Removing and replacing a faulty node
You can use this procedure to remove a faulty node and replace it with a new node. You can remove the parts from the faulty node and reinstall them into the new node. You can also use this procedure to allow for replacement of parts inside the node.
About this task
Notes:
- Ensure the FRU part number (P/N) of the replacement part matches that of the failed node, or is an approved substitute. The FRU P/N is identified on the label of the and on the FRU packaging.
- Do not operate the control enclosure with one node that is removed for longer than 16 minutes. Operating for longer than this period might cause the enclosure to shut down due to overheating.
- A Phillips screw driver is required to remove the node cover. Do not remove or loosen any other screws.
- Use care when you remove a node from the control enclosure. The node is long and its center of gravity is far forward. It can be helpful to have a lift or other sturdy, flat surface ready to receive the node during removal.
Procedure
- Review the Event Log to identify the faulty node.
- Review Procedure: Understanding system volume dependencies to identify any volume dependencies on the node .
- Follow Procedure: Powering off a node canister to verify that the hosts do not lose access to data in volumes.
- From the rear of the control enclosure, label each cable and remove it from the node.
Removing the faulty node
- Remove the node, as described in Removing and reseating a node, and place it on a flat, level surface.
-
Remove the new node from its packaging.
Ensure that the FRU P/N of the replacement node matches that of the failed node or that the new P/N is an approved substitute. See Replaceable units for more information.
- Remove the covers from the faulty and replacement nodes and set them aside, as described in Removing and replacing the cover of a node.
- Remove the air baffles from the faulty and replacement nodes and set them aside, as described in Removing and replacing the air baffle of a node.
-
Complete the following procedures to remove parts from
the faulty node and install them in the replacement node.
- Removing and replacing a memory module
- Removing and replacing a fan module
- Removing and replacing the Trusted Platform Module
- Removing and replacing the node battery
- Removing and replacing an adapter cageNotes:
- You do not need to remove each adapter from its adapter cage. Each assembled riser and adapter are transferred to the replacement node.
- When you install each PCIe risers and adapter assembly into the replacement node , use the same numbered slot that was used in the faulty node.
- Removing and replacing a boot drive
Note: Transfer each boot drive one at a time. Ensure that you install the drive into the same slot in the replacement node .
- Removing and replacing a compression card
Replacing the new node
- Replace the air baffle in the new node canister, as described in Removing and replacing the air baffle of a node.
- Replace the cover on the new node, as described in, as described in Removing and replacing the cover of a node.
- Install the new node into the control enclosure, as described in Removing and reseating a node.
- Reconnect the cables that were removed in step 4 to the appropriate ports in the replacement node.
-
If the node was communicating with other
nodes using RDMA over Ethernet, then use the Service
Assistant Tool or the sainfo lsnodeip command to check if the node IP
configuration has been lost. Use the Service Assistant Tool or the satask
chnodeip command to set the node IP if needed.
- Use the management GUI or service assistant GUI to check that the node is online (or is Active) in the system.
-
Enter the service assistant command satask chbootdrive -replacecanister to
update the drives to match the serial number of the new node.
Note: Node error code 545 is expected. For more information, see 545.
To help identify the node, the inside of the release levers are labeled with the serial number.
- Review the management GUI to determine that all errors are resolved.