Azure Arc Diagnostic

src/connectedk8s/azext_connectedk8s/_constants.py

@@ -19,6 +19,8 @@
 Azure_ChinaCloudName = 'AZURECHINACLOUD'
 Azure_DogfoodCloudName = 'AZUREDOGFOOD'
 PublicCloud_OriginalName = 'AZURECLOUD'
+MSI_Certificate_Secret_Name = 'azure-identity-certificate'
+KAP_Certificate_Secret_Name = 'kube-aad-proxy-certificate'
 USGovCloud_OriginalName = 'AZUREUSGOVERNMENT'
 Dogfood_RMEndpoint = 'https://api-dogfood.resources.windows-int.net/'
 Helm_Environment_File_Fault_Type = 'helm-environment-file-error'
@@ -118,6 +120,58 @@
 Get_PublicKey_Info_Fault_Type = 'Error while fetching the PoP publickey information from client proxy'
 PoP_Public_Key_Expried_Fault_Type = 'The PoP public key used to generate the at has expired'
 Post_AT_To_ClientProxy_Failed_Fault_Type = 'Failed to post access token to client proxy'
+Kubectl_Get_Events_Failed_Fault_Type = "Error while doing kubectl get events"
+Fetch_Arc_Agent_Logs_Failed_Fault_Type = "Error occured in arc agents logger"
+Fetch_Arc_Agents_Events_Logs_Failed_Fault_Type = "Error occured in arc agents events logger"
+Fetch_Arc_Deployment_Logs_Failed_Fault_Type = "Error occured in deployments logger"
+Agent_State_Check_Fault_Type = "Error occured while performing the agent state check"
+Agent_Version_Check_Fault_Type = "Error occured while performing the agent version check"
+Diagnoser_Job_Failed_Fault_Type = "Error while executing Diagnoser Job"
+Diagnoser_Container_Check_Failed_Fault_Type = "Error occured while performing the diagnoser container checks"
+Cluster_DNS_Check_Fault_Type = "Error occured while performing cluster DNS check"
+Outbound_Connectivity_Check_Fault_Type = "Error occured while performing outbound connectivity check in the cluster"
+MSI_Cert_Check_Fault_Type = "Error occurred while trying to perform MSI ceritificate presence check"
+Cluster_Security_Policy_Check_Fault_Type = "Error occured while performing cluster security policy check"
+KAP_Cert_Check_Fault_Type = "Error occurred while trying to perform KAP ceritificate presence check"
+MSI_Cert_Expiry_Check_Fault_Type = "Error occured while trying to perform the MSI cert expiry check"
+Diagnostics_Folder_Creation_Failed_Fault_Type = "Error while trying to create diagnostic logs folder"
+Describe_Stuck_Agents_Fault_Type = "Error occured while storing the description of non running agents"
+No_Storage_Space_Available_Fault_Type = "No space left on device"
+Connected_Cluster_Resource_Fetch_Fault_Type = "Error occured while fetching the Get output of connected cluster"
+Diagnoser_Result_Fault_Type = "Error while storing the diagnoser results"
+Kubectl_Cluster_Info_Failed_Fault_Type = "Error while doing kubectl cluster-info"
+Fetch_Kubectl_Cluster_Info_Fault_Type = "Error occured while fetching cluster-info"
+Fetch_Kubectl_Cluster_Info = "kubectl_cluster_info"
+Diagnostic_Check_Passed = "Passed"
+Diagnostic_Check_Failed = "Failed"
+Diagnostic_Check_Incomplete = "Incomplete"
+# Name of the checks and operations
+Retrieve_Arc_Agents_Event_Logs = "retrieved_arc_agents_event_logs"
+Retrieve_Arc_Agents_Logs = "retrieved_arc_agents_logs"
+Retrieve_Deployments_Logs = "retrieved_deployments_logs"
+Fetch_Connected_Cluster_Resource = "fetch_connected_cluster_resource"
+Storing_Diagnoser_Results_Logs = "storing_diagnoser_results_logs"
+MSI_Cert_Expiry_Check = "msi_cert_expiry_check"
+KAP_Security_Policy_Check = "kap_security_policy_check"
+KAP_Cert_Check = "kap_cert_check"
+Diagnoser_Check = "diagnoser_check"
+MSI_Cert_Check = "msi_cert_check"
+Agent_Version_Check = "agent_version_check"
+Arc_Agent_State_Check = "arc_agent_state_check"
+# Diagnoser files name
+Arc_Diagnostic_Logs = "arc_diagnostic_logs"
+Agent_State = "Agent_State.txt"
+Arc_Agents_Events = "Arc_Agents_Events.txt"
+Diagnoser_Results = "Diagnoser_Results.txt"
+Connected_Cluster_Resource = "Connected_cluster_resource.txt"
+DNS_Check = "DNS_Check.txt"
+K8s_Cluster_Info = "K8s_Cluster_Info.txt"
+Outbound_Network_Connectivity_Check = "Outbound_Network_Connectivity_Check.txt"
+Events_of_Incomplete_Diagnoser_Job = "Events_of_Incomplete_Diagnoser_Job.txt"
+
+# Diagnostic Results Name
+Outbound_Connectivity_Check_Result_String = "Outbound Network Connectivity Result:"
+DNS_Check_Result_String = "DNS Result:"
 AZ_CLI_ADAL_TO_MSAL_MIGRATE_VERSION = '2.30.0'
 CLIENT_PROXY_VERSION = '1.3.019103'
 API_SERVER_PORT = 47011
@@ -133,3 +187,4 @@
 CSP_Storage_Url_Mooncake = "https://k8sconnectcsp.blob.core.chinacloudapi.cn"
 HELM_STORAGE_URL = "https://k8connecthelm.azureedge.net"
 HELM_VERSION = 'v3.6.3'
+Download_And_Install_Kubectl_Fault_Type = "Failed to download and install kubectl"

src/connectedk8s/azext_connectedk8s/_help.py

@@ -121,3 +121,11 @@
   - name: Disable multiple features.
     text: az connectedk8s disable-features -n clusterName -g resourceGroupName --features custom-locations azure-rbac
 """
+
+helps['connectedk8s troubleshoot'] = """
+  type: command
+  short-summary: Performs diagnostic checks on the arc-enabled kubernetes cluster.
+  examples:
+  - name: Executes diagnostic checks on an arc enabled kubernetes cluster
+    text: az connectedk8s troubleshoot -n clusterName -g resourceGroupName
+"""

src/connectedk8s/azext_connectedk8s/_params.py

@@ -89,3 +89,9 @@ def load_arguments(self, _):
         c.argument('context_name', options_list=['--kube-context'], help='If specified, overwrite the default context name.')
         c.argument('path', options_list=['--file', '-f'], type=file_type, completer=FilesCompleter(), default=os.path.join(os.path.expanduser('~'), '.kube', 'config'), help="Kubernetes configuration file to update. If not provided, updates the file '~/.kube/config'. Use '-' to print YAML to stdout instead.")
         c.argument('api_server_port', options_list=['--port'], help='Port used for accessing connected cluster.')
+
+    with self.argument_context('connectedk8s troubleshoot') as c:
+        c.argument('tags', tags_type)
+        c.argument('cluster_name', options_list=['--name', '-n'], help='The name of the connected cluster.')
+        c.argument('kube_config', options_list=['--kube-config'], help='Path to the kube config file.')
+        c.argument('kube_context', options_list=['--kube-context'], help='Kubconfig context from current machine.')