>> live from San Francisco, celebrating 10 years of high tech coverage. It's the Cube covering Veum, World 2019 brought to you by VM Wear and its ecosystem partners. >> Welcome back. We're here! Mosconi North for VM World 2019 10th Year of the Cube covering VM World. I'm stupid and my co host is John Troyer. And welcome to the program to guest from Del Technologies. Sitting to my right is Tender, my Mondal, who's the director of storage solutions and sitting to his right is David when the senior director of server, product planning and management also with Dell. Gentlemen, thanks so much for joining us. All right, so we've got server and storage and talk about something that we've been talking about for a while on the server side been delivered for a bit and on the storage side is now rolling out. So everybody's favorite topic. Nonviolent till memory express or envy me as it rolls off the tongue storage class memory, or SCM and lots of other things, you know, down there, really helping a big, transformational wave that, you know, we really changes how our applications interact with the infrastructure channel, you know, bring us up to date on the latest. >> Sure on, let's start where you ended. We're seeing explosion off applications, right? And in fact, in mornings, keynote. Bad girl singer had a stocky speaks. There are 352 million enterprise applications today. On it will be 792 million in three years. Now, as the applications are growing exponentially, we cannot keep growing the infrastructure at that rate, So N v m e is the way we can consolidate it. Ah, lot off the infrastructure. If we can think about in tow and envy, Emmy starting from the server in fear me off our fabric through the stories area down, toe the back end with envy Emmy necessities. This actually can put together a great platform where you can consulate it. Ah, lot off the applications and delivering the high performance low latency that will need while meeting video surfaced level objectives so we can go over a little bit off the details, but I think it all starts from envy me over fabric coming from the server to the story, Ari. So probably like that's the fourth step we need to consider >> David. Do You know, I love this discussion when we get to talk at the application later because, you know, Flash changed the market a lot. You know, it's like, you know, much better energy, and it's much faster, Anything. But you know, this inflection point that we're talking about for application modernization, you know, envy me is one of those enablers there and something they know your team's been working on >> for a while. Yeah, actually, on the power each side we've been, You know, we've been embracing the benefits of enemy for quite some so many years now, right? We start out by introducing enemy in our 12 generations servers, you know, frontloaded hot, serviceable drives. And then, of course, we branch out from there on in today, you know, Ah, a lot of the servers from a Polish family all support enemy devices. So the benefit there is really giving customer choices in terms of what kind of storage kind of cheering they wanted, you know, for the applications needs. Right now, one of things that's great about, you know, enemy over fabric is it's more than just a flash storage itself. It's about enabling the standards, you know, across the host across the data fire Break down to the storage really to deliver on the overall performance that you know the applications of needs and buy, you know, improving I ops and lower late, Easy overall, from a server perspective, this just means that we're releasing more CPU cycles back into the application so that they can run different types of workloads. And for us, this is this is a great story from power. Just was from Power Macs and coming together to enable this Emmy, Emmy or fabric. >> You know, I'm I'm I'm kind of slow about some of these things, but if you kind of squint at the history and, you know, we went from the PC revolution and then we had, you know, we had Sands and raise right and we had we had centralized toward shared storage last couple of years, a lot of interest and stale right hyper converged. And you had a You had a lot of pizza boxes with the storage right there. It's I mean, I now think right and I'm following the threat, I think which is now that where we now can have ah, Iraq with again a fabric and and again, now we can We can focus on our envy me storage over our envy me over fabric driven, solid state storage somewhere below my servers that are that are doing handling compute somewhere else. Is that that the future we're headed towards now >> Yes. I mean, everything has its place. But to give you the perspective, right? It's not just, I mean coming down to the storage area, but how This is enough bling, the future storage as well. And the storage class memory is the perfect example. And as Defeat said, let's take power, Max, as an example, right. Eso in power Max, you can It is like entrant, envy me ready like you get envy emi over Fabrica de front end But then we have n v m E s s trees in the back end. The thing is now it is also the N v m e is enabling technologies like stories class memory which is bringing in very high performance, very less latency Latency is going down in the order off like tents off microseconds. Now this is as close as you can get. Tow the like Dedham with persistent story. However, you need a balance. This is like order of magnitude are costlier. Now you got bar Max. What we're doing in terms of first, it's envy me. Done right? What do you mean by that? You have, like, Marty controller architectures that can actually do this level of parallel processing and our concurrency. And then we have bought, like, ECM for storage, class, memory and envy, Emmy essences. And we're doing intelligent tearing best on the built in mission learning engine that we have. And it is looking at 40 million data sets. Really time to decide. Like which sort of walk lords should go on this same drives which should go on and the M. E s estates. And on top of it, you add quality of service. So this platform gives you are service level objectives. You can choose from diamond, platinum, gold, silver or bronze, and you can consulate it. Ah, lot off those 352 million different types of applications on this area guaranteeing you are going to meet all off your SL s, no matter what type of applications they were consolidated into. >> Okay, I'm wonder if you could boast. You know bring us into what this means for VM wear customers and break it into two pieces. One is kind of a traditional virtualized shop. And secondly, you know, spend a lot of time in the keynote this morning talking about the cloud native containerized, you know, type of environment. Will there be any difference from from both of your world? >> Yeah, absolutely. I'm glad you brought that up because, you know, from from our perspective, right, what we've seen with the enablement of enemy platforms. You know, John, you brought up a very interesting point, right? It seems like you know, past couple years, we went from moving storage onto the host and now would envy me with fabric. We're actually taking the storage away from the host again. Right? And that's exactly true, because, you know, the first, the first statement you brought up stew. It's about how flash enabled different applications to run better on the host. What? We see that still right? And so what enemy? You know, we see the lower response time enabling our customers Thio run more jobs and more v ems per server. That's one aspect of it. You know, we've seen his benefit a lot of our platform today or using various different applications and solutions, and you talk about the ex rail that's a visa and story for Del. You Talk about Visa and ready notes for customers who want to build it themselves. Right platforms enabled would envy me back playing enemies. Storage allows them to use enemy or SAS sata whatever they want. But the point is, here is that when they're using every me flash, for instance, and I'll talk a little bit about the power climaxed with this all flash, uh, me back plane in a case in the study that we did with V San application running, oh ltp type of workload, we saw the response time with every me over traditional SAS, you know, from our competitors improved by 56% right, which means that from that same particular solution build out, we were able to add 44% more of'em on the platform. Now, at the same time, we increase the overall orders per minute by roughly over 600,000. Oh, pm's for that type of, uh, benchmark over our nearest competitors so that right there is the benefit that we see from my virtual eyes from, Ah, being where perspective >> on. I'll add from the storage perspective in two ways. In fact, in last vehement in a MIA, we demonstrated in tow and envy, EMI over five break up with special build off this fear supporting Envy me over fabric and stories. Class memory with envy Me drives what it gives you a regular like this fear best environment is that you have the ability to move your PM's around like the applications where the highest performance and Latin's is critical. It will be on those special service levels and special like de testers. In fact, that demonstration was like ECM did a store, and in P m E Sense media does so in the same fabric with in Bar Mexican moved things around, whether it's like regular Fibre Channel or CNN and then the other part. I want to add in the morning like we saw the announcement that now communities is built in or will be built in with the years Excite platform, right and you're sexy is bread and butter off all the storage customers that we have now with like when you consider those, uh, those things built in under this fear black from Think about, like how many applications? How many actualized workloads you can run, where that it's on premise or humor. Cloud on AWS. All of those consolidation, as well as like the performance needs while reducing your footprint does the benefit of the V M R R shops. But the PM admits are going to see from the storage site >> again. I'm not following the parts, but what kind of we're not talking about a couple of megabytes here anymore, Right? What size of parts are shipping these days? So >> So, from our perspective, up to 77 gigabyte actually start. Seven terabytes drives are available on the markets today for Envy Me Now, whether customer by those drives, you know, it depends on economic factor. But yeah, it's something that's in this available from Dell >> so on. I'll act to what David said so far in CM drives 750 gig to 1.5. Articulate a C M drives on Dwell ported often drives that will be available in the power Max Acela's 15 terabyte envy EMI assistants. So this is the capacity we're talking about. And again the Latin's is at the application level, like from the storage like you're going to see, like, less than 300 microsecond. That's the power we are bringing in with this technology to the market. >> Give >> us a >> little look forward we talked about, you know, envy me has been shipping for a bit on the servers now, really rolling out on the storage side, I saw there's a lot of started from the space. You know, one recent acquisition got guts and people talking. What? What should we be looking for from both of you over kind of the next 6 to 12 months. >> So over next to a next 6 to 12 months, he will see a lot of innovation in this case from the storage site where wth e order of magnitude. I mean, the one single Ari, I mean, today it supports, say, like, 10 million I offs less than 500 microsecond latency. Ah, I cannot give you the exact details, but within like, a short time, these numbers are going to go up by more than, like, 50%. Latency is goingto get reduced. The troop would will be driving will actually like more than double s o. You see, like a lot of these innovations and kind of like evolution in terms off the drive capacities both from the CME, drives perspective. Envy me, assess these. Those will continue to expand, leading to foster performance. Better consolidation, Uh, for all the workloads. >> Yeah, from our perspective, I mean, you know, data growth is gonna continue. We all know that, And for us, it's like designing systems based on what the customers need, what the applications needs, right. And that's why we have different types of storage available today. So for us, you know, while we're doing a lot of things from a direct attached storage perspective, customers continue to have a need for share storage. EMI over fabric just provides a better know intense story for us, really from a Power edge and Power Macs perspective. But in the future, you asked what we're going to do. Well, we see the need to probably decouple stories, class memory from the host again. And really, what's preventing us from doing today? It's really having the right fabric in place to be able to deliver to that performance level that applications needs. MM evil fabrics, fibre Channel Ethernet ice, scuzzy or I'm sorry, Infinite Band, whatever. These are some of the things that you know we're looking forward to in the future to make that that lead. All >> right, well, it's really been great to see technology that I know the people that build your products have been excited about for many years. But rolling out into the real world deployment for customers that will transform what they're doing. So for John Troyer, I'm still Minuteman back with lots more coverage here from Be enrolled 2019. Thanks for watching the Cube.