PlexxiPulse—Facebook’s New Network

The internet has been buzzing about Facebook’s redesigned datacenter architecture. Facebook, which is used by more than 1.35 billion people, recently restructured their infrastructure to increase flexibility and agility to rapidly adjust to application requirements. Our own Marten Terpstra shared his take on the redesigned infrastructure this week on the Plexxi blog—it’s definitely worth a read. Below we share some of the articles that covered Facebook’s new datacenter architecture, as well as other happenings in the networking space this week.

In this week’s PlexxiTube of the week, Dan Backman explains how much fiber is required to connect datacenters using Plexxi’s datacenter transport fabric solution.

Gigaom: Facebook Redesigned the Data Center Network: 3 Reasons It Matters
By Derrick Harris
Earlier this month, Facebook announced a new data center networking architecture that it calls, fittingly, “data center fabric.” The company explained the design and the rationale in an engineering blog post, and Gigaom’s Jonathan Vanian covered the news, but it’s a big enough deal that we had Facebook Director of Network Engineering Najam Ahmad on the Structure Show podcast this week to talk about the new fabric in more detail.

CIO: How (and Why) Facebook Excels at Data Center Continue reading

The 6 Requirements for Data Center Networks

One way or another, all data center networks exhibit at least 6 different functional areas that their operators need to engineer, implement, and operate with a differing set of needs and requirements. Similarly, in one way or another, most of the available SDN and virtualized network solutions available today or in progress aim to deal with issues in one or more of these areas to improve their functional effectiveness, cost, automated-ness, or integrated-ness. Yet some areas receive an inordinate amount of focus/attention and those areas may not necessarily have the most opportunity for improvement. Let’s take a look at these 6 requirements in order of the opportunity value to bring new levels of effectiveness to data centers.

1) Edge Switching (inter-server or more generically, inter-end point):

Edge switching loosely covers the function of providing switching between end points, whether they be virtual servers, physical servers, storage devices, or terminating services devices (load balancers, firewalls, etc.) It is important to note that in a virtualized server environment, there is typically 2 layers of edge – a set of virtual switches that connect together VMs and a set of physical switches that connect the physical hosts.

Much of the attention and Continue reading

The Coming App-ocalypse – are we seeing Dot-Com 2.0?

Bubble 2.0?

I recently received a note from a colleague from ZeroHedge (http://www.zerohedge.com/news/2014-11-21/not-so-fab-1-billion-valuation-15-million-year) that was officially calling the beginning of the bubble bursting based on the untimely (or timely depending on your perspective) demise of the startup Fab. I had never heard of Fab, but according to ZeroHedge, Fab “started out as a dating site for the gay community and then relaunched as a flash sale site for home decor – raised $150 million just over a year ago (at a $1 billion valuation), but as TechCrunch reports today, multiple sources have confirmed that Fab is in talks to sell to PCH International for $15 million in a half cash and half stock deal. Pets.com?”

And Therefore…

Its a fair question indeed – are we seeing the same pattern we saw in the last bubble (i.e. Dot-Com 1.0) being repeated? Certainly, crazy valuations of equally crazy or non-existent business models are a cause for concern, but more important than that are the fundamentals of what is driving the speculation in the first place. In Dot-Com 1.0 we saw simultaneous speculative investment across at least 3 major areas: internet backbone infrastructure, internet edge/access Continue reading

PlexxiPulse— Plenty To Be Thankful For At Plexxi

As many of you know, it’s been a busy month here at Plexxi. It’s hard to believe that November is coming to a close and that Thanksgiving is next week. We have a lot to be thankful for this year, particularly our new CEO Rich Napolitano and for the support of our skilled and dynamic team members – both new and old. Wishing everyone a safe and happy Thanksgiving holiday!

In this week’s PlexxiTube of the week, our own Dan Backman explains how Plexxi’s datacenter transport fabric can be used in a datacenter or on campus.

Check out what we’ve been up to over the past few weeks on social media!

The post PlexxiPulse— Plenty To Be Thankful For At Plexxi appeared first on Plexxi.

PlexxiPulse—A Big Week for Plexxi and a New Era in IT

If you’ve been following Plexxi in the news and on social media, you will see that we announced our new CEO, Rich Napolitano, who comes to us from EMC to continue the company’s expansion and help lead Plexxi into a new era of IT. Rich has been a friend of Plexxi’s for a while; he sat on our Board of Directors before taking on his current role CEO. You can read Rich’s first blog post on why he joined Plexxi here. We also announced this week that Tim Lieto has been named senior vice president of sales and customer service to lead the company’s worldwide sales and channel effort. It sure is an exciting time for Plexxi, and we’re thrilled to have both Rich and Tim on board!

In this week’s PlexxiTube of the week, Dan Backman explains how Plexxi’s Big Data fabric solution is managed.

Cisco, Arista disaggregating?

Jim Duffy wrote an interesting piece in Network World this week questioning whether Cisco and Arista should develop versions of their operating systems for bare metal hardware (similar to Cumulus). The industry shift that is taking place here is actually very simple. Research and development spend reflects where the value and Continue reading

PlexxiPulse—Conversations on the SDN “Technique Churn”

Ethan Banks (@ecbanks) initiated an interesting Twitter conversation last weekend by claiming that the constant “technique churn” within organizations that utilize SDN and NetOps is doing the networking industry a disservice. Banks feels that ever-changing frameworks make it nearly impossible to thoroughly understand new technologies. Our own Mike Bushong (@mbushong) took a deep dive into the subject on the Plexxi blog this week in response to those claims. Be sure to check it out before you head out for the day.

In this week’s PlexxiTube video of the week, Dan Backman explains how Plexxi’s Big Data fabric solution can run both L2 and L3 simultaneously.

SDN Users’ Wish Lists Sounds a Lot Like White Box Switching

In an article this week for SDN Central, Craig Matsumoto looks at users that are growing increasingly tired of vendor lock-in and therefore turn to white box switching to provide additional interoperability. In my opinion, the interoperability provided is interesting as it is not a property of vendor intentions. When we accelerate the pace of innovation, there are going to be new capabilities that get added to gear. At the time of first-add, no one else supports the feature. At Continue reading

The Case for Hybrids

Plexxi along with Piston Cloud, Colovore, and King Star Computing published a white paper a few months back looking at the cost of a private cloud running OpenStack in a hosted environment versus renting compute instances from Amazon. The details are here. The short story is that in this analysis, at about 129 Cores, the costs for a private cloud start to become better than public cloud. Certainly the efficiency of colocation, commodity computing/storage, and an application oriented network fabric integrated tightly with a cloud orchestration management platform (OpenStack) has a lot of built in efficiencies so its not surprising to see the result of this analysis.

We’ve Seen this Story Before, Haven’t We?

Similarly, years ago in software development circles, the debates about outsourcing were fierce and emotional. Back then, much centered on the cost leverage available to companies to move development to low-cost areas such as India, China, and Eastern Europe. However, over time, companies found that while cost gave them flexibility and resourcing mite, the more important benefit ended up being owning development resources and presences close to emerging markets while leveraging outsourcing partners for on-demand resource expansion. Wow, sounds a lot like Colocation + Hybrid Cloud Continue reading

Plexxi Pulse—Don’t Be Spooked by Big Data

We are getting into the Halloween spirit here at Plexxi—check out this Plexxi pumpkin carved by our talented marketing manager, Khoa Ma!

Jack-o-lanterns aside, we know the thought of navigating trends like the Internet of Things and Big Data can be frightening, especially if you are unsure of how to approach them. As these trends gain popularity and deployments increase, IT architects often worry about increased activity on already taxed infrastructures. Our own Mike Bushong is our resident expert on this topic and he penned an interesting blog post this week on networking’s atomic unit and “going small to scale up.” Creating smaller units of capacity makes the network easier to manage, and most importantly, scale. It’s definitely worth a read before heading out to trick-or-treat.

In this week’s PlexxiTube of the week, Dan Backman explains failure scenarios in case of hardware or software outages in a Plexxi pod design.

Don’t Engineer a Mess

Network architect Brian Heder contributed an article to Network World this week on the importance and challenges of simplicity in computer network design. While I think Heder’s list is solid, I would add an additional obstacle to network simplicity: customization. Avoid making your network environment Continue reading

Plexxi Pulse—Challenging the Value of the Public Cloud + DemoFriday

Plexxi recently teamed up with Colovore, Piston Cloud Computing and King Star Computers to publish a whitepaper that challenges the assumption that the public cloud is inherently cheaper than the private cloud. Though the rapid speed of deployment and reduced capital expenditure has made services such as Amazon EC2 very attractive, the study shows that the rate of cost increase is often higher than that of a self-hosted private cloud solution. Brandon Butler recently reported on the paper’s findings for Network World.

We hope you were able to tune into DemoFriday today on SDNCentral. Our own Ed Henry and Nils Stewart did an excellent job of explaining how to construct Big Data fabrics that easily integrate with systems like OpenStack and Cloudera. We’ll share the full webinar once it’s live on SDNCentral’s site.

In this week’s PlexxiTube of the week, Dan Backman explains how Plexxi’s datacenter transport fabric can light up dark fiber between buildings on university campuses.

We’ve had a busy October! Check out what we’ve been up to on social media this month below. Have a great weekend!

The post Plexxi Pulse—Challenging the Value of the Continue reading

Making the World a Better Place with Big Data

I spent last week at the Strata + Hadoop World Conference in New York City with 5000 other “big data” customers, vendors, and enthusiasts. In the last 6 months we’ve seen demand for a “big data” based network infrastructure really start to take off, and I’ve spent a lot of time recently trying to better understand the evolving market and technology landscape and use cases. I’m particularly interested in how network infrastructure can drive a better experience for users of big data applications, or networking/infrastructure teams that need to support these applications, but ultimately I want to know what do businesses get out of these investments in data, analytics, and infrastructure.

[On a related note, as part of our efforts to provide the best “Big Data Fabric” we recently brought on @networkn3rd (Ed Henry) to Plexxi to fully define our reference architecture. Ed will be demo’ing the first fruits of his labor this Friday on SDN’s Central’s Demo Friday - Register Here].

Hadoop World was a really great experience. As a relative newbie to Big Data, I have a lot to learn and this was a great place to soak up actual customer use cases. While there was certainly Continue reading

Plexxi Pulse – This Week at Strata + Hadoop World

This week we joined thousands of thought leaders, analysts, vendors and end-users at the O’Reilly Strata + Hadoop World in New York. This event brings together the business and science of Big Data, allowing attendees to learn about emerging technologies through case studies and guest speakers. It’s been a busy week featuring excellent speakers from all over, including The New York Times and Cloudera. While we’re veterans of other industry events such as Interop and VMworld, we’re newbies here, so it’s exciting to experience this all for the first time. Judging by how things have gone so far, you can bet we’ll be back next year for more.

In this week’s PlexxiTube video of the week, Dan Backman highlights how Plexxi integrates with VMware.

Below are our best reads of the week – enjoy!

Data Center SDN growing 65% this year

In a recent article in Network World, Jim Duffy highlights the massive growth within the datacenter market – evidenced by a 65 percent growth in 2014 as reported by the Dell’Oro Group. Personally, I think it will be interesting to see if SDN survives as a separate feature out of the larger networking market. If the datacenter Continue reading

Certified Application to Network Isomorphism Engineer, anyone?

Why would network engineers die?

PlexxiPulse—Mark Your Calendar: DemoFriday is 10/24

Plexxi is teaming up with SDNCentral to host DemoFriday on October 24 at 10 a.m. PST. Tune in to hear our own Ed Henry and Nils Stewart demonstrate how to build scalable and manageable Big Data fabrics that easily integrate with systems such as OpenStack and Cloudera. You can register to attend here.

In this week’s PlexxiTube of the week, Dan Backman explains how Plexxi’s Big Data fabric solution is applicable beyond Big Data.

SDN: Unshackling the Network Application Environment

Art Cole claims that SDN will enable the development of a robust ecosystem of network applications in a recent article for Enterprise Networking Planet. As we look at applications, it is worth making the distinction between network apps (things that run on the network) and business apps (apps the network enables). The real value in SDN will permit the business apps to influence the network (whether that is automated or not is an interesting side conversation). To bring this to life there has to be a focus on policy abstraction. This is why Congress (part of OpenStack) and OpenDaylight are potentially powerful. If we can agree on policy abstraction, then the applications can interact with the network and Continue reading

Plexxi Pulse—HadoopWorld 2014: Is your network ready for Big Data?

We are two short weeks away from HadoopWorld, one of the world’s largest Big Data conferences. October 15—17 our team will be in in New York City to demo our Big Data fabric and answer questions about preparing networks for Big Data. Stop by booth 552 to catch up with our team and pick up a pair of Plexxi Socks. We look forward to seeing you there.

In this week’s PlexxiTube of the week, Dan Backman describes how Plexxi manages load balancing in Big Data networks.

Check out what we’ve been up to on social media this week. Have a great weekend!

The post Plexxi Pulse—HadoopWorld 2014: Is your network ready for Big Data? appeared first on Plexxi.

Plexxi Pulse—Preparing for Big Data

Plexxi Pulse—Preparing for Big Data

As enterprises launch Big Data platforms, it is necessary to tailor network infrastructure to support increased activity. Big Data networks must be constructed to handle distributed resources that are simultaneously working on a single task—a functionality that can be taxing on existing infrastructure. Our own Mike Bushong contributed an article to TechRadar Pro this week on this very subject where he outlines the necessary steps to prepare networks for Big Data deployments. He also identifies how software-defined networking can be used as a tool to alleviate bandwidth issues and support application requirements when scaling for Big Data. It’s definitely worth a read before you head out for the weekend.

In this week’s PlexxiTube of the week, Dan Backman explains how Plexxi’s Big Data fabric mitigates incast problems.

Check out what we’ve been up to on social media this September. Enjoy!

The post Plexxi Pulse—Preparing for Big Data appeared first on Plexxi.

It’s the Applications, Stupid (Part 3 of 3)!

If you missed the first 2 parts of this series, you can catch them here and here. The short version is that there are Enterprise customers that are actively seeking to automate the production deployment of their workloads, which leads them to discover that capturing business policy as part of the process is critical. We’ve arrived here at the point that once policy can be encapsulated in the process of application workload orchestration, it is then necessary to have infrastructure that understands how to enact and enforce that policy. This is largely a networking discussion, and to-date, networking has largely been about any-to-any all equal connectivity (at least in Data Centers), which in many ways means no policy. This post looks at how networking infrastructure can be envisioned differently in the face of applications that can express their own policy.

[As an aside, Rich Fichera over at Forrester researcher wrote a great piece on this topic (which unfortunately is behind a pretty hefty paywall unless you're a Forrester client, but I'll provide a link anyway). Rich coins the term "Systems of Engagement" to describe new models for Enterprise applications that depart from the legacy "Systems of Record." If you have access Continue reading

It’s the Applications, Stupid (Part 2 of 3)!

In part 1 of this series, I mentioned a customer that was starting to understand how to build application policy into their deployment processes and in turn was building new infrastructure that could understand those policies. That’s a lot of usage of the word “policy” so it’s probably a good idea to go into a bit more detail on what that means.

In this context, policy refers to how specific IT resources are used in accordance with a business’s rules or practices. A much more detailed discussion of policy in the data center is covered in this most excellent networkheresy blog post (with great additional discussions here and here).  But suffice it to say that getting to full self-service IT nirvana requires that we codify business-centric policy and encapsulate the applications with that policy.

The goals of the previously mentioned customer were pretty simple, actually. They wanted to provide self-service compute, storage, networking, and a choice of application software stacks to their vast army of developers. They wanted this self-service capability to extend beyond development and test workloads to full production workloads, including fully automated deployment. They wanted to provide costs back to the business that were on par Continue reading

It’s the Applications, Stupid (Part 1 of 3)!

I remember when we first started talking to customers about the concepts of applications driving networks, about 3 years ago (This was a very different conversation from other networking era’s where we talked about ‘intelligent’ networks that could better understand and adapt to applications.) While most customers loved the concepts of a scale-out network that leveraged dynamic photonic connections instead of hard-wired paths, most of them also told us that they “didn’t really know (or want to know)” about the applications at all. Some even said they didn’t want their networks to understand the applications at all!

Hmm.. this was very strange. After all, we were talking to Data Center networking folks, and wasn’t the purpose of the data center network to provide connectivity solutions for applications? How could the folks in charge of these networks not know (and worse, not want to know!) about the whole purpose of their network in the first place?

But of course, it wasn’t really strange. After all, networking, like many IT disciplines, had developed into a nice neat silo that defined nice neat operational boundaries that allowed folks within those boundaries to say “I don’t know, and I don’t want Continue reading

Plexxi Pulse—Adding Flexibility to the Cloud

It’s been a busy week here at Plexxi. On Tuesday, we announced our partnership with Cari.net, a high-performance, scalable and flexible hosting platform based on Microsoft Cloud OS. CARI.net’s newly released CARIcloud service is powered by Plexxi and uses software-defined networking to allow companies to automatically adjust to conditions on their networks and make sure that the most important applications are never starved for performance. The platform enables customers to manage organizations and scale their data centers without being restricted to a single cloud service provider.

In this week’s PlexxiTube of the week, Dan Backman explains how Plexxi’s datacenter fabric transport solution is different from a more traditional WAN gateway.

Hardware Customization in a Software-Driven Universe

Art Cole contributed an interesting piece to Enterprise Networking Planet this week on customizing IT hardware in a “software-driven” universe. In my opinion, we tend to think about the discrete layers within information technology hardware—the boxes that make up the network, the servers that make up compute, and the devices that make up storage. Having flexibility in each layer of hardware is crucial, but we also want the same flexibility in the interconnect that ties them all together. We want programmability Continue reading