diff --git a/fm-doc/fm_doc/events.yaml b/fm-doc/fm_doc/events.yaml index 507334ea..58c4bb89 100755 --- a/fm-doc/fm_doc/events.yaml +++ b/fm-doc/fm_doc/events.yaml @@ -895,6 +895,21 @@ #--------------------------------------------------------------------------- # VM Compute Services #--------------------------------------------------------------------------- +270.001: + Type: Alarm + Description: "Host compute services failure[, reason = ]" + Entity_Instance_ID: host=.services=compute + Severity: critical + Proposed_Repair_Action: Wait for host services recovery to complete; if problem persists contact next level of support + Maintenance_Action: + Inhibit_Alarms: + Alarm_Type: processing-error + Probable_Cause: unspecified-reason + Service_Affecting: True + Suppression: True + Management_Affecting_Severity: warning + Degrade_Affecting_Severity: none + 270.101: Type: Log Description: "Host compute services failure[, reason = ]" @@ -1385,7 +1400,7 @@ OR system.certificate.k8sRootCA Severity: major - Proposed_Repair_Action: Check certificate expiration time. Renew certificate for the entity identified. + Proposed_Repair_Action: Renew certificate for the entity identified Maintenance_Action: Inhibit_Alarms: Alarm_Type: operational-violation @@ -1412,7 +1427,7 @@ OR system.certificate.k8sRootCA Severity: critical - Proposed_Repair_Action: Check certificate expiration time. Renew certificate for the entity identified. + Proposed_Repair_Action: Renew certificate for the entity identified Maintenance_Action: Inhibit_Alarms: Alarm_Type: operational-violation @@ -2773,8 +2788,7 @@ Description: "Application Apply Failure" Entity_Instance_ID: k8s_application= Severity: major - Proposed_Repair_Action: "Retry applying the application. Check application is managed by the system application framework. - If the issue persists, please check system inventory log for cause." + Proposed_Repair_Action: "Retry applying the application. If the issue persists, please check system inventory log for cause." Maintenance_Action: Inhibit_Alarms: Alarm_Type: processing-error @@ -3069,10 +3083,10 @@ 900.002: Type: Alarm - Description: Patch host install failure. Command "sw-patch host-install" failed. + Description: Patch host install failure. Entity_Instance_ID: host= Severity: major - Proposed_Repair_Action: Undo patching operation. Check patch logs on the target host (i.e. /var/log/patching.log) + Proposed_Repair_Action: Undo patching operation. Maintenance_Action: Inhibit_Alarms: Alarm_Type: environmental @@ -3084,7 +3098,7 @@ 900.003: Type: Alarm - Description: A patch with state 'obsolete' in its metadata has been uploaded. + Description: Obsolete patch in system. Entity_Instance_ID: host=controller Severity: warning Proposed_Repair_Action: Remove and delete obsolete patches. @@ -3099,7 +3113,7 @@ 900.004: Type: Alarm - Description: The upgrade and running software version do not match. Command host-upgrade failed. + Description: Host version mismatch. Entity_Instance_ID: host= Severity: major Proposed_Repair_Action: Reinstall host to update applied load. @@ -3174,7 +3188,7 @@ 900.009: Type: Alarm - Description: Kubernetes root CA update aborted, certificates may not be fully updated. Command "system kube-rootca-update-abort" has been run. + Description: Kubernetes root CA update aborted, certificates may not be fully updated. Entity_Instance_ID: host=controller Severity: minor Proposed_Repair_Action: Fully update certificates by a new root CA update. @@ -3219,7 +3233,7 @@ 900.103: Type: Alarm - Description: Software patch auto-apply failed. Command "sw-manager patch-strategy apply" failed. + Description: Software patch auto-apply failed Entity_Instance_ID: orchestration=sw-patch Severity: critical Proposed_Repair_Action: Attempt to apply software patches manually; if problem persists contact next level of support @@ -3363,7 +3377,7 @@ 900.203: Type: Alarm - Description: Software upgrade auto-apply failed. Command "sw-manager update-strategy apply" failed + Description: Software upgrade auto-apply failed Entity_Instance_ID: orchestration=sw-upgrade Severity: critical Proposed_Repair_Action: Attempt to apply software upgrade manually; if problem persists contact next level of support @@ -3507,7 +3521,7 @@ 900.303: Type: Alarm - Description: Firmware Update auto-apply failed. Command "sw-manager kube-rootca-update-strategy apply" failed. + Description: Firmware Update auto-apply failed Entity_Instance_ID: orchestration=fw-update Severity: critical Proposed_Repair_Action: Attempt to apply firmware update manually; if problem persists contact next level of support @@ -3795,7 +3809,7 @@ 900.503: Type: Alarm - Description: Kubernetes rootca update auto-apply failed. Command "sw-manager kube-upgrade-strategy apply" failed. + Description: Kubernetes rootca update auto-apply failed Entity_Instance_ID: orchestration=kube-rootca-update Severity: critical Proposed_Repair_Action: Attempt to apply kubernetes rootca update manually; if problem persists contact next level of support