Preparing the 8247-42L, 8286-41A, or 8286-42A system to remove and replace a PCIe adapter with the power turned on in Linux
Learn about steps you must complete before you remove and replace the Peripheral Component Interconnect (PCI) Express (PCIe) adapters from the system, to replace a failing part or as part of another service procedure.
To prepare the
system to remove and replace a PCIe adapter in
the system, complete the steps in this procedure.
Important: Before removing a PCIe3 1.6 TB NVMe Flash adapter (FC EC54 and EC55; CCIN
58CB) or a PCIe3 3.2 TB NVMe Flash adapter (FC EC56 and EC57; CCIN 58CC), ensure that all data on
the adapter or the array that contains the adapter is backed up. Restore the data after the adapter
is replaced.
- Before you hot-plug an adapter, ensure that the server or partition is at the correct level of the Linux operating system.
- Verify that the Linux, hot-plug PCI tools are installed. For instructions, see Verifying that the hot-plug PCI tools are installed for Linux.
- Ensure that you have the POWER® Linux Service Aids installed on your system. These service aids enable system serviceability, as well to improve system management. If you are using a Linux on POWER distribution with Linux kernel version 2.6 or later, you can install the Service Aids that gives you access to more capabilities, which can help you diagnose problems on your system. This software is available at the Service and productivity tools for Linux on POWER website.
- You must take the PCIe adapter offline before removing and replacing a PCIe adapter with the system power turned on (hot-plugging). Before you take an adapter offline, the devices that are attached to the adapter must be taken offline as well. This action must be done by a system administrator. Taking the PCIe adapter offline prevents a service representative or user from causing an unexpected outage for other users of the system.
- Before hot-plugging adapters for storage devices, ensure that the file systems on those devices are unmounted.
- Familiarize yourself with the locations of PCIe adapter slots and the service indicators
for the PCIe adapter that you want
to service. The PCIe adapters are
installed in the rear of the system. Figure 1 and Figure 2 show the locations
of the PCIe adapters in a system and the locations of the light-emitting
diodes (LEDs) for the PCIe adapter. Note: The number of the PCIe adapter slots that are available in the system depends on the number of system processors in the system. For the PCIe adapter placement information regarding the available slots in this system, see PCIe adapter placement rules and slot priorities for the 8247-42L, 8286-41A, or 8286-42A.The PCIe adapter has two LEDs that indicate the status:
- An activity LED (green)
- An error and identify function LED (amber)
Figure 1. PCIe adapter slot locations and locations of the LEDs in a rack-mounted system
Figure 2. PCIe adapter slot locations and locations of the LEDs in a stand-alone 8286-41A system
- Take appropriate precautions for avoiding electric shock and for handling static-sensitive devices. For information, see Avoiding electric shock and Handling static-sensitive devices.
- Use the service indicator light-emitting diodes (LEDs) to help identify the part. For instructions, see Identifying a part.
- Open the rack door at the rear of the system.
- If
you are removing the PCIe adapter as
part of another service procedure, record the details about the PCIe adapter and its location code,
and then go to the next step.
If you are servicing a failed PCIe adapter, look for the flashing amber LED for the failed PCIe adapter that you set to flash in the step to identify the failed part.
See Figure 3 and Figure 4 that show the state of the LEDs. Note that the amber LED for the failed PCIe adapter is Flashing, as shown in (D) in Figure 3 and Figure 4.Attention: If the PCIe adapter is operating correctly then the Activity LED is ON (green) and the Error amber LED is OFF, as shown in (B) in Figure 3 and Figure 4. Do not attempt to remove the working PCIe adapter.Figure 3. PCIe adapter slot locations and locations of the LEDs in a rack-mounted system
Figure 4. PCIe adapter slot locations and locations of the LEDs in a stand-alone 8286-41A system
- Label and disconnect all cables and transceivers that are attached to the adapter you plan to remove. For instructions to remove transceivers, see Removing and replacing the tailstock on a PCIe adapter.
- If you have not yet recorded the PCIe
slot details, record the slot number and location of each adapter
being removed. Note: Adapter slots are numbered on the rear of the system.
- Remove the front cover.
- For instructions to remove the front cover from a rack-mounted 8247-42L, 8286-41A, or 8286-42A system, see Removing the front cover from a rack-mounted 8247-42L, 8286-41A, or 8286-42A system.
- For instructions to remove the front cover from a stand-alone 8286-41A system, see Removing the front cover from a stand-alone 8286-41A system.
- For a rack-mounted system, place the system into the service position. For instructions, see Placing a rack-mounted model into the service position.
- Attach the electrostatic discharge
(ESD) wrist strap. The ESD wrist strap must be connected
to an unpainted metal surface until the service procedure is completed,
and if applicable, until the service access cover is replaced.Attention:
- Attach an electrostatic discharge (ESD) wrist strap to the front ESD jack, to the rear ESD jack, or to an unpainted metal surface of your hardware to prevent the electrostatic discharge from damaging your hardware.
- When you use an ESD wrist strap, follow all electrical safety procedures. An ESD wrist strap is used for static control. It does not increase or decrease your risk of receiving electric shock when using or working on electrical equipment.
- If you do not have an ESD wrist strap, just prior to removing the product from ESD packaging and installing or replacing hardware, touch an unpainted metal surface of the system for a minimum of 5 seconds. If at any point in this service process you move away from the system, it is important to once again discharge yourself by touching an unpainted metal surface for at least 5 seconds before you continue with the service process.
- Remove the service access cover. For instructions, see Removing the service access cover.
- Enter drmgr on
the console to enable an adapter to be removed: For example, to remove the PCIe adapter in slot U7879.001.DQD014E-P1-C3 enter:
drmgr -c pci -r -s locationcodeFollow the instructions on the display to complete the task.