diff --git a/fm-doc/fm_doc/events.yaml b/fm-doc/fm_doc/events.yaml index 55652f96..1b7a33cb 100755 --- a/fm-doc/fm_doc/events.yaml +++ b/fm-doc/fm_doc/events.yaml @@ -1,7 +1,7 @@ --- # -# Copyright (c) 2013-2022 Wind River Systems, Inc. +# Copyright (c) 2013-2023 Wind River Systems, Inc. # # SPDX-License-Identifier: Apache-2.0 # @@ -3125,11 +3125,12 @@ 800.001: Type: Alarm Description: |- - Storage Alarm Condition: - 1 mons down, quorum 1,2 controller-1,storage-0 + Possible data loss. Any mds, mon or osd is unavailable in storage replication group. Entity_Instance_ID: cluster= Severity: [critical, major] - Proposed_Repair_Action: "If problem persists, contact next level of support." + Proposed_Repair_Action: "Manually restart Ceph processes and check the state of the Ceph cluster with + 'ceph -s' + If problem persists, contact next level of support." Maintenance_Action: Inhibit_Alarms: Alarm_Type: equipment @@ -3149,7 +3150,10 @@ Entity_Instance_ID: cluster=.peergroup= Severity: [critical] Proposed_Repair_Action: "Ensure storage hosts from replication group are unlocked and available. + Check replication group state with 'system host-list' Check if OSDs of each storage host are up and running. + Manually restart Ceph processes and check the state of the Ceph OSDs with + 'ceph osd stat' OR 'ceph osd tree' If problem persists, contact next level of support." Maintenance_Action: Inhibit_Alarms: @@ -3169,7 +3173,10 @@ Entity_Instance_ID: cluster=.peergroup= Severity: [major] Proposed_Repair_Action: "Ensure storage hosts from replication group are unlocked and available. + Check replication group state with 'system host-list' Check if OSDs of each storage host are up and running. + Manually restart Ceph processes and check the state of the Ceph OSDs with + 'ceph osd stat' AND/OR 'ceph osd tree' If problem persists, contact next level of support." Maintenance_Action: Inhibit_Alarms: @@ -3298,6 +3305,9 @@ Entity_Instance_ID: .lvmthinpool=/ Severity: critical Proposed_Repair_Action: "Increase Storage Space Allotment for Cinder on the 'lvm' backend. + Try the following commands: + 'vgextend ' or 'vgextend -L + + Check status with 'vgdisplay' Consult the System Administration Manual for more details. If problem persists, contact next level of support." Maintenance_Action: @@ -3318,6 +3328,10 @@ Entity_Instance_ID: storage_backend= Severity: critical Proposed_Repair_Action: "Update backend setting to reapply configuration. + Use the following commands to try again: + 'system storage-backend-delete ' + AND + 'system storage-backend-add ' Consult the System Administration Manual for more details. If problem persists, contact next level of support." Maintenance_Action: