add docker compose

_docker/alertmanager/alert.rules/alerts.rules.yml

@@ -0,0 +1,145 @@
+groups:
+ 
+- name: Alertes monitoring
+  rules:
+  - alert: NodeHasSwapIn
+    expr: irate(node_vmstat_pswpin{job="prod"}[5m]) > 0 
+    for: 15m
+    labels:
+      severity: critique
+    annotations:
+      identifier: "{{ $labels.instance }}"
+      summary: "Node has swap in (instance {{ $labels.instance }})"
+      description: "<!channel>  La VM SWAP (in)  LABELS: {{ $labels.job }} : {{ $labels.instance }}"
+
+  - alert: NodeHasSwapOut
+    expr: irate(node_vmstat_pswpin{job="prod"}[5m]) > 0 
+    for: 15m
+    labels:
+      severity: critique
+    annotations:
+      identifier: "{{ $labels.instance }}"
+      summary: "Node has swap out (instance {{ $labels.instance }})"
+      description: "<!channel>  La VM SWAP (out)  LABELS: {{ $labels.job }} : {{ $labels.instance }}"
+
+  - alert: OutOfInodes
+    expr: node_filesystem_files_free{mountpoint ="/rootfs"} / node_filesystem_files{mountpoint ="/rootfs"} * 100 < 10
+    for: 15m
+    labels:
+      severity: critique
+    annotations:
+      identifier: "{{ $labels.instance }}"
+      summary: "Out of inodes (instance {{ $labels.instance }})"
+      description: "<!channel>  Le disque n'a presque plus d'inode (< 10% restant)    VALUE = {{ humanize $value }}    LABELS: {{ $labels.job }} : {{ $labels.instance }}"
+
+
+  - alert: OutOfMemory
+    expr: (node_memory_MemFree_bytes + node_memory_Cached_bytes + node_memory_Buffers_bytes) / node_memory_MemTotal_bytes * 100 < 10
+    for: 15m
+    labels:
+      severity: critique
+    annotations:
+      identifier: "{{ $labels.instance }}"
+      summary: "Out of memory (instance {{ $labels.instance }})"
+      description: "<!channel>  L'hôte n'a presque plus de RAM (< 10% restant)    VALUE = {{ $value }}    LABELS: {{ $labels.job }} : {{ $labels.instance }}"
+
+
+  - alert: UnusualNetworkThroughputIn
+    expr: sum by (instance) (irate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100
+    for: 15m
+    labels:
+      severity: critique
+    annotations:
+      identifier: "{{ $labels.instance }}"
+      summary: "Unusual network throughput in (instance {{ $labels.instance }})"
+      description: "<!channel>  Les interfaces réseau reçoivent sans doute trop de données (> 100 MB/s)    VALUE = {{ $value }}    LABELS: {{ $labels.job }} : {{ $labels.instance }}"
+
+  - alert: UnusualNetworkThroughputOut
+    expr: sum by (instance) (irate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100
+    for: 15m
+    labels:
+      severity: critique
+    annotations:
+      identifier: "{{ $labels.instance }}"
+      summary: "Unusual network throughput out (instance {{ $labels.instance }})"
+      description: "<!channel>  Les interfaces réseau envoient sans doute trop de données (> 100 MB/s)    VALUE = {{ $value }}    LABELS: {{ $labels.job }} : {{ $labels.instance }}"
+
+  - alert: UnusualDiskReadRate
+    expr: sum by (instance) (irate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50
+    for: 15m
+    labels:
+      severity: critique
+    annotations:
+      identifier: "{{ $labels.instance }}"
+      summary: "Unusual disk read rate (instance {{ $labels.instance }})"
+      description: "<!channel>  Le disque lit sans doute trop de données (> 50 MB/s)    VALUE = {{ $value }}    LABELS: {{ $labels.job }} : {{ $labels.instance }}"
+
+  - alert: UnusualDiskWriteRate
+    expr: sum by (instance) (irate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50
+    for: 15m
+    labels:
+      severity: critique
+    annotations:
+      identifier: "{{ $labels.instance }}"
+      summary: "Unusual disk write rate (instance {{ $labels.instance }})"
+      description: "<!channel>  Le disque écrit sans doute trop de données (> 50 MB/s)    VALUE = {{ $value }}    LABELS: {{ $labels.job }} : {{ $labels.instance }}"
+
+  - alert: OutOfDiskSpace
+    expr: node_filesystem_free_bytes{mountpoint ="/"} / node_filesystem_size_bytes{mountpoint ="/"} * 100 < 20
+    for: 15m
+    labels:
+      severity: critique
+    annotations:
+      identifier: "{{ $labels.instance }}"
+      summary: "Out of disk space (instance {{ $labels.instance }})"
+      description: "<!channel>  L'espace disque est presque complet (< 20% restant)    VALUE = {{ $value }}    LABELS: {{ $labels.job }} : {{ $labels.instance }}"
+
+  - alert: UnusualDiskReadLatency
+    expr: rate(node_disk_read_time_seconds_total[1m]) / rate(node_disk_reads_completed_total[1m]) > 100
+    for: 15m
+    labels:
+      severity: critique
+    annotations:
+      identifier: "{{ $labels.instance }}"
+      summary: "Unusual disk read latency (instance {{ $labels.instance }})"
+      description: "<!channel>  La latence du disque augmente  (read operations > 100ms)    VALUE = {{ $value }}    LABELS: {{ $labels.job }} : {{ $labels.instance }}"
+
+  - alert: CpuLoad
+    expr: node_load15 / (count without (cpu, mode) (node_cpu_seconds_total{mode="system"})) > 2
+    for: 15m
+    labels:
+      severity: critique
+    annotations:
+      identifier: "{{ $labels.instance }}"
+      summary: "CPU load (instance {{ $labels.instance }})"
+      description: "<!channel>  La charge CPU (15m) est élevée    VALUE = {{ $value }}    LABELS: {{ $labels.job }} : {{ $labels.instance }}"
+
+  - alert: ContextSwitching
+    expr: rate(node_context_switches_total[5m]) > ((count without (cpu, mode) (node_cpu_seconds_total{mode="system"})) * 1500) 
+    for: 15m
+    labels:
+      severity: critique
+    annotations:
+      identifier: "{{ $labels.instance }}"
+      summary: "Context switching (instance {{ $labels.instance }})"
+      description: "<!channel>  Le contexte switch augement sur l'hôte   VALUE = {{ $value }}    LABELS: {{ $labels.job }} : {{ $labels.instance }}"
+
+  - alert: Health endpoint down
+    expr: probe_success == 0
+    for: 10s
+    labels:
+      severity: critique
+    annotations:
+      identifier: "{{ $labels.instance }}"
+      summary: "Health endpoint is down"
+      description: "<!channel>  L'URL ne répond pas : {{ $labels.addresse }}"
+
+  - alert: Certificate exprire
+    expr: probe_ssl_earliest_cert_expiry{job="blackbox"} - time() < 86400 * 30
+    for: 10m
+    labels:
+      severity: critique
+    annotations:
+      identifier: "{{ $labels.instance }}"
+      summary: "SSL certificate expire"
+      description: "<!channel>  Le certificat SSL exprire dans 3 mois {{ $labels.addresse }}"

_docker/alertmanager/alertmanager.yml

@@ -0,0 +1,20 @@
+global:
+  resolve_timeout: 5m
+
+route:
+  group_by: ['...']
+  receiver: slack_general                                           # <-- Si une alerte est soulevée, l'envoyée à slack
+
+receivers:
+- name: slack_general
+  slack_configs:
+  - api_url: https://hooks.slack.com/services/<VOTRE WEBHOOK SLACK> # <-- Pensez à mettre votre URL de webhook slack ici
+    channel: alert-prod                                             # <-- Penser à mettre le bon channel ici
+    icon_emoji: ":rotating_light:"                                  # <-- L'emoji de votre choix pour s'afficher dans le channel slack
+    title_link: "http://127.0.0.1:9090/alerts"                      # <-- Ici on met l'url d'alertmanage pour reprendre le nom des alertes sur le /alerts
+    send_resolved: true                                             # <-- Ce booléen nous permet d'envoyer une seconde alerte quand elle est résolue
+    title: '{{ template "custom_title" . }}'                        # <-- Reprise du template
+    text: '{{ template "custom_slack_message" . }}'                 # <-- Reprise du template
+
+templates:
+  - '/etc/alertmanager/templates/default.tmpl'                      # <-- Template en go pour l'alerte slack, vous pouvez à peu près tout faire

_docker/alertmanager/templates/default.tmpl

@@ -0,0 +1,10 @@
+{{ define "custom_title" }}
+   {{ range .Alerts }}
+       {{ if eq .Status "firing" }}:broken_heart:{{else}}:green_heart:{{ end }} [{{ .Annotations.identifier }}] {{.Annotations.summary }}
+   {{end}}
+{{ end }}
+{{ define "custom_slack_message" }}
+    {{ range .Alerts }}
+        {{ .Annotations.description }}
+    {{end}}
+{{end}}

_docker/grafana/dashboards.yml

@@ -0,0 +1,12 @@
+apiVersion: 1
+
+providers:
+
+- name: 'Monitoring'
+  orgId: 1
+  folder: ''
+  type: file
+  disableDeletion: false
+  updateIntervalSeconds: 10 #how often Grafana will scan for changed dashboards
+  options:
+    path: /var/lib/grafana/dashboards

_docker/grafana/dashboards/flower.json

@@ -0,0 +1,770 @@
+{
+  "__inputs": [
+    {
+      "name": "DS_PROMETHEUS",
+      "label": "DS_PROMETHEUS",
+      "description": "",
+      "type": "datasource",
+      "pluginId": "prometheus",
+      "pluginName": "Prometheus"
+    }
+  ],
+  "__requires": [
+    {
+      "type": "grafana",
+      "id": "grafana",
+      "name": "Grafana",
+      "version": "7.5.2"
+    },
+    {
+      "type": "panel",
+      "id": "graph",
+      "name": "Graph",
+      "version": ""
+    },
+    {
+      "type": "datasource",
+      "id": "prometheus",
+      "name": "Prometheus",
+      "version": "2.0.0"
+    }
+  ],
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": "-- Grafana --",
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "description": "Basic celery monitoring example",
+  "editable": true,
+  "gnetId": null,
+  "graphTooltip": 0,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": "${DS_PROMETHEUS}",
+      "description": "This panel shows status of celery workers. 1 = online, 0 = offline.",
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": []
+      },
+      "fill": 1,
+      "fillGradient": 0,
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "hiddenSeries": false,
+      "id": 4,
+      "legend": {
+        "avg": false,
+        "current": false,
+        "max": false,
+        "min": false,
+        "show": true,
+        "total": false,
+        "values": false
+      },
+      "lines": true,
+      "linewidth": 1,
+      "nullPointMode": "null",
+      "options": {
+        "alertThreshold": true
+      },
+      "percentage": false,
+      "pluginVersion": "7.5.2",
+      "pointradius": 2,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "exemplar": true,
+          "expr": "flower_worker_online",
+          "interval": "",
+          "legendFormat": "{{ worker }}",
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeRegions": [],
+      "timeShift": null,
+      "title": "Celery Worker Status",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "buckets": null,
+        "mode": "time",
+        "name": null,
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "$$hashKey": "object:150",
+          "format": "short",
+          "label": "",
+          "logBase": 1,
+          "max": "1",
+          "min": "0",
+          "show": true
+        },
+        {
+          "$$hashKey": "object:151",
+          "decimals": null,
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": false
+        }
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": "${DS_PROMETHEUS}",
+      "description": "This panel shows number of tasks currently executing at worker.",
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": []
+      },
+      "fill": 1,
+      "fillGradient": 0,
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "hiddenSeries": false,
+      "id": 9,
+      "legend": {
+        "alignAsTable": true,
+        "avg": true,
+        "current": true,
+        "max": true,
+        "min": true,
+        "show": true,
+        "total": false,
+        "values": true
+      },
+      "lines": true,
+      "linewidth": 1,
+      "nullPointMode": "null",
+      "options": {
+        "alertThreshold": true
+      },
+      "percentage": false,
+      "pluginVersion": "7.5.2",
+      "pointradius": 2,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "exemplar": true,
+          "expr": "flower_worker_number_of_currently_executing_tasks",
+          "interval": "",
+          "legendFormat": "{{worker}}",
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeRegions": [],
+      "timeShift": null,
+      "title": "Number of Tasks Currently Executing at Worker",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "buckets": null,
+        "mode": "time",
+        "name": null,
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "$$hashKey": "object:79",
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        },
+        {
+          "$$hashKey": "object:80",
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": false
+        }
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": "${DS_PROMETHEUS}",
+      "description": "This panel shows average task runtime at worker by worker and task name.",
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": []
+      },
+      "fill": 1,
+      "fillGradient": 0,
+      "gridPos": {
+        "h": 9,
+        "w": 24,
+        "x": 0,
+        "y": 8
+      },
+      "hiddenSeries": false,
+      "id": 11,
+      "legend": {
+        "alignAsTable": true,
+        "avg": true,
+        "current": true,
+        "max": true,
+        "min": true,
+        "show": true,
+        "total": false,
+        "values": true
+      },
+      "lines": true,
+      "linewidth": 1,
+      "nullPointMode": "null",
+      "options": {
+        "alertThreshold": true
+      },
+      "percentage": false,
+      "pluginVersion": "7.5.2",
+      "pointradius": 2,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "exemplar": true,
+          "expr": "rate(flower_task_runtime_seconds_sum[5m]) / rate(flower_task_runtime_seconds_count[5m])",
+          "interval": "",
+          "legendFormat": "{{task}}, {{worker}}",
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeRegions": [],
+      "timeShift": null,
+      "title": "Average Task Runtime at Worker",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "buckets": null,
+        "mode": "time",
+        "name": null,
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "$$hashKey": "object:337",
+          "format": "s",
+          "label": "",
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        },
+        {
+          "$$hashKey": "object:338",
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": false
+        }
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": "${DS_PROMETHEUS}",
+      "description": "This panel shows task prefetch time at worker by worker and task name.",
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": []
+      },
+      "fill": 1,
+      "fillGradient": 0,
+      "gridPos": {
+        "h": 9,
+        "w": 24,
+        "x": 0,
+        "y": 17
+      },
+      "hiddenSeries": false,
+      "id": 12,
+      "legend": {
+        "alignAsTable": true,
+        "avg": true,
+        "current": true,
+        "max": true,
+        "min": true,
+        "show": true,
+        "total": false,
+        "values": true
+      },
+      "lines": true,
+      "linewidth": 1,
+      "nullPointMode": "null",
+      "options": {
+        "alertThreshold": true
+      },
+      "percentage": false,
+      "pluginVersion": "7.5.2",
+      "pointradius": 2,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "exemplar": true,
+          "expr": "flower_task_prefetch_time_seconds",
+          "interval": "",
+          "legendFormat": "{{task}}, {{worker}}",
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeRegions": [],
+      "timeShift": null,
+      "title": "Task Prefetch Time at Worker",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "buckets": null,
+        "mode": "time",
+        "name": null,
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "$$hashKey": "object:337",
+          "format": "s",
+          "label": "",
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        },
+        {
+          "$$hashKey": "object:338",
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": false
+        }
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": "${DS_PROMETHEUS}",
+      "description": "This panel shows number of tasks prefetched at worker by task and worker name.",
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": []
+      },
+      "fill": 1,
+      "fillGradient": 0,
+      "gridPos": {
+        "h": 9,
+        "w": 24,
+        "x": 0,
+        "y": 26
+      },
+      "hiddenSeries": false,
+      "id": 10,
+      "legend": {
+        "alignAsTable": true,
+        "avg": true,
+        "current": true,
+        "max": true,
+        "min": true,
+        "show": true,
+        "total": false,
+        "values": true
+      },
+      "lines": true,
+      "linewidth": 1,
+      "nullPointMode": "null",
+      "options": {
+        "alertThreshold": true
+      },
+      "percentage": false,
+      "pluginVersion": "7.5.2",
+      "pointradius": 2,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "exemplar": true,
+          "expr": "flower_worker_prefetched_tasks",
+          "interval": "",
+          "legendFormat": "{{task}}, {{worker}}",
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeRegions": [],
+      "timeShift": null,
+      "title": "Number of Tasks Prefetched At Worker",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "buckets": null,
+        "mode": "time",
+        "name": null,
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "$$hashKey": "object:337",
+          "format": "short",
+          "label": "",
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        },
+        {
+          "$$hashKey": "object:338",
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": false
+        }
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": "${DS_PROMETHEUS}",
+      "description": "This panel presents average task success ratio over time by task name.",
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": []
+      },
+      "fill": 1,
+      "fillGradient": 0,
+      "gridPos": {
+        "h": 7,
+        "w": 12,
+        "x": 0,
+        "y": 35
+      },
+      "hiddenSeries": false,
+      "id": 2,
+      "legend": {
+        "alignAsTable": true,
+        "avg": false,
+        "current": true,
+        "max": true,
+        "min": true,
+        "show": true,
+        "total": false,
+        "values": true
+      },
+      "lines": true,
+      "linewidth": 1,
+      "nullPointMode": "null",
+      "options": {
+        "alertThreshold": true
+      },
+      "percentage": false,
+      "pluginVersion": "7.5.2",
+      "pointradius": 2,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "exemplar": true,
+          "expr": "(sum(avg_over_time(flower_events_total{type=\"task-succeeded\"}[15m])) by (task)  / sum(avg_over_time(flower_events_total{type=~\"task-failed|task-succeeded\"}[15m])) by (task)) * 100",
+          "interval": "",
+          "legendFormat": "{{ task }}",
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeRegions": [],
+      "timeShift": null,
+      "title": "Task Success Ratio",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "buckets": null,
+        "mode": "time",
+        "name": null,
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "$$hashKey": "object:63",
+          "format": "percent",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        },
+        {
+          "$$hashKey": "object:64",
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": false
+        }
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": "${DS_PROMETHEUS}",
+      "description": "This panel presents average task failure ratio over time by task name.",
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": []
+      },
+      "fill": 1,
+      "fillGradient": 0,
+      "gridPos": {
+        "h": 7,
+        "w": 12,
+        "x": 12,
+        "y": 35
+      },
+      "hiddenSeries": false,
+      "id": 7,
+      "legend": {
+        "alignAsTable": true,
+        "avg": false,
+        "current": true,
+        "max": true,
+        "min": true,
+        "show": true,
+        "total": false,
+        "values": true
+      },
+      "lines": true,
+      "linewidth": 1,
+      "nullPointMode": "null",
+      "options": {
+        "alertThreshold": true
+      },
+      "percentage": false,
+      "pluginVersion": "7.5.2",
+      "pointradius": 2,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "exemplar": true,
+          "expr": "(sum(avg_over_time(flower_events_total{type=\"task-failed\"}[15m])) by (task) / sum(avg_over_time(flower_events_total{type=~\"task-failed|task-succeeded\"}[15m])) by (task)) * 100",
+          "interval": "",
+          "legendFormat": "{{ task }}",
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeRegions": [],
+      "timeShift": null,
+      "title": "Task Failure Ratio",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "buckets": null,
+        "mode": "time",
+        "name": null,
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "$$hashKey": "object:63",
+          "format": "percent",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": true
+        },
+        {
+          "$$hashKey": "object:64",
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": false
+        }
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
+    }
+  ],
+  "refresh": "10s",
+  "schemaVersion": 27,
+  "style": "dark",
+  "tags": [
+    "celery",
+    "monitoring",
+    "flower"
+  ],
+  "templating": {
+    "list": [
+      {
+        "hide": 0,
+        "label": "datasource",
+        "name": "DS_PROMETHEUS",
+        "options": [],
+        "query": "prometheus",
+        "refresh": 1,
+        "regex": "",
+        "type": "datasource"
+      }
+    ]
+  },
+  "time": {
+    "from": "now-15m",
+    "to": "now"
+  },
+  "timepicker": {},
+  "timezone": "",
+  "title": "Flower",
+  "uid": "3OBI1flGz",
+  "version": 9
+}

_docker/grafana/datasource.yml

@@ -0,0 +1,50 @@
+# config file version
+apiVersion: 1
+
+# list of datasources that should be deleted from the database
+deleteDatasources:
+  - name: Prometheus
+    orgId: 1
+
+# list of datasources to insert/update depending
+# whats available in the database
+datasources:
+  # <string, required> name of the datasource. Required
+  - name: Prometheus
+    # <string, required> datasource type. Required
+    type: prometheus
+    # <string, required> access mode. direct or proxy. Required
+    access: proxy
+    # <int> org id. will default to orgId 1 if not specified
+    orgId: 1
+    # <string> url
+    url: http://prometheus:9090
+    # <string> database password, if used
+    password:
+    # <string> database user, if used
+    user:
+    # <string> database name, if used
+    database:
+    # <bool> enable/disable basic auth
+    basicAuth: false
+    # <string> basic auth username, if used
+    basicAuthUser:
+    # <string> basic auth password, if used
+    basicAuthPassword:
+    # <bool> enable/disable with credentials headers
+    withCredentials:
+    # <bool> mark as default datasource. Max one per org
+    isDefault: true
+    # <map> fields that will be converted to json and stored in json_data
+    jsonData:
+      graphiteVersion: "1.1"
+      tlsAuth: false
+      tlsAuthWithCACert: false
+    # <string> json object of data that will be encrypted.
+    secureJsonData:
+      tlsCACert: "..."
+      tlsClientCert: "..."
+      tlsClientKey: "..."
+    version: 1
+    # <bool> allow users to edit datasources from the UI.
+    editable: true

_docker/grafana/grafana.ini

@@ -0,0 +1,486 @@
+##################### Grafana Configuration Example #####################
+#
+# Everything has defaults so you only need to uncomment things you want to
+# change
+
+# possible values : production, development
+;app_mode = production
+
+# instance name, defaults to HOSTNAME environment variable value or hostname if HOSTNAME var is empty
+;instance_name = ${HOSTNAME}
+
+#################################### Paths ####################################
+[paths]
+# Path to where grafana can store temp files, sessions, and the sqlite3 db (if that is used)
+;data = /var/lib/grafana
+
+# Temporary files in `data` directory older than given duration will be removed
+;temp_data_lifetime = 24h
+
+# Directory where grafana can store logs
+;logs = /var/log/grafana
+
+# Directory where grafana will automatically scan and look for plugins
+;plugins = /var/lib/grafana/plugins
+
+# folder that contains provisioning config files that grafana will apply on startup and while running.
+;provisioning = /etc/grafana/provisioning
+
+#################################### Server ####################################
+[server]
+# Protocol (http, https, socket)
+;protocol = http
+
+# The ip address to bind to, empty will bind to all interfaces
+;http_addr =
+
+# The http port  to use
+;http_port = 3000
+
+# The public facing domain name used to access grafana from a browser
+;domain =
+
+# Redirect to correct domain if host header does not match domain
+# Prevents DNS rebinding attacks
+;enforce_domain = false
+
+# The full public facing url you use in browser, used for redirects and emails
+# If you use reverse proxy and sub path specify full url (with sub path)
+;root_url = 
+
+# Log web requests
+;router_logging = false
+
+# the path relative working path
+;static_root_path = public
+
+# enable gzip
+;enable_gzip = false
+
+# https certs & key file
+;cert_file =
+;cert_key =
+
+# Unix socket path
+;socket =
+
+#################################### Database ####################################
+[database]
+# You can configure the database connection by specifying type, host, name, user and password
+# as separate properties or as on string using the url properties.
+
+# Either "mysql", "postgres" or "sqlite3", it's your choice
+;type = sqlite3
+;host = 127.0.0.1:3306
+;name = grafana
+;user = root
+# If the password contains # or ; you have to wrap it with triple quotes. Ex """#password;"""
+;password =
+
+# Use either URL or the previous fields to configure the database
+# Example: mysql://user:secret@host:port/database
+;url =
+
+# For "postgres" only, either "disable", "require" or "verify-full"
+;ssl_mode = disable
+
+# For "sqlite3" only, path relative to data_path setting
+;path = grafana.db
+
+# Max idle conn setting default is 2
+;max_idle_conn = 2
+
+# Max conn setting default is 0 (mean not set)
+;max_open_conn =
+
+# Connection Max Lifetime default is 14400 (means 14400 seconds or 4 hours)
+;conn_max_lifetime = 14400
+
+# Set to true to log the sql calls and execution times.
+log_queries =
+
+#################################### Session ####################################
+[session]
+# Either "memory", "file", "redis", "mysql", "postgres", default is "file"
+;provider = file
+
+# Provider config options
+# memory: not have any config yet
+# file: session dir path, is relative to grafana data_path
+# redis: config like redis server e.g. `addr=127.0.0.1:6379,pool_size=100,db=grafana`
+# mysql: go-sql-driver/mysql dsn config string, e.g. `user:password@tcp(127.0.0.1:3306)/database_name`
+# postgres: user=a password=b host=localhost port=5432 dbname=c sslmode=disable
+;provider_config = sessions
+
+# Session cookie name
+;cookie_name = grafana_sess
+
+# If you use session in https only, default is false
+;cookie_secure = false
+
+# Session life time, default is 86400
+;session_life_time = 86400
+
+#################################### Data proxy ###########################
+[dataproxy]
+
+# This enables data proxy logging, default is false
+;logging = false
+
+#################################### Analytics ####################################
+[analytics]
+# Server reporting, sends usage counters to stats.grafana.org every 24 hours.
+# No ip addresses are being tracked, only simple counters to track
+# running instances, dashboard and error counts. It is very helpful to us.
+# Change this option to false to disable reporting.
+;reporting_enabled = true
+
+# Set to false to disable all checks to https://grafana.net
+# for new vesions (grafana itself and plugins), check is used
+# in some UI views to notify that grafana or plugin update exists
+# This option does not cause any auto updates, nor send any information
+# only a GET request to http://grafana.com to get latest versions
+;check_for_updates = true
+
+# Google Analytics universal tracking code, only enabled if you specify an id here
+;google_analytics_ua_id =
+
+#################################### Security ####################################
+[security]
+# default admin user, created on startup
+admin_user = admin
+
+# default admin password, can be changed before first start of grafana,  or in profile settings
+admin_password = admin
+
+# used for signing
+;secret_key = SW2YcwTIb9zpOOhoPsMm
+
+# Auto-login remember days
+;login_remember_days = 7
+;cookie_username = grafana_user
+;cookie_remember_name = grafana_remember
+
+# disable gravatar profile images
+;disable_gravatar = false
+
+# data source proxy whitelist (ip_or_domain:port separated by spaces)
+;data_source_proxy_whitelist =
+
+# disable protection against brute force login attempts
+;disable_brute_force_login_protection = false
+
+#################################### Snapshots ###########################
+[snapshots]
+# snapshot sharing options
+;external_enabled = true
+;external_snapshot_url = https://snapshots-origin.raintank.io
+;external_snapshot_name = Publish to snapshot.raintank.io
+
+# remove expired snapshot
+;snapshot_remove_expired = true
+
+#################################### Dashboards History ##################
+[dashboards]
+# Number dashboard versions to keep (per dashboard). Default: 20, Minimum: 1
+;versions_to_keep = 20
+
+#################################### Users ###############################
+[users]
+# disable user signup / registration
+;allow_sign_up = true
+
+# Allow non admin users to create organizations
+;allow_org_create = true
+
+# Set to true to automatically assign new users to the default organization (id 1)
+;auto_assign_org = true
+
+# Default role new users will be automatically assigned (if disabled above is set to true)
+;auto_assign_org_role = Viewer
+
+# Background text for the user field on the login page
+;login_hint = email or username
+
+# Default UI theme ("dark" or "light")
+;default_theme = dark
+
+# External user management, these options affect the organization users view
+;external_manage_link_url =
+;external_manage_link_name =
+;external_manage_info =
+
+# Viewers can edit/inspect dashboard settings in the browser. But not save the dashboard.
+;viewers_can_edit = false
+
+[auth]
+# Set to true to disable (hide) the login form, useful if you use OAuth, defaults to false
+;disable_login_form = false
+
+# Set to true to disable the signout link in the side menu. useful if you use auth.proxy, defaults to false
+;disable_signout_menu = false
+
+# URL to redirect the user to after sign out
+;signout_redirect_url =
+
+# Set to true to attempt login with OAuth automatically, skipping the login screen.
+# This setting is ignored if multiple OAuth providers are configured.
+;oauth_auto_login = false
+
+#################################### Anonymous Auth ##########################
+[auth.anonymous]
+# enable anonymous access
+;enabled = false
+
+# specify organization name that should be used for unauthenticated users
+;org_name = Main Org.
+
+# specify role for unauthenticated users
+;org_role = Viewer
+
+#################################### Github Auth ##########################
+[auth.github]
+;enabled = false
+;allow_sign_up = true
+;client_id = some_id
+;client_secret = some_secret
+;scopes = user:email,read:org
+;auth_url = https://github.com/login/oauth/authorize
+;token_url = https://github.com/login/oauth/access_token
+;api_url = https://api.github.com/user
+;team_ids =
+;allowed_organizations =
+
+#################################### Google Auth ##########################
+[auth.google]
+# enabled = true
+# allow_sign_up = true
+# client_id =
+# client_secret =
+# scopes = https://www.googleapis.com/auth/userinfo.profile https://www.googleapis.com/auth/userinfo.email
+# auth_url = https://accounts.google.com/o/oauth2/auth
+# token_url = https://accounts.google.com/o/oauth2/token
+# api_url = https://www.googleapis.com/oauth2/v1/userinfo
+;allowed_domains =
+
+#################################### Generic OAuth ##########################
+[auth.generic_oauth]
+;enabled = false
+;name = OAuth
+;allow_sign_up = true
+;client_id = some_id
+;client_secret = some_secret
+;scopes = user:email,read:org
+;auth_url = https://foo.bar/login/oauth/authorize
+;token_url = https://foo.bar/login/oauth/access_token
+;api_url = https://foo.bar/user
+;team_ids =
+;allowed_organizations =
+;tls_skip_verify_insecure = false
+;tls_client_cert =
+;tls_client_key =
+;tls_client_ca =
+
+#################################### Grafana.com Auth ####################
+[auth.grafana_com]
+;enabled = false
+;allow_sign_up = true
+;client_id = some_id
+;client_secret = some_secret
+;scopes = user:email
+;allowed_organizations =
+
+#################################### Auth Proxy ##########################
+[auth.proxy]
+;enabled = false
+;header_name = X-WEBAUTH-USER
+;header_property = username
+;auto_sign_up = true
+;ldap_sync_ttl = 60
+;whitelist = 192.168.1.1, 192.168.2.1
+;headers = Email:X-User-Email, Name:X-User-Name
+
+#################################### Basic Auth ##########################
+[auth.basic]
+;enabled = true
+
+#################################### Auth LDAP ##########################
+[auth.ldap]
+;enabled = false
+;config_file = /etc/grafana/ldap.toml
+;allow_sign_up = true
+
+#################################### SMTP / Emailing ##########################
+[smtp]
+;enabled = true
+;host =
+;user =
+# If the password contains # or ; you have to wrap it with trippel quotes. Ex """#password;"""
+;password = ""
+;cert_file =
+;key_file =
+;skip_verify = true
+;from_address =
+;from_name =
+# EHLO identity in SMTP dialog (defaults to instance_name)
+;ehlo_identity = dashboard.example.com
+
+[emails]
+;welcome_email_on_sign_up = false
+
+#################################### Logging ##########################
+[log]
+# Either "console", "file", "syslog". Default is console and  file
+# Use space to separate multiple modes, e.g. "console file"
+;mode = console file
+
+# Either "debug", "info", "warn", "error", "critical", default is "info"
+;level = info
+
+# optional settings to set different levels for specific loggers. Ex filters = sqlstore:debug
+;filters =
+
+# For "console" mode only
+[log.console]
+;level =
+
+# log line format, valid options are text, console and json
+;format = console
+
+# For "file" mode only
+[log.file]
+;level =
+
+# log line format, valid options are text, console and json
+;format = text
+
+# This enables automated log rotate(switch of following options), default is true
+;log_rotate = true
+
+# Max line number of single file, default is 1000000
+;max_lines = 1000000
+
+# Max size shift of single file, default is 28 means 1 << 28, 256MB
+;max_size_shift = 28
+
+# Segment log daily, default is true
+;daily_rotate = true
+
+# Expired days of log file(delete after max days), default is 7
+;max_days = 7
+
+[log.syslog]
+;level =
+
+# log line format, valid options are text, console and json
+;format = text
+
+# Syslog network type and address. This can be udp, tcp, or unix. If left blank, the default unix endpoints will be used.
+;network =
+;address =
+
+# Syslog facility. user, daemon and local0 through local7 are valid.
+;facility =
+
+# Syslog tag. By default, the process' argv[0] is used.
+;tag =
+
+#################################### Alerting ############################
+[alerting]
+# Disable alerting engine & UI features
+;enabled = true
+# Makes it possible to turn off alert rule execution but alerting UI is visible
+;execute_alerts = true
+
+# Default setting for new alert rules. Defaults to categorize error and timeouts as alerting. (alerting, keep_state)
+;error_or_timeout = alerting
+
+# Default setting for how Grafana handles nodata or null values in alerting. (alerting, no_data, keep_state, ok)
+;nodata_or_nullvalues = no_data
+
+# Alert notifications can include images, but rendering many images at the same time can overload the server
+# This limit will protect the server from render overloading and make sure notifications are sent out quickly
+;concurrent_render_limit = 5
+
+#################################### Explore #############################
+[explore]
+# Enable the Explore section
+;enabled = false
+
+#################################### Internal Grafana Metrics ##########################
+# Metrics available at HTTP API Url /metrics
+[metrics]
+# Disable / Enable internal metrics
+;enabled           = true
+
+# Publish interval
+;interval_seconds  = 10
+
+# Send internal metrics to Graphite
+[metrics.graphite]
+# Enable by setting the address setting (ex localhost:2003)
+;address =
+;prefix = prod.grafana.%(instance_name)s.
+
+#################################### Distributed tracing ############
+[tracing.jaeger]
+# Enable by setting the address sending traces to jaeger (ex localhost:6831)
+;address = localhost:6831
+# Tag that will always be included in when creating new spans. ex (tag1:value1,tag2:value2)
+;always_included_tag = tag1:value1
+# Type specifies the type of the sampler: const, probabilistic, rateLimiting, or remote
+;sampler_type = const
+# jaeger samplerconfig param
+# for "const" sampler, 0 or 1 for always false/true respectively
+# for "probabilistic" sampler, a probability between 0 and 1
+# for "rateLimiting" sampler, the number of spans per second
+# for "remote" sampler, param is the same as for "probabilistic"
+# and indicates the initial sampling rate before the actual one
+# is received from the mothership
+;sampler_param = 1
+
+#################################### Grafana.com integration  ##########################
+# Url used to import dashboards directly from Grafana.com
+[grafana_com]
+;url = https://grafana.com
+
+#################################### External image storage ##########################
+[external_image_storage]
+# Used for uploading images to public servers so they can be included in slack/email messages.
+# you can choose between (s3, webdav, gcs, azure_blob, local)
+;provider =
+
+[external_image_storage.s3]
+;bucket =
+;region =
+;path =
+;access_key =
+;secret_key =
+
+[external_image_storage.webdav]
+;url =
+;public_url =
+;username =
+;password =
+
+[external_image_storage.gcs]
+;key_file =
+;bucket =
+;path =
+
+[external_image_storage.azure_blob]
+;account_name =
+;account_key =
+;container_name =
+
+[external_image_storage.local]
+# does not require any configuration
+
+[rendering]
+# Options to configure external image rendering server like https://github.com/grafana/grafana-image-renderer
+;server_url =
+;callback_url =
+
+[enterprise]
+# Path to a valid Grafana Enterprise license.jwt file
+;license_path =

_docker/postgres/create_tables.sql

@@ -0,0 +1,154 @@
+-- Source unique de creation des tables de la base booksync.
+
+CREATE TABLE IF NOT EXISTS "AUTHORS" (
+	id VARCHAR(36) NOT NULL,
+	name VARCHAR(255) NOT NULL,
+	first_name VARCHAR(255),
+	tasks_count INTEGER NOT NULL,
+	PRIMARY KEY (id)
+);
+
+CREATE TABLE IF NOT EXISTS "JOBS" (
+	id VARCHAR(36) NOT NULL,
+	title VARCHAR(255) NOT NULL,
+	PRIMARY KEY (id)
+);
+
+CREATE TABLE IF NOT EXISTS "KINDS" (
+	id VARCHAR(36) NOT NULL,
+	name VARCHAR(255) NOT NULL,
+	PRIMARY KEY (id)
+);
+
+CREATE TABLE IF NOT EXISTS "PUBLISHERS" (
+	id VARCHAR(36) NOT NULL,
+	title VARCHAR(500) NOT NULL,
+	closed BOOLEAN NOT NULL,
+	editions_count INTEGER NOT NULL,
+	no_amazon BOOLEAN NOT NULL,
+	PRIMARY KEY (id)
+);
+
+CREATE TABLE IF NOT EXISTS "SERIES_TYPES" (
+	id VARCHAR(36) NOT NULL,
+	title VARCHAR(255) NOT NULL,
+	to_display BOOLEAN,
+	PRIMARY KEY (id)
+);
+
+CREATE TABLE IF NOT EXISTS "BOX_EDITIONS" (
+	id VARCHAR(36) NOT NULL,
+	title VARCHAR(500) NOT NULL,
+	publisher_id VARCHAR(36) NOT NULL,
+	boxes_count INTEGER NOT NULL,
+	adult_content BOOLEAN NOT NULL,
+	box_follow_editions_count INTEGER NOT NULL,
+	PRIMARY KEY (id),
+	FOREIGN KEY(publisher_id) REFERENCES "PUBLISHERS" (id)
+);
+
+CREATE TABLE IF NOT EXISTS "SERIES" (
+	id VARCHAR(36) NOT NULL,
+	title VARCHAR(500) NOT NULL,
+	type_id VARCHAR(36),
+	adult_content BOOLEAN,
+	editions_count INTEGER,
+	tasks_count INTEGER,
+	PRIMARY KEY (id),
+	FOREIGN KEY(type_id) REFERENCES "SERIES_TYPES" (id)
+);
+
+CREATE TABLE IF NOT EXISTS "BOXES" (
+	id VARCHAR(36) NOT NULL,
+	title VARCHAR(500) NOT NULL,
+	number INTEGER NOT NULL,
+	release_date DATE,
+	isbn VARCHAR(32),
+	asin VARCHAR(32),
+	commercial_stop BOOLEAN NOT NULL,
+	box_edition_id VARCHAR(36) NOT NULL,
+	box_possessions_count INTEGER NOT NULL,
+	image_url TEXT,
+	content TEXT,
+	PRIMARY KEY (id),
+	FOREIGN KEY(box_edition_id) REFERENCES "BOX_EDITIONS" (id)
+);
+
+CREATE TABLE IF NOT EXISTS "EDITIONS" (
+	id VARCHAR(36) NOT NULL,
+	title VARCHAR(500),
+	series_id VARCHAR(36) NOT NULL,
+	publisher_id VARCHAR(36) NOT NULL,
+	parent_edition_id VARCHAR(36),
+	volumes_count INTEGER NOT NULL,
+	last_volume_number INTEGER,
+	commercial_stop BOOLEAN NOT NULL,
+	not_finished BOOLEAN NOT NULL,
+	follow_editions_count INTEGER NOT NULL,
+	PRIMARY KEY (id),
+	FOREIGN KEY(series_id) REFERENCES "SERIES" (id),
+	FOREIGN KEY(publisher_id) REFERENCES "PUBLISHERS" (id),
+	FOREIGN KEY(parent_edition_id) REFERENCES "EDITIONS" (id)
+);
+
+CREATE TABLE IF NOT EXISTS "SERIES_KINDS" (
+	series_id VARCHAR(36) NOT NULL,
+	kind_id VARCHAR(36) NOT NULL,
+	PRIMARY KEY (series_id, kind_id),
+	FOREIGN KEY(series_id) REFERENCES "SERIES" (id) ON DELETE CASCADE,
+	FOREIGN KEY(kind_id) REFERENCES "KINDS" (id) ON DELETE CASCADE
+);
+
+CREATE TABLE IF NOT EXISTS "TASKS" (
+	id VARCHAR(36) NOT NULL,
+	series_id VARCHAR(36) NOT NULL,
+	author_id VARCHAR(36),
+	job_id VARCHAR(36),
+	PRIMARY KEY (id),
+	FOREIGN KEY(series_id) REFERENCES "SERIES" (id),
+	FOREIGN KEY(author_id) REFERENCES "AUTHORS" (id),
+	FOREIGN KEY(job_id) REFERENCES "JOBS" (id)
+);
+
+CREATE TABLE IF NOT EXISTS "VOLUMES" (
+	id VARCHAR(36) NOT NULL,
+	title VARCHAR(500),
+	number INTEGER NOT NULL,
+	release_date DATE,
+	isbn VARCHAR(32),
+	asin VARCHAR(32),
+	edition_id VARCHAR(36) NOT NULL,
+	possessions_count INTEGER NOT NULL,
+	not_sold BOOLEAN NOT NULL,
+	image_url TEXT,
+	nb_pages INTEGER,
+	content TEXT,
+	PRIMARY KEY (id),
+	FOREIGN KEY(edition_id) REFERENCES "EDITIONS" (id)
+);
+
+CREATE TABLE IF NOT EXISTS "BOX_VOLUMES" (
+	id VARCHAR(36) NOT NULL,
+	box_id VARCHAR(36) NOT NULL,
+	volume_id VARCHAR(36) NOT NULL,
+	included BOOLEAN NOT NULL,
+	PRIMARY KEY (id),
+	FOREIGN KEY(box_id) REFERENCES "BOXES" (id),
+	FOREIGN KEY(volume_id) REFERENCES "VOLUMES" (id)
+);
+
+CREATE TABLE IF NOT EXISTS "VOLUME_POSSESSION_HISTORY" (
+	id_volume VARCHAR(36) NOT NULL,
+	observed_at TIMESTAMP WITH TIME ZONE NOT NULL,
+	possessions_count INTEGER NOT NULL,
+	PRIMARY KEY (id_volume, observed_at),
+	FOREIGN KEY(id_volume) REFERENCES "VOLUMES" (id) ON DELETE CASCADE
+);
+
+CREATE TABLE IF NOT EXISTS "BOX_POSSESSION_HISTORY" (
+	id_box VARCHAR(36) NOT NULL,
+	observed_at TIMESTAMP WITH TIME ZONE NOT NULL,
+	box_possessions_count INTEGER NOT NULL,
+	PRIMARY KEY (id_box, observed_at),
+	FOREIGN KEY(id_box) REFERENCES "BOXES" (id) ON DELETE CASCADE
+);

_docker/prometheus/prometheus.yml

@@ -0,0 +1,57 @@
+# my global config
+global:
+  scrape_interval:     5s # By default, scrape targets every 15 seconds.
+  evaluation_interval: 5s # By default, scrape targets every 15 seconds.
+  # 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:
+    env: 'infrastructure' # C'est simplement le nom de votre environnement
+
+# spécification du serveur alertmanager
+alerting:
+  alertmanagers:
+  - static_configs:
+    - targets:
+      - alertmanager:9093
+    scheme: http
+    timeout: 10s
+
+# fichier de règles pour l'alerting, c'est dans ce fichier que sont les définitions des alertes
+rule_files:
+- '/alertmanager/alert.rules/alerts.rules.yml'
+
+scrape_configs:
+- job_name: 'prometheus'
+  scrape_interval: 5s
+  static_configs:
+    - targets: ['prometheus:9090']
+
+- job_name: 'node-exporter'
+  scrape_interval: 5s
+  static_configs:
+  - targets: ['node-exporter:9100']
+
+- job_name: 'postgres-exporter'
+  scrape_interval: 300s
+  scrape_timeout: 60s
+  static_configs:
+  - targets: ['postgres-exporter:9187']
+
+- job_name: 'rabbitmq'
+  metrics_path: /metrics/per-object
+  static_configs:
+  - targets: ['rabbitmq:15692']
+
+- job_name: 'redis-exporter'
+  static_configs:
+  - targets: ['redis-exporter:9121']
+
+- job_name: 'flower'
+  static_configs:
+  - targets: ['flower:5555']
+
+- job_name: 'booksync-api'
+  static_configs:
+  - targets: ['booksync-api:5000']