 From theCUBE Studios in Palo Alto in Boston, connecting with thought leaders all around the world, this is a CUBE Conversation. Hi, welcome back. I'm Stu Miniman, and this is a CUBE Conversation. Digging in with Pensando, talking about what they're doing to help people, really bringing some of the networking ideals to cloud native environments, both in the clouds, in the data centers. Happy to welcome to the program, Krishna Dota Penny. He is the vice president of software with Pensando. Krishna, thanks so much for joining us. Thank you, Stu, for talking to me. All right, so Krishna, the Pensando team, very well known in the industry, innovation startup, especially in the networking world, gives a little bit about your background specifically, how long you've been part of this team and what helped you and the team start Pensando. Yeah, so I'm VP of software in Pensando, before founding Pensando, I worked in a few startups in CMA networks, newer systems and Greenfield networks. All those three startups have been acquired by Cisco. My recent role before this company was I was VP of engineering in Cisco. I was responsible for a product called ACI, which is Cisco's flagship SDN product. So I mean, when, why did we find or found Pensando? So when we were looking at the industry the last few years, right? The few trends that are becoming clear. So obviously we have a lot of enterprise background. We were watching ACI being deployed in the enterprise data centers. One sore point for customers from operational point of view was installing service devices, network appliances or storage appliances. So not only the operational complexity that this device is bringing, it's also, they don't give you the performance and bandwidth and PPS that you expect for traffic, especially from East-West. So that was one major issue. And also if you look at where the intelligence is going has been, this been the trend, it's been going to the edge. The reason for that is the routers or switches or the devices in the middle, they cannot handle the scale. I mean, the bandwidths are growing, the scale is growing, the stateful stuff is going in the network and the switches and the appliances are not able to handle it. So you need something at the edge, close to the application that can handle this kind of services and bandwidth. And the third thing is obviously, X86, few years back, every two years you're getting more transistors. I mean, obviously the Moore's Law ended and we know how that part is going. So the X86 cycles are more valuable and we don't want to use them for all this network services including SDN or firewalls or load balancers or NVMe virtualization. So looking at all these trends in the industry, we thought there is a good opportunity to do a domain specific processor for IO and build products around it. And that's how we started PenSyndall. Yeah, so Krishna, it's always fascinating to watch. If you look at startups, they are often product of the time that they're in and the technologies that are available. Sometimes there are ideas that it takes a few times and maturation of the technology and other times, I'll hear teams and they're like, oh, well, we did this and then, oh wow, there was this next new innovation that came out that I wish I had had that when I did this last time. So we do a 2.0 or 3.0 generation. We've been talking about distributed architectures for well over a decade. It's been a long time now. In many ways I feel edge computing is just the latest discussion of this, but when it comes to, you've got software under your purview, what are some of the things that are available for PenSyndall that might not have been in your toolkit five years ago? Yeah, so the growth of open source software has been very helpful for us because we built a scale out microservices based controller. The last time around when we were building that, we had to build our own consensus algorithm. We had to build our own distributed database for metrics and events and logs. So right now, we have, because of open source thing, we leverage at CD, Elastic, Influx, in all this open source technologies that you hear, since we want to leverage the Kubernetes base ecosystem, that helped us a lot. At the same time, if you think about it, the even the software which has not open source, closed source thing, are maturing. I mean, if you talk about SDN, seven, eight years back, it was like, there are N versions of doing of SDN, but now the industry standard is on EVPN, which is one of the core pieces of what we do. We do a SDN solution with EVPN. So it's more of, the industry is coming to a place where these are the standards, and this is open source software that you could leverage and quickly innovate, compared to building all of this some scratch, which will be a big effort for a startup to succeed and build it in time for your customer success. Yeah, and Krishna, you talk about open source, not only in the software, it's in the hardware standpoint. I think about things like open compute or the proliferation of GPUs and PPUs and everything along that. How has that impacted what you've built? So I mean, it's a good thing you're talking about. For example, we are working in the future on OCP card. It's a good thing that OCP card goes into a HPE server, it goes into a Dell server. So pretty much, we want to, I mean, see our goal is to enable this platform that what we build in all the use cases that customer could think of. So in that way, hardware standardization is a good thing for the industry. And then same thing, if you go in how we program the ASIC, we are about standards of this P4 programming. That's an industry consortium led by a few people. We want to make sure that we follow those standards so that for the customer who's coming in, who wants to program it, it's good to have a standards-based thing rather than doing something completely proprietary. At the same time, you have to enable innovations and then those innovations, you have to push it back to the open source. That's what we're trying to do with P4. Excellent. I've had some real good conversations about P4 and the way Pensando is leveraging that, maybe a little bit differently. And that, you talk about standards and open source, oftentimes it's like, well, is there differentiate? There are certain parts of the ecosystem that you say, well, it's kind of been commoditized. Obviously you're taking a lot of different technologies, putting them together, help share the uniqueness of Pensando, what differentiates what you're doing from what was available in the marketplace, where that I couldn't just cobble together a bunch of open source hardware and software together. I mean, if you look at technologies like the, I think the networking that both of us are very familiar with it, if you want to build an SDN solution or you can take OBS or you can use X86 and take some match and silicon and cobble it together. But the problem is you will not get the performance and bandwidth that you're looking for. So let's say, if you want a high PPS solution or you want a high CPS solution because the number of connections are growing for your IoT use case or 5G use case, right? If you cobble together with an open source thing without any assist from a domain specific processor, your performance will be low. So that is the, I mean, that's one enterprise side in the cloud use case, right? As you know, you're trying to pack as many VMs as containers in one server because you know, you get charged. I mean, the customer, our customers make money based on that, right? So you want to offload all of those things into a domain specific processor that what we built, which we call the TSC which will do all the services at pretty much no cost to X86. I mean, X86, you'll be using zero cycles for doing features like security groups or VPCs or VPN or encryption or storage virtualization, right? That's where our value comes in. I mean, if you count the TCO model, using bunch of X86 cores or in a bunch of in ARM cores or AMD cores, compared to what we do at TCO model works out great for our customers. I mean, that's why, you know, there's so much interest in our product. Excellent. I'm glad you brought up customers. Krishna, one of the challenges I definitely have seen over the years with networking is it tends to be, you know, a completely separate language that we speak there. It's, you know, a lot of acronyms and protocols and, you know, not necessarily accessible to people outside of the silo of networking. I think back to, you know, SDN, you know, people on the outside would be like, that stands for still does nothing, right? Because it's like networking, you know, mumbo jumbo there. For people outside of networking, you know, when I think about, you know, if I was going to the C-suite of an enterprise customer, they don't necessarily care about those networking protocols. They care about the, you know, the business results and the productivity. How do you help explain what Pensando does to those that aren't, you know, steeped in the network? The way I look at it, right? What is customer looking for? Yeah, you're right. Customer doesn't need what in-cap you use. Customer is looking for his operational simplicity and then he wants looking for security, right? You know, and if you look at it sometimes, you know, both are like in orthogonal. If you make it very highly secure, but you make it like 10,000 operational procedure before you deploy a workload, that doesn't work for the customer because the operational complexity increases tremendously, right? So where we are coming in is that we want to simplify this for the customer. You know, there's a very simple way to deploy policies. There's a simple way to deploy a networking infrastructure. And in the way we do it is we don't care what your physical network is in some sense, right? So because we are close to the server, that's a very good advantage we have. We apply the policies before even the packet leaves the server, right? So in that way, he knows his fully secure environment and you don't want to manage each one individually. We have this product called PSM, which manages all the servers from the central place. And it's easy to operationalize a fabric whether you talk about upgrades or you talk about deploying new services. It's all of driven with REST API and you have a GUI. So you can do it single place and that's where a customer's value is rather than talking about, as you're talking about end caps or exactly the raw throughput, that is not the main thing that, I mean, they wake up every day. They wake up every day thinking about it or do I have a security risk? And then how easy for me is to deploy new services or bring up new data centers. All right, Krishna, you're also spanning with your product a few different worlds out there. Traditionally, if I think about an enterprise data center versus a hyperscale public cloud and edge sites, it comes to mind very different skillsets for managing them, different types of deployments there. If I understand right, you were going to play in all of those environments. So talk a little bit about exactly how you do that and just where you sit in that overall discussion. Yes, so I mean, number one rule inside the company is we are driven by customers and obviously our customer success is our success. So, but given said that right, what we try to do is that we try to build a platform that is kind of programmable, obviously starting from before that we talked about earlier, but it's also from software point of view, it's kind of pluggable, right? So when we build the software, for example, our cloud customers and they use DSC, they use the same set of APIs or GRPC or SAPIs that DSC provides with their controller. But when we ship the same platform for enterprise customers, we build our own controller and we use the same DSC APIs. So the way we are trying to do is think there's fully leverage in what we do for enterprise customers and cloud customers. We don't try to reinvent the wheel, obviously. At the same time, if you look at the highest level constructs from a network perspective, right? Or even storage perspective, what are you trying to do? You're trying to provide connectivity, but you're trying to provide isolation and you're trying to provide security. So all these constructs we encapsulated in APIs, which in some mostly like cloud-like APIs and those APIs are used for cloud customers and enterprise customers. And the software is built in a way where any layer can be removed or any layer can be added, right? Because it's in our interest, we don't want to build multiple different softwares for different customers, right? Then we will not scale. So the idea when we started the software architecture is that how we make it pluggable and how we make it programmable so that customers say, I don't want this piece of it. We can put the third-party piece on it and still integrate at a common layer with using REST APIs. Yeah, well, Krishna, I have a little bit of appreciation for some of the hard work that goes through what your team's been doing, a couple of years in stealth, but really accelerating from the announcement coming out of stealth at the end of 2019 to just about half a year, you're a GA with a major OEM of HPE, definitely a lot of work that needs to be done. Bring us, what are you most proud about from the work that your team's doing? We don't need to hear any major horror stories, but there always are some of the not holes or challenges that often get hidden behind the curtain. Personally, I'm most proud of the team that we've built. So obviously, our executives have a good track record of disrupting the market multiple times, but I'm most proud of the team because the team is not just worried about technology, that even there are very senior technologists and they're great leaders, but they're also worried about a customer problem, right? So it's always about getting the right mix of execution combined with technology is when you succeed. That is what I'm most proud of. We have a team with independent leaders running all these projects independently and then releasing almost, we have a release every week if you look at all our customers, right? And then being a small company, doing that is pretty challenging in a way, but we came up with methodologies where we fully believe in automation, everything is automated and whenever we release software, we run through the full set of automation so that we are confident that customer is getting good quality code. It's not like, you know, we cooked up something and they should be worried when they need to upgrade to this software. So that's, I think that's the key part if you want to succeed in this day and age, developing the features of the velocity that you would want to develop and still support all these customers at the same time. That's cool. Well, congratulations on that, Krisha. All right, final question I have for you. Give us a little bit of guidance going forward. You know, often when we see a company out and we, you know, try to say, oh, well, this is what that company does. You've got a very flexible architecture, a lot of different types of solutions. What kind of markets or services, you know, might we be looking at from Pensando, you know, down the road a little bit ways? So I think we have a long journey ahead. So we have a platform right now. We already, I mean, we have a varied baby, we are shipping, the platform is already shipping in a storage provider. We are integrating with the premier clouds, public clouds, and, you know, enterprise market, you know, we already deployed distributed firewall, some of our customers deployed distributed firewall. So, you know, so if you take this platform, it can be extendable to add, you know, all the services that you see in data centers on clouds. Right? But primarily we are driven from our customer perspective to a customer priority point of view. So where we will go is we will try to add more edge services. We'll try to add more storage features. And then we are also this initial interest in service provider market, what we can do for 5G and IoT, because we have the flexible platform. We have to see, you know, how to apply this platform to this new applications. That's where probably we'll go in future. All right, well, Krishna Dutta Penny, Vice President of Software with Pensando. Thank you so much for joining. Thank you, Stu. It was great talking to you. All right, be sure to check out thecube.net. You can find lots of interviews from Pensando. I'm Stu Miniman, and thank you for watching theCUBE.