starlingx/fault
Code Issues Proposed changes

Add alarm IDs for expiring-soon & expired certificates

Browse Source 
Added two new alarm IDs and details for expiring-soon and
expired certificates.

Story: 2008946
Task: 43049

Signed-off-by: Sabeel Ansari <Sabeel.Ansari@windriver.com>
Change-Id: I61cb835c38473cef61238de8cf4a21361e123da4
This commit is contained in:
Sabeel Ansari 2021-08-18 15:02:35 -04:00
parent 83f5caa9b7
commit cdf8dc6f6e
2 changed files with 61 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
fm-api/fm_api/constants.py
View File

@ -39,6 +39,7 @@ FM_ENTITY_TYPE_STORAGE_BACKEND = 'storage_backend'
FM_ENTITY_TYPE_IMAGE_CONVERSION = 'fs_name'
FM_ENTITY_TYPE_SUBCLOUD = 'subcloud'
FM_ENTITY_TYPE_APPLICATION = 'k8s_application'
FM_ENTITY_TYPE_CERTIFICATE = 'certificate'
# alarm service sub entity values
FM_SERVICE_NETWORKING = 'networking'
@ -301,13 +302,16 @@ FM_ALARM_ID_KUBE_ROOTCA_UPDATE_IN_PROGRESS = ALARM_GROUP_SW_MGMT + ".008"
FM_LOG_ID_INVALID_PASSWORD = ALARM_GROUP_SECURITY + ".001"
FM_LOG_ID_USER_LOCKOUT = ALARM_GROUP_SECURITY + ".002"
# Security alarm id
FM_ALARM_ID_TPM_INIT = ALARM_GROUP_SECURITY + ".100"
# Security nonstandard certificate in use for patching alarm id
FM_ALARM_ID_NONSTANDARD_CERT_PATCH = ALARM_GROUP_SECURITY + ".101"
# Security ExpiringSoon & Expired Certificates
FM_ALARM_ID_CERT_EXPIRING_SOON = ALARM_GROUP_SECURITY + ".200"
FM_ALARM_ID_CERT_EXPIRED = ALARM_GROUP_SECURITY + ".210"
# Software Update Orchestration
FM_ALARM_ID_SW_PATCH_AUTO_APPLY_INPROGRESS = ALARM_GROUP_SW_MGMT + ".101"
FM_ALARM_ID_SW_PATCH_AUTO_APPLY_ABORTING = ALARM_GROUP_SW_MGMT + ".102"
@ -496,6 +500,7 @@ ALARM_PROBABLE_CAUSE_73 = 'key-expired'
ALARM_PROBABLE_CAUSE_74 = 'out-of-hours-activity'
ALARM_PROBABLE_CAUSE_75 = 'configuration-out-of-date'
ALARM_PROBABLE_CAUSE_76 = 'configuration-provisioning-required'
ALARM_PROBABLE_CAUSE_77 = 'certificate-expiration'
ALARM_PROBABLE_CAUSE_UNKNOWN = 'unknown'
ALARM_STATE = [FM_ALARM_STATE_SET, FM_ALARM_STATE_CLEAR,
@ -551,6 +556,7 @@ ALARM_PROBABLE_CAUSE = [ALARM_PROBABLE_CAUSE_1, ALARM_PROBABLE_CAUSE_2,
ALARM_PROBABLE_CAUSE_71, ALARM_PROBABLE_CAUSE_72,
ALARM_PROBABLE_CAUSE_73, ALARM_PROBABLE_CAUSE_74,
ALARM_PROBABLE_CAUSE_75, ALARM_PROBABLE_CAUSE_76,
ALARM_PROBABLE_CAUSE_77,
ALARM_PROBABLE_CAUSE_UNKNOWN]

54
fm-doc/fm_doc/events.yaml
View File

@ -1354,6 +1354,60 @@
Management_Affecting_Severity: none
Degrade_Affecting_Severity: none
500.200:
Type: Alarm
Description: |-
Certificate ‘system certificate-show <uuid>' (mode=<ssl/ssl_ca/docker_registry/openstack/openstack_ca>) expiring soon on <date>.
OR
Certificate ‘<Namespace>/<Certificate/Secret>’ expiring soon on <date>.
OR
Certificate ‘<k8sRootCA/EtcdCA>’ expiring soon on <date>.
Entity_Instance_ID: |-
system.certificate.mode=<mode>.uuid=<uuid>
OR
namespace=<namespace-name>.certificate=<certificate-name>
OR
namespace=<namespace-name>.secret=<secret-name>
OR
system.certificate.k8sRootCA
Severity: major
Proposed_Repair_Action: Renew certificate for the entity identified
Maintenance_Action:
Inhibit_Alarms:
Alarm_Type: operational-violation
Probable_Cause: certificate-expiration
Service_Affecting: False
Suppression: False
Management_Affecting_Severity: none
Degrade_Affecting_Severity: none
500.210:
Type: Alarm
Description: |-
Certificate ‘system certificate-show <uuid>' (mode=<ssl/ssl_ca/docker_registry/openstack/openstack_ca>) expired.
OR
Certificate ‘<Namespace>/<Certificate/Secret>’ expired.
OR
Certificate ‘<k8sRootCA/EtcdRootCA>’ expired.
Entity_Instance_ID: |-
system.certificate.mode=<mode>.uuid=<uuid>
OR
namespace=<namespace-name>.certificate=<certificate-name>
OR
namespace=<namespace-name>.secret=<secret-name>
OR
system.certificate.k8sRootCA
Severity: critical
Proposed_Repair_Action: Renew certificate for the entity identified
Maintenance_Action:
Inhibit_Alarms:
Alarm_Type: operational-violation
Probable_Cause: certificate-expiration
Service_Affecting: False
Suppression: False
Management_Affecting_Severity: none
Degrade_Affecting_Severity: none
500.500:
Type: Log
Description: "Host <host_name> has IMA Appraisal failure for service <service> when executing <file>, reason = <reason_text>]"