High-performance object storage is a data storage architecture designed for handling large amounts of unstructured data. It has historically been known for its ability to store these massive amounts of information as objects, rather than files. But use cases have broadened in recent years as more organizations produce large amounts of data and want the ability to organize, manage, and search it.
“High-performance object storage is common in two scenarios,” says GigaOm analyst Enrico Signoretti. “On one hand, these types of systems are used to consolidate more workloads on a single system. On the other hand, they are used as interactive storage for highly demanding workloads that also present huge data sets, like in AI, HPC, or big data analytics.”
In his new GigaOm Radar Report for High-Performance Object Storage, Signoretti looks at the fast-moving market of high-performance object storage solutions and the value that vendors bring to the table with their offerings. Things are moving so fast in the space that Signoretti expects it to look very different in just a few years.
“The pressing need for speed associated with growing demand for data management functionality will quickly change the scenario,” he says. “We will have more HP (high-performance) object stores while traditional stores will be relegated to a niche. At the same time, object stores will become smarter with functionality to analyze data and augment data while ingested. This will open additional opportunities, including innovative edge-core architectures for sophisticated IoT use cases.”
With this rapid-pace change in mind, what should buyers keep in mind when evaluating high-performance object storage solutions?
- Data consolidation: Combining and storing various types of data in a single place can help to minimize the number of storage systems, lower costs, and improve infrastructure efficiency.
- New workloads and applications: Thanks to the cloud and other technology, developers have finally embraced object storage APIs, and both custom and commercial applications now support object storage. Moreover, there is high demand for object storage for AI/ML and other advanced workflows in which rich metadata can play an important role.
- Better economics at scale: Object storage is typically much more cost effective than file storage and easier to manage at the petabyte scale. And $/GB is just one aspect; generally, the overall TCO of an object storage solution is better than it is for file and block systems.
- Security: Some features of object stores, such as the object lock API, increase data safety and security against errors and malicious attacks.
- Accessibility: Object stores are easier to access than file or block storage, making it the right target for IoT, AI, analytics, and any workflow that collects and shares large amounts of data or requires parallel and diversified data access.
“In general, balanced architectures are those that work best for enterprise use cases and workload consolidation and they are usually placed on the right of our Radar,” says Signoretti. “At the same time, if the user is mostly concerned with performance for highly demanding workloads, it is highly likely that the left section of the radar will be the area to look at.”