?

Comparing Two-Tier and Three-Tier Data Center Networks

Modern applications require a modern data center infrastructure, and Two-Tier, spine-leaf architectures offers many advantages over traditional Three-Tier designs.

January 29, 2020 5 minute read

We know that the world of networking is constantly changing. The needs and requirements for your network continue to evolve with the pace of data center transformation.

More than 70 percent of all traffic today moves from server to server, or what we consider East-West traffic. Traditional data center networks were initially designed for resiliency and were concerned with speed into and out of the data center, not within it.

To solve for this, we have been recommending that customers move to a Two-Tier, or spine-leaf architecture, in their data centers for several years now. The reason for the change is that modern applications require significantly more data to travel within a data center, at faster speeds and are less forgiving about latency.

We can get a better understanding of the considerations for modern data center networks by comparing multi-tiered network designs and how they can solve for today's business needs.

Three-Tier data center networks

Traditional data center networks utilized a Three-Tier design that consists of a core, distribution and access layer of switches.

Three-Tier data center network design
  • Core switches are usually large modular chassis with very high throughput and advanced routing capabilities.
  • Distribution layer switches are mid-tier speed switches with emphasis on uplink speeds. Services, such as load balancing or firewalls, could often be found at this layer.
  • Access Switches are the traditional top-of-rack (TOR) switch that regularly consists of 24 to 48 ports of 1 or 10Gbps ports with similarly sized uplinks.

Three-Tier data center networks were the generally recommended data center network design in the past. They worked very well when the majority of traffic moved North-South (from outside the data center in) or vice versa. A packet flows to the core, is routed to the correct distribution switch, then forwarded on to the access switch where the server was connected; moving through only 3 physical hops which limits the amount of latency added per-packet flow. 

The issue with this design for the modern data center is that much more intra-DC traffic is the new norm. Due to server to server traffic, three hops now quickly become four, five or more, adding significant latency per flow as well as adding more possibility for bottlenecks, buffer overruns and dropped packets.

Three-Tier data center networks introduced loops, which you can see in the graphic above — this requires correct spanning-tree protocol configuration. Spanning-tree issues are notorious for causing network outages as a spanning-tree failure causes continuous looping.

Two-Tier data center networks

Today, we recommend Two-Tier, or spine-leaf achitectures (also called Folded-CLOS), to meet the needs of modern applications: high-throughput and low-latency. 

Two-Tier spine-leaf network design
  • Spine Switches are very high-throughput, low-latency and port-dense switches that have direct high-speed (40-300Gbps) connections to each leaf switch.
  • Leaf Switches are very similar to traditional TOR switches in that they are often 24 or 48 port 1, 10 or 40Gbps access layer connections, but have the increased capability of either 40, 100 or 300Gbps uplinks to each spine switch.

Advantages of Two-Tier, spine-leaf architectures

  1. Resiliency: Each leaf switch connects to every spine switch, spanning-tree is not needed and due to TRILL, SPB or SDN protocols, every uplink can be used concurrently.
  2. Latency: There is a maximum of 2 hops for any East-West packet flows so ultra-low-latency is standard.
  3. Performance: True active-active uplinks enable traffic to flow over the least congested high-speed links available.
  4. Scalability: You are able to increase leaf switch quantity to desired port capacity and add spine switches as needed for uplinks.
  5. Adaptability: Multiple spine-leaf networks across a multicloud ecosystem can be connected and managed from a single pane of glass. Also, this topology has benefits in other areas of the enterprise network (for example, industrial cell architecture or corporate LAN).

Considerations for using Two-Tier, spine-leaf architectures

With a Two-Tier architecture, the data center will need to be re-cabled. Each leaf will need to connect to each spine. This new design requires a considerable amount of cable as well as optics for connectivity.

Two-Tier, spine-leaf architectures may still require core switches for layer three routing. Planning both the physical and logical network is critical before purchasing the hardware for a new data center.

Summary

Modern applications require a modern data center infrastructure design; Two-Tier, spine-leaf architecture offers many advantages over traditional Three-Tier architectures. 

Two-Tier architectures eliminate single points of failure, traffic bottlenecks and issues with scalability, as well as improving overall throughput and ease of management. The Two-Tier architecture addresses modernizing the physical network. 

To modernize the logic network, WWT recommends adding a software-defined network (SDN) platform like Cisco ACI or VMWare NSX. You can learn more about transitioning data center infrastructure in one of our  latest articles on intent-based networking or by scheduling an on-demand Cisco ACI lab, which will allow you to see how ACI can help you to set up your network in an automated way.

Ready to get started? Your WWT account manager can bring the right experts together to help design your modern data center.

Share this

Comments