Category: data center

Almost a year ago, I predicted that eventually the hypervisor vendors will wake up and realize it’s time to get rid of VLANs and decouple virtual networks from the physical world. We’ve got the first glimpse of the brave new world a few weeks after that post was published with the VXLAN launch, but that was still a Cisco’s solution running on top of VMware’s (and now everyone else’s) hypervisor. The recent VMware’s acquisition of Nicira proves that VMware finally woke up big time.

Every time I rant about large-scale bridging and stretched L2 subnets, someone inevitably points out that Carrier (or Metro) Ethernet works perfectly fine using the same technologies and principles.

I won’t spend any time on the “perfectly fine” part, but focus on the fundamental difference between the two: the use case.

Sometime in 2012, Chuck Hollis described how some of EMC customers use long-distance workload mobility. Not surprisingly, he focused on the VPLEX Metro part of the solution and didn’t even mention the earth-flattening requirements this idea imposes on the network. I guess you already know my views on that topic, but regardless of my personal opinions, he got me curious.

David Le Goff sent me several great SDN-related questions. Here’s the first one:

What is your take on the performance issue with software-based equipment when dealing with general purpose CPU only? Do you see this challenge as a hard stop to SDN business?

Short answer (as always) is it depends. However, I think most people approach this issue the wrong way.

This post is probably a bit premature, but I’m positive your CIO will get a visit from a vendor offering clean-slate OpenFlow/SDN-based data center fabrics in not so distant future. At that moment, one of the first questions you should ask is “how well does your new wonderland integrate with my existing network?” or more specifically “which L2 and L3 protocols do you support?”

A lot of engineers are concerned with what seems to be frivolous creation of new encapsulation formats supporting virtual networks. While STT makes technical sense (it allows soft switches to use existing NIC TCP offload functionality), it’s harder to figure out the benefits of VXLAN and NVGRE. Scott Lowe wrote a great blog post recently where he asked a very valid question: “Couldn’t we use MPLS over GRE or IP?” We could, but we wouldn’t gain anything by doing that.

It’s clear that major hypervisor vendors consider MAC-over-IP to be the endgame for virtual networking; they’re still squabbling about the best technology and proper positioning of bits in various headers, but the big picture is crystal-clear. Once they get there (solving “a few” not-so-trivial problems on the way), and persuade everyone to use virtual appliances, the network will have to provide seamless IP transport, nothing more.

At that moment, large-scale bridging will finally become a history (until the big layer pendulum swings again) and one has to wonder whether there’s any data center future for TRILL, SPB, FabricPath and other vendor-specific derivatives.

A few days ago Big Switch announced they’ll support overlay networks in their upcoming software release. After a brief “told you so” moment (because virtual networks in physical devices don’t scale all that well) I started wondering whether they simply gave up and decided to become a Nicira copycat, so I was more than keen to have a brief chat with Kyle Forster (graciously offered by Isabelle Guis).

QFabric from Juniper is probably the best data center fabric architecture (not implementation) I’ve seen so far – single management plane, implemented in redundant controllers, and distributed control plane. The “only” problem it had was that it was way too big for data centers that most of us are building (how many times do you need 6000 10GE ports?). Juniper just solved that problem with a scaled-down version of QFabric, officially named QFX3000-M.

Understanding equal-cost multipathing in Brocade’s VCS Fabric is a bit tricky, not because it would be a complex topic, but because it’s a bit counter-intuitive (while still being perfectly logical once you understand it). Michael Schipp tried to explain how it works, Joel Knight went even deeper, and I’ll try to draw a parallel with the routed networks because most of us understand them better than the brave new fabric worlds.

A while ago I was writing about the behavior of Microsoft’s Network Load Balancing, the problems it’s causing and how Microsoft tried to hack around them using multicast MAC addresses as the hardware address of sender in ARP replies (which is illegal). A few days ago one of my readers asked me whether I know which RFC prohibits the use of multicast MAC address in ARP replies.

A quick consultation with friendly Google search engine returned this web page, which contained the answer: section 3.3.2 of RFC 1812 (Requirements for IP Version 4 Routers):

A router MUST not believe any ARP reply that claims that the Link Layer address of another host or router is a broadcast or multicast address.

Problem solved – now I know the real reason we have to configure static ARP entries on Cisco routers and switches.

This topic has been on my to-write list for over a year and its working title was phrased as a question, but all the horror stories you’ve shared with me over the last year or so (some of them published in my blog) have persuaded me that there’s no question – it’s a fact.

If you think I’m rephrasing the same topic ad nauseam, you’re right, but every month or so I get an external trigger that pushes me back to the same discussion, this time an interesting comment thread on Massimo Re Ferre’s blog.

When I mentioned the uselessness of stateless NAT64, I got in nice discussion with Tore Anderson who wanted to use stateless NAT64 in reverse direction (stateless NAT46) to build an IPv6-only data center. Some background information first (to define the context of his thinking before we jump into the technical details):

Brad Hedlund did an excellent analysis of fixed versus chassis-based switches in his Interop presentation and concluded that fixed switches offer higher port density and lower per-port power consumption than chassis-based ones. That’s true when comparing individual products, but let’s ask a different question: how much does it take to implement a 384-port non-blocking fabric (equivalent to Arista’s 7508 switch) with fixed switches?

I usually use the “Nicira is Skype of virtual networking” analogy when describing the differences between Nicira’s NVP and traditional VLAN-based implementations. Cade Metz liked it so much he used it in his What Is a Virtual Network? It’s Not What You Think It Is article, so I guess a blog post is long overdue.

Before going into more details, you might want to browse through my Cloud Networking Scalability presentation (or watch its recording) – the crucial slide is this one: