10 posts • joined 18 Jul 2012
Re: What is it
SeverSAN has a big future of performance optimised storage. It's not the only route, there are plenty of other choices but the performance vs cost arguments are very compelling. It won't be for everyone, and for others there are all flash arrays, hybrid arrays etc. There's a home for all of them. And yes, the basis of the concept has been around for a while, but a number of things had to change in order to facilitate the growth of this technology - the key one being the accelerated pace of solid state memory development, both from a technical and cost standpoint. Drawing parallel's, you need look no further than object storage. It's been around for ages, yet why didn't it take off before? Customer need. Problem is object storage is now not a technology looking for a problem. Explosive growth of file data is the problem, and object is now the only technology which can scale economically to support it.
What about the impact of software defined storage?
Always eager to read your blogs and, either by hope or design, they really are a reflection of what I am seeing in the market. I have a diagram, which I discuss with my partners, which pretty much summarises all the external influencing factors you ahve mentioned such as big data, but also includes mobility as I believe this will also help define reuqirements of future storage architectures.
Interestingly, smack in the middle of my graphic, sandwiched between high performance flash/hybrid and scale-out file/ojbect storage is software defined storage. Now technically, SDS is really an overlay play as one could argue that any vendor who deloys their storage on supermicro servers is infact an SDS player (or at least has the potential to be) beit T0 flash, T1 SAN/NAS arrays or T2/Archive scale-out oject stores. So, I was curious, why no mention of SDS in your blog? Is it too immature to have an impact in the foreseeable? are there not enough vendors visible to make it a relevant conversation right now? Would appreciate your thoughts.
These tables hold very little credibility. Practically worthless. There are no apples for apples comparison's here. The are comparing SAN's, NAS's, Unified Solutions, Hyperconverged Platforms, Scale-Out File Systems and Object Stores. All have a different role to play in cloud storage.
Adoption will be driven by customer need
I agree with almost everything you have stated here Martin. There is a definite case of SDS from traditional NAS/SAN through to scale out object storage (I think there may be a case for flash/hybrid arrays, where performance guarantees require dedicated platforms), but the speed of adoption will depend on a number of parameters.
1) End user/Integrator skill set
2) Knowledge of the market, options
3) Uses cases/ references
I believe the complete abstraction, ie software on ANY platform, is a little way off yet. It'll require more general confidence in the software technology first. I see no issue with compatibility lists or validated commodity hardware delivered as part of the solution, as things stand. Look at the general move towards prevalidated technical stacks such as Vblock, flexpod, vspex etc, there is huge customer demand for those type of solutions, as it removes much of the complexity and operational cost when rolling out services. I thinks we need to get to this stage first in the storage market (for all the same reasons), before we start talking about storage software on ANY platform.
It's not just cloud
Love the article Chris, whether you are right of not, at least it creates conjecture and debate. I believe the cloud will have a big part to play in the rapidly evolving storage market, but the solutions have their challenges currently. I don't buy cost and security as inhibitors. This stuff is cheap (although their pricing models are pretty confusing currently) and their security is well architected, they dont have a business if it isn't! Their challenges are latency and issues around data management (lock in was an issue smeome described earlier).
However, in the short term i dont believe cloud will be the only challenge to legancy storage arrays. For a number of reasons - flash, hybrid, object and software defined storage based solutions will eat into their market as companies evdeavour to improve the speed, scale or cost reduction in storing and managing their data.
Re: I'm not convinced
What happens when all the applications and processing are in the cloud? Pipes are an issue now, but the whole compute model has an opportunity for change too. Then its not pipe size but avaiability that becmes the problem.
Re: All Flash. No Cache
"There is definately a place for all-flash arrays but hybrid will capture the mainstream"
That will depend on the economics of AFA's. When SSD's achieve cost parity with HDD's, there are limited reasons to need a hybrid solution. I see hybrid currently as a transitional play for the next 3/4 years, those hybrid vendors that can gain a significant enough footprint before the SSD vs HDD commercial tippingpoint is reached will be in a strong position to capitalise on the opportunity.
Re: This drive technology needs a new name,
Given the fact you are reading an article in the storage section of a website by a well renowned storage journo, I hope your comment about Adobe was a joke :-)
Phone calls are way more annoying than the texts. We get at least 1 every day. I would love to see this practice stop in it's tracks.
It's not just about saving direct costs
Agreeing with others here and those in the main article, it's about increased security and improved productivity as users can publish their desktop of applicaiton to a number of different devices and access them in the most convenient way. It's also about enabling scale, managing moves and changes. It's far easier to deploy and manage new desktops using VDI model.
- NASA boffin: RIDDLE of odd BULGE FOUND on MOON is SOLVED
- Pic Mars rover 2020: Oxygen generation and 6 more amazing experiments
- Microsoft's Euro cloud darkens: US FEDS can dig into foreign servers
- Plug and PREY: Hackers reprogram USB drives to silently infect PCs
- Boffins spot weirder quantum capers as neutrons take the high road, spin takes the low