Rack A/B Power and PDU Design

1. Define the failure you want to survive

A/B power can mean different things. Define whether the goal is surviving a PDU failure, UPS failure, circuit failure or a larger upstream event.

2. Trace independence upstream

Two rack PDUs are not independent if they share the same single UPS/circuit without intentional redundancy. Draw the one-line power path.

3. Inventory equipment cords

List single-cord and dual-cord equipment, plug type, expected load and PSU redundancy. Single-cord equipment may require an ATS or a different resilience strategy.

4. Select PDU outlet and input correctly

Match voltage, current, plug/receptacle types, mounting format and metering/switched features to the site and equipment.

5. Balance dual-corded loads

For equipment that load-shares across PSUs, ensure either surviving path can carry the defined failure load. Do not size each PDU only from normal half-load.

6. Label A and B physically

Use consistent rack labels, outlet maps and cord identification so a technician can work on one path without unplugging both.

7. Keep power and data serviceable

Route power cords to their PDUs without blocking hot-swap PSUs, rails or network cable paths.

8. Test the design under change control

Where safe and permitted, isolate one path at a time and verify equipment remains healthy and the surviving PDU/UPS is within capacity.

9. Maintain the rack power schedule

Update the outlet map when hardware moves. A stale A/B diagram is a maintenance hazard.

Worked field scenario

Two vertical PDUs are labelled A and B but both are connected to the same UPS output. The labels provide no upstream resilience. Redraw the path from server PSU to PDU to UPS/circuit and decide which failure the design must actually survive.

Procurement questions before ordering

The ordering stage is where many field problems are created. Capture the following before selecting the exact product:

• Equipment U height, depth and mass
• Rail-kit mounting-depth range
• Front/rear cable and service clearance
• PDU position and power connectors
• Airflow direction and cabinet load limit

Where a manufacturer compatibility list, rail matrix, supported-optics table or battery cartridge reference exists, record the exact source used for the decision. That gives the later installer evidence rather than a verbal assumption.

Fault-finding decision path

For physical rack problems, trace the constraint rather than forcing the equipment. Determine whether the issue is rail spacing, square/round-hole hardware, rear clearance, PDU collision, cable bend, weight support or door interference. For thermal faults, follow airflow from intake to exhaust and look for recirculation or obstruction.

Keep a simple change log while troubleshooting: observation, action, result. If a change does not alter the symptom, put the system back unless there is a documented reason to retain it. This prevents troubleshooting from becoming an uncontrolled configuration drift.

Common mistakes that create repeat faults

Do not choose a cabinet from U height alone. Do not support heavy servers on one improvised shelf edge or mismatched rails. Do not leave deep coils of cable in exhaust paths, and do not call two PDUs A and B unless the upstream paths are genuinely defined.

A technically successful installation can still be a poor operational result if the next technician cannot identify what was installed, why it was selected, or how it was tested. Serviceability is part of infrastructure quality.

Acceptance and handover evidence

Keep a rack elevation, equipment/rail inventory, PDU outlet map, cable-path notes and photographs of front/rear finished state. For server racks, include depth measurements and any equipment that has unusual airflow or service-clearance requirements.

Use filenames, labels and port/bay identifiers that match the physical installation. Handover evidence should let someone who was not present at the installation verify the final state and repeat the important tests later.