What do people mean by east-west and north-south traffic, and why did it change data center design?
Show the answer
Say this first
North-south traffic enters or leaves the data center, for example a user reaching a web server. East-west traffic stays inside it: web to app, app to database, storage replication, VM migration, microservices calling each other. Virtualization and distributed applications made east-west the larger share in most data centers, so designs moved to spine-leaf, which gives every server pair the same bandwidth and latency.
Go deeper
What shifted the traffic
- Multi-tier and microservice apps. One user request fans out into many internal calls.
- Distributed storage and databases. Replication and rebuilds move large volumes between racks.
- Virtualization. Live migration copies VM memory across the network.
- Big data and AI training. Shuffle phases and collective operations hit every node at once.
What it changed
- Topology. Three tier sends cross-block east-west traffic up through aggregation and core. Spine-leaf makes every rack two hops from every other rack.
- Capacity planning. You size leaf uplinks (oversubscription) for server-to-server load, not just for the internet link.
- Security. A perimeter firewall only sees north-south. East-west needs its own controls: segmentation, inter-VRF firewalls, microsegmentation.
- Layer 2 scope. Apps wanted the same subnet in many racks, which pushed overlays such as VXLAN.
They will ask next
How would you prove the traffic mix on an existing network?
Flow telemetry (NetFlow, IPFIX or sFlow) from the aggregation or leaf layer, grouped by source and destination prefix. Compare bytes that stay inside data center prefixes with bytes going to the WAN or internet edge.
Traps
- Swapping the terms. North-south crosses the data center edge, east-west stays inside.
How did you do?Book 1.1 Applications