 Okay, good afternoon everybody. This is Dave Vellante live inside the Cube from Wikibon's headquarters in Marlboro, Massachusetts And I'm on with my colleague and Analyst extraordinaire David Floyer. Hello David. Hi there We're gonna talk about the three par HP announcement left-hand had some announcement So HP made big storage announcement today The company continues to evolve its its line of high-end storage About a year after the acquisition of three par HP's, you know cranking away new v-series announcement federated storage. So so David Let's dive right into it. What did HP announce today? And what's your assessment? What are the highlights? So the highlights of what they announced today were the new v Models of the three par HP three-par storage That's got more connectivity a higher faster processor and a lot more Cash inside the box. So That's that's the V 800 and the AV 400 at the top end of the three par HP three-part series and That's a boost in that area and they've announced Federated storage And then they've also announced a couple of smaller items. They've to be all to be honest, they've They've added some more thinness to their story. They're now even thinner They save more and more storage But really as I think it's more like putting right things that they probably thought they had before and just Just put just Just to make tweaking things to make them even even more efficient. Okay, so basically bigger faster better Does this essentially replace the t-series? They're they are obviously Strongly saying it's a it's a total line You can take the t-series you can take the f-series and you can take the v-series And they all have different price points. They Haven't announced it, but I would be very surprised if they didn't have a significant reduction on the t-series to provide Space and room for them to move it as a total product line So realistically it replaces the high end of the t-series, right? It will do But but for the for the time being they've got all three in there in their product line Okay, another big part of the announcement was a federated storage. Yeah, that's a highlight to me Awesome feature still maybe you bring up that that slide So we've got a slide. This is actually the the HP version So they call it pure motion Yeah claims. It's the first storage federation in the market for entry mid-range and high-end storage So what what is? Federated storage. Why don't we start there David? well, so federated storage is about connecting the storage arrays into a Into if you like a complex And they can connect it both within the data center and between metro data centers within the metro environment And then with that they can dynamically move the workloads between the the different The different systems Dynamically and that's that's pretty awesome. There's some really nice use cases for that. Okay Great, let's talk about the use case. What are the main use cases for this and I know you wrote an article today? And you've got a lovely graphic So we can see I don't I don't have months to create these graphics beforehand It's just a very simple one to show what's going on here. Yes, so before you get into it So David wrote a piece today. It's on wikibon if you go to wikibon.org you can you can find it It's HP Peer motion you've called it a must-have feature for HP 3 par and HP left-hand arrays So what are the use cases? Why is it must have? right well The first use case is the most cost-effective of all We did a study in wikibon if you remember a year or two ago We were looking at the cost of migration for a new array going into a data center And the cost is somewhere between fifty and a hundred thousand dollars And that works out even at the fifty thousand level that works out to be about, you know, forty three percent of the purchase price of A new array is going into migrating the applications as the data off that old array and putting it on to the new So you have to allow time for that the average time is around five months and it can take up to 12 months You have to have space in the data center. You have to have Extra time on the lease you've got Unutilized resources It's really a very very expensive proposition just migrating from one to another And if on top of that you've got to lease payments and all these extensions which are coming up on you That can add to a lot of stress and a lot of overtime so The key advantage here is that you can connect this new array in connected to another Three-par array for example if we take two three-par boxes And you can set up the dual parting between the two arrays and Then the the arrays themselves manage the address and they manage the movement of data between the two systems And You fill up that think that's showing that it's nearly empty on one side and then it's being filled up on the other side And at the end of the process You can choose just to leave it in limbo or you can just say now This has been fully moved over and it moves the address of the volume Across to that new one and the scousy address and and and you can disconnect at that point So you can migrate data and then tear down the old array with no Without taking an application outage. No application outage. You can do them. You know when you want to You don't have you you have to always plan any migration like this But you're not going to do it all in prime time, but you it's much much more flexible And and as you say you don't have to take down the system at all You don't have to schedule those weekend Nightmares when you try and get everything across these you know these storage arrays have a huge amount of data on them And the discs aren't getting that much faster and they they take a long long time to migrate that data across even across Fiber channel, okay link between the two systems. So it's a perpetual migration capability for users now now my understanding is the HP capability is homogeneous It's not a heterogeneous Virtualization engine. Can you talk a little bit about that? Yes, it's a homogeneous and they've also announced it for the left hand as well Which again is a great addition So you've got one of the entry level more of the entry level and with the ice-cozy and one at the fuller and more high-end block storage so a nice coverage there and the the It's both of those are homogeneous You know chat about some time may be being between them But there's a lot of a lot of complexity in doing that So but homogeneous is many ways is goodness This is if you're doing this and your applications running you really want to test it 100 percent between the two The only other alternative way is well, there are two other manufacturers that have stuff out there's EMC have federated live migration, which is a similar technique that became available in June of this year and Compellent they have something called live volume, which they were back the first to to actually get it out there and working So there are a couple of other solutions out there in the marketplace Virtualization engines can also do the same job. For example, IBM's FVC. That's the most common the Hitachi USB or VSP can do the same job and and EMC has investor and and B-plex there's two ways that they can use investor But that that that is a disadvantage the disadvantage of that is that although you can you have to virtualize it and keep it virtualized all the time and You can't at the end of it De-virtualize it and have it stand alone working on its own, okay? So that's gives us a sense as to the sort of approach that HP's taking they call it peer-to-peer So there's not an abstraction layer like you would find in an SVC and you you mentioned in Vista Which is no longer marketed. I don't think it's in Vista still marketed. No, it's not still market But anyway, those engines put a virtualization layer an abstraction layer in between And our appliance-based HP's is an embedded peer-to-peer capability. Is that correct? Yeah What I think the best thing to compare it with is actually VMware's V storage Motion sorry storage V motion And and the great advantage is that you've now got the ability to do peer motion and I think that's a great name for it peer motion between the arrays and move stuff around dynamically Without any virtualization tax overhead And that's very significant on the VMware. Okay, so you I was going to ask why would I use? an embedded peer-to-peer capability in array versus just doing it with VMware and you're saying the overhead of the hypervisor is onerous at the upper head of the hypervisor and the IO subsystem through the hypervisor and and As a result the the really mission critical applications haven't been migrated across To VMware and in anywhere like the same amount as the left mission critical So this is a way of being able to move mission critical workloads Really important stuff but large volumes very very efficiently high speed Both metro distances and the local distances With with great deal of confidence that they're going to get there in one piece and it's excellent I think it's It really extends the capabilities of the storage administration to Move stuff around. Okay, so we've talked about the use cases with what it is the use cases. We've talked about the some of the competition, I guess you mentioned EMC Component or similar products. I don't know if they're head-to-head competition, but EMC Component and and and VMware and The last question I had for you David is You know three we've seen three power emerge from startup mode did an IPO reached 200 million and then was sold for Close to 2.5 billion Just an incredible run And three part always was targeting that you know the high-end of The the marketplace, you know, we call it some others call it tier 1.5 Is three part now in your view a tier one Storage player they join the ranks of the IBM DS 8000 Hitachi VSP and EMC symmetrics Well, they certainly are close in terms of functionality they've got the Federation federated storage now the peer motion which is really excellent and That brings them into the fold at one of the great advantages of joining the HP fold is that they could get direct Marketing of their boxes right the way across the world That's again another very important capability that the tier one vendors all have The the the real differentiation of tier one is when the the largest Financial institutions running the absolutely critical workloads choose Three part to do there for example three data center Replication type Applications on that and they they're not there It takes a long time for these cautious people with these very very high value applications to do anything different Three power isn't actually offering anything Anything extra other than maybe being slightly cheaper So the the bar to be considered as a tier one supplier is it's pretty high You've got to have been there and shown it and and be part of that club to to really to be considered as a tier one So we're talking we're talking about the three power as a potential This looks like they're they're knocking at the door. Would you agree with that? Absolutely. They're definitely knocking at the door My only concern is that by the time these type of arrays By the time they get there, there'll be a new class of array Only before we before we talk about that we so three bars knocking at the door. Is there anybody else that that you know There's nobody else as they are top of the 1.5 absolutely definitely there they're at the top there straining to to to get out of that but there's no doubt that they're Faster performance in the boxes and the wider performance capability then net up for example or any left hand or compelent or Okay, it's logic or any of the other Similar 1.5 type per box. Okay, so it's a it's kind of a four-horse race at this point for the tier one You're saying okay now You mentioned we love disruption here wikibon silicon angle And you mentioned these all flash companies, you know one that comes to mind is solid fire We've we've been you know taught been briefed by those guys. There's some others who just come out of stealth I think pure just your story came out of stealth today I am and and and some others nimbas Of course we've covered fusion IO very closely you just recently wrote a piece sort of describing the different areas fusion IO memory class storage the the all Flash block-based guys Like solid fire for example Look very disruptive to the to the tier one space an interesting thing about Solid fires they're targeting cloud service providers explicitly trying to enable new classes of applications Which I think is a unique positioning some of the other guys are sort of building up a different channel direct sales force and and Going after that but nonetheless, they're disruptive to the block based storage guys Aren't they can you talk about that a little bit? Absolutely, they're now competing on a on a cost basis so I mean the tier ones that they're still not competing with the tier ones because of the functionality within the system, but they All the competing they're competing on performance. Would you would you agree? They're good. Oh, definitely. They're competing on performance. They they they and they will get there and in the in the next three years and Very definitely because they're the performance and the consistency of the performance that they can offer is just Absolutely stunning and and they don't need any of the complexity of storage tiering or anything like that You know, they they have got rid of the slowest piece in the in the in the hierarchy Which is the disc itself and that makes huge improvements in consistency and variability So it did they they have an excellent story. They brought the costs down by by a great efficiency some very innovative Designs that are happening right the way across the board solid fire. I've got a very strong team, for example Design team. So yeah, that's to me over the next two or three years is going to be the future of high-performance computing in the data center along with fusion IO at the at the at the very high-end doing the extension of data in memory so you just did an analysis of the flash memory summit and you did a One of your courses for horses or horses time. It was the other way around It was courses for horses instead of horses. Yeah, so but in there I think you had some projections on the market size of these various classes of Arrays, right? Well, yes, I mean the first attempt at it. I mean, it's the very early days But yeah, we we put one out there just to to get the conversation started because this This is really going to separate out three classes of Solution and in terms of number of gigabytes that the high-end, you know the fusion IOs and other people Flash on them on the motherboard itself, for example We're suggesting that that will be 3% of the actual gigabytes, but in terms of volume That's likely in terms of money. It's likely to be in the order of 20% of the actual Spend so I have the data up here So he basically saying that and from a storage capacity perspective if I sliced the pie Flash storage on the server like fusion IOs 3% of the capacity Flash only arrays will be just over 10% of the capacity and traditional storage arrays mainly SATA cheap and deep are going to be 85 plus percent of the capacity, but when you translate that into Spend and you've got relative pricing per terabyte if the traditional SATA based arrays are the baseline of one You think flash only is going to be 6x that baseline This is by 2015 and flash storage on memory class flash will be 12x and that translates into enterprise spend of 45% less than half for the SATA arrays and then 35% for the Solid fire class flash only storage arrays and then 20% on the fusion IO class So you're really projecting by 2015 a major disruption To the spinning disk landscape Absolutely the the by that time the the fast high-performance discs will Then they're never dead with nothing's ever dead in this industry, but they will they may have a home in Very wide striping very fast transfers of tape sequential tape between between tiers Which actually makes them look more like a tape deck, wouldn't it? And that would be that would be interesting to be the final resting home of high-speed disc Okay, great. All right. We're out of time David. Thanks very much for joining us today to review the HP left-hand three-par announcement New v-class stuff federated peer motion sounds like great capabilities Last word from you. What's what what advice would you give to users in regard to this announcement and then Talked about just get get to a peer motion. It's it's fantastic and It's a must-have feature. I think it's on left hand it's it comes free on on the Three-par boxes. It's from about six thousand to twenty five K. So to me. This is a Really good deal and it's gonna save a huge amount of heartache and planning and and and cost in the data center So get it. All right, David. Thanks very much. This is Dave Vellante and David floor signing off from the Cube inside of Malboro Wikibon's Malboro headquarters. Thanks for listening everybody. Talk to you soon