Skip to main content

CIOs are Seeking Optimal Enterprise Storage Solutions

The exponential growth of data within the typical enterprise presents a huge challenge for CIOs that must seek new ways to fund and deploy comprehensive storage solutions. Enterprise IT organizations are embracing a range of Flash-optimized architectures as they continue to transform their storage infrastructures, according to the latest market study by 451 Research.

Overall, almost 90 percent of these organizations now have some form of Flash-based storage installed in their data centers, while "all Flash" approaches are becoming increasingly standard to support transactional applications.

Meanwhile, more enterprise IT leaders are assessing the merits of creating an optimal hybrid storage solution, where object storage platforms are deployed for warm or cold data in active archive applications. These lower-cost solutions can free-up IT budget that was otherwise allocated for legacy SAN and NAS upgrades.

Quest for Unified Storage Transformation

"Organizations of all sizes are looking to transform their storage infrastructures to drive both improved performance and efficiency, and Flash-based approaches are at the heart of this transformation," said Simon Robinson, vice president at 451 Research.

While all-Flash approaches have gained substantial momentum in recent years and will continue to grow in popularity, it's also clear that many prospective buyers still view these solutions as cost-prohibitive.

451 Research analysts expect that these barriers may erode over time, but most enterprise decision-makers will continue to use a blend of Flash and HDD-based storage technologies for the foreseeable future.

Moreover, the ongoing challenge for many IT leaders is making the informed determination of an optimal mix of storage technologies -- given their particular set of diverse workload requirements. This is a scenario where a vendor's infrastructure audit tools and skilled storage architecture consultants can recommend optimized best-fit configurations.

Key insights from the enterprise storage study include:

  • The most common method for deploying data center Flash is as a tier in a hybrid SAN array, with just over half (51 percent) of organizations citing this implementation method as in use today, and a further 29 percent planning to deploy Flash as a tier in the next two years.
  • However, All-Flash Array (AFA) adoption is growing most rapidly, with 27 percent of enterprises having deployed this technology already, and a further 28 percent planning to deploy an AFA within the next two years.
  • Three-quarters of AFA deployments support multiple applications, with only a quarter supporting single applications. The top two use cases for AFA deployments are databases and virtual desktop infrastructure (VDI), while data analytics is expected to be a top two use case within two years.
  • Data-optimization efficiencies such as deduplication and compression are in use by a majority of organizations that have deployed Flash; most respondents – 59 percent – said they gained between 2x and 5x space savings from using these technologies.
  • The traditional storage vendors, led by EMC, dominate the AFA market today, though smaller specialists such as Pure Storage are still proving popular; a quarter of respondents say they are considering buying Pure Storage in 2016.
  • A sizeable minority of organizations – 19 percent – is aggressively embracing Flash-based storage to the extent that these organizations have already – or will over the next two years – entirely replaced HDD technology for SAN-based storage workloads.
  • However, high cost was highlighted as the largest single barrier to broader AFA adoption, with 51 percent saying AFAs are too expensive. A further 47 percent said their existing storage performance was sufficient as a reason for not purchasing an AFA.

Popular posts from this blog

Frontier AI Peaked. Here's What Comes Next

The prevailing narrative around artificial intelligence (AI) has been one of relentless scale. Bigger models, bigger clusters, bigger budgets. The assumption, largely unchallenged until recently, was that raw parameter count translated directly into competitive advantage. New research from Omdia suggests it's time to retire that assumption. According to the latest market study by Omdia, parameter growth in frontier AI models has slowed to around 5 percent annually since 2021, a stark contrast to the more than hundredfold expansion seen between 2019 and 2021. Enterprise AI Market Development For executives who have been making infrastructure and investment decisions based on the assumption that AI would keep demanding ever-larger, ever-more-expensive hardware, this finding deserves serious attention. The race to the top of the model size leaderboard has, at least for now, plateaued. Crucially, Omdia's analysts are not reading this as an AI winter. Alexander Harrowell, senior pri...