Leverage standard servers with next-generation storage & networking
Pools NVMe storage across a network at local speeds and latencies
Enables 100% converged infrastructure
Deployed as a virtual, distributed non-volatile array and supports both converged and disaggregated architectures
Negligible overhead – leverage the full potential of your hardware
Client-Side, Distributed Architecture
Enables NVMe sharing that scales performance and capacity linearly
Local Performance at Data Center Scale
Remote IOPS = Local IOPS
Remote BW = Local BW
Remote Lat. = Local Lat. + ~5us
Capacity-optimized platform with 24 NVMe drives delivers:
> 4.9M 4KB IOPS
< 200us of latency
Using RDDA, 0% target CPU usage
Scales linearly to 100s of millions of IOPs per rack
20 servers, shared data, > 99% efficiency
128 servers @ NASA > 140 GB/s write throughput (bound by NVMe devices)
Maximize Resource Utilization
NVMesh was designed to enable customers to maximize NVMe utilization (capacity, performance & endurance) across their infrastructure. Leveraging the new parity-based data protection, NVMesh 2 delivers over 80% greater storage efficiency, which helps further drive down the NVMe TCO.
Standard Hardware & Protocols
NVMesh was designed from the ground up to support any hardware. With the added support for traditional network fabrics and protocols, enabling NVMe over Ethernet, and InfiniBand, customers don’t have to invest new networking technologies to deploy NVMesh.
More Diagnostic Capabilities
NVMesh 2 enables users to analyze cluster-wide and per-object performance and utilization, and build a customized dashboard from a selection of data visualization widgets.