starlingx
/
fault
Code Issues Proposed changes

Merge "Add System Config Update orch alarms and events"

This commit is contained in:
Zuul 2023-05-23 21:55:36 +00:00 committed by Gerrit Code Review
parent 6438565a4d 04d6b31d95
commit 6172b8ee41
2 changed files with 213 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
fm-api/source/fm_api/constants.py
View File

@ -305,6 +305,14 @@ FM_ALARM_ID_KUBE_ROOTCA_UPDATE_IN_PROGRESS = ALARM_GROUP_SW_MGMT + ".008"
# Kubernetes RootCA Update abort alarm id
FM_ALARM_ID_KUBE_ROOTCA_UPDATE_ABORTED = ALARM_GROUP_SW_MGMT + ".009"
# The SYSTEM_CONFIG_UPDATE alarms are originated by vim strategy which is the
# same as the other sw-mgmt alarms, put them in the same group
# System Config Update alarm id
FM_ALARM_ID_SYSTEM_CONFIG_UPDATE_IN_PROGRESS = ALARM_GROUP_SW_MGMT + ".010"
# System Config Update abort alarm id
FM_ALARM_ID_SYSTEM_CONFIG_UPDATE_ABORTED = ALARM_GROUP_SW_MGMT + ".011"
# Security log id
FM_LOG_ID_INVALID_PASSWORD = ALARM_GROUP_SECURITY + ".001"
FM_LOG_ID_USER_LOCKOUT = ALARM_GROUP_SECURITY + ".002"
@ -400,6 +408,21 @@ FM_LOG_ID_KUBE_ROOTCA_UPDATE_AUTO_APPLY_ABORT_REJECTED = ALARM_GROUP_SW_MGMT + "
FM_LOG_ID_KUBE_ROOTCA_UPDATE_AUTO_APPLY_ABORT_FAILED = ALARM_GROUP_SW_MGMT + ".520"
FM_LOG_ID_KUBE_ROOTCA_UPDATE_AUTO_APPLY_ABORTED = ALARM_GROUP_SW_MGMT + ".521"
FM_ALARM_ID_SYSTEM_CONFIG_UPDATE_AUTO_APPLY_INPROGRESS = ALARM_GROUP_SW_MGMT + ".601"
FM_ALARM_ID_SYSTEM_CONFIG_UPDATE_AUTO_APPLY_ABORTING = ALARM_GROUP_SW_MGMT + ".602"
FM_ALARM_ID_SYSTEM_CONFIG_UPDATE_AUTO_APPLY_FAILED = ALARM_GROUP_SW_MGMT + ".603"
FM_LOG_ID_SYSTEM_CONFIG_UPDATE_AUTO_APPLY_START = ALARM_GROUP_SW_MGMT + ".611"
FM_LOG_ID_SYSTEM_CONFIG_UPDATE_AUTO_APPLY_INPROGRESS = ALARM_GROUP_SW_MGMT + ".612"
FM_LOG_ID_SYSTEM_CONFIG_UPDATE_AUTO_APPLY_REJECTED = ALARM_GROUP_SW_MGMT + ".613"
FM_LOG_ID_SYSTEM_CONFIG_UPDATE_AUTO_APPLY_CANCELLED = ALARM_GROUP_SW_MGMT + ".614"
FM_LOG_ID_SYSTEM_CONFIG_UPDATE_AUTO_APPLY_FAILED = ALARM_GROUP_SW_MGMT + ".615"
FM_LOG_ID_SYSTEM_CONFIG_UPDATE_AUTO_APPLY_COMPLETED = ALARM_GROUP_SW_MGMT + ".616"
FM_LOG_ID_SYSTEM_CONFIG_UPDATE_AUTO_APPLY_ABORT = ALARM_GROUP_SW_MGMT + ".617"
FM_LOG_ID_SYSTEM_CONFIG_UPDATE_AUTO_APPLY_ABORTING = ALARM_GROUP_SW_MGMT + ".618"
FM_LOG_ID_SYSTEM_CONFIG_UPDATE_AUTO_APPLY_ABORT_REJECTED = ALARM_GROUP_SW_MGMT + ".619"
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_STATE_SET = 'set'
FM_ALARM_STATE_CLEAR = 'clear'

190
fm-doc/fm_doc/events.yaml
View File

@ -3534,6 +3534,38 @@
Degrade_Affecting_Severity: none
Context: starlingx
900.010:
Type: Alarm
Description: System Config update in progress
Entity_Instance_ID: host=controller
Severity: minor
Proposed_Repair_Action: Wait for system config update to complete
Maintenance_Action:
Inhibit_Alarms:
Alarm_Type: operational-violation
Probable_Cause: unspecified-reason
Service_Affecting: False
Suppression: False
Management_Affecting_Severity: warning
Degrade_Affecting_Severity: none
Context: starlingx
900.011:
Type: Alarm
Description: System Config update aborted, configurations may not be fully updated
Entity_Instance_ID: host=<hostname>
Severity: minor
Proposed_Repair_Action: Lock the host, wait for the host resource in the deployment namespace to become in-sync, then unlock the host
Maintenance_Action:
Inhibit_Alarms:
Alarm_Type: operational-violation
Probable_Cause: unspecified-reason
Service_Affecting: False
Suppression: False
Management_Affecting_Severity: warning
Degrade_Affecting_Severity: none
Context: starlingx
900.101:
Type: Alarm
Description: Software patch auto-apply in progress
@ -4323,4 +4355,162 @@
Probable_Cause: unspecified-reason
Service_Affecting: False
Context: starlingx
900.601:
Type: Alarm
Description: System config update auto-apply in progress
Entity_Instance_ID: orchestration=system-config-update
Severity: major
Proposed_Repair_Action: Wait for system config update auto-apply to complete; if problem persists contact next level of support
Maintenance_Action:
Inhibit_Alarms:
Alarm_Type: equipment
Probable_Cause: unspecified-reason
Service_Affecting: True
Suppression: True
Management_Affecting_Severity: warning
Degrade_Affecting_Severity: none
Context: starlingx
900.602:
Type: Alarm
Description: System config update auto-apply aborting
Entity_Instance_ID: orchestration=system-config-update
Severity: major
Proposed_Repair_Action: Wait for system config update auto-apply abort to complete; if problem persists contact next level of support
Maintenance_Action:
Inhibit_Alarms:
Alarm_Type: equipment
Probable_Cause: unspecified-reason
Service_Affecting: True
Suppression: True
Management_Affecting_Severity: warning
Degrade_Affecting_Severity: none
Context: starlingx
900.603:
Type: Alarm
Description: System config update auto-apply failed. Command "sw-manager kube-upgrade-strategy apply" failed
Entity_Instance_ID: orchestration=system-config-update
Severity: critical
Proposed_Repair_Action: Attempt to apply system config update manually; if problem persists contact next level of support
Maintenance_Action:
Inhibit_Alarms:
Alarm_Type: equipment
Probable_Cause: underlying-resource-unavailable
Service_Affecting: True
Suppression: True
Management_Affecting_Severity: warning
Degrade_Affecting_Severity: none
Context: starlingx
900.611:
Type: Log
Description: System config update auto-apply start
Entity_Instance_ID: orchestration=system-config-update
Severity: critical
Alarm_Type: equipment
Probable_Cause: unspecified-reason
Service_Affecting: False
Context: starlingx
900.612:
Type: Log
Description: System config update auto-apply in progress
Entity_Instance_ID: orchestration=system-config-update
Severity: critical
Alarm_Type: equipment
Probable_Cause: unspecified-reason
Service_Affecting: False
Context: starlingx
900.613:
Type: Log
Description: System config update auto-apply rejected
Entity_Instance_ID: orchestration=system-config-update
Severity: critical
Alarm_Type: equipment
Probable_Cause: unspecified-reason
Service_Affecting: False
Context: starlingx
900.614:
Type: Log
Description: System config update auto-apply cancelled
Entity_Instance_ID: orchestration=system-config-update
Severity: critical
Alarm_Type: equipment
Probable_Cause: unspecified-reason
Service_Affecting: False
Context: starlingx
900.615:
Type: Log
Description: System config update auto-apply failed
Entity_Instance_ID: orchestration=system-config-update
Severity: critical
Alarm_Type: equipment
Probable_Cause: unspecified-reason
Service_Affecting: False
Context: starlingx
900.616:
Type: Log
Description: System config update auto-apply completed
Entity_Instance_ID: orchestration=system-config-update
Severity: critical
Alarm_Type: equipment
Probable_Cause: unspecified-reason
Service_Affecting: False
Context: starlingx
900.617:
Type: Log
Description: System config update auto-apply abort
Entity_Instance_ID: orchestration=system-config-update
Severity: critical
Alarm_Type: equipment
Probable_Cause: unspecified-reason
Service_Affecting: False
Context: starlingx
900.618:
Type: Log
Description: System config update auto-apply aborting
Entity_Instance_ID: orchestration=system-config-update
Severity: critical
Alarm_Type: equipment
Probable_Cause: unspecified-reason
Service_Affecting: False
Context: starlingx
900.619:
Type: Log
Description: System config update auto-apply abort rejected
Entity_Instance_ID: orchestration=system-config-update
Severity: critical
Alarm_Type: equipment
Probable_Cause: unspecified-reason
Service_Affecting: False
Context: starlingx
900.620:
Type: Log
Description: System config update auto-apply abort failed
Entity_Instance_ID: orchestration=system-config-update
Severity: critical
Alarm_Type: equipment
Probable_Cause: unspecified-reason
Service_Affecting: False
Context: starlingx
900.621:
Type: Log
Description: System config update auto-apply aborted
Entity_Instance_ID: orchestration=system-config-update
Severity: critical
Alarm_Type: equipment
Probable_Cause: unspecified-reason
Service_Affecting: False
Context: starlingx
...