Latency
Latency is the time it takes data to travel between two points on a network, usually measured in milliseconds round trip. In fiber, light travels roughly five microseconds per kilometer one way, so route distance, not straight-line distance, sets the floor. Latency matters most for edge, colocation and interactive workloads, and less for training or batch workloads that can sit far from users.
The full guide · Decisions and trade-offsNear the Metro or Near the Power? Choosing a Data Center LocationHow to weigh a data center site near a metro market against a remote site with abundant power: latency, fiber, labor, land, entitlement, water and timing.Where Latency comes up
- Water, gas & fiberLatency Requirements by Workload: Where Data Center Proximity Matters
- Site strategy by data center typeAI Training vs. Inference Data Centers: How Site Needs Differ
- Water, gas & fiberFiber Route Diversity and Latency for Data Center Sites
- Site strategy by data center typeSite Needs by Data Center Type: Edge, Colocation and Hyperscale
- Water, gas & fiberHow Long-Haul and Subsea Fiber Routes Affect Data Center Site Selection
- Water, gas & fiberInternet Exchange Points and Carrier Hotels: Why They Shape Data Center Markets
- Water, gas & fiberFiber Connectivity for Data Center Sites
- Site strategy by data center typeEdge Data Center Site Selection: Location, Power and Zoning