JRB - Fotolia
With another year just getting underway, we here at Taneja Group felt we needed a few analyst predictions to get things off on the right foot. The easiest predictions, and often the most likely ones, are that things will continue mostly as they are. But what fun is that? So, like any good fortune teller, we held hands around a crystal ball, gathered our prescient thoughts and with the help of the storage spirits came up with these six predictions for change in the data storage market for 2015.
1. The overall traditional storage market will stay relatively flat despite huge growth in big data and the onrushing Internet of Things. Most new big data will be unstructured and big data architectures like Hadoop will still tend to leverage DAS for storage. In addition, many big data players are pushing the data lake or hub concept to land even bigger chunks of other enterprise data on big data clusters. While we do see some salvation in this space from vendors like BlueData that enable big data analysis to leverage traditional enterprise storage, it won't be enough to make a big dent in 2015.
We've also noticed that many storage shops have yet to take advantage of the emerging capacity optimizations now available (e.g., thin provisioning, linked clones, global deduplication, inline compression and so on) in recent versions of competitive arrays that are becoming table stakes for new acquisition decisions. Hybrid arrays, in particular, are bringing flash-enabling space efficiencies across their full complement of storage tiers, and most arrays these days are turning at least hybrid.
2. Speaking of flash, there are too many all-flash array (AFA) vendors and not enough differentiation. During 2012/2013 the first AFA vendors had the market to themselves, but with all the big players rolling out full-fledged flash offerings, opportunities are declining. With EMC, Hewlett-Packard, Hitachi Data Systems, IBM and NetApp all pushing their own solutions (both AFA and hybrid), the remaining independent vendors will have a harder time finding a niche where they can survive. We also expect to see a new round of very high-end performance storage architectures in 2015, such as EMC's DSSD and Avalanche Technology's super-performance design.
As a related trend, we anticipate that hybrid-based Tier-1 arrays will lose ground to AFAs in general, as the cost of flash drops and flash performance proves valuable to most if not all Tier-1 I/O. In virtualization environments, this trend will be somewhat lessened by the rise in popularity of server-side flash and/or memory caching/tiering solutions.
3. Data protection and other add-on storage capabilities will become more directly baked into storage solutions. We expect to see more traditional arrays follow the examples of Nimble and Microsoft StorSimple, which build in data protection features as a way to offer more complete, end-to-end storage services. Traditional layered, third-party backup software may take a hit, as will separate data deduplication and replication products. More and more storage, both traditional and "new" platforms, will have cloud-ready features built in for cloud tiering, archiving, backup and disaster recovery. EMC and NetApp have each acquired cloud gateway technologies recently, and we assume it's because they think the traditional storage market is finally warming up to leveraging cloud storage for colder capacity.
4. Storage will move past serving database-friendly LUNs, human-friendly files and Web-friendly generic objects to provide more application-centric storage features. In 2015, this will start in a big way with virtual machine (VM)-centric storage capabilities as pioneered by Tintri and embraced by VMware's Virtual SAN. With the long expected VVOLs support coming from VMware, every array will soon be competing to provide VM-specific storage, with provisioning, management, quality of service, data protection, troubleshooting and reporting all done at the array per VM. As the world continues to virtualize IT and increase automation to lower both Capex and Opex, we'll soon see per-VM storage become a major requirement driving new storage requests for proposals.
5. The software-defined storage and hyper-convergence trends will, themselves, converge and begin to dominate virtualization deployments. EVO:RAIL, Nutanix, Scale Computing and SimpliVity will be among the first choices for any new virtualization projects. Convergence players will scramble to incorporate more software-defined resources to become more like hyper-converged solutions. In general, we'll see wider adoption of virtual storage appliances and Virtual SAN-like solutions by small and medium-sized businesses looking for simple converged solutions and larger enterprises with distributed storage requirements. Software-defined storage solutions will become generally accepted for Tier-2 storage and start to threaten Tier-1 storage options by the end of the year. We expect to see a new crop of third-party vendors providing cheap DAS and PCI Express flash intended specifically to support software-defined storage, and even wrapping them into appliances to compete with more traditional offerings outside of the virtual environment.
6. Private cloud storage, particularly Tier-2 storage, will be rolled out in earnest in larger deployments in 2015 by both the government sector and larger enterprises. Object storage comes into much wider play in internal private clouds in production as key applications slowly convert/migrate into Web/cloud hosting shape, but even just archive, big data workflow and file sync-and-share workloads will drive adoption.
We're sure 2015 will be a "shake-out" year for the data storage industry, no more business as usual. Do you like our list, or do you have different predictions? Let us know and we'll keep score.
About the author:
Mike Matchett is a senior analyst and consultant at Taneja Group.