In their latest installment on NVMe storage systems, 451 Research spells out a clear vision for NVMe storage where NVMe-Over-Fabrics (NVMe-oF) is the clear winner for Web-Scale, Media and Entertainment, Governments and Financial Services firms with a need for NVMe speed. Research Analyst, Tim Stammers identifies four pillars of NVMe deployment that merit further investigation:
- Modifying existing storage systems to use NVMe does not maximize performance
- Offloading processing onto host servers drives up costs by preventing disaggregation
- Relying on applications for data services also drives up complexity and management overheads
- Architecting storage to maximize NVMe performance while retaining services maintains disaggregation
In Tim’s thoughtful and measured approach, he explains that “the inevitable switch from the disk-era SAS and SATA storage protocols to the solid-state NVMe protocol will drive the industry to adopt new internal storage architectures.” Adding, “The storage architectures that truly preserve disaggregation will enjoy major advantages.”
With the latest version of its award-winning platform, Pavilion Data continues to enhance a design for NVMe that avoids IO bottlenecks, while providing storage management services like consistent snapshots and thin provisioning. By reducing latency from the host, across NVMe-oF networks, through the array to 40 microseconds, boosting read and write throughput of 90GB/sec and 120GB/sec respectively and adding SWARM Recovery for rapid node rebuilds, Pavilion Data is defining the playing field for NVMe-oF disaggregation.
If you already have NVMe SSDs deployed as Direct-Attach Storage (DAS) or are considering moving to NVMe with an All-Flash Array (AFA), this report is a must-read. You can find it exclusively on our website: 451 Business Impact Report on Maximizing NVMe Performance.