ansible installation [wip]

ansible/README.md

@@ -6,6 +6,14 @@ This folder contains configuration files and ansible playbooks for installing CS
 
 Ansible documentation can be found at [https://docs.ansible.com/](https://docs.ansible.com/).
 
+## Network topology for the installation
+
+The network topology for a typical Ansible installation is shown in the figure below -- a user host runs Ansible and installs CSLE on a cluster of remote hosts.
+
+<p align="center">
+<img src="ansible_topology.png" width="600">
+</p>
+
 ## Installing Ansible
 
 Ansible can be installed by running the command:

ansible/group_vars/all/variables.yml

@@ -1,6 +1,6 @@
 user: "kim"
 csle_git_repo_url: "https://github.com/Limmen/csle"
-leader_ip: "172.31.212.82"
+leader_ip: "164.92.81.86"
 nginx_content_name: "nginx_configuration_content.txt"
 web_port: 7777
 postgres_version: "15"
@@ -10,7 +10,6 @@ anaconda_url: "https://repo.anaconda.com/archive/Anaconda3-2022.10-Linux-x86_64.
 anaconda_install_script: "Anaconda3-2022.10-Linux-x86_64.sh"
 conda_environment_name: "base"
 python_version: "3.9"
-trusted_subnetwork: "172.31.212.0/24"
 postgres_password: "postgres"
 citus_port: 5432
 csle_config:
@@ -57,15 +56,15 @@ csle_config:
   postgresql_log_dir: "/var/log/postgresql/"
   nginx_log_dir: "/var/log/nginx/"
   default_log_dir: "/tmp/csle/"
-  metastore_ip: "172.31.212.82"
+  metastore_ip: "164.92.81.86"
   metastore_user: "csle"
   metastore_password: "csle"
   metastore_database_name: "csle"
   cluster_config:
     cluster_nodes:
-      - ip: "172.31.212.82"
+      - ip: "164.92.81.86"
         leader: true
-        cpus: 24
+        cpus: 4
         gpus: 0
-        RAM: 64
+        RAM: 8
   allow_registration: true

ansible/install_emulation_system_leader.yml

@@ -35,10 +35,11 @@
         executable: /bin/bash
       register: docker_swarm_status
       changed_when: false
+      ignore_errors: yes
 
     - name: Check if the docker swarm has been initialized
       set_fact:
-        swarm_initialized: "{{ active in docker_swarm_status.stdout }}"
+        swarm_initialized: "{{ docker_swarm_status.rc == 0 and active in docker_swarm_status.stdout }}"
 
     - name: Initialize Docker Swarm
       become: true
@@ -59,6 +60,3 @@
         docker_swarm_join_command: "{{ docker_swarm_join_command_output.stdout | regex_search(stdout_regex, multiline=True)}}"
       vars:
         stdout_regex: 'docker swarm join --token (.*)'
-
-    - debug:
-        var: hostvars[leader_ip]['docker_swarm_join_command']

ansible/install_management_system.yml

@@ -97,8 +97,6 @@
       args:
         executable: /bin/bash
       when:
-        - nvm_installed.rc == 0
-        - npm_installed.rc == 0
         - not web_app_installed.stat.exists
         - not web_app_built.stat.exists
       ignore_errors: true

ansible/install_metastore.yml

@@ -83,49 +83,6 @@
       become: true
       shell: "sudo echo 'host\tall\tall\t127.0.0.0/8\ttrust' >> /etc/postgresql/{{ postgres_version }}/main/pg_hba.conf"
 
-#    - name: Update the postgres configuration file
-#      become: true
-#      lineinfile:
-#        dest: "/etc/postgresql/{{ postgres_version }}/main/pg_hba.conf"
-#        line: |
-#          local	all		postgres				trust
-#          local   all             all                                     trust
-#          host	all		all		127.0.0.1/32		trust
-#          host	all		all		::1/128			trust
-#          local   replication     all                                     trust
-#          host	all		all		{{ trusted_subnetwork }}		trust
-
-#    - name: Update local authentication method in postgres config file
-#      become: true
-#      lineinfile:
-#        path: "/etc/postgresql/{{ postgres_version }}/main/pg_hba.conf"
-#        regexp: '^local\s+all\s+postgres\s+trust$'
-#        line: "local\tall\t\tpostgres\t\t\t\ttrust"
-#        state: present
-#
-#    - name: Update 127.0.0.1 authentication method in postgres config file
-#      become: true
-#      lineinfile:
-#        path: "/etc/postgresql/{{ postgres_version }}/main/pg_hba.conf"
-#        regexp: '^host\s+all\s+all\s+127.0.0.1/32\s+scram-sha-256$'
-#        line: "host\tall\t\tall\t\t127.0.0.1/32\t\ttrust"
-#        state: present
-#
-#    - name: Update general authentication method in postgres config file
-#      become: true
-#      lineinfile:
-#        path: "/etc/postgresql/{{ postgres_version }}/main/pg_hba.conf"
-#        regexp: '^host\s+all\s+all\s+::1/128\s+scram-sha-256$'
-#        line: "host\tall\t\tall\t\t::1/128\t\t\ttrust"
-#        state: present
-#
-#    - name: Add trusted subnetwork to postgres config file
-#      become: true
-#      lineinfile:
-#        path: "/etc/postgresql/{{ postgres_version }}/main/pg_hba.conf"
-#        line: "host\tall\t\tall\t\t{{ trusted_subnetwork }}\t\ttrust"
-#        insertafter: EOF
-#        state: present
 
     - name: Restart postgres
       become: true

ansible/inventory

@@ -1,5 +1,5 @@
 [leader]
-172.31.212.82
+164.92.81.86
 
 [worker]
 

ansible/start.yml

@@ -8,6 +8,14 @@
 
   tasks:
 
+  - name: List running docker containers
+    become: true
+    shell: "docker ps"
+    args:
+      executable: /bin/bash
+    register: docker_containers_list
+    changed_when: false
+
   - name: Restart clustermanager
     shell: "source /home/{{ user }}/.bashrc; source /home/{{ user }}/anaconda3/bin/activate {{ conda_environment_name }} && csle stop clustermanager && sleep 5; csle start clustermanager && sleep 10"
     args:

simulation-system/libs/csle-cli/src/csle_cli/cli.py

@@ -2005,7 +2005,7 @@ def list_node_exporter() -> None:
                                                    f"ip:{node.ip}, port:{constants.COMMANDS.NODE_EXPORTER_PORT}",
                         bold=False)
         else:
-            click.secho("Node exporter status: " + f" {click.style('[stopped],', fg='red')} ip:{node.ip}",
+            click.secho("Node exporter status: " + f" {click.style('[stopped]', fg='red')} ip:{node.ip}",
                         bold=False)
 
 

simulation-system/libs/csle-common/src/csle_common/constants/constants.py

@@ -917,7 +917,8 @@ class COMMANDS:
     POSTGRESQL_LOG_DIR = "/var/log/postgresql/"
     NGINX_LOG_DIR = "/var/log/nginx/"
     PROMETHEUS_PORT = 9090
-    START_PROMETHEUS = f"nohup prometheus --config.file={PROMETHEUS_CONFIG_FILE} " \
+    START_PROMETHEUS = f"nohup $CSLE_HOME/management-system/prometheus/prometheus " \
+                       f"--config.file={PROMETHEUS_CONFIG_FILE} " \
                        "--storage.tsdb.retention.size=10GB " \
                        f"--storage.tsdb.retention.time=5d & > {PROMETHEUS_LOG_FILE} " \
                        f"&& echo $! > {PROMETHEUS_PID_FILE}"
@@ -952,7 +953,8 @@ class COMMANDS:
     CSLE_MGMT_WEBAPP_PID_FILE = "/var/log/csle/csle_mgmt_webapp.pid"
     NODE_EXPORTER_LOG_FILE = "/var/log/csle/node_exporter.log"
     FLASK_LOG_FILE = "/var/log/csle/flask.log"
-    START_NODE_EXPORTER = f"nohup node_exporter & > {NODE_EXPORTER_LOG_FILE} && echo $! " \
+    START_NODE_EXPORTER = f"nohup $CSLE_HOME/management-system/node_exporter/node_exporter " \
+                          f"& > {NODE_EXPORTER_LOG_FILE} && echo $! " \
                           f"> {NODE_EXPORTER_PID_FILE}"
     BUILD_CSLE_MGMT_WEBAPP = f"cd ${CONFIG_FILE.CSLE_HOME_ENV_PARAM}/management-system/csle-mgmt-webapp && npm run " \
                              f"build"