monitoring.yml

@@ -34,6 +34,9 @@
     snmp_unifi_password: "{{ vault_snmp_unifi_password }}"
 
     # Prometheus targets.json
+    prometheus_ups_snmp_targets:
+       - ups-ec-1.ups.auro.re
+
     prometheus_targets:
       - targets: |
           {{ groups['edc_pve'] + groups['edc_vm'] | list | sort }}

roles/baseconfig/tasks/main.yml.save

@@ -0,0 +1,89 @@
+---
+# Should contain only small tools that everyone can't live without
+- name: Install basic tools
+  when: ansible_os_family == "Debian"
+  apt:
+    name:
+      - sudo
+      - molly-guard  # prevent reboot
+      - ntp  # network time sync
+      - apt  # better than apt-get
+      - nano  # for vulcain
+      - vim  # better than nano
+      - emacs-nox  # for maman
+      - htop  # better than top
+      - zsh  # to be able to ssh @erdnaxe
+      - fish  # to motivate @edpibu
+      - oidentd  # postgresql identification
+      - aptitude  # nice to have for Ansible
+      - acl  # advanced ACL
+      - iotop  # monitor i/o
+      - tree  # create a graphical tree of files
+      - bash-completion  # because bash
+      - git  # code versioning
+      - less  # i like cats
+      - screen  # Vulcain asked for this
+      - lsb-release
+    update_cache: true
+  register: apt_result
+  retries: 3
+  until: apt_result is succeeded
+
+# Pimp my server
+- name: Customize motd
+  copy:
+    src: "update-motd.d/{{ item }}"
+    dest: "/etc/update-motd.d/{{ item }}"
+    mode: 0755
+  loop:
+    - 00-logo
+    - 10-uname
+
+- name: Remove Debian warranty motd
+  file:
+    path: /etc/motd
+    state: absent
+
+# Configure APT mirrors on Debian Stretch
+- name: Configure APT mirrors
+  when:
+    - ansible_distribution == 'Debian'
+    - ansible_distribution_release == 'stretch'
+  template:
+    src: apt/sources.list.j2
+    dest: /etc/apt/sources.list
+    mode: 0644
+
+# Patriotisme
+- name: Ensure French UTF-8 locale exists
+  locale_gen:
+    name: fr_FR.UTF-8
+    state: present
+
+# Fix LC_CTYPE="C"
+- name: Select default locale
+  debconf:
+    name: locales
+    question: locales/default_environment_locale
+    value: fr_FR.UTF-8
+    vtype: select
+  notify: Reconfigure locales
+
+# APT-List Changes : send email with changelog
+- include_tasks: apt-listchanges.yml
+
+# User skeleton
+- name: Configure user skeleton
+  copy:
+    src: "skel/dot_{{ item }}"
+    dest: "/etc/skel/.{{ item }}"
+    mode: 0644
+  loop:
+    - zshrc
+    - zshrc.local
+
+- name: Configure resolvconf
+  template:
+    src: resolv.conf
+    dest: /etc/resolv.conf
+    mode: 0644

roles/prometheus/tasks/main.yml

@@ -56,6 +56,13 @@
     dest: /etc/prometheus/targets_unifi_snmp.json
     mode: 0644
 
+- name: Configure Prometheus UPS SNMP devices
+  copy:
+    content: "{{ [{'targets': prometheus_ups_snmp_targets }] | to_nice_json }}\n"
+    dest: /etc/prometheus/targets_ups_snmp.json
+    mode: 0644
+
+
 - name: Activate prometheus service
   systemd:
     name: prometheus

roles/prometheus/tasks/main.yml.save

@@ -0,0 +1,76 @@
+---
+- name: Install Prometheus
+  apt:
+    update_cache: true
+    name:
+      - prometheus
+      - prometheus-snmp-exporter
+  register: apt_result
+  retries: 3
+  until: apt_result is succeeded
+
+- name: Configure Prometheus
+  template:
+    src: prometheus/prometheus.yml.j2
+    dest: /etc/prometheus/prometheus.yml
+    mode: 0644
+  notify: Restart Prometheus
+
+- name: Configure Prometheus alert rules
+  template:
+    src: "prometheus/{{ item }}.j2"
+    dest: "/etc/prometheus/{{ item }}"
+    mode: 0644
+  notify: Restart Prometheus
+  loop:
+    - alert.rules.yml
+    - django.rules.yml
+
+- name: Make Prometheus snmp-exporter listen on localhost only
+  lineinfile:
+    path: /etc/default/prometheus-snmp-exporter
+    regexp: '^ARGS='
+    line: "ARGS=\"--web.listen-address=127.0.0.1:9116\""
+  notify: Restart prometheus-snmp-exporter
+
+# This file store SNMP OIDs
+- name: Configure Prometheus snmp-exporter
+  template:
+    src: "prometheus/snmp.yml.j2"
+    dest: "/etc/prometheus/snmp.yml"
+    mode: 0600
+    owner: prometheus
+  notify: Restart prometheus-snmp-exporter
+
+# We don't need to restart Prometheus when updating nodes
+- name: Configure Prometheus nodes
+  copy:
+    content: "{{ prometheus_targets | to_nice_json }}"
+    dest: /etc/prometheus/targets.json
+    mode: 0644
+
+# We don't need to restart Prometheus when updating nodes
+- name: Configure Prometheus Ubiquity Unifi SNMP devices
+  copy:
+    content: "{{ prometheus_unifi_snmp_targets | to_nice_json }}"
+    dest: /etc/prometheus/targets_unifi_snmp.json
+    mode: 0644
+
+- name: Configure Prometheus UPS SNMP devices
+  copy:
+    content: "{{ [{'target | to_nice_json }}"
+    dest: /etc/prometheus/targets_ups_snmp.json
+    mode: 0644
+
+
+- name: Activate prometheus service
+  systemd:
+    name: prometheus
+    enabled: true
+    state: started
+
+- name: Indicate role in motd
+  template:
+    src: update-motd.d/05-service.j2
+    dest: /etc/update-motd.d/05-prometheus
+    mode: 0755

roles/prometheus/templates/prometheus/prometheus.yml.j2

@@ -65,3 +65,19 @@ scrape_configs:
     scheme: https
     static_configs:
     - targets: []
+
+  - job_name: ups_snmp
+    file_sd_configs:
+      - files:
+        - '/etc/prometheus/targets_ups_snmp.json'
+    metrics_path: /snmp
+    params:
+      module: [eatonups]
+    relabel_configs:
+      - source_labels: [__address__]
+        target_label: __param_target
+      - source_labels: [__param_target]
+        target_label: instance
+      - target_label: __address__
+        replacement: 127.0.0.1:9116
+

roles/prometheus/templates/prometheus/snmp.yml.j2

@@ -6,6 +6,78 @@
 # - Optimiser les règles pour les bornes Unifi,
 #   on pourrait indexer avec les SSID
 
+eatonups:
+  walk:
+  - 1.3.6.1.2.1.33.1.2
+  - 1.3.6.1.2.1.33.1.3
+  - 1.3.6.1.2.1.33.1.4
+  - 1.3.6.1.4.1.534.1.6
+  get:
+  - 1.3.6.1.2.1.1.3.0
+  metrics:
+  - name: sysUpTime
+    oid: 1.3.6.1.2.1.1.3
+    type: gauge
+    help: The time (in hundredths of a second) since the network management portion
+      of the system was last re-initialized. - 1.3.6.1.2.1.1.3
+  - name: upsBatteryStatus
+    oid: 1.3.6.1.2.1.33.1.2.1
+    type: gauge
+    help: The indication of the capacity remaining in the UPS system's batteries -
+      1.3.6.1.2.1.33.1.2.1
+  - name: upsEstimatedMinutesRemaining
+    oid: 1.3.6.1.2.1.33.1.2.3
+    type: gauge
+    help: An estimate of the time to battery charge depletion under the present load
+      conditions if the utility power is off and remains off, or if it were to be
+      lost and remain off. - 1.3.6.1.2.1.33.1.2.3
+  - name: upsInputVoltage
+    oid: 1.3.6.1.2.1.33.1.3.3.1.3
+    type: gauge
+    help: The magnitude of the present input voltage. - 1.3.6.1.2.1.33.1.3.3.1.3
+    indexes:
+    - labelname: upsInputLineIndex
+      type: gauge
+  - name: upsOutputSource
+    oid: 1.3.6.1.2.1.33.1.4.1
+    type: gauge
+    help: The present source of output power - 1.3.6.1.2.1.33.1.4.1
+  - name: upsOutputVoltage
+    oid: 1.3.6.1.2.1.33.1.4.4.1.2
+    type: gauge
+    help: The present output voltage. - 1.3.6.1.2.1.33.1.4.4.1.2
+    indexes:
+    - labelname: upsOutputLineIndex
+      type: gauge
+  - name: upsOutputPower
+    oid: 1.3.6.1.2.1.33.1.4.4.1.4
+    type: gauge
+    help: The present output true power. - 1.3.6.1.2.1.33.1.4.4.1.4
+    indexes:
+    - labelname: upsOutputLineIndex
+      type: gauge
+  - name: upsOutputPercentLoad
+    oid: 1.3.6.1.2.1.33.1.4.4.1.5
+    type: gauge
+    help: The percentage of the UPS power capacity presently being used on this output
+      line, i.e., the greater of the percent load of true power capacity and the percent
+      load of VA. - 1.3.6.1.2.1.33.1.4.4.1.5
+    indexes:
+    - labelname: upsOutputLineIndex
+      type: gauge
+  - name: xupsEnvRemoteTemp
+    oid: 1.3.6.1.4.1.534.1.6.5
+    type: gauge
+    help: The reading of an EMP's temperature sensor. - 1.3.6.1.4.1.534.1.6.5
+  - name: xupsEnvRemoteHumidity
+    oid: 1.3.6.1.4.1.534.1.6.6
+    type: gauge
+    help: The reading of an EMP's humidity sensor. - 1.3.6.1.4.1.534.1.6.6
+  version: 1
+  auth:
+    community: public
+
+
 procurve_switch:
   walk:
   - 1.3.6.1.2.1.31.1.1.1.10