Merge "Adding new alarm definition for node taint."

This commit is contained in:
Zuul 2024-02-27 17:36:54 +00:00 committed by Gerrit Code Review
commit a2fadb04dc
2 changed files with 23 additions and 0 deletions

View File

@ -429,6 +429,8 @@ FM_LOG_ID_SYSTEM_CONFIG_UPDATE_AUTO_APPLY_ABORT_REJECTED = ALARM_GROUP_SW_MGMT +
FM_LOG_ID_SYSTEM_CONFIG_UPDATE_AUTO_APPLY_ABORT_FAILED = ALARM_GROUP_SW_MGMT + ".620"
FM_LOG_ID_SYSTEM_CONFIG_UPDATE_AUTO_APPLY_ABORTED = ALARM_GROUP_SW_MGMT + ".621"
FM_ALARM_ID_USM_NODE_TAINTED = ALARM_GROUP_SW_MGMT + ".701"
FM_ALARM_STATE_SET = 'set'
FM_ALARM_STATE_CLEAR = 'clear'
FM_ALARM_STATE_MSG = 'msg'

View File

@ -544,6 +544,7 @@
Degrade_Affecting_Severity: critical
Context: starlingx
#---------------------------------------------------------------------------
# MAINTENANCE
#---------------------------------------------------------------------------
@ -4575,4 +4576,24 @@
Probable_Cause: unspecified-reason
Service_Affecting: False
Context: starlingx
900.701:
Type: Alarm
Description: Node <hostname> tainted.
Entity_Instance_ID: host=<hostname>
Severity: major
Proposed_Repair_Action: |-
"Execute 'kubectl taint nodes <hostname> services=disabled:NoExecute-'
If it fails, Execute 'system host-lock <hostname>' followed by
'system host-unlock <hostname>'.
If issue still persists, contact next level of support."
Maintenance_Action: none
Inhibit_Alarms:
Alarm_Type: operational-violation
Probable_Cause: unknown
Service_Affecting: True
Suppression: False
Management_Affecting_Severity: warning
Degrade_Affecting_Severity: major
Context: starlingx
...