What is a function of spine-and-leaf architecture?

In a spine-and-leaf architecture, every leaf switch is connected to every spine switch, creating a maximum of two hops between any two leaf switches, which ensures predictable and low-latency traffic delivery between end devices.

While spine-and-leaf *can* mitigate oversubscription through proper design and bandwidth planning, simply 'adding a layer of leaf switches' does not inherently mitigate it; it's the specific interconnections and capacity planning that achieve this.

Spine-and-leaf architecture is a general-purpose network fabric designed for all types of traffic, not exclusively for multicast traffic, and servers are typically connected to leaf switches, not spines.

Spine-and-leaf architecture does not inherently limit the payload size of traffic within the leaf layer; payload size is typically determined by the MTU settings configured on interfaces and devices.