware monitoring and drill-down dashboard reporting, competitors and their customers must rely on a collection of tools and time consuming log file sifting to determine the root cause of degraded performance or component failures.
Enterprise customers and leading research universities have voiced strong opinions on the high value of TeraOS in their HPC environment.
“We have deployed nearly 3 petabytes of TerasOS managed Lustre storage as part of our HiPerGator supercomputer. It would be very difficult to manage that scale of storage and complexity without the comprehensive and integrated hardware monitoring that TeraOS provides,” commented Dr. Erik Deumens, director of research computing for the University of Florida.
“Our users expect our HPC capabilities to be always available with no degradation in performance. The monitoring that TeraOS provides covers everything in the storage appliance aggregated to a single health metric. If we have a problem, we can drill down. And if we need support, there is one company, Terascala that supports the entire storage system. This allows a small staff to meet our user’s reliability demands,” observed James Lowey, vice president information technology at the Translational Genomics Research Institute (TGEN).
“The TeraOS comprehensive hardware monitoring and reporting are key to administering large scale Lustre installations like BlueRidge,” said Brian Marshall, computational scientist at the Virginia Tech Advanced Research Computing facility. “We can focus on research rather than the intricacies associated with Lustre and all the hardware.”
“Large clusters like Hyades that use a Lustre file system, need hardware monitoring to ensure that it’s always up and running,” noted Shawfeng Dong, director of astrophysics and high performance computing at the University of California, Santa Cruz. “TeraOS and its intuitive dashboard give us real time operational status for easy management of a complex system.”
About Terascala
Terascala—the High Performance Computing (HPC) storage management company—has pioneered software that lowers total cost of ownership by managing and optimizing data, performance, and reliability. Savings are quickly realized through minimizing downtime, moving data very fast between scratch and inexpensive backup storage, and optimizing workload throughput. The company’s TeraOS software provides system-level high availability to reduce costly degraded performance and downtime. It integrates workload, network, storage, and file system monitoring, analysis, pre-emptive failure alerts, and fast failover. Terascala’s real-time analysis and phone-home support keeps these highly complex systems up and running at peak performance. Support costs are minimized with no HPC or parallel file system expertise required.
—
Source: Terascala