At Storage Networking World in Europe – the big one when it comes to conferences for storage pros – I had a chance to sit down with David Dale of Storage Networking Industry Association, who told me that companies that have never been interested in standards are suddenly becoming interested in standards. We also talked about …
ViPR would be that reason, I'd hazard a guess. Bridge the control plane across EMC's myriad platforms plus as many others as possible if there's standards in place.
Deduplication allowed a one-time deferral of new storage kit when it first started showing up in bulk around 2006. Storage volume was the Big Problem of the day and the ability to delay new filer purchases was a Good Thing. Very shortly thereafter all the dedup houses were bought up and integrated into the major filers in order to ensure that they could retain control.
Host-based caching is filling this void today; instead of allowing a deferral of storage volume it is addressing the growing need for high IOPS. In-SAN flash caching and hybrid arrays aren't enough. All-flash is too expensive. data access needs to move closer to the application.
Converged infrastructure and host-based caching are rewriting the IOPS and latency portions of this market just as deduplication rewrote the bulk storage.
Standards are thus critical if you're EMC because you can't just buy up the competition (there are too many this time.) EMC needs standards because standards will enable smart tiering at the hypervisor and eventually the guest/application level. It's the only play they have left. If any of the converged infrastructure or host-based caching companies survive then their offerings will drive down demand for Fat SANs at the center of things and Thin Simply Can Not Be.
If you want the future of storage, look to Nutanix, Simplivity and Maxta on the converged side and Proximal or Flashsoft on the Host-based caching side. These are the folks making storage cheaper for enterprises. They are a direct threat...and the reason standards are now being seriously considered.
I'd add that this looks like an old tactic here: embrace, extend, extinguish.
Is SNIA relevant?
"David Dale of Storage Networking Industry Association, who told me that companies that have never been interested in standards are suddenly becoming interested in standards"
Really? I think most storage companies dip and then back out of SNIA at some point in time. Publicly all will say good things about SNIA, privately SNIA is seen as an irrelevance.
Lots of problems with SNIA as I perceive it. Firstly a standard normally only comes to play when its good for the vendors, not the consumer. But if a standard is being promoted by one main company, then it is likely to fail as the other vendors don't want it to succeed. So everyone signs up so they look like nice industry players but as @jackofshadows said "embrace, extend, extinguish."
The second problem as I see it is SNIA is run by tired old men. You know your career is in demise when you become the SNIA guy for your company.
The third problem is that to be in the fold as a vendor , you need to pay. Even if you are quite small. It's bad enough for the fresh minds not wanting to expend energy but when you have to justify the costs it reduces to the usual suspects and the few companies that are banking the farm that a standard gets released.
Lastly, SNIA track record is just appalling.
I have to say, I stopped looking at them a few years back so please correct me if in the last 2-3 years things have moved on......
- Geek's Guide to Britain Kingston's aviation empire: From industry firsts to Airfix heroes
- Analysis Happy 2nd birthday, Windows 8 and Surface: Anatomy of a disaster
- Review Vulture trails claw across Lenovo's touchy N20p Chromebook
- Adobe spies on readers: EVERY DRM page turn leaked to base over SSL
- Analysis The future health of the internet comes down to ONE simple question…