From 65a8ff3d66bbd87f83136ab6b587bad8e531c0b3 Mon Sep 17 00:00:00 2001
From: "Zhang Rong(Jon)" <rong.zhang@windriver.com>
Date: Tue, 22 Aug 2023 20:52:21 +0800
Subject: [PATCH] Add alarm id, definition for system peer and subcloud peer
 group

The alarm 280.004 is added and will be raised when the system peer
connection failure has been detected, and will be cleared when the
system peer connection has been restored.
The alarm 280.005 is added and will be raised when the a subcloud peer
group is being managed by a remote system with a lower priority, and
will be cleared when the subclouds belonging to the subcloud peer group
have been migrated back to current system.

Test Plan:
 PASS - Verify successful tox test and package build

Story: 2010852
Task: 48492
Change-Id: I3068676933c0446a88bd4290277456cd0962f941
Signed-off-by: Zhang Rong(Jon) <rong.zhang@windriver.com>
---
 doc/source/conf.py                |  2 +-
 fm-api/source/fm_api/constants.py |  4 ++++
 fm-doc/fm_doc/events.yaml         | 36 +++++++++++++++++++++++++++++++
 3 files changed, 41 insertions(+), 1 deletion(-)

diff --git a/doc/source/conf.py b/doc/source/conf.py
index 0b18553e..abf687c1 100644
--- a/doc/source/conf.py
+++ b/doc/source/conf.py
@@ -63,7 +63,7 @@ openstackdocs_auto_name = False
 #
 # This is also used if you do content translation via gettext catalogs.
 # Usually you set "language" from the command line for these cases.
-language = None
+language = 'en' # Default value
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
diff --git a/fm-api/source/fm_api/constants.py b/fm-api/source/fm_api/constants.py
index 5304c8fe..a890215e 100755
--- a/fm-api/source/fm_api/constants.py
+++ b/fm-api/source/fm_api/constants.py
@@ -40,6 +40,8 @@ FM_ENTITY_TYPE_IMAGE_CONVERSION = 'fs_name'
 FM_ENTITY_TYPE_SUBCLOUD = 'subcloud'
 FM_ENTITY_TYPE_APPLICATION = 'k8s_application'
 FM_ENTITY_TYPE_CERTIFICATE = 'certificate'
+FM_ENTITY_TYPE_SYSTEM_PEER = 'system_peer'
+FM_ENTITY_TYPE_SUBCLOUD_PEER_GROUP = 'subcloud_peer_group'
 
 # alarm service sub entity values
 FM_SERVICE_NETWORKING = 'networking'
@@ -130,6 +132,8 @@ FM_LOG_ID_HYPERVISOR_STATE_CHANGE = ALARM_GROUP_HYPERVISOR + ".001"
 FM_ALARM_ID_DC_SUBCLOUD_OFFLINE = ALARM_GROUP_DISTRIBUTED_CLOUD + ".001"
 FM_ALARM_ID_DC_SUBCLOUD_RESOURCE_OUT_OF_SYNC = ALARM_GROUP_DISTRIBUTED_CLOUD + ".002"
 FM_ALARM_ID_DC_SUBCLOUD_BACKUP_FAILED = ALARM_GROUP_DISTRIBUTED_CLOUD + ".003"
+FM_ALARM_ID_DC_SYSTEM_PEER_HEARTBEAT_FAILED = ALARM_GROUP_DISTRIBUTED_CLOUD + ".004"
+FM_ALARM_ID_DC_SUBCLOUD_PEER_GROUP_NOT_MANAGED = ALARM_GROUP_DISTRIBUTED_CLOUD + ".005"
 
 # HA alarm id
 FM_ALARM_ID_HA_SERVICE_GROUP_STATE = ALARM_GROUP_HA + ".001"
diff --git a/fm-doc/fm_doc/events.yaml b/fm-doc/fm_doc/events.yaml
index 368f1717..e57630b5 100755
--- a/fm-doc/fm_doc/events.yaml
+++ b/fm-doc/fm_doc/events.yaml
@@ -1113,6 +1113,42 @@
     Degrade_Affecting_Severity: none
     Context: none
 
+280.004:
+    Type: Alarm
+    Description: |-
+        Critical: Peer <peer_uuid> is in disconnected state. The following subcloud peer groups are impacted: <peer-groups>.
+        Major:    Peer <peer_uuid> connections in disconnected state.
+    Entity_Instance_ID: |-
+        peer=<peer_uuid>
+    Severity: [critical, major]
+    Proposed_Repair_Action: "Check the connectivity between the current system and the reported peer site. If the peer system is down, migrate the affected peer group(s) to the current system for continued subcloud management."
+    Maintenance_Action:
+    Inhibit_Alarms:
+    Alarm_Type: communication
+    Probable_Cause: unknown
+    Service_Affecting: False
+    Suppression: True
+    Management_Affecting_Severity: none
+    Degrade_Affecting_Severity: none
+    Context: starlingx
+
+280.005:
+    Type: Alarm
+    Description: |-
+        Subcloud peer group <peer_group_name> is managed by remote system <peer_uuid> with a lower priority.
+    Entity_Instance_ID: peer_group=<peer_group_name>,peer=<peer_uuid>
+    Severity: [major]
+    Proposed_Repair_Action: "Check the reported peer group state. Migrate it back to the current system if the state is 'rehomed' and the current system is stable. Otherwise, wait until these conditions are met."
+    Maintenance_Action:
+    Inhibit_Alarms: False
+    Alarm_Type: other
+    Probable_Cause: unknown
+    Service_Affecting: False
+    Suppression: True
+    Management_Affecting_Severity: none
+    Degrade_Affecting_Severity: none
+    Context: starlingx
+
 #---------------------------------------------------------------------------
 #   NETWORK
 #---------------------------------------------------------------------------