Common cerberus

krkn/cerberus/setup.py

@@ -2,19 +2,33 @@
 import requests
 import sys
 import json
+from krkn_lib.utils.functions import get_yaml_item_value
 
+check_application_routes = ""
+cerberus_url = None
+exit_on_failure = False
+cerberus_enabled = False
 
-def get_status(config, start_time, end_time):
+def set_url(config):
+    global exit_on_failure
+    exit_on_failure = get_yaml_item_value(config["kraken"], "exit_on_failure", False)
+    global cerberus_enabled
+    cerberus_enabled = get_yaml_item_value(config["cerberus"],"cerberus_enabled", False)
+    if cerberus_enabled:
+        global cerberus_url
+        cerberus_url = get_yaml_item_value(config["cerberus"],"cerberus_url", "")
+        global check_application_routes
+        check_application_routes = \
+            get_yaml_item_value(config["cerberus"],"check_applicaton_routes","")
+
+def get_status(start_time, end_time):
     """
     Get cerberus status
     """
     cerberus_status = True
     check_application_routes = False
     application_routes_status = True
-    if config["cerberus"]["cerberus_enabled"]:
-        cerberus_url = config["cerberus"]["cerberus_url"]
-        check_application_routes = \
-            config["cerberus"]["check_applicaton_routes"]
+    if cerberus_enabled:
         if not cerberus_url:
             logging.error(
                 "url where Cerberus publishes True/False signal "
@@ -61,40 +75,38 @@ def get_status(config, start_time, end_time):
     return cerberus_status
 
 
-def publish_kraken_status(config, failed_post_scenarios, start_time, end_time):
+def publish_kraken_status( start_time, end_time):
     """
     Publish kraken status to cerberus
     """
-    cerberus_status = get_status(config, start_time, end_time)
+    cerberus_status = get_status(start_time, end_time)
     if not cerberus_status:
-        if failed_post_scenarios:
-            if config["kraken"]["exit_on_failure"]:
-                logging.info(
-                    "Cerberus status is not healthy and post action scenarios "
-                    "are still failing, exiting kraken run"
-                )
-                sys.exit(1)
-            else:
-                logging.info(
-                    "Cerberus status is not healthy and post action scenarios "
-                    "are still failing"
-                )
+        if exit_on_failure:
+            logging.info(
+                "Cerberus status is not healthy and post action scenarios "
+                "are still failing, exiting kraken run"
+            )
+            sys.exit(1)
+        else:
+            logging.info(
+                "Cerberus status is not healthy and post action scenarios "
+                "are still failing"
+            )
     else:
-        if failed_post_scenarios:
-            if config["kraken"]["exit_on_failure"]:
-                logging.info(
-                    "Cerberus status is healthy but post action scenarios "
-                    "are still failing, exiting kraken run"
-                )
-                sys.exit(1)
-            else:
-                logging.info(
-                    "Cerberus status is healthy but post action scenarios "
-                    "are still failing"
-                )
+        if exit_on_failure:
+            logging.info(
+                "Cerberus status is healthy but post action scenarios "
+                "are still failing, exiting kraken run"
+            )
+            sys.exit(1)
+        else:
+            logging.info(
+                "Cerberus status is healthy but post action scenarios "
+                "are still failing"
+            )
 
 
-def application_status(cerberus_url, start_time, end_time):
+def application_status( start_time, end_time):
     """
     Check application availability
     """

krkn/scenario_plugins/abstract_scenario_plugin.py

@@ -4,7 +4,7 @@
 from krkn_lib.models.telemetry import ScenarioTelemetry
 from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
 
-from krkn import utils
+from krkn import utils, cerberus
 
 
 class AbstractScenarioPlugin(ABC):
@@ -13,7 +13,6 @@ def run(
         self,
         run_uuid: str,
         scenario: str,
-        krkn_config: dict[str, any],
         lib_telemetry: KrknTelemetryOpenshift,
         scenario_telemetry: ScenarioTelemetry,
     ) -> int:
@@ -76,10 +75,10 @@ def run_scenarios(
                 logging.info(
                     f"Running {self.__class__.__name__}: {self.get_scenario_types()} -> {scenario_config}"
                 )
+                start_time = int(time.time())
                 return_value = self.run(
                     run_uuid,
                     scenario_config,
-                    krkn_config,
                     telemetry,
                     scenario_telemetry,
                 )
@@ -110,6 +109,9 @@ def run_scenarios(
             if scenario_telemetry.exit_status != 0:
                 failed_scenarios.append(scenario_config)
             scenario_telemetries.append(scenario_telemetry)
+            end_time = int(time.time())
+            cerberus.publish_kraken_status(start_time, end_time)
             logging.info(f"wating {wait_duration} before running the next scenario")
             time.sleep(wait_duration)
+
         return failed_scenarios, scenario_telemetries

krkn/scenario_plugins/application_outage/application_outage_scenario_plugin.py

@@ -14,11 +14,9 @@ def run(
         self,
         run_uuid: str,
         scenario: str,
-        krkn_config: dict[str, any],
         lib_telemetry: KrknTelemetryOpenshift,
         scenario_telemetry: ScenarioTelemetry,
     ) -> int:
-        wait_duration = krkn_config["tunings"]["wait_duration"]
         try:
             with open(scenario, "r") as f:
                 app_outage_config_yaml = yaml.full_load(f)
@@ -68,14 +66,8 @@ def run(
                     "kraken-deny", namespace
                 )
 
-                logging.info(
-                    "End of scenario. Waiting for the specified duration: %s"
-                    % wait_duration
-                )
-                time.sleep(wait_duration)
-
                 end_time = int(time.time())
-                cerberus.publish_kraken_status(krkn_config, [], start_time, end_time)
+
         except Exception as e:
             logging.error(
                 "ApplicationOutageScenarioPlugin exiting due to Exception %s" % e

krkn/scenario_plugins/arcaflow/arcaflow_scenario_plugin.py

@@ -15,7 +15,6 @@ def run(
         self,
         run_uuid: str,
         scenario: str,
-        krkn_config: dict[str, any],
         lib_telemetry: KrknTelemetryOpenshift,
         scenario_telemetry: ScenarioTelemetry,
     ) -> int:

krkn/scenario_plugins/container/container_scenario_plugin.py

@@ -18,13 +18,10 @@ def run(
         self,
         run_uuid: str,
         scenario: str,
-        krkn_config: dict[str, any],
         lib_telemetry: KrknTelemetryOpenshift,
         scenario_telemetry: ScenarioTelemetry,
     ) -> int:
-        start_time = int(time.time())
         pool = PodsMonitorPool(lib_telemetry.get_lib_kubernetes())
-        wait_duration = krkn_config["tunings"]["wait_duration"]
         try:
             with open(scenario, "r") as f:
                 cont_scenario_config = yaml.full_load(f)
@@ -44,14 +41,7 @@ def run(
                     )
                     return 1
                 scenario_telemetry.affected_pods = result
-                logging.info("Waiting for the specified duration: %s" % (wait_duration))
-                time.sleep(wait_duration)
 
-                # capture end time
-                end_time = int(time.time())
-
-                # publish cerberus status
-                cerberus.publish_kraken_status(krkn_config, [], start_time, end_time)
         except (RuntimeError, Exception):
             logging.error("ContainerScenarioPlugin exiting due to Exception %s" % e)
             return 1

krkn/scenario_plugins/managed_cluster/managed_cluster_scenario_plugin.py

@@ -7,7 +7,6 @@
 from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
 from krkn_lib.utils import get_yaml_item_value
 
-from krkn import cerberus, utils
 from krkn.scenario_plugins.abstract_scenario_plugin import AbstractScenarioPlugin
 from krkn.scenario_plugins.managed_cluster.common_functions import get_managedcluster
 from krkn.scenario_plugins.managed_cluster.scenarios import Scenarios
@@ -18,7 +17,6 @@ def run(
         self,
         run_uuid: str,
         scenario: str,
-        krkn_config: dict[str, any],
         lib_telemetry: KrknTelemetryOpenshift,
         scenario_telemetry: ScenarioTelemetry,
     ) -> int:
@@ -38,8 +36,6 @@ def run(
                                 managedcluster_scenario_object,
                                 lib_telemetry.get_lib_kubernetes(),
                             )
-                            end_time = int(time.time())
-                            cerberus.get_status(krkn_config, start_time, end_time)
                         except Exception as e:
                             logging.error(
                                 "ManagedClusterScenarioPlugin exiting due to Exception %s"

krkn/scenario_plugins/native/native_scenario_plugin.py

@@ -13,7 +13,6 @@ def run(
         self,
         run_uuid: str,
         scenario: str,
-        krkn_config: dict[str, any],
         lib_telemetry: KrknTelemetryOpenshift,
         scenario_telemetry: ScenarioTelemetry,
     ) -> int:
@@ -29,7 +28,6 @@ def run(
             PLUGINS.run(
                 scenario,
                 lib_telemetry.get_lib_kubernetes().get_kubeconfig_path(),
-                krkn_config,
                 run_uuid,
             )
             result = pool.join()
@@ -48,7 +46,7 @@ def run(
     def get_scenario_types(self) -> list[str]:
         return [
             "pod_disruption_scenarios",
-            "pod_network_scenario",
+            "pod_network_scenarios",
             "vmware_node_scenarios",
             "ibmcloud_node_scenarios",
         ]