900180028
NVDIMM has lost persistence. Setting the node to read-only to protect the journal.
Description
The NVDIMM detects something in its subsystem that does not allow it to persist DRAM through a power-loss event. The event
might be related to the DRAM itself or the BBU (battery backup unit).
Administrator action
The node is placed into a read-only state to protect the journal. If the NVDIMM was bad during startup, the node is not armed.
The node automatically restarts (the cluster is notified, the cluster waits 60 s, and then restarts), and regains persistence. If the
issue does not clear itself, escalate, and determine if the issue is related to the NVDIMM or the battery.
900180029
NVDIMM has regained persistence. Node reboots itself to rearm NVDIMM.
Description
The node lost persistence but has recovered. The node requires a reboot to rearm the NVDIMM.
Administrator action
Wait for the node restart (60 s from when the event occurs), or manually restart the OneFS node if the message continues.
900180030
NVDIMM has failed. Node transitions to read-only mode until the NVDIMM has been replaced.
Description
●
NVDIMM experiences similar wear to regular DIMMs.
●
The NVDIMM is seated incorrectly, damaged, or not responding.
●
End of supported life duration.
●
Unable to save the data during the previous system shutdown operation, or power loss. The NVDIMM is placed in write-
protect mode.
Administrator action
●
See the error message and follow the OEM instructions.
●
For an unreachable NVDIMM, reseat the DIMM. If the issue continues, replace the NVDIMM.
●
Ensure that the NVDIMM is replaced in the correct slot.
●
For an end of life, bad, or degraded NVDIMM, replace the NVDIMM.
198
Hardware events
