Adding new alarm definition for node taint.

Currently there is no alarm for node taint.
This new alarm 900.701 describes the attributes
of the node taint.

Test Plan:
PASSED: Verified the details of the alarm
using fm alarm-list.

Partial-Bug: 2046273

Change-Id: I929ddb45b75f1e4b097b84919f703d458d8fa39e
Signed-off-by: Vanathi.Selvaraju <vanathi.selvaraju@windriver.com>
This commit is contained in:
Vanathi.Selvaraju 2024-01-04 13:30:37 -05:00
parent 1684514c79
commit 14468b9d21
2 changed files with 23 additions and 0 deletions

View File

@ -428,6 +428,8 @@ 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_ABORT_FAILED = ALARM_GROUP_SW_MGMT + ".620"
FM_LOG_ID_SYSTEM_CONFIG_UPDATE_AUTO_APPLY_ABORTED = ALARM_GROUP_SW_MGMT + ".621" 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_SET = 'set'
FM_ALARM_STATE_CLEAR = 'clear' FM_ALARM_STATE_CLEAR = 'clear'
FM_ALARM_STATE_MSG = 'msg' FM_ALARM_STATE_MSG = 'msg'

View File

@ -544,6 +544,7 @@
Degrade_Affecting_Severity: critical Degrade_Affecting_Severity: critical
Context: starlingx Context: starlingx
#--------------------------------------------------------------------------- #---------------------------------------------------------------------------
# MAINTENANCE # MAINTENANCE
#--------------------------------------------------------------------------- #---------------------------------------------------------------------------
@ -4558,4 +4559,24 @@
Probable_Cause: unspecified-reason Probable_Cause: unspecified-reason
Service_Affecting: False Service_Affecting: False
Context: starlingx 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
... ...