Managing Active Unstructured Data

InterModal Data Briefing Note

Unstructured data continues its endless growth. Much of this data is never accessed again after its creation, but there is a portion of it that is frequently accessed and needs to respond to those requests. The inactive portion is suitable for low performance and inexpensive object or archive storage solutions, but what about the active data? These technologies are often too slow for production systems. Most enterprises want a storage tier for their active unstructured data that is similar to Google, Amazon or Facebook but lack the staff and expertise to build their infrastructure from the ground up. InterModal Data recently came out of stealth and introduced their Disaggregated Storage Solution (DSS) to give traditional enterprises a head start.

What is Active Unstructured Data?

Active unstructured data is more than the opposite of an archive. Not only is the data currently being acted upon active, it needs quick processing. Unlike archive data on object storage, performance matters in the active use case and the storage system has to deliver that performance. The active unstructured data market is underserved as most vendors have focused either on active structured data like databases or stale unstructured data that just needs retention.

Active Unstructured Data Options

IT planners looking to create a high-performance storage solution for their organizations have limited options available to them. The first choice is to select a legacy storage solution from NetApp or EMC that is mostly monolithic in nature. While these companies have added some scale-out capabilities, the techniques they use are also outdated, tightly coupled architectures that don’t provide the flexibility and cost effectiveness that organizations need. The various components of the storage system are intact on each node. When a node is added to address a capacity problem, for example, that node also brings with it compute and networking resources. Eventually the scale-out NAS is out of balance, it has too much of most of its resources but not enough of a single one.

Another option is to custom design a solution similar to Google, Amazon and Facebook. Again, the problem with this approach is most organizations don’t have the staffing or expertise to create one of these solutions from scratch.

Giving IT a Head Start

InterModal Data gives IT a head start. Instead of the classic scale-out NAS approach, InterModal’s solution is a DSS or Disaggregated Storage Solution which physically separates the various components. For example, nodes can address performance and capacity separately. The private Ethernet network allows resources and even the data to quickly reallocate to different nodes.

The InterModal Data solution supports millions of data stores over either NFS or iSCSI protocols. For maximum performance predictability, Quality of Service (QoS) is granular to a workload level instead of the normal LUN or volume level. It leverages a flash and DRAM cache to deliver high-performance to active unstructured data workloads. The solution is available as software only and InterModal’s certified hardware compatibility list (HCL) insures smooth operation and high quality support.

StorageSwiss’ Take

Much of the attention on unstructured data is storing it as cheaply as possible – but retaining it just in case it is needed later. There is a percentage of unstructured data that is active and needs very high-performance for quick processing. Solutions in this space are either aging legacy solutions or science projects that traditional data centers don’t have the time to manage. InterModal Data offers a fresh approach, providing turnkey storage software that can run on hardware that the organization purchases. It may be the logical alternative for organizations looking to web-scale their data center like large scale virtualization, technical computing, media & entertainment, life sciences, IaaS, SaaS, or other applications leveraging Ethernet protocols.

Twelve years ago George Crump founded Storage Switzerland with one simple goal; to educate IT professionals about all aspects of data center storage. He is the primary contributor to Storage Switzerland and is a heavily sought after public speaker. With over 25 years of experience designing storage solutions for data centers across the US, he has seen the birth of such technologies as RAID, NAS and SAN, Virtualization, Cloud and Enterprise Flash. Prior to founding Storage Switzerland he was CTO at one of the nation's largest storage integrators where he was in charge of technology testing, integration and product selection.

Tagged with: , , , , , , , , , , ,
Posted in Briefing Note

Enter your email address to follow this blog and receive notifications of new posts by email.

Join 22,182 other followers

Blog Stats
  • 1,512,972 views
%d bloggers like this: