Greg joined VMware in January 2018 and currently serves as Senior Vice President and Chief Technology Officer. His main focus area is to ensure VMware’s long-term technology leadership through research and innovation programs, with the primary goal of positively impacting and shaping the future of VMware, its ecosystem and its customers.View the profile
About the talk
Greg Lavender, SVP & CTO of VMware, joins John Furrier and Dave Vellante for coverage of VMworld 2020.
#VMworld #theCUBE #VMware @SiliconANGLE theCUBE @VMware
Q&A: Welcome to Project Monterey: VMware gets ready to rip apart the I/O stack
VIDEO EXCLUSIVE BY BETSY AMY-VOGT
VMworld is known for being a technical conference. Last year Project Pacific made a match between vSphere and Kubernetes. This year Project Monterey is aimed at reimagining the data center for next-generation applications.
During an interview today with theCUBE, SiliconANGLE Media’s livestreaming studio, VMware Inc. Chief Executive Officer Pat Gelsinger described the project as “ripping apart the I/O stack from the intrinsic operation of a vSphere.”
To delve deeper into the technology behind Project Monterey and other technological innovations in the VMware pipeline, Greg Lavender (pictured), senior vice president and chief technology officer of VMware, spoke with John Furrier and Dave Vellante, co-hosts of theCUBE, during VMworld. (* Disclosure below.)
[Editor’s note: The following content has been condensed for clarity.]
Furrier: Where did the innovation behind Project Monterey come from?
Lavender: Four years ago, in the office of the CTO, we actually had a future-looking project to get our core hypervisor technology running on Arm processors. That incubated for three years, and then last December, I moved the engineering team that had done that research and advanced development work over to our cloud platforms business unit, and SmartNIC kind of converged with that. So we were already well along the innovation path there, and it’s really now about building the partnerships we have with SmartNIC vendors and driving this technology out to the benefit of our customers who want to leverage it.
Vellante: Could you clarify something on that? When we interviewed Pat Gelsinger he talked about Monterey as a complete re-architecting of the I/O stack. What specifically was he talking about there?
Lavender: With any computing server in the data center, in a colo facility or even in the cloud, a large portion of the CPU resources, and even some memory resources, can get consumed by just processing the high volumes of I/O that’s going out to storage devices, communicating between the different parts of multitiered applications. So there’s an overhead that gets consumed in the core server CPU, even if it’s multicore, multisocket.
By offloading a lot of that I/O work onto the Arm core and taking advantage of hardware offloads there in those SmartNICs, you can offload that processing and free up even as much as 30% of the CPU of a multi-socket, multi-core server and give that back to the application so that the application gets the benefit of those extra compute and memory resources.
Vellante: VMware published data that shows hybrid is 30 to 40% cheaper than the cloud. Can you add some color to the economics of hybrid?
Lavender: Somebody asked me one time: ‘What’s really a cloud. Greg?’ And I said: ‘Automation. Automation. Automation.’ You can take your current environments and highly automate the release, lifecycle management, develop more agile software delivery methods, and so therefore you could get sort of cloud benefits from your existing applications by just highly optimizing them on the cost of goods and services.
Then again, the hybrid cloud model just gives customers more choice. For example, I want to reduce the number of data centers I have but I need to maintain reliability, scalability, et cetera. So, take advantage of the hybrid cloud that we offer, but you’ll still run things cloud native. You’re seeing this true multicloud technology and paradigm grow out as people have these choices.
Then the question is: If you have those choices, how do you maintain security? How do you maintain reliability? How do you maintain up-time yet be able to move quickly? So I think there’s different speeds in which those platforms will evolve, and our goal is to give you the ability to basically make those choices and optimize for economics as well as technical capability.
Furrier: VMware announced last month that the United States Space Force has committed to the Tanzu platform. When theCUBE interviewed Lieutenant General John Thompson recently, he talked about how Space Force is looking at software-defined as a key operating reality. What’s your take on this?
Here’s the complete video interview, part of SiliconANGLE’s and theCUBE’s coverage of VMworld. (* Disclosure: VMware sponsored this segment of theCUBE. Neither VMware nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.)
From around the globe. It's the cue with digital coverage of vmworld 2020 brought to you by the end where and its ecosystem partners. Hello and welcome back to the vmworld 2020 virtual coverage with the Q virtual I'm job for Dave. Vellante your host or 11th year covering vmworld, a great Gathering, lavender spp and the CTO of VMware, welcome to the cube virtual for vmworld 2020. Virtual great, thanks for coming on. Privileged to be here. Thank you really. You know, one of the things David, I was commenting with Pat and just in general start 11th. You're covering
vmworld. Absolute if it's not face-to-face, but the conference always a lot of technical Innovation project Monterey's out. There is pretty nerdy, but it's it's I called the catnip of the future, right? People get excited by it, right? So there's really a lot of awareness to it because it kind of it smells like a systems. Overhaul smells like an operating system feels like a, you know, a lot of moving parts that are quite frankly, what distributed computing, and software keeps love to hear about it. And to end distributed software intelligence with new kinds of Hardware, Innovations, from Nvidia
and whatnot. Where's that Innovation coming from? Can you share your thoughts on this direction? Yeah, I think of course I should say this isn't like seeing something that just know we decided to do, you know, six months ago actually in the office as CTO, for years ago, we actually had a project to project to get the ark or hypervisor technology, running on arm processors. And that incubated in the office of the CTO for 3 years. And then last of December move the engineering team that its research Advanced development work over to our Cloud platforms business unit, you know, in
smartnick, see those kind of a could converge with that. And so we were already going to well along the Innovation to truly know how about building the Partnerships. We have with the smart like Benjamins and driving this technology out to the benefit of our customers do we don't want to leverage it. You're getting back. I want to clarify something from you on that took Pat talked about Monterey and completely architecting of the io stack. And he talked about it, affecting Nvidia, and Intel mellanox and Sandoz part of that. When he talks about the io stack, your specifically,
what are we talkin about there? You need any Computing server in the data center in a cola facility? Or even if it in the cloud and even some memory resources can get consumed by just processing in the high volumes of. I o that's going out to the storage devices. You not communicating between the different parts that multi-tier applications and so is this server CPU? Even if it's multi core multi-socket and so play, offloading the a lot of that I owe work on to the
arm core and taking advantage of the hardware off loads there in the smart. Alex by you can you can also that processing a free up even as much as 30% of the CPU of of of a server multi-socket multi-core server and give that back to the application. So that the application gets the benefit of that extra computer and memory resources. So what about a single to the low-cost flash tear to avoid the complex? Names of teetering is that part of the equation,
using something like nvme fabric over. A reason that you can essentially, you have built large-scale storage networks more efficiently. You no more cheaply and take advantage of that. Also, try to reduce the audio latency, that's required Texas, that network attached storage and a notch as storage, but the other devices that you can use your network attached to. This is that, is that a yes or is that a stay tuned different classes of storage and storage tiering is definitely the
crime use case there. How could people think about the edge now? Because one of the things that's in this end-to-end is The Edge Pat boarded up. Multi-cloud, and and edger to areas that are extending off cloud and hybrid, what should people think about the Innovation equation around those things? Is that these off low technique, What specifically in the systems architecture, you guys see as the key keys there, so it has a very Diversified heterogeneous place in in the architectures of a multi cloud services. So what do we do now is you know,
workload I like to say workload for data in a lot of the data will be analyzed the process at the edge. So the more that you can accelerate that data processing at the edge in the play, some machine learning and fencing, at the edge, certainly going to have kubernetes everywhere including the edge control, plane and services, and machine learning workloads, you know, traveling to the edge where the where the date is going to be processed. In the actions could be taken to Thomas Lee at the edge. So I think we're in
this convergence point. The industry were all that comes together. How important is he? Okay, and how important, the intelligence speech because the Kansas state is at the edge How do you guys see? The data architecture being build out there? Depending on the other through the thin Edge has been a different different types of data. And what could happen if the edge is more akin to take action at the edge, is opposed to calling home to a cloud. You have to decide what to do. So if anyone you know, the the confrontational power and the problem with its video
processing or monitoring, well, the kind of different things that will happen at the end will be dependent on that data type and what kind of decisions you want to be. So he created will be moving and get them from the historical analytics and maybe a transitional training mechanism, but the 5G is going to play heavily into this as well, write for the network connectivity. So we're at this unique point is open a cruise in the industry every few years of all these technology Innovations convergent, open up an entirely new platform in a new way of compute. Computing, that happens that
he is not just in your data center at the cloud. Directions to The Fairly major stint at a large bag. What would something you mentioned you like an oil rig but what would something like that changes mean for an industry like banking or financial, will it have an impact there and put on your customer hat for a minute and take it to make mistakes? Always been a very distributed computing platform. Right? And so, you know, people want to deliver more user experience Services, more video services, at least things at the edge to interact,
possibly with the customer without using you have people in the loop. And so, the banking industry is already gone through the SD win and I win transformation to deliver the band with more capably to the edge. And I just think that they'll just a bill to Livermore Edge services. That happened can have it more at ominously at the edge is supposed to have in The Hairpin, the home run, everything back to the Davis Center. Awesome. Well, Pat talks about the modern platform the modern companies. Craig I want to ask you because we're seeing with covid-19 use cases, you know, the people who
don't have a Tailwind companies that are not doing well because there's no business to be had the modernizing their business. While they have some downtime other ones have a tail. When they have a modern app that that takes advantage of covid situation that brings up this idea of what is a modern app look like. Because now, if you talking about a distributed architecture, some of the things you're mentioning around inference data Edge, People start the thing about these modern apps and they are changing the game for the business. Now you got vertical Industries, Mission, oil and gas, you
got Financial Services industry solution, and work like God and was siloed. Now you have a little bit of a different architecture if we believed that they were looking up not down. Does it matter by industry? How's your people think about a modern application? How they move faster? Can you share your insights into the? In some of this is conceptual, what is a modern approach and does it doesn't matter by vertical or industry set of use cases that will put the man's on the infrastructure in the architecture in the networking? So I'm a modern modern a half. I mean if we built a
sort of these model, if he can have some crafts with the client side, middle Riverside, the database, the back in is the system of record. I mean, this is even being more disaggregated in terms of, you know, that they would leave the consumer edges, both not just ripped here but mobile tier and you know, we'll see what, what, what emerges out of that. The one thing for sure that is that is becoming less monolithic and more focused the conglomerate SAS and other services that are being brought together with it from the cloud services or whether it's is b o i s v. S delivery in a
bring your own software and overcoming were distributed because people be. Free to the higher degrees of scale. There's a limit of hurdles vertical scaling. So you have to go to horizontal scaling which of the cloud is really good at letting all these things are driving a whole new set of Technologies. Like next Generation API, gateways, you message buses servicemen were Nazis, hands-free service message, vmworld, integrated with other apps SAS Services
faster time-to-market. The speed of delivery is everything, so modern modern software technology, and ability to deploy and run network live anywhere at the edge of the core in the data center in the cloud. History in our industry. You've seen so many companies have hit a wall in the amazing engineering culture experienced, technical debt and it started four years ago, but can you give us a peek inside? You know, that sort of transformation and how you're pulling that off? The platform
in the spring boot is a technology that used widely across the industry already, which is to be that as part of our little acquisition. And so what route to try to do is just keep keep delivering the technology in the platform that allows people to go faster with Quality Security and safety and resiliency. That's what we do really well, it'd be a more so building these apps cloud-native is opposed to, you know, taking an existing Legacy app and trying to refactor it, it might be due to Medical to get these mice called to speed architectures. Take the user front in the consumer
front in and put that thought in the cloud with the back in-system of Records, the runs in the private cloud in a highly resilient little backed up is that the recovered wife? So you have a brand new Cloud native apps were sitting in the same people very careful because there's a cost to it of looking at, how do I basically modernize the front end but maintained that the reliability of the scale. Security in the liability of that, through a system of record. Back in this week, either ways is winning for the companies cuz they can do faster delivery to their businesses and their clients
and their Partners. But yet have Brazilian general liability that were queer. What we're done for running those mission-critical workloads. The scenario is that back and stays on his calling. Pat said or somebody said that that I think I can fix it on forever. Maybe they've been Harvard 30 to 40% cheaper than doing it in the closet. I presume they were talking about those and a back-end systems that you don't want to fly great. Can you add some color that again from your customer perspective? That's the economics. Yeah, you know, what's really a clock? Greg, nice. It's automation,
automation automation, you can take, you can take, you can take your current environment since highly automate, the release lifecycle management develop more, agile, software delivery methods and so, therefore, you could, you can get sort of cloud benefits, you know, from your existing applications by just highly optimizing them and note on the cost of goods and services. And then again the hybrid Cloud Model just gives customers more Choice, which is okay. I want to reduce the number of data centers. I have, but he's maintained reliability scalability etcetera. Take advantage
of the other hybrid Cloud that we offer, but you'll still run things cloud-native. So, I think you're saying is true multi-cloud. Technology Paradigm, you'll grow out. If people have these choices, and then the question is okay, if you maintain security, how do you maintain reliability? How do you maintain enough time to move quickly? And so I think there's different speeds, and which those platforms will evolve and our goal is Give you the ability to basically make those choices and an optimized for economics, as well as technical capability with
covid-19, and we've been reporting the cute virtual evolve cuz we stand being at events but we're not there anymore, but everyone has to realize with covid-19 projects that you might not want to double down on or highlighted some gaps in architecture. And he certainly who would have forecast for the disruption of hundred percent, work-from-home VPN for visiting to access and access management security. And it really is expose what kind of who's wearing the journey and digital transformation. So I got to ask you, what's the most important story or a thing to pay attention to
as the smart money and smart customers go. Hey, you know what? I'm going to double down on that. I'm going to kill that project or Sunset that or I'm not going to refactor. Then I'm going to containerize it and is probably there's a lot of that going on in our conversations. It's pretty obvious. This critical path looks like we stay in business. We build a modern app, but I'm doubling down. I'm transitioning. It's a whole nother ballgame. What is the most important thing that you see? The people should pay attention to around maintaining an innovation and coming out on the other side? Yeah.
Well, I think this journey goes to the whole thesis of suffered fine. I mean, you know, the idea of taking Appliance physical, get to order the hardware, get it on your loading dock, install a new Datacenter. You know, Goku figure it, mattered into the rest of your environment, you know, where is or you can just spend up new Sovereign since is a load balancers firewalls, Etc. So I think that, you know what's, what's really helped in the covid-19? Find Everything, Computers storage networking man, really allowed customers and many of our customers to
rapidly make that pivot. And so you know what is the workspace? The remote work space. You got to secure it, that's a key part of it, and you've got to give it snow again in the scalability. Back in your data centers or if you don't have it be able to run those virtual desktops in the cloud and I think. So this ability again to take your current environment and more importantly, your operating model, which the other technology could be agile and fast before operating models, not a drill and you can text You did well for the best, so I heard from the customer, CIO was there for 6 months, we
debated, you know, the virtual networking architecture and how to deploy the virtual Network and you know when covid hit we made the decision. Is it all in one week to the question to see how your ass smells like a? Why do we, why do we have to operate in that 6-month model. Going for this operation. The one week model going for. I think that's the big that's a big inflection point is the operating model has to be agile. We got all kinds of agile technology and choices. I mention. It's like, how do you make your organization as usual to take advantage of those
technological offering the last six months helping our customers achieve? I think that's a key Point worth calling out in and doubling down on day because, you know, whether you talk about rqq virtual, our operating model has changed and we're doing new things, but it's not bad. It's actually beneficial. We can talk to more people. This idea of virtualization, I mean pun intended. Virtualizing Workforce is based Face interactions are now remote. This is a software-defined operating business. This is the real Innovation. I think this is the exposure as companies wake up and gone. Why
didn't we do that before? Reminds me of the old Mainframe days Days Inn in and grabbing on to it. They got a trans will. So this is the new, the new, the new reality we were joking earlier that, you know, of April, don't fix it and all of a sudden covid, broke everything and so it'll virtualization becomes a few fundamental component of how you respond. But I wonder if Greg could talk about the security how that fits in, you know, everybody to know the bromide of courses, are you security? Can't be a bolt on. It's got to be designed in from the Star. Pat gelsinger
said years ago? In the cube security is a do-over. You guys have purchased many different security components of built-in security code. So, how should we think about? And, how are you thinking about, designing, in security, across that an entire stack without bolting in your pieces? Weather, is carbon carbon black or other Acquisitions that you've made. Cyber security, engineering Inc, the platforms of the engineers at deployed across the the bank locally and the the channel in the challenge, a
hundred fifty plus security products and you go to bed at night wondering, what, which one did I forget to deploy your, what did I get this for Gap or have you think if you think you're safe by the sheer number? But you leave when you really boils down to is like, you know, cuz you have to sort of like both all this stuff together to create a secure environment to do on a global level. It's really hard for us to be on the bus to the service in your data
center. If we have you heard if you ever Network virtualization, we see all the traffic going between all those hypervisors it up to the cloud as well, hybrid cloud or public club with are intersex technology and then, you know, the new show to bring into that the load balancer is in the soccer to find firewalls and pretty soon. You have to be like, okay, look we have we have most of the estate therefore we can see everything and bring some intelligent machine learning to that. End Indian get proactive as opposed to reactive as if you are a model that was billed as technology and some
pots. And we get reactive about proactively telling me that something nasty is going on. I need to ask you a question. May be remediated. Sorry. Johnny may be remediated mean open at some point anyway. Bring in some machine intelligence to do it and sent it. Like you said getting an alert, actually tells me what what happened and how it was fixed in a or at least the recommending what I should do, right? Gian make things as you you sort of do the virtual networking, The Reckless stories are personal computer, all the software, you know of a sudden you have, you have a
different platform, you have lots of standardization therefore you don't have to your operating model simplifies right in the middle of a spot just collecting all the data and then making sense of the data. So you're not overwhelming the humans capacity to respond to it and so they think that's really the fun will think we're all trying to get to but the surface areas is large outside the date. As soon as we've discussed out to the edge, whatever the edges, you know, into the cloud hybrid Republic. So now you got this big surface area, where you've got to have all that to limit. Read
all that disability again back to getting proactive so you got to do it in band supposed to have and I want to ask you a question on the cybersecurity. We have an event on October 4th at Brookfield vet. The cube is hosting with Cal Poly around this s space and cybersecurity Symposium is intersection of space and cyber. I noticed VMware recently announced last month that the United States space force has committed to the Panzer platform. Freaking freaking Tunes, devops operation for agility. I interviewed Lieutenant General John Thompson space force and we talked about that.
He said, quote is hard to do, brakes fixed in space illustrating really you just can't send someone to swap out, something and space, not yet, at least. So they're looking at software defined as a key. Operating reality. Okay. So again, talk about the edge of space is his edges going to get. It seems to be completely managed by what payloads and and data. This is kind of an interesting data point cuz you have security issues because space is going to be contested and congested as an edge device. So such of the government's interested in there, but the problem that you're you guys are
involved in, this is the reality is reality idea of operating models based in reality, have to be software. What year did the term we use now is devsecops because you think it in their fundamental networking, right? I mean, you have the starlink satellites that Tesla has his life story on most of his lunch and, you know, bringing sort of the heart band with lower latency to those in the all new opportunities for what we can do. And so yeah I think just the software that holds the whole software development. Ecosystem again back to this idea, I think of three things you got to have speed, you got
to have scale and you got to have security. And so that's really merging class for mothers of terrestrial or in near space that that's giving us the opportunity to do. Do architectures pre-service meshes of services. Terrestrial. Some, some remote in. Did you bring these new application architecture? That system platform, architecture together with all the other underlying hardware and networking in the patients that are occurring p.m. for cysts that memory rights of this business. So much happening that is converging with exciting to me about being a vampire. Is
the CDL with all the hardware vendors. We partnered with all the system providers like Nvidia and others, who don't support Nick vendors and then we could come up with the software architectures. It sort of brings that together holistically and give people a platform. We can run your work list to get work done or wherever you need to land those worthless. And that's really the excitement about a candy store and yet you got problems hard problems to work on. So it's all this really brings the whole project Monterey full circle cuz we think about space and networks and all these things
you're talking about. You need to have some more everything. It is not software. It's a complete tie into the Monterey area, Chloe and securely and that's in machine learning and AI, but use the machine learning Technologies in a properly trained with the proper data sets, you know, when the proper algorithms, you know, that you can then employed at the edge of small ledge, they catch, you know, it in the data center at the cloud, is it sure you give the visibility? So let me get to that. Proactive world, I was talking about Great
Stop Craig, great insight and great conversation. Looking forward to talking more check with you. I see you are in the right spot vehement in the center of all the action across the board. Final point, if you can just close it out for, as what is the most important story at vmworld 2020 this year? Well, I think, you know, I like to say that might I haven't been the best job. I think, you know, that I've had in my career on that, had some great ones is no, we get to be disruptive innovators and we have a culture of Perpetual Innovation and really be a world for us at all the employees
and all the people that work together to put it together as we get to Showcase. You know that some of that I've seen it more up our sleeves for the future but the vmworld is are coming. Coming out spout, show of the latest set of Innovations in technology so there's going to be so much. I have a vision in Innovation. Keynote kick-off, right is of lightning demos and actually I talked about work, we're doing its sustainability and we're putting a micro grid on our campus in Palo Alto in partnership with the City of Palo Alto. So that when the wildfires come through or there's power outages,
in a weird Oasis of power generating capacity with our solar and our batteries into the City of Palo Alto could take their emergency command vehicles and plug into our batteries when the power is out in Palo Alto. Operate city services in City, emergency services to become a more sustainable company and provide sustainable technology for our customers to adopt. And I think about it next time. But I think you know organizations are going to basically help change the world with regard to climate as well, let's definitely do that. Let's follow up
for another in-depth conversation on this island pack, of course, VMware vmware's be in Worlds, 2020. Is virtual is a ton of sessions. There's a cloud city portion check out the 60 solution demo. Of course, the ask the expert regular in there with your Betta Ragu. All the experts engage and check it out. Thank you so much for the inside here in the cube virtual. Thanks for coming on. Appreciate the opportunity, great conversation that good questions. Thank you very much nicer at VMware. It's a hard of their missions. Always has been but they do it with on the business side, Dave? Okay?
Buy this talk
Buy this video
With ConferenceCast.tv, you get access to our library of the world's best conference talks.