DAS Aggravation or Disaggregation?

A disturbing trend is occurring with cloud-scale and enterprise accounts where the deployment of NVMe SSDs is capped at less than 3TB.  The reason?  Node recovery.  With DAS deployments, the average recovery time for 1TB of NVMe can take hours and negatively impact application performance!

The result?  We are deploying complete nodes (servers, storage, network, memory) to accommodate capacity growth when all we really need are fatter SSDs.

Modern applications were designed to scale out using Direct-Attached Storage (DAS) with many servers working together processing sharded data in a parallel fashion.  In most cases, customers have enjoyed the benefits of NVMe for low latency and high performance.

But NVMe’s growth continues to accelerate, and drive makers are pushing the envelope of density/capacity with SSDs now shipping with capacities of >15TB.  30+ TB NVMe drives are just around the corner.  Given slow rebuild times, we have reached the limits of DAS designs.

Pavilion Data future-proofs NVMe deployments.  Through disaggregated Rack-Scale Flash, you have an OpenChoice to deploy the latest, high-capacity NVMe SSDs using RAID-6 at any logical volume size to your clusters.  By default, failure of several SSDs in a Pavilion system has zero impact on cluster operations.  With our SWARM Recovery feature, the rebuild time for a single drive averages 5 minutes per terabyte!

SWARM Recovery is a simple concept that is unattainable with JBOFs, DAS, or Software-Defined Storage.  With up to 20 storage controllers, we harness as much processing power as you define to rebuild a specific drive within a RAID group.  Similar to blood cells swarming to repair damaged tissue, the controllers in a Pavilion Data array work in parallel to reconstruct the drive as a background task, meaning no node is off-line during a rebuild, DAS recovery-related network traffic is eliminated, and cluster high-availability is never compromised.

Of course, there are other benefits to the Pavilion NVMe-oF Storage Platform including snapshots, thin provisioning, extraordinary read and write performance at latencies as low as 42 microseconds.  But when it comes to NVMe high-availability, there is nothing on the planet that can compare to the benefits of Pavilion Data with RAID-6 and SWARM Recovery.