0 0

We Need an All-Flash Game Changer

The all-flash space has been abuzz lately with a slew of vendors announcing new developments:

  • Solidfire announced new nodes, a software-only implementation (which oddly comes without hardware freedom) and a new program around its Flash Forward guarantee.
  • Pure Storage announced an update to its Flash Array lineup and a program around Evergreen Storage.
  • HP announced its 20K 3PAR line up, basically a hardware refresh.
  • EMC announced software updates to XtremeIO and a lot of other flashy stuff in ScaleIO and DSSD (typical of EMC to think ahead and have multiple bets).
  • NetApp relaunched All-Flash FAS with new pricing to complement the rich data services that ONTAP brings to the table, and has been pounding its chest about how ONTAP is the best thing to happen to all-flash arrays.

What’s It All Mean?

There’s a theme here: Bigger, Faster and Cheaper.

This mostly results from new hardware technologies (compute), increasing flash capacities and flash cost reductions. Newer product functionalities are catching up to traditional ones, and traditional products (like HP 3PAR, NetApp FAS) are optimizing the code for flash and taking advantage of their preexisting data services and application integrations. Each vendor is playing catch-up to the other.

Where is the Differentiator?

Still, most vendors have similar features—dedupe, compression, snapshot, clones, replication, LUN/volume-based QoS and application and cloud integration—so it’s difficult to differentiate themselves. Hence, marketing starts to innovate more than engineering, spawning messages like these:

  • We provide better space savings (6x vs. 5x) (yes, that’s around 10% better)
  • Our space savings technology never goes post-process (okay, but the other vendor is 10% better for savings)
  • We provide Evergreen Flash (marketing spin on a creative sales rep)
  • Our Flash Forward program is unique in the industry (another marketing spin)
  • We are the only vendor that provides cloud integration (not true)
  • Designed from the ground up for flash (faster performance/response or longevity of flash doesn’t necessarily need a ground-up design in all cases)1
  • We have the cheapest flash solution (when nothing works, talk price)

LUN or Volume

Running out of Ideas?

None of these vendors have taken a “completely different” approach—and their superiority has an expiration date. To be truly different, traditional vendors have to develop wholly new products without any baggage. But even younger organizations base their products on 30-year-old constructs and abstractions that don’t fit in the modern datacenter—mainly LUNs, volumes and their associated challenges.2

But it’s always been the companies that take the “completely different” approach that shine. Data Domain defined a new model for backups. Even NetApp took a filesystem approach to storage (for file and block), enabling a completely different implementation of technologies like snapshot, clones, dedupe (primary storage) etc. Now, everyone has started to have some sort of filesystem layer, but it took a long time for them to get there.

And though starting out different is great, it is important for any vendor to stay different and keep reinventing itself (through acquisition or innovation) based on changing needs—rather than getting bogged down by a “if it ain’t broke, don’t fix it” mentality. As far as the all-flash market is concerned, we need products with a constantly “completely different” approach to change the game and bring new possibilities. We need to design from the ground up for the modern datacenter (and modern applications), rather than for flash.

After all, flash is just a medium, and mediums change. Vendors need to prepare for what comes next.

Cheers,
@storarch

Satinder Sharma is a storage and virtualization expert certified on Tintri, Sun, NetApp, Microsoft and VMware technologies, helping customers design their virtualization and cloud solutions using Tintri technology. He is based out of Toronto, Canada.

Adapted from Satinder Sharma's original blog post at Virtual Data Blocks, with permission.


1. I say this even though the flash layer and spinning drives have a completely different block layout on Tintri VMstore with the flash layer designed specifically with flash in mind.

2. These constructs worked great for some traditional workloads, but they require a lot of assumptions for architecting storage in a modern datacenter (RAID group size, block size, queue depths, LUN/volume sizes, LUN/volume quantities, number of workloads per LUN/volume, grouping based on data protection needs, etc.).

Satinder Sharma / Jul 28, 2015

Satinder Sharma is a subject matter expert for storage & virtualization.  He works for Tintri, based out of Toronto, Canada. He is responsible for evangelizing and helping customers design th...more

Temporary_css