Merge pull request 'Global_monitoring' (#24) from Global_monitoring into master

Reviewed-on: Aurore/ansible#24

hosts

@@ -63,6 +63,8 @@ vpn-ovh.adm.auro.re
 docker-ovh.adm.auro.re
 switchs-manager.adm.auro.re
 ldap-replica-ovh.adm.auro.re
+prometheus-ovh.adm.auro.re
+prometheus-federate.adm.auro.re
 
 [ovh_testing_vm]
 #re2o-test.adm.auro.re

monitoring.yml

@@ -1,6 +1,6 @@
 #!/usr/bin/env ansible-playbook
 ---
-- hosts: prometheus-fleming.adm.auro.re,prometheus-fleming-fo.adm.auro.re
+- hosts: prometheus-fleming.adm.auro.re
   vars:
     prometheus_alertmanager: docker-ovh.adm.auro.re:9093
     snmp_unifi_password: "{{ vault_snmp_unifi_password }}"
@@ -88,10 +88,43 @@
     # Prometheus targets.json
     prometheus_targets:
       - targets: |
-          {{ groups['aurore_pve'] + groups['aurore_vm'] + groups['ovh_pve'] + groups['ovh_vm'] | list | sort }}
+          {{ groups['aurore_pve'] + groups['aurore_vm'] | list | sort }}
   roles:
     - prometheus
 
+- hosts: prometheus-ovh.adm.auro.re
+  vars:
+    prometheus_alertmanager: docker-ovh.adm.auro.re:9093
+    snmp_unifi_password: "{{ vault_snmp_unifi_password }}"
+
+    # Prometheus targets.json
+    prometheus_targets:
+      - targets: |
+          {{ groups['ovh_pve'] + groups['ovh_vm'] | list | sort }}
+    prometheus_docker_targets:
+      - docker-ovh.adm.auro.re:8087
+  roles:
+    - prometheus
+
+
+- hosts: prometheus-federate.adm.auro.re
+  vars:
+    prometheus_alertmanager: docker-ovh.adm.auro.re:9093
+    snmp_unifi_password: "{{ vault_snmp_unifi_password }}"
+
+    # Prometheus targets.json
+    prometheus_targets:
+      - prometheus-edc.adm.auro.re
+      - prometheus-gs.adm.auro.re
+      - prometheus-fleming.adm.auro.re
+      - prometheus-pacaterie.adm.auro.re
+      - prometheus-rives.adm.auro.re
+      - prometheus-aurore.adm.auro.re
+      - prometheus-ovh.adm.auro.re
+      - prometheus-federate.adm.auro.re
+  roles:
+    - prometheus_federate
+
 
 # Monitor all hosts
 - hosts: all,!edc_unifi,!fleming_unifi,!pacaterie_unifi,!gs_unifi,!rives_unifi,!aurore_testing_vm,!ovh_container

roles/prometheus/tasks/main.yml

@@ -64,6 +64,13 @@
     mode: 0644
   when: prometheus_ups_snmp_targets is defined
 
+- name: Configure Prometheus docker monitoring
+  copy:
+    content: "{{ [{'targets': prometheus_docker_targets }] | to_nice_json }}\n"
+    dest: /etc/prometheus/targets_docker.json
+    mode: 0644
+  when: prometheus_docker_targets is defined
+
 - name: Activate prometheus service
   systemd:
     name: prometheus

roles/prometheus/templates/prometheus/alert.rules.yml.j2

@@ -59,6 +59,15 @@ groups:
       severity: warning
     annotations:
       summary: "{{ $labels.name }} a échoué sur {{ $labels.instance }}"
+
+  # Check load of instance
+  - alert: LoadUsage
+    expr: node_load1 > 5
+    for: 2m
+    labels:
+      severity: warning
+    annotations:
+      summary: "La charge de {{ $labels.instance }} est à {{ $value }} !"
   
   # Check UPS
   - alert: UpsOutputSourceChanged

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

@@ -81,3 +81,7 @@ scrape_configs:
       - target_label: __address__
         replacement: 127.0.0.1:9116
 
+  - job_name: docker
+    file_sd_configs:
+      - files:
+        - '/etc/prometheus/targets_docker.json'

roles/prometheus_federate/handlers/main.yml

@@ -0,0 +1,5 @@
+---
+- name: Restart Prometheus
+  service:
+    name: prometheus
+    state: restarted

roles/prometheus_federate/tasks/main.yml

@@ -0,0 +1,46 @@
+---
+- name: Install Prometheus
+  apt:
+    update_cache: true
+    name:
+      - prometheus
+  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
+
+# We don't need to restart Prometheus when updating nodes
+- name: Configure Prometheus Federate devices
+  copy:
+    content: "{{  [{'targets': prometheus_targets }] | to_nice_json }}"
+    dest: /etc/prometheus/targets.json
+    mode: 0644
+  when: prometheus_targets is defined
+
+- 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_federate/templates/prometheus/alert.rules.yml.j2

@@ -0,0 +1,138 @@
+# {{ ansible_managed }}
+{# As this is also Jinja2 it will conflict without a raw block #}
+{# Depending of Prometheus Node exporter version, rules can change depending of version #}
+{% raw %}
+groups:
+- name: alert.rules
+  rules:
+
+  # Alert for any instance that is unreachable for >3 minutes.
+  - alert: InstanceDown
+    expr: up == 0
+    for: 3m
+    labels:
+      severity: critical
+    annotations:
+      summary: "Federate : {{ $labels.exported_instance }} est invisible depuis plus de 3 minutes !"
+
+  # Alert for out of memory
+  - alert: OutOfMemory
+    expr: (node_memory_MemFree_bytes + node_memory_Cached_bytes + node_memory_Buffers_bytes) / node_memory_MemTotal_bytes * 100 < 10
+    for: 5m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Federate : Mémoire libre de {{ $labels.exported_instance }} à {{ humanize $value }}%."
+
+  # Alert for out of disk space
+  - alert: OutOfDiskSpace
+    expr: node_filesystem_free_bytes{fstype="ext4"} / node_filesystem_size_bytes{fstype="ext4"} * 100 < 10
+    for: 5m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Espace libre de {{ $labels.mountpoint }} sur {{ $labels.exported_instance }} à {{ humanize $value }}%."
+
+  # Alert for out of inode space on disk
+  - alert: OutOfInodes
+    expr: node_filesystem_files_free{fstype="ext4"} / node_filesystem_files{fstype="ext4"} * 100 < 10
+    for: 5m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Federate : Presque plus d'inodes disponibles ({{ $value }}% restant) dans {{ $labels.mountpoint }} sur {{ $labels.exported_instance }}."
+
+  # Alert for high CPU usage
+  - alert: CpuUsage
+    expr: (100 - avg by (instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 75
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Federate : CPU sur {{ $labels.exported_instance }} à {{ humanize $value }}%."
+
+  # Check systemd unit (> buster)
+  - alert: SystemdServiceFailed
+    expr: node_systemd_unit_state{state="failed"} == 1
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Federate : {{ $labels.name }} a échoué sur {{ $labels.exported_instance }}"
+
+  # Check load of instance
+  - alert: LoadUsage
+    expr: node_load1 > 5
+    for: 2m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Federate : la charge de {{ $labels.exported_instance }} est à {{ $value }} !"
+
+  # Check UPS
+  - alert: UpsOutputSourceChanged
+    expr: upsOutputSource != 3
+    for: 1m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Federate : La source d'alimentation de {{ $labels.exported_instance }} a changé !"
+
+  - alert: UpsBatteryStatusWarning
+    expr: upsBatteryStatus == 3
+    for: 2m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Federate : L'état de la batterie de {{ $labels.exported_instance }} est faible !"
+
+  - alert: UpsBatteryStatusCritical
+    expr: upsBatteryStatus == 4
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      summary: "L'état de la batterie de {{ $labels.exported_instance }} est affaibli !"
+
+  - alert: UpsHighLoad
+    expr: upsOutputPercentLoad > 70
+    for: 5m
+    labels:
+      severity: critical
+    annotations:
+      summary: "Federate : La charge de {{ $labels.exported_instance }} est de {{ $value }}% !"
+
+  - alert: UpsWrongInputVoltage
+    expr: (upsInputVoltage < 210) or (upsInputVoltage > 250)
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Federate : La tension d'entrée de {{ $labels.exported_instance }} est de {{ $value }}V."
+
+  - alert: UpsWrongOutputVoltage
+    expr: (upsOutputVoltage < 220) or (upsOutputVoltage > 240)
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Federate : La tension de sortie de {{ $labels.exported_instance }} est de {{ $value }}V."
+
+  - alert: UpsTimeRemainingWarning
+    expr: upsEstimatedMinutesRemaining < 15
+    for: 1m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Federate : L'autonomie restante sur {{ $labels.exported_instance }} est de {{ $value }} min."
+
+  - alert: UpsTimeRemainingCritical
+    expr: upsEstimatedMinutesRemaining < 5
+    for: 1m
+    labels:
+      severity: critical
+    annotations:
+      summary: "Federate : L'autonomie restante sur {{ $labels.exported_instance }} est de {{ $value }} min."
+
+
+{% endraw %}

roles/prometheus_federate/templates/prometheus/django.rules.yml.j2

@@ -0,0 +1,106 @@
+# {{ ansible_managed }}
+{# As this is also Jinja2 it will conflict without a raw block #}
+{% raw %}
+groups:
+- name: django.rules
+  rules:
+  - record: job:django_http_requests_before_middlewares_total:sum_rate30s
+    expr: sum(rate(django_http_requests_before_middlewares_total[30s])) BY (job)
+  - record: job:django_http_requests_unknown_latency_total:sum_rate30s
+    expr: sum(rate(django_http_requests_unknown_latency_total[30s])) BY (job)
+  - record: job:django_http_ajax_requests_total:sum_rate30s
+    expr: sum(rate(django_http_ajax_requests_total[30s])) BY (job)
+  - record: job:django_http_responses_before_middlewares_total:sum_rate30s
+    expr: sum(rate(django_http_responses_before_middlewares_total[30s])) BY (job)
+  - record: job:django_http_requests_unknown_latency_including_middlewares_total:sum_rate30s
+    expr: sum(rate(django_http_requests_unknown_latency_including_middlewares_total[30s]))
+      BY (job)
+  - record: job:django_http_requests_body_total_bytes:sum_rate30s
+    expr: sum(rate(django_http_requests_body_total_bytes[30s])) BY (job)
+  - record: job:django_http_responses_streaming_total:sum_rate30s
+    expr: sum(rate(django_http_responses_streaming_total[30s])) BY (job)
+  - record: job:django_http_responses_body_total_bytes:sum_rate30s
+    expr: sum(rate(django_http_responses_body_total_bytes[30s])) BY (job)
+  - record: job:django_http_requests_total:sum_rate30s
+    expr: sum(rate(django_http_requests_total_by_method[30s])) BY (job)
+  - record: job:django_http_requests_total_by_method:sum_rate30s
+    expr: sum(rate(django_http_requests_total_by_method[30s])) BY (job, method)
+  - record: job:django_http_requests_total_by_transport:sum_rate30s
+    expr: sum(rate(django_http_requests_total_by_transport[30s])) BY (job, transport)
+  - record: job:django_http_requests_total_by_view:sum_rate30s
+    expr: sum(rate(django_http_requests_total_by_view_transport_method[30s])) BY (job,
+      view)
+  - record: job:django_http_requests_total_by_view_transport_method:sum_rate30s
+    expr: sum(rate(django_http_requests_total_by_view_transport_method[30s])) BY (job,
+      view, transport, method)
+  - record: job:django_http_responses_total_by_templatename:sum_rate30s
+    expr: sum(rate(django_http_responses_total_by_templatename[30s])) BY (job, templatename)
+  - record: job:django_http_responses_total_by_status:sum_rate30s
+    expr: sum(rate(django_http_responses_total_by_status[30s])) BY (job, status)
+  - record: job:django_http_responses_total_by_charset:sum_rate30s
+    expr: sum(rate(django_http_responses_total_by_charset[30s])) BY (job, charset)
+  - record: job:django_http_exceptions_total_by_type:sum_rate30s
+    expr: sum(rate(django_http_exceptions_total_by_type[30s])) BY (job, type)
+  - record: job:django_http_exceptions_total_by_view:sum_rate30s
+    expr: sum(rate(django_http_exceptions_total_by_view[30s])) BY (job, view)
+  - record: job:django_http_requests_latency_including_middlewares_seconds:quantile_rate30s
+    expr: histogram_quantile(0.5, sum(rate(django_http_requests_latency_including_middlewares_seconds_bucket[30s]))
+      BY (job, le))
+    labels:
+      quantile: "50"
+  - record: job:django_http_requests_latency_including_middlewares_seconds:quantile_rate30s
+    expr: histogram_quantile(0.95, sum(rate(django_http_requests_latency_including_middlewares_seconds_bucket[30s]))
+      BY (job, le))
+    labels:
+      quantile: "95"
+  - record: job:django_http_requests_latency_including_middlewares_seconds:quantile_rate30s
+    expr: histogram_quantile(0.99, sum(rate(django_http_requests_latency_including_middlewares_seconds_bucket[30s]))
+      BY (job, le))
+    labels:
+      quantile: "99"
+  - record: job:django_http_requests_latency_including_middlewares_seconds:quantile_rate30s
+    expr: histogram_quantile(0.999, sum(rate(django_http_requests_latency_including_middlewares_seconds_bucket[30s]))
+      BY (job, le))
+    labels:
+      quantile: "99.9"
+  - record: job:django_http_requests_latency_seconds:quantile_rate30s
+    expr: histogram_quantile(0.5, sum(rate(django_http_requests_latency_seconds_bucket[30s]))
+      BY (job, le))
+    labels:
+      quantile: "50"
+  - record: job:django_http_requests_latency_seconds:quantile_rate30s
+    expr: histogram_quantile(0.95, sum(rate(django_http_requests_latency_seconds_bucket[30s]))
+      BY (job, le))
+    labels:
+      quantile: "95"
+  - record: job:django_http_requests_latency_seconds:quantile_rate30s
+    expr: histogram_quantile(0.99, sum(rate(django_http_requests_latency_seconds_bucket[30s]))
+      BY (job, le))
+    labels:
+      quantile: "99"
+  - record: job:django_http_requests_latency_seconds:quantile_rate30s
+    expr: histogram_quantile(0.999, sum(rate(django_http_requests_latency_seconds_bucket[30s]))
+      BY (job, le))
+    labels:
+      quantile: "99.9"
+  - record: job:django_model_inserts_total:sum_rate1m
+    expr: sum(rate(django_model_inserts_total[1m])) BY (job, model)
+  - record: job:django_model_updates_total:sum_rate1m
+    expr: sum(rate(django_model_updates_total[1m])) BY (job, model)
+  - record: job:django_model_deletes_total:sum_rate1m
+    expr: sum(rate(django_model_deletes_total[1m])) BY (job, model)
+  - record: job:django_db_new_connections_total:sum_rate30s
+    expr: sum(rate(django_db_new_connections_total[30s])) BY (alias, vendor)
+  - record: job:django_db_new_connection_errors_total:sum_rate30s
+    expr: sum(rate(django_db_new_connection_errors_total[30s])) BY (alias, vendor)
+  - record: job:django_db_execute_total:sum_rate30s
+    expr: sum(rate(django_db_execute_total[30s])) BY (alias, vendor)
+  - record: job:django_db_execute_many_total:sum_rate30s
+    expr: sum(rate(django_db_execute_many_total[30s])) BY (alias, vendor)
+  - record: job:django_db_errors_total:sum_rate30s
+    expr: sum(rate(django_db_errors_total[30s])) BY (alias, vendor, type)
+  - record: job:django_migrations_applied_total:max
+    expr: max(django_migrations_applied_total) BY (job, connection)
+  - record: job:django_migrations_unapplied_total:max
+    expr: max(django_migrations_unapplied_total) BY (job, connection)
+{% endraw %}

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

@@ -0,0 +1,56 @@
+# {{ ansible_managed }}
+
+global:
+  # scrape_interval is set to the global default (60s)
+  # evaluation_interval is set to the global default (60s)
+  # scrape_timeout is set to the global default (10s).
+
+  # Attach these labels to any time series or alerts when communicating with
+  # external systems (federation, remote storage, Alertmanager).
+  external_labels:
+      monitor: 'example'
+
+# Alertmanager configuration
+# Use prometheus alertmanager installed on the same machine
+alerting:
+  alertmanagers:
+  - static_configs:
+    - targets: ['{{ prometheus_alertmanager }}']
+
+# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
+rule_files:
+  - "alert.rules.yml"  # Monitoring alerts, this is the file you may be searching!
+  - "django.rules.yml"  # Custom rules specific for Django project monitoring
+
+# A scrape configuration containing exactly one endpoint to scrape:
+# Here it's Prometheus itself.
+scrape_configs:
+  # The .json in file_sd_configs is dynamically reloaded
+
+
+  - job_name: federate
+    scrape_interval: 15s
+    metrics_path: '/federate'
+    file_sd_configs:
+      - files:
+        - '/etc/prometheus/targets.json'
+    relabel_configs:
+      # Do not put :9100 in instance name, rather here
+      - source_labels: [__address__]
+        target_label: __param_target
+      - source_labels: [__param_target]
+        target_label: instance
+      - source_labels: [__param_target]
+        target_label: __address__
+        replacement: '$1:9090'
+    params:
+      'match[]':
+        - '{job="servers"}'
+        - '{job="prometheus"}'
+        - '{job="unifi_snmp"}'
+        - '{job="django"}'
+        - '{job="ups_snmp"}'
+        - '{job="django"}'
+        - '{job="docker"}'
+        - '{job="switch"}'
+

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

@@ -0,0 +1,387 @@
+# {{ ansible_managed }}
+# TODOlist :
+# - Faire fonctionner le monitoring des switchs défini ici
+#   * Configurer tous les switchs avec un compte SNMPv3
+#   * Mettre l'inventaire des switchs dans Ansible
+# - 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
+  - 1.3.6.1.2.1.31.1.1.1.6
+  get:
+  - 1.3.6.1.2.1.1.3.0
+  - 1.3.6.1.2.1.1.5.0
+  - 1.3.6.1.2.1.1.6.0
+  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: sysName
+    oid: 1.3.6.1.2.1.1.5
+    type: DisplayString
+    help: An administratively-assigned name for this managed node - 1.3.6.1.2.1.1.5
+  - name: sysLocation
+    oid: 1.3.6.1.2.1.1.6
+    type: DisplayString
+    help: The physical location of this node (e.g., 'telephone closet, 3rd floor')
+      - 1.3.6.1.2.1.1.6
+  - name: ifHCOutOctets
+    oid: 1.3.6.1.2.1.31.1.1.1.10
+    type: counter
+    help: The total number of octets transmitted out of the interface, including framing
+      characters - 1.3.6.1.2.1.31.1.1.1.10
+    indexes:
+    - labelname: ifIndex
+      type: gauge
+  - name: ifHCInOctets
+    oid: 1.3.6.1.2.1.31.1.1.1.6
+    type: counter
+    help: The total number of octets received on the interface, including framing
+      characters - 1.3.6.1.2.1.31.1.1.1.6
+    indexes:
+    - labelname: ifIndex
+      type: gauge
+  version: 3
+  auth:
+    username: prometheus
+
+ubiquiti_unifi:
+  walk:
+  - 1.3.6.1.4.1.41112.1.6
+  get:
+  - 1.3.6.1.2.1.1.5.0
+  - 1.3.6.1.2.1.1.6.0
+  metrics:
+# Pour faire une WifiMap un jour, on peut entrer la location dans la conf des bornes
+#  - name: sysLocation
+#    oid: 1.3.6.1.2.1.1.6
+#    type: DisplayString
+#    help: The physical location of this node (e.g., 'telephone closet, 3rd floor')
+#      - 1.3.6.1.2.1.1.6
+  - name: unifiVapIndex
+    oid: 1.3.6.1.4.1.41112.1.6.1.2.1.1
+    type: gauge
+    help: ' - 1.3.6.1.4.1.41112.1.6.1.2.1.1'
+    indexes:
+    - labelname: unifiVapIndex
+      type: gauge
+  - name: unifiVapChannel
+    oid: 1.3.6.1.4.1.41112.1.6.1.2.1.4
+    type: gauge
+    help: ' - 1.3.6.1.4.1.41112.1.6.1.2.1.4'
+    indexes:
+    - labelname: unifiVapIndex
+      type: gauge
+  - name: unifiVapEssId
+    oid: 1.3.6.1.4.1.41112.1.6.1.2.1.6
+    type: DisplayString
+    help: ' - 1.3.6.1.4.1.41112.1.6.1.2.1.6'
+    indexes:
+    - labelname: unifiVapIndex
+      type: gauge
+  - name: unifiVapName
+    oid: 1.3.6.1.4.1.41112.1.6.1.2.1.7
+    type: DisplayString
+    help: ' - 1.3.6.1.4.1.41112.1.6.1.2.1.7'
+    indexes:
+    - labelname: unifiVapIndex
+      type: gauge
+  - name: unifi_vap_num_stations
+    oid: 1.3.6.1.4.1.41112.1.6.1.2.1.8
+    type: gauge
+    help: ' - 1.3.6.1.4.1.41112.1.6.1.2.1.8'
+    indexes:
+    - labelname: unifi_vap_index
+      type: gauge
+    lookups:
+    - labels: [unifi_vap_index]
+      labelname: unifi_vap_essid
+      oid: 1.3.6.1.4.1.41112.1.6.1.2.1.6
+      type: DisplayString
+    - labels: [unifi_vap_index]
+      labelname: unifi_vap_radio
+      oid: 1.3.6.1.4.1.41112.1.6.1.2.1.9
+      type: DisplayString
+    - labels: []
+      labelname: unifi_vap_index
+#  - name: unifiVapNumStations
+#    oid: 1.3.6.1.4.1.41112.1.6.1.2.1.8
+#    type: gauge
+#    help: ' - 1.3.6.1.4.1.41112.1.6.1.2.1.8'
+#    indexes:
+#    - labelname: unifiVapIndex
+#      type: gauge
+  - name: unifiVapRadio
+    oid: 1.3.6.1.4.1.41112.1.6.1.2.1.9
+    type: DisplayString
+    help: ' - 1.3.6.1.4.1.41112.1.6.1.2.1.9'
+    indexes:
+    - labelname: unifiVapIndex
+      type: gauge
+  - name: unifiVapRxBytes
+    oid: 1.3.6.1.4.1.41112.1.6.1.2.1.10
+    type: counter
+    help: ' - 1.3.6.1.4.1.41112.1.6.1.2.1.10'
+    indexes:
+    - labelname: unifiVapIndex
+      type: gauge
+  - name: unifiVapRxCrypts
+    oid: 1.3.6.1.4.1.41112.1.6.1.2.1.11
+    type: counter
+    help: ' - 1.3.6.1.4.1.41112.1.6.1.2.1.11'
+    indexes:
+    - labelname: unifiVapIndex
+      type: gauge
+  - name: unifiVapRxDropped
+    oid: 1.3.6.1.4.1.41112.1.6.1.2.1.12
+    type: counter
+    help: ' - 1.3.6.1.4.1.41112.1.6.1.2.1.12'
+    indexes:
+    - labelname: unifiVapIndex
+      type: gauge
+  - name: unifiVapRxErrors
+    oid: 1.3.6.1.4.1.41112.1.6.1.2.1.13
+    type: counter
+    help: ' - 1.3.6.1.4.1.41112.1.6.1.2.1.13'
+    indexes:
+    - labelname: unifiVapIndex
+      type: gauge
+  - name: unifiVapRxFrags
+    oid: 1.3.6.1.4.1.41112.1.6.1.2.1.14
+    type: counter
+    help: ' - 1.3.6.1.4.1.41112.1.6.1.2.1.14'
+    indexes:
+    - labelname: unifiVapIndex
+      type: gauge
+  - name: unifiVapRxPackets
+    oid: 1.3.6.1.4.1.41112.1.6.1.2.1.15
+    type: counter
+    help: ' - 1.3.6.1.4.1.41112.1.6.1.2.1.15'
+    indexes:
+    - labelname: unifiVapIndex
+      type: gauge
+  - name: unifiVapTxBytes
+    oid: 1.3.6.1.4.1.41112.1.6.1.2.1.16
+    type: counter
+    help: ' - 1.3.6.1.4.1.41112.1.6.1.2.1.16'
+    indexes:
+    - labelname: unifiVapIndex
+      type: gauge
+  - name: unifiVapTxDropped
+    oid: 1.3.6.1.4.1.41112.1.6.1.2.1.17
+    type: counter
+    help: ' - 1.3.6.1.4.1.41112.1.6.1.2.1.17'
+    indexes:
+    - labelname: unifiVapIndex
+      type: gauge
+  - name: unifiVapTxErrors
+    oid: 1.3.6.1.4.1.41112.1.6.1.2.1.18
+    type: counter
+    help: ' - 1.3.6.1.4.1.41112.1.6.1.2.1.18'
+    indexes:
+    - labelname: unifiVapIndex
+      type: gauge
+  - name: unifiVapTxPackets
+    oid: 1.3.6.1.4.1.41112.1.6.1.2.1.19
+    type: counter
+    help: ' - 1.3.6.1.4.1.41112.1.6.1.2.1.19'
+    indexes:
+    - labelname: unifiVapIndex
+      type: gauge
+  - name: unifiVapTxRetries
+    oid: 1.3.6.1.4.1.41112.1.6.1.2.1.20
+    type: counter
+    help: ' - 1.3.6.1.4.1.41112.1.6.1.2.1.20'
+    indexes:
+    - labelname: unifiVapIndex
+      type: gauge
+  - name: unifiVapTxPower
+    oid: 1.3.6.1.4.1.41112.1.6.1.2.1.21
+    type: gauge
+    help: ' - 1.3.6.1.4.1.41112.1.6.1.2.1.21'
+    indexes:
+    - labelname: unifiVapIndex
+      type: gauge
+  - name: unifiVapUp
+    oid: 1.3.6.1.4.1.41112.1.6.1.2.1.22
+    type: gauge
+    help: ' - 1.3.6.1.4.1.41112.1.6.1.2.1.22'
+    indexes:
+    - labelname: unifiVapIndex
+      type: gauge
+  - name: unifiVapUsage
+    oid: 1.3.6.1.4.1.41112.1.6.1.2.1.23
+    type: DisplayString
+    help: guest or regular user - 1.3.6.1.4.1.41112.1.6.1.2.1.23
+    indexes:
+    - labelname: unifiVapIndex
+      type: gauge
+  - name: unifiIfIndex
+    oid: 1.3.6.1.4.1.41112.1.6.2.1.1.1
+    type: gauge
+    help: ' - 1.3.6.1.4.1.41112.1.6.2.1.1.1'
+    indexes:
+    - labelname: unifiIfIndex
+      type: gauge
+  - name: unifiIfName
+    oid: 1.3.6.1.4.1.41112.1.6.2.1.1.5
+    type: DisplayString
+    help: ' - 1.3.6.1.4.1.41112.1.6.2.1.1.5'
+    indexes:
+    - labelname: unifiIfIndex
+      type: gauge
+  - name: unifiIfRxBytes
+    oid: 1.3.6.1.4.1.41112.1.6.2.1.1.6
+    type: counter
+    help: ' - 1.3.6.1.4.1.41112.1.6.2.1.1.6'
+    indexes:
+    - labelname: unifiIfIndex
+      type: gauge
+  - name: unifiIfRxDropped
+    oid: 1.3.6.1.4.1.41112.1.6.2.1.1.7
+    type: counter
+    help: ' - 1.3.6.1.4.1.41112.1.6.2.1.1.7'
+    indexes:
+    - labelname: unifiIfIndex
+      type: gauge
+  - name: unifiIfRxError
+    oid: 1.3.6.1.4.1.41112.1.6.2.1.1.8
+    type: counter
+    help: ' - 1.3.6.1.4.1.41112.1.6.2.1.1.8'
+    indexes:
+    - labelname: unifiIfIndex
+      type: gauge
+  - name: unifiIfRxMulticast
+    oid: 1.3.6.1.4.1.41112.1.6.2.1.1.9
+    type: counter
+    help: ' - 1.3.6.1.4.1.41112.1.6.2.1.1.9'
+    indexes:
+    - labelname: unifiIfIndex
+      type: gauge
+  - name: unifiIfRxPackets
+    oid: 1.3.6.1.4.1.41112.1.6.2.1.1.10
+    type: counter
+    help: ' - 1.3.6.1.4.1.41112.1.6.2.1.1.10'
+    indexes:
+    - labelname: unifiIfIndex
+      type: gauge
+  - name: unifiIfTxBytes
+    oid: 1.3.6.1.4.1.41112.1.6.2.1.1.12
+    type: counter
+    help: ' - 1.3.6.1.4.1.41112.1.6.2.1.1.12'
+    indexes:
+    - labelname: unifiIfIndex
+      type: gauge
+  - name: unifiIfTxDropped
+    oid: 1.3.6.1.4.1.41112.1.6.2.1.1.13
+    type: counter
+    help: ' - 1.3.6.1.4.1.41112.1.6.2.1.1.13'
+    indexes:
+    - labelname: unifiIfIndex
+      type: gauge
+  - name: unifiIfTxError
+    oid: 1.3.6.1.4.1.41112.1.6.2.1.1.14
+    type: counter
+    help: ' - 1.3.6.1.4.1.41112.1.6.2.1.1.14'
+    indexes:
+    - labelname: unifiIfIndex
+      type: gauge
+  - name: unifiIfTxPackets
+    oid: 1.3.6.1.4.1.41112.1.6.2.1.1.15
+    type: counter
+    help: ' - 1.3.6.1.4.1.41112.1.6.2.1.1.15'
+    indexes:
+    - labelname: unifiIfIndex
+      type: gauge
+  - name: unifiApSystemModel
+    oid: 1.3.6.1.4.1.41112.1.6.3.3
+    type: DisplayString
+    help: ' - 1.3.6.1.4.1.41112.1.6.3.3'
+  - name: unifiApSystemUptime
+    oid: 1.3.6.1.4.1.41112.1.6.3.5
+    type: counter
+    help: ' - 1.3.6.1.4.1.41112.1.6.3.5'
+  version: 3
+  auth:
+    security_level: authPriv
+    username: snmp_prometheus
+    password: {{ snmp_unifi_password }}
+    auth_protocol: SHA
+    priv_protocol: AES
+    priv_password: {{ snmp_unifi_password }}

roles/prometheus_federate/templates/update-motd.d/05-service.j2

@@ -0,0 +1,4 @@
+#!/bin/sh
+# {{ ansible_managed }}
+echo "> prometheus a été déployé sur cette machine."
+echo "  Voir /etc/prometheus/"