Adding Cluster Connect endpoint network check (OBO endpoint) (#6308)

src/connectedk8s/HISTORY.rst

@@ -2,6 +2,11 @@
 
 Release History
 
+1.3.19
+++++++
+
+* Adding outbound network connectivity check for Cluster Connect (OBO endpoint)
+
 1.3.18
 ++++++
 

src/connectedk8s/azext_connectedk8s/_constants.py

@@ -195,24 +195,26 @@
 Connected_Cluster_Resource = "connected_cluster_resource_snapshot.txt"
 DNS_Check = "dns_check.txt"
 K8s_Cluster_Info = "k8s_cluster_info.txt"
-Outbound_Network_Connectivity_Check = "outbound_network_connectivity_check.txt"
+Outbound_Network_Connectivity_Check_for_onboarding = "outbound_network_connectivity_check_for_onboarding.txt"
+Outbound_Network_Connectivity_Check_for_cluster_connect = "outbound_network_connectivity_check_for_cluster_connect.txt"
 Events_of_Incomplete_Diagnoser_Job = "diagnoser_failure_events.txt"
 # Connect Precheck Diagnoser constants
-Cluster_Diagnostic_Checks_Job_Registry_Path = "mcr.microsoft.com/azurearck8s/helmchart/stable/clusterdiagnosticchecks:0.1.1"
+Cluster_Diagnostic_Checks_Job_Registry_Path = "mcr.microsoft.com/azurearck8s/helmchart/stable/clusterdiagnosticchecks:0.1.2"
 Cluster_Diagnostic_Checks_Helm_Install_Failed_Fault_Type = "Error while installing cluster diagnostic checks helm release"
 Cluster_Diagnostic_Checks_Execution_Failed_Fault_Type = "Error occured while executing cluster diagnostic checks"
 Cluster_Diagnostic_Checks_Release_Cleanup_Failed = "Error occured while cleaning up the cluster diagnostic checks helm release"
 Cluster_Diagnostic_Checks_Job_Not_Scheduled = 'Unable to schedule cluster-diagnostic-checks job'
 Cluster_Diagnostic_Checks_Job_Not_Complete = 'Unable to complete cluster-diagnostic-checks job after scheduling'
 Pre_Onboarding_Diagnostic_Checks_Execution_Failed = 'Exception occured while trying to execute pre-onboarding diagnostic checks'
-Outbound_Connectivity_Check_Failed = "Outbound network connectivity check failed"
+Outbound_Connectivity_Check_Failed_For_Onboarding = "Outbound network connectivity check failed for onboarding"
 DNS_Check_Failed = "DNS Resolution failed"
 Cluster_Diagnostic_Prechecks_Failed = "Cluster diagnostic prechecks failed"
 Cluster_Diagnostic_Prechecks_Incomplete = "Cluster diagnostic prechecks failed to complete"
 Cluster_Diagnostic_Checks_Pod_Description_Save_Failed = 'Failed to save cluster diagnostic checks pod description'
 Cluster_Diagnostic_Checks_Job_Log_Save_Failed = 'Failed to save cluster diagnostic checks job log'
 # Diagnostic Results Name
-Outbound_Connectivity_Check_Result_String = "Outbound Network Connectivity Result:"
+Outbound_Connectivity_Check_Check_String = "Outbound Network Connectivity Check"
+Outbound_Connectivity_Check_Failed_For_Cluster_Connect = "Outbound network connectivity check failed for Cluster Connect"
 DNS_Check_Result_String = "DNS Result:"
 AZ_CLI_ADAL_TO_MSAL_MIGRATE_VERSION = '2.30.0'
 CLIENT_PROXY_VERSION = '1.3.022011'

src/connectedk8s/azext_connectedk8s/_precheckutils.py

@@ -59,18 +59,23 @@ def fetch_diagnostic_checks_results(corev1_api_instance, batchv1_api_instance, h
             cluster_diagnostic_checks_container_log_list = cluster_diagnostic_checks_container_log.split("\n")
             cluster_diagnostic_checks_container_log_list.pop(-1)
             dns_check_log = ""
+            outbound_connectivity_check_log = ""
             counter_container_logs = 1
             # For retrieving only cluster_diagnostic_checks logs from the output
             for outputs in cluster_diagnostic_checks_container_log_list:
-                if consts.Outbound_Connectivity_Check_Result_String in outputs:
+                if consts.Outbound_Connectivity_Check_Check_String in outputs:
                     counter_container_logs = 1
+                    if outbound_connectivity_check_log == "":
+                        outbound_connectivity_check_log += outputs
+                    else:
+                        outbound_connectivity_check_log += "  " + outputs
                 elif consts.DNS_Check_Result_String in outputs:
                     dns_check_log += outputs
                     counter_container_logs = 0
                 elif counter_container_logs == 0:
                     dns_check_log += "  " + outputs
             dns_check, storage_space_available = azext_utils.check_cluster_DNS(dns_check_log, filepath_with_timestamp, storage_space_available, diagnoser_output)
-            outbound_connectivity_check, storage_space_available = azext_utils.check_cluster_outbound_connectivity(cluster_diagnostic_checks_container_log_list[-1], filepath_with_timestamp, storage_space_available, diagnoser_output)
+            outbound_connectivity_check, storage_space_available = azext_utils.check_cluster_outbound_connectivity(outbound_connectivity_check_log, filepath_with_timestamp, storage_space_available, diagnoser_output)
         else:
             return consts.Diagnostic_Check_Incomplete, storage_space_available
 

src/connectedk8s/azext_connectedk8s/_utils.py

@@ -234,25 +234,46 @@ def check_cluster_DNS(dns_check_log, filepath_with_timestamp, storage_space_avai
 def check_cluster_outbound_connectivity(outbound_connectivity_check_log, filepath_with_timestamp, storage_space_available, diagnoser_output):
 
     try:
-        outbound_connectivity_response = outbound_connectivity_check_log[-1:-4:-1]
-        outbound_connectivity_response = outbound_connectivity_response[::-1]
-        if consts.Outbound_Connectivity_Check_Result_String not in outbound_connectivity_check_log:
+        if consts.Outbound_Connectivity_Check_Check_String not in outbound_connectivity_check_log:
             return consts.Diagnostic_Check_Incomplete, storage_space_available
+
+        Outbound_Connectivity_Log_For_Cluster_Connect = outbound_connectivity_check_log.split('  ')[0]
+        # extracting the endpoints for cluster connect feature
+        Cluster_Connect_Precheck_Endpoint_Url = Outbound_Connectivity_Log_For_Cluster_Connect.split(" : ")[1]
+        # extracting the obo endpoint response code from outbound connectivity check
+        Cluster_Connect_Precheck_Endpoint_response_code = Outbound_Connectivity_Log_For_Cluster_Connect.split(" : ")[2]
+
+        if(Cluster_Connect_Precheck_Endpoint_response_code != "000"):
+            if storage_space_available:
+                cluster_connect_outbound_connectivity_check_path = os.path.join(filepath_with_timestamp, consts.Outbound_Network_Connectivity_Check_for_cluster_connect)
+                with open(cluster_connect_outbound_connectivity_check_path, 'w+') as outbound:
+                        outbound.write("Response code " + Cluster_Connect_Precheck_Endpoint_response_code + "\nOutbound network connectivity check to cluster connect precheck endpoints passed successfully.")
+        else:
+            logger.warning("The outbound network connectivity check has failed for the endpoint - " + Cluster_Connect_Precheck_Endpoint_Url + "\nThis will affect the \"cluster-connect\" feature. If you are planning to use \"cluster-connect\" functionality , please ensure outbound connectivity to the above endpoint.\n")
+            telemetry.set_exception(exception='Outbound network connectivity check failed for the Cluster Connect endpoint', fault_type=consts.Outbound_Connectivity_Check_Failed_For_Cluster_Connect, summary="Outbound network connectivity check failed for the Cluster Connect precheck endpoint")
+            if storage_space_available:
+                cluster_connect_outbound_connectivity_check_path = os.path.join(filepath_with_timestamp, consts.Outbound_Network_Connectivity_Check_for_cluster_connect)
+                with open(cluster_connect_outbound_connectivity_check_path, 'w+') as outbound:
+                        outbound.write("Response code " + Cluster_Connect_Precheck_Endpoint_response_code + "\nOutbound connectivity failed for the endpoint:" + Cluster_Connect_Precheck_Endpoint_Url + " ,this is an optional endpoint needed for cluster-connect feature.")
+
+        Onboarding_Precheck_Endpoint_outbound_connectivity_response = outbound_connectivity_check_log[-1:-4:-1]
+        Onboarding_Precheck_Endpoint_outbound_connectivity_response = Onboarding_Precheck_Endpoint_outbound_connectivity_response[::-1]
+
         # Validating if outbound connectiivty is working or not and displaying proper result
-        if(outbound_connectivity_response != "000"):
+        if(Onboarding_Precheck_Endpoint_outbound_connectivity_response != "000"):
             if storage_space_available:
-                outbound_connectivity_check_path = os.path.join(filepath_with_timestamp, consts.Outbound_Network_Connectivity_Check)
+                outbound_connectivity_check_path = os.path.join(filepath_with_timestamp, consts.Outbound_Network_Connectivity_Check_for_onboarding)
                 with open(outbound_connectivity_check_path, 'w+') as outbound:
-                    outbound.write("Response code " + outbound_connectivity_response + "\nOutbound network connectivity check passed successfully.")
+                        outbound.write("Response code " + Onboarding_Precheck_Endpoint_outbound_connectivity_response + "\nOutbound network connectivity check to the onboarding precheck endpoint passed successfully.")
             return consts.Diagnostic_Check_Passed, storage_space_available
         else:
-            logger.warning("Error: We found an issue with outbound network connectivity from the cluster.\nPlease ensure to meet the following network requirements 'https://docs.microsoft.com/en-us/azure/azure-arc/kubernetes/quickstart-connect-cluster?tabs=azure-cli#meet-network-requirements' \nIf your cluster is behind an outbound proxy server, please ensure that you have passed proxy parameters during the onboarding of your cluster.\nFor more details visit 'https://docs.microsoft.com/en-us/azure/azure-arc/kubernetes/quickstart-connect-cluster?tabs=azure-cli#connect-using-an-outbound-proxy-server' \n")
-            diagnoser_output.append("Error: We found an issue with outbound network connectivity from the cluster.\nPlease ensure to meet the following network requirements 'https://docs.microsoft.com/en-us/azure/azure-arc/kubernetes/quickstart-connect-cluster?tabs=azure-cli#meet-network-requirements' \nIf your cluster is behind an outbound proxy server, please ensure that you have passed proxy parameters during the onboarding of your cluster.\nFor more details visit 'https://docs.microsoft.com/en-us/azure/azure-arc/kubernetes/quickstart-connect-cluster?tabs=azure-cli#connect-using-an-outbound-proxy-server' \n")
+            logger.warning("Error: We found an issue with outbound network connectivity from the cluster to the endpoints required for onboarding.\nPlease ensure to meet the following network requirements 'https://docs.microsoft.com/en-us/azure/azure-arc/kubernetes/quickstart-connect-cluster?tabs=azure-cli#meet-network-requirements' \nIf your cluster is behind an outbound proxy server, please ensure that you have passed proxy parameters during the onboarding of your cluster.\nFor more details visit 'https://docs.microsoft.com/en-us/azure/azure-arc/kubernetes/quickstart-connect-cluster?tabs=azure-cli#connect-using-an-outbound-proxy-server' \n")
+            diagnoser_output.append("Error: We found an issue with outbound network connectivity from the cluster to the endpoints required for onboarding.\nPlease ensure to meet the following network requirements 'https://docs.microsoft.com/en-us/azure/azure-arc/kubernetes/quickstart-connect-cluster?tabs=azure-cli#meet-network-requirements' \nIf your cluster is behind an outbound proxy server, please ensure that you have passed proxy parameters during the onboarding of your cluster.\nFor more details visit 'https://docs.microsoft.com/en-us/azure/azure-arc/kubernetes/quickstart-connect-cluster?tabs=azure-cli#connect-using-an-outbound-proxy-server' \n")
             if storage_space_available:
-                outbound_connectivity_check_path = os.path.join(filepath_with_timestamp, consts.Outbound_Network_Connectivity_Check)
+                outbound_connectivity_check_path = os.path.join(filepath_with_timestamp, consts.Outbound_Network_Connectivity_Check_for_onboarding)
                 with open(outbound_connectivity_check_path, 'w+') as outbound:
-                    outbound.write("Response code " + outbound_connectivity_response + "\nWe found an issue with Outbound network connectivity from the cluster.")
-            telemetry.set_exception(exception='Outbound network connectivity check failed', fault_type=consts.Outbound_Connectivity_Check_Failed, summary="Outbound network connectivity check failed in the cluster")
+                    outbound.write("Response code " + Onboarding_Precheck_Endpoint_outbound_connectivity_response + "\nWe found an issue with Outbound network connectivity from the cluster required for onboarding.")
+            telemetry.set_exception(exception='Outbound network connectivity check failed for onboarding', fault_type=consts.Outbound_Connectivity_Check_Failed_For_Onboarding, summary="Outbound network connectivity check for onboarding failed in the cluster")
             return consts.Diagnostic_Check_Failed, storage_space_available
 
     # For handling storage or OS exception that may occur during the execution

src/connectedk8s/setup.py

@@ -17,7 +17,7 @@
 # TODO: Confirm this is the right version number you want and it matches your
 # HISTORY.rst entry.
 
-VERSION = '1.3.18'
+VERSION = '1.3.19'
 
 # The full list of classifiers is available at
 # https://pypi.python.org/pypi?%3Aaction=list_classifiers