FreeBSD link aggregation no faster than single link

What is the load balancing algorithm in use on both the system and the switch?

All my experience with this is on Linux and Cisco, not FreeBSD and SMC, but the same theory still applies.

The default load balancing mode on the Linux bonding driver's LACP mode, and on older Cisco switches like the 2950, is to balance based on MAC address only.

This means if all your traffic is going from one system (file server) to one other MAC (either a default gateway or a Switched Virtual Interface on the switch) then the source and destination MAC will be the same, so only one slave will ever be used.

From your diagram it doesn't look like you're sending traffic to a default gateway, but I'm not sure if the test servers are in 10.0.0.0/24, or if the test systems are in other subnets and being routed via a Layer 3 interface on the switch.

If you are routing on the switch, there's your answer.

The solution to this is to use a different load balancing algorithm.

Again I don't have experience with BSD or SMC, but Linux and Cisco can balance either based on L3 information (IP address) or L4 information (port number).

As each of your test systems must have a different IP, try balancing based on L3 information. If that still doesn't work, change a few IPs around and see if you change the load balancing pattern.