Fix Your NAS Silos with Automated Cross-Storage Tiering

Fix Your NAS Silos with Automated Cross-Storage Tiering

Posted in tech

In this blog series, we examine the inefficiencies of traditional NAS systems and how DataSphere solves them. This post discusses how DataSphere maximizes the performance and efficient utilization of storage resources while minimizing costs by tiering data across heterogeneous NAS systems. Previous posts discussed how DataSphere improves NAS performance and capacity utilization. A future post will discuss how DataSphere enhances the capabilities of existing NAS systems.

Manually Tiered NAS Systems are Complex and Costly

To meet different application requirements, enterprises frequently deploy multiple NAS clusters with varying capabilities, or deploy an additional NAS system when another reaches its scalability limits. This means each NAS system will suffer from performance and capacity inefficiencies and each must be managed separately. In addition, as enterprises seek to leverage cloud and object storage, they will be monitoring and maintaining even more silos. All of this complexity adds costs and slows down IT agility.

IT at some enterprises, such as Media and Entertainment companies, must manually tier data across different NAS clusters to support diverse storage requirements over the course of workflows. Unfortunately, to err is human, especially given the complexity of manually managing data at this scale. For example, to maintain application access to data as data is copied, admins might create a root NFS export, mount it across the cluster, then use an automounter to graft mounts from each tier to the root NFS export. Data movement is still manual, though scriptable, and the copy process disrupts applications, drains compute jobs and stalls work. Data access can be maintained via symlinks that must be recorded so admins can reference them whenever they move data. Tracking this continually increasing system of symlinks becomes more and more difficult, increasing the risk of production applications breaking when data is moved.

Deploy an Efficient, Integrated NAS Ecosystem

The DataSphere software platform creates a global namespace that makes heterogeneous storage systems simultaneously available to all applications. Enterprises can add many NAS systems to create a “meta-cluster” that is made up of different systems with diverse capabilities. The metadata engine knows what storage devices are capable of and can move data transparently across storage as required by workflows. This increases resource efficiency and utilization to provide a number of benefits to IT:

  • Free up higher tier storage capacity to serve active data. DataSphere can move data to lower cost storage in response to a manually applied policy, or dynamically if, for example, data has not been accessed within a given period of time. This can cut Tier 1 capacity needs by as much as 4X, as discussed in the previous post.
  • Improve productivity and business continuity with bidirectional tiering. Unlike most tiering approaches, which are unidirectional, DataSphere can move data back up tiers, as needed. For example, when Media and Entertainment companies work on a sequel, IT makes data from the original movie available to artists by manually moving data from an archive to a Tier 1 NAS system . DataSphere can automate this process, detecting when artists are accessing archived data and retrieve it to a Tier 1 system without IT intervention required.
  • Save IT resources and infrastructure.By automating data migration, DataSphere alleviates IT from the burden of late night and weekend migrations so they can focus on value added projects instead of operational tasks.

The diagram below illustrates a DataSphere NAS environment:


Figure 1 – DataSphere connects different types of NAS storage and the cloud, then automatically places the right data on the right resource to meet IT-defined objectives.

DataSphere makes all storage simultaneously accessible to applications. This helps enterprises create a dynamic ecosystem comprised of different NAS types and even cloud/object storage to maximize performance and efficiency, while minimizing costs. Can’t wait to learn how to put storage to work in the service of your data? Read more on our NAS solutions brief, or contact us at deepdive@primarydata.com.


Contact Form

Channel Partner