HDS' Hu makes a point in his latest blog entry in that Storage Virtualisation allows the end-user to turn commodity disk into enterprise disk by sticking it behind a virtualisation appliance; in Hu's case, he'd deeply love that to be USP.
I think in many ways his idea gets to the core about what might have gone wrong with the storage industry; we are paying too much for the commodity bit of the storage i.e the spinning stuff!!
But is what Hu is talking about truly virtualisation? Arguably not! What HDS do and what IBM do with SVC is more loosely couple the array controller with the disk at the back-end. USP and SVC are simply array controllers. Storage virtualisation actually is not really that clever, the USP and SVC may have some fantastic code in but they are "simply" array controllers. And yes they have to deal with the vagaries of FC implementation across many different back-end disks and EMC would probably argue 'more fool them'.
So perhaps if instead of selling Virtualisation; IBM and HDS simply sold array controllers and said, 'You can buy your disk from us, EMC or whoever is giving the best deal today' and didn't make it out to be some mystical and magical thing; they might get more acceptance.
It actually changes the nature of conversation somewhat, end-users could then go back to EMC et al and ask the question, 'What makes your back-end disk so special? Why can't I just buy the directors and put what ever disk I like behind it?'.
I think the discussion becomes a lot less philosophical and a lot more pragmatic if this approach is taken. I know EMC have answers as to why their back-end disk is special but perhaps you should ask the question also. We can get down to talking about each storage array's USP…no pun intended!
Hi Martin,
It’s an interesting point that you make about Storage Virtualisation, but I feel that you have not examined the market quite thoroughly enough. There are products out there that are truly Vendor Agnostic, will enable ANY manufacturer’s disk to work with ANY other manufacturer’s disk, and also allow replication between unlike disk types.
As far as the virtualisation piece goes, there are products out there that will “over-provision” storage, will dynamically allocate writes to give the best performance and will improve the performance of an application server regardless of file system, type of server or application.
My impression of virtualisation in it’s truest form is the amalgamation of many disparate resources to present a single, homogenous resource, able to be used by any other device, whilst presenting clear efficiency improvements and management attributes.
I would be very keen to hear your definition and have a further chat about this.
Indeed there are; there are products like USP-V, NetApp vSeries, SVC and a few others which take the approach of putting another controller in front of another vendor’s disk. Then there are things like Invista and Incipient which take another approach. And then there are pure software plays like using Storage Foundations.
Whether you want to call this virtualisation or something else is up to you but for years, storage arrays have been abstracting physical spinning disks and presenting them in the way that the storage admin wishes to. Arguably, we have had storage virtualisation for years and these x86 bods are simply late to the party!
I am simply suggesting that all things like USP, SVC, v-Series actually are is loosely coupled array controllers. And if we look at them like that, they both become less scarey but also slightly less special but still extremely useful.
I think we agree that commoditizing storage capacity and enhancing it with enterprise capability with an intelligent control unit is a good thing for storage users. I would define that as storage virtualization by every definition I could find.
You had previously put the USP V in the category of storage virtualization in yourprevious post: http://storagebod.typepad.com/storagebods_blog/2009/02/v-is-for-value.html
However, if you choose to call it some thing else that is fine by me as long as it helps users understand the value that it can bring.
Martin G’s comment may sum it up best in that if you look at them as intelligent controllers, they become less scary…but still extremely useful.
Thanks Hu…Martin G is Storagebod BTW.
And yes I did include USP-V in Storage Virtualisation but for some time now, I’ve felt that that Storage Virtualisation is not an especially comfortable term. The problem is that server virtualisation has pretty much monopolised the V word and we get people jumping up and down saying we must virtualise everything, without understanding the differences.
Now if we drop the V word it might not be as sexy but it might just be more useful.
Hi Martin,
Barry B made a similar point a while ago –
http://thestorageanarchist.typepad.com/weblog/2007/05/storage_virtual.html#more
Im not sure where the “virtualisation” word comes from as HDS actually market the technology as “Universal Volme Manager” and I think HP market it as “External Storage XP”. I guess virtualisation is a buzz word and people want to “virtualise” so by referring to it by the V word you get peoples attention……
As for HDS and IBM dropping the V word and making it sound simpler might help them get more acceptance…..?? It seems to me that, at least with HDS customers, it has huge acceptance and i know of several cutomers that were won from other vendors and site this functionality as one of the reasons they switched to HDS (although I dont doubt cost played a big part too).
I’m not seeing huge acceptance across the board; you might see it in HDS customers but at the moment I’m not really seeing it in some of the conversations I have with other storage managers. These aren’t just EMC customers; I’m just not seeing storage virtualisation as a huge area of interest.
Great site this storagebod.typepad.com and I am really pleased to see you have what I am actually looking for here and this this post is exactly what I am interested in. I shall be pleased to become a regular visitor 🙂