Virtual Networks : The Way Ahead - 1

Virtualization changed server market dramatically. Dramatic enough to raise a new market force called VmWare in server market.  Apart from changing marketing dynamics, virtualization started changing the school of thought about information transfer into which networking market got admission lately.

 In the past, network designers built fat-tree topologies in which traffic traveled in a north-south orientation up and down the tree. That’s an adequate design for client-facing traffic and workloads that don’t move. A smart designer could put systems that need to talk to one another nearby and reduce the amount of traffic flowing up and down the tree.

Networks were always determined by the Spanning Tree Protocol that forced a tree like structure from core to edge. Today, we refer to this as North/South Alignment because traffic flows were predominantly Server to LAN Core to WAN Core to WAN Edge to Client.

Virtualization breaks this paradigm. Virtual machines are talking to other VMs in other racks and rows in an east-west fashion. And VMs can move to unpredictable data center locations. A designer can’t know where a workload is at any given time, because it’s no longer physically constrained. In that world, the fat tree fails at scale.  Also, Typical Spanning-Tree topologies would fail as well.  Alternatively L2 Multi-Path (L2MP) technologies are replacing Spanning-Tree. 

Today’s network architects and engineers have a multitude of options to meet demands raised because of virtualization. I would like to categorize at significant data center network technologies in three major categories:

(i) Layer 2 multi-path

(ii)Layer 2 extension 

(iii)software-defined networking.

I will try to take a stab at these technologies once.  I will try to go in deep about these in my next-posts.

L2 Multi-Path

Layer 2 multi-path tackles the built-in limitations of Spanning Tree Protocol by enabling all links to forward traffic while ensuring redundancy and eliminating loops that could take down a network. While some of these L2 Multipath technologies are standards/work group based, come are proprietary. IETF has a workgroup which introduced TRILL(Trasparent Interconnection of Lots of Links) whereas IEEE has a standard 802.1aq known as SPB(Shortest Path Bridging). Emerging protocols such as TRILL and SPB let designers create meshes or fabrics that enable traffic to take the shortest path between switches.

Proprietary Options include MLAG and virtual chassis, which allow multiple switches to act like a single device.

L2 Extension

One of the reasons for Server Virtualization becoming prominent was it makes the server movement a cake walk. Virtual Machines can be moved across servers without any physical movement. VM movement has some problems to be solved in which case L2 Extension technologies are discovered. Layer 2 extension allows physically separate data centers to be linked into a Layer 2 domain across Layer 3 boundaries. Originally aimed at carrier networks(think VPLS and Q-in-Q, among others), some Layer 2 extension protocols are appearing the data center because they support the ability to move VMs from one data center to another, an ideal capability for load sharing, business continuity and disaster recovery. We look at Cisco’s Overlay Transport Virtualization, the Virtual Extensible Local Area Network(VXLAN), Network Virtualization using Generic Routing Encapsulation(NVGRE) and Stateless Transport Tunneling(STT).

Software Defined Networking(SDN)

Software-defined networking is emerging as an alternative to the traditional switch model in which the control plane resides within each switch. While SDN and OpenFlow are not synonymous, OpenFlow demonstrates SDN’s promise: take the decision-making away from the switches and routers, and move it into a centralized controller that will tell the network as a whole how to forward traffic, allowing for more flexible networks that can respond in near real time to changing conditions. It also doesn’t hurt that Open-Flow and SDN have the potential to make networking gear less expensive.This can make the network more flexible and better able to respond to changing demands. In addition to SDN,in my next posts, I will try to dig into OpenFlow, a new protocol for communicating between switches and a controller. In next posts, I will try to explain the potential implicationsof SDN and OpenFlow and evaluate its impact on data center networks.

[In my next post, I will take a deep dive on L2 Multipath technolgies]