From 0e1321913bd4e16f3abb46d8d5a4ab23a5374727 Mon Sep 17 00:00:00 2001 From: Agustin Carranza Date: Thu, 2 Feb 2023 17:15:07 -0300 Subject: [PATCH] Add ceph commands in the 800 series alarm document When a 800-Series alarm occurs, users refer to the documentation to know what kind of error is shown. But sometimes that is not enough information. The output of some commands can be useful information and could save time when solving issues related to the storage alarms. Closes-bug: 2004601 Test plan PASS: * Build fm packages and deploy an ISO containing new fm packages. * Trigger alarms that were modified by this commit, (e.g. shutdown a controller). * Run fm alarm-list --uuid and copy the uuid of a 800-series alarm. * Run fm alarm-show and check that the field has changed. Signed-off-by: Agustin Carranza Change-Id: I94e2719b55b4fc14b692439526b5b47204460ac7 --- fm-doc/fm_doc/events.yaml | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) 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: