starlingx
/
fault
Code Issues Proposed changes

Add alarm id for resources out of sync 

This commit adds a new alarm id and definition for resources
that has INSYNC=False.

The alarm will be raised when a resource is not
synchronized during a process of update. It will be cleared when
the resource is synchronized again.

Test Plan:
 - Verify successful tox test and package build
 - Verify the alarm can be raised using FmClientCli

Story: 2010719
Task: 47910

Change-Id: I24a976ed4beaa8248df25fd97eeee27f5754b969
Signed-off-by: Enzo Candotti <enzo.candotti@windriver.com>
This commit is contained in:
Enzo Candotti 2023-04-26 15:18:56 -03:00
parent dad8caed91
commit a891bdcfd0
2 changed files with 22 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
fm-api/source/fm_api/constants.py
View File

@ -51,6 +51,7 @@ ALARM_GROUP_GENERAL = "100"
ALARM_GROUP_MAINTENANCE = "200"
ALARM_GROUP_BACKUP_RESTORE = "210"
ALARM_GROUP_SYSCONFIG = "250"
ALARM_GROUP_DEPLOYMENT_MANAGER = "260"
ALARM_GROUP_HOST_SERVICES = "270"
ALARM_GROUP_HYPERVISOR = "275"
ALARM_GROUP_DISTRIBUTED_CLOUD = "280"
@ -112,6 +113,11 @@ FM_ALARM_ID_STORAGE_BACKEND_FAILED = ALARM_GROUP_STORAGE + ".104"
# Kubernetes Resource Alarms
FM_ALARM_ID_K8S_RESOURCE_PV = ALARM_GROUP_K8S + ".001"
# Deployment Manager Monitor alarm id
FM_ALARM_ID_UNRECONCILED_RESOURCE = ALARM_GROUP_DEPLOYMENT_MANAGER + ".001"
FM_ALARM_ID_UNSYNCHRONIZED_RESOURCE = ALARM_GROUP_DEPLOYMENT_MANAGER + ".002"
# Host-Services log id
FM_LOG_ID_HOST_SERVICES_FAILED = ALARM_GROUP_HOST_SERVICES + ".101"
FM_LOG_ID_HOST_SERVICES_ENABLED = ALARM_GROUP_HOST_SERVICES + ".102"

16
fm-doc/fm_doc/events.yaml
View File

@ -983,6 +983,22 @@
Degrade_Affecting_Severity: none
Context: starlingx
260.002:
Type: Alarm
Description: "Deployment Manager resource not synchronized: <name>"
Entity_Instance_ID: resource=<crd-resource>,name=<resource-name>
Severity: minor
Proposed_Repair_Action: Monitor and if condition persists, validate deployment configuration.
Maintenance_Action:
Inhibit_Alarms:
Alarm_Type: operational-violation
Probable_Cause: configuration-out-of-date
Service_Affecting: False
Suppression: True
Management_Affecting_Severity: warning
Degrade_Affecting_Severity: none
Context: starlingx
#---------------------------------------------------------------------------
# VM Compute Services
#---------------------------------------------------------------------------