[Feat] Allow multiple globalmon instances per host

cloudmon/ansible/project/roles/globalmon/defaults/main.yml

@@ -7,20 +7,21 @@ distro_lookup_path:
 
 globalmon_os_user: "cloudmon"
 globalmon_os_group: "cloudmon"
-globalmon_systemd_service_name: "cloudmon-globalmon.service"
+globalmon_suffix: "prod"
+globalmon_systemd_service_name: "cloudmon-globalmon_{{ globalmon_suffix }}.service"
 globalmon_systemd_unit_path: "{{ ('/etc/systemd/system/'+ globalmon_systemd_service_name) }}"
 globalmon_image: "quay.io/stackmon/globalmon"
 globalmon_config_dir: "/etc/cloudmon"
-globalmon_config_file_name: "cloudmon-globalmon.yaml"
+globalmon_config_file_name: "cloudmon-globalmon_{{ globalmon_suffix }}.yaml"
 globalmon_config_path: "{{ globalmon_config_dir }}/{{ globalmon_config_file_name }}"
-globalmon_log_dir: "/var/log/globalmon"
+globalmon_log_dir: "/var/log/globalmon/{{ globalmon_suffix }}"
 globalmon_secure_config_file_name: "cloudmon-globalmon-secure.yaml"
 globalmon_secure_config_path: "{{ globalmon_config_dir }}/{{ globalmon_secure_config_file_name }}"
 globalmon_env_file_name: "globalmon_env"
 globalmon_env_path: "{{ globalmon_config_dir }}/{{ globalmon_env_file_name }}"
 # globalmon_config:
 # globalmon_secure_config:
-globalmon_container_name: "cloudmon_globalmon"
+globalmon_container_name: "cloudmon_globalmon_{{ globalmon_suffix }}"
 
 container_command: "podman"
 container_runtime: "/usr/bin/{{ container_command }}"

cloudmon/ansible/project/start_globalmon.yaml

@@ -7,5 +7,5 @@
   tasks:
     - name: Start globalmon
       ansible.builtin.service:
-        name: "cloudmon-globalmon"
+        name: "{{ globalmon_service_name }}"
         state: "started"

cloudmon/ansible/project/stop_globalmon.yaml

@@ -7,5 +7,5 @@
   tasks:
     - name: Stop globalmon
       ansible.builtin.service:
-        name: "cloudmon-globalmon"
+        name: "{{ globalmon_service_name }}"
         state: "stopped"

cloudmon/plugin/globalmon.py

@@ -65,13 +65,16 @@ def process_config(self):
     def process_plugin_entry(self, plugin_ref, matrix_entry, plugin):
         env_name = matrix_entry.env
         zone = matrix_entry.monitoring_zone
+        key = f"{zone}_{env_name}"  # Unique key per env + zone
+
         globalmon_config = self.globalmon_configs.setdefault(
-            zone, GlobalmonConfig())
+            key, GlobalmonConfig())
         globalmon_config.environment = env_name
         globalmon_config.zone = zone
         ansible_group_name = plugin.globalmons_inventory_group_name
         globalmon_config.ansible_group_name = ansible_group_name
         globalmon_config.image = plugin_ref.image
+
         config = None
 
         # Read config file
@@ -89,21 +92,17 @@ def process_plugin_entry(self, plugin_ref, matrix_entry, plugin):
             raise RuntimeError("Globalmon config not found. Please either use --config-dir and relative path for globalmon config in cloudmon config OR use --insecure option with full path of globalmon config in cloudmon config")  # noqa
 
         globalmon_config.services = config["services"]
-
         globalmon_config.watch_clouds[env_name] = dict(
-            # which services
             services=globalmon_config.services,
-            # how cloud is named
             cloud=plugin.cloud_name,
         )
 
     def provision(self, options):
-
-        for _, globalmon_config in self.globalmon_configs.items():
+        for key, globalmon_config in self.globalmon_configs.items():
             self.log.info(
-                "Provisioning Globalmon in monitoring zone %s",
+                "Provisioning Globalmon in monitoring zone %s for env %s",
                 globalmon_config.zone,
-            )
+                globalmon_config.environment)
 
             statsd_group_name = self.config.model.get_monitoring_zone_by_name(
                 globalmon_config.zone
@@ -157,6 +156,7 @@ def provision(self, options):
             globalmon_secure_cfg = dict(clouds=clouds_creds)
 
             extravars = dict(
+                globalmon_suffix=environment,
                 globalmon_group_name=globalmon_config.ansible_group_name,
                 globalmon_image=globalmon_config.image,
                 globalmon_config_dir="/home/ubuntu",
@@ -175,15 +175,18 @@ def provision(self, options):
                 verbosity=3,
             )
             if r.rc != 0:
-                raise RuntimeError("Error provisioning Globalmon")
+                raise RuntimeError(
+                    f"Error provisioning Globalmon in {zone} for {environment}") # noqa
 
     def stop(self, options):
         for _, globalmon_config in self.globalmon_configs.items():
             self.log.info(
                 "Stopping Globalmon in monitoring zone %s",
                 globalmon_config.zone,
             )
+            environment = globalmon_config.environment
             extravars = dict(
+                globalmon_service_name=f"cloudmon-globalmon_{environment}",
                 globalmon_group_name=globalmon_config.ansible_group_name,
             )
             r = ansible_runner.run(
@@ -204,7 +207,9 @@ def start(self, options):
                 "Starting Globalmon in monitoring zone %s",
                 globalmon_config.zone,
             )
+            environment = globalmon_config.environment
             extravars = dict(
+                globalmon_service_name=f"cloudmon-globalmon_{environment}",
                 globalmon_group_name=globalmon_config.ansible_group_name,
             )
             r = ansible_runner.run(