Today Panasas announced the launch a new version of its parallel file system, PanFS. The new system has Dynamic Data Acceleration, which is said to support workflows in HPC and AI. The new system is said to deliver high performance by automatically adapting to the changing and evolving small file and mixed workloads.
Today Panasas announced the launch a new version of its parallel file system, PanFS. The new system has Dynamic Data Acceleration, which is said to support workflows in HPC and AI. The new system is said to deliver high performance by automatically adapting to the changing and evolving small file and mixed workloads.
Panasas PanFS is a parallel file system that is highly adaptable. It is also the operating environment for the company’s ActiveStor Architecture. The big selling point is PanFS ability to offer consistent and predictable performance by automatically adapting to changing files sezes and workloads. The system is also said to support limitless scaling through a scale-out object back-end. The new Dynamic Data Acceleration continues on the foundation laid out in PanFS this time delivering predictable and consistent performance in HPC and AI workloads, too areas that suffer from lack of adaptability.
Tiered HPC storage systems are highly complex and manual intervention can cause headaches. Panasas’ Dynamic Data Acceleration sets itself apart from other HPC storage systems by maintaining high, consistent performance in the face of changing file sizes and workloads. In order to do this the integrated system uses NVMe SSDs to store metadata, low-latency SSDs to store small files, and large files are stored on low-cost, high-bandwidth HDDs. This auto tiering leverages the best technology for the job while helping to manage costs as well.
According to the company PanFS is deployed on the commodity off-the-shelf (COTS) hardware-based Panasas ActiveStor Ultra HPC turn-key appliance to deliver a fully integrated storage solution.
Engage with StorageReview
Newsletter | YouTube | Podcast iTunes/Spotify | Instagram | Twitter | Facebook | RSS Feed
