Scale-out NAS

Handling the scale-out NAS problem: Compuverde does away with performance bottlenecks and stores metadata in the cluster instead of in the gateways.

The result? Clean, efficient and linear scaling up to exabytes of data.

  • Single file system spanning over all servers
  • Native support of protocols
  • Flash support for high performance
  • Flexible scale-out by adding nodes

Scale -out -nas


The illustration shows the support of multiple protocols and integrated cache, and how one namespace span over multiple nodes.


Scale -out -nas -protocols

A scale-out NAS using Compuverde offers multiple entry points and removes potential performance bottlenecks. Metadata needed by the gateways to form structured storage (CIFS/NFS) within an unstructured cluster is stored within the storage cluster rather than in the gateways as many competitors do.

There are a lot of advantages to store metadata in the cluster instead of in the gateways. Scalability is the most obvious one. Metadata is also very sensitive information and needs to be protected from data loss. We store and handle metadata using the same algorithms as normal files. This creates a more robust and less complex architecture, for both software and hardware.

Furthermore, using a solution from Compuverde, allows for a single file system spanning over both multiple gateways and multiple object store clusters – opening up for exabytes of data with scalability to many trillion files. And with support for systems with integrated cache as well as integration through the NFS 3, CIFS, Open Stack, Amazon, CDMI as well as NFS 4.1 and PNFS protocol, your file system setup is well beyond ready.

 

The film shows how Compuverde is solving the need for scale-out NAS.