04/12/25

observabilite/observability/vm_observabilite/observability/grafana/dashboards/dev/00_app_runtime_overview.json

@@ -0,0 +1,40 @@
+{
+  "title": "App Runtime Overview (Dev)",
+  "uid": "dev-app-runtime-overview",
+  "tags": ["dev","application"],
+  "time": { "from": "now-1h", "to": "now" },
+  "schemaVersion": 42,
+  "panels": [
+    {
+      "type": "timeseries",
+      "title": "Requests per Second (RPS)",
+      "gridPos": {"x":0,"y":0,"w":12,"h":8},
+      "datasource": "prometheus",
+      "targets": [
+        { "refId": "A", "expr": "sum(rate(http_requests_total[2m]))" }
+      ]
+    },
+    {
+      "type": "timeseries",
+      "title": "Error Rate (%)",
+      "gridPos": {"x":12,"y":0,"w":12,"h":8},
+      "datasource": "prometheus",
+      "fieldConfig": { "defaults": { "unit": "percent" }, "overrides": [] },
+      "targets": [
+        { "refId": "A", "expr": "sum(rate(http_requests_total{status=~\"5..\"}[2m])) / sum(rate(http_requests_total[2m])) * 100" }
+      ]
+    },
+    {
+      "type": "timeseries",
+      "title": "Latency P95 (s)",
+      "gridPos": {"x":0,"y":8,"w":24,"h":8},
+      "datasource": "prometheus",
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "histogram_quantile(0.95, sum by (le) (rate(http_request_duration_seconds_bucket[2m])))"
+        }
+      ]
+    }
+  ]
+}

observabilite/observability/vm_observabilite/observability/grafana/dashboards/dev/01_logs_by_service.json

@@ -0,0 +1,58 @@
+{
+  "title": "Logs by Service (Dev)",
+  "uid": "dev-logs-by-service",
+  "tags": ["dev","logs","loki"],
+  "time": { "from": "now-1h", "to": "now" },
+  "schemaVersion": 42,
+  "templating": {
+    "list": [
+      {
+        "name": "service",
+        "label": "Service (label app)",
+        "type": "query",
+        "datasource": "loki",
+        "query": "label_values({app!=\"\"}, app)",
+        "includeAll": true,
+        "multi": true,
+        "refresh": 2,
+        "current": {}
+      }
+    ]
+  },
+  "panels": [
+    {
+      "type": "logs",
+      "title": "Logs – $service",
+      "gridPos": { "x": 0, "y": 0, "w": 24, "h": 12 },
+      "datasource": "loki",
+      "options": {
+        "showLabels": true,
+        "showTime": true,
+        "wrapLogMessage": true,
+        "prettifyLogMessage": true
+      },
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "{app=~\"$service\"}"
+        }
+      ]
+    },
+    {
+      "type": "timeseries",
+      "title": "Error rate (logs/min) – $service",
+      "gridPos": { "x": 0, "y": 12, "w": 24, "h": 8 },
+      "datasource": "loki",
+      "fieldConfig": { "defaults": { "unit": "ops" }, "overrides": [] },
+      "options": {
+        "legend": { "showLegend": true, "placement": "bottom" }
+      },
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "sum by (app)(rate({app=~\"$service\"} |~ \"(?i)(error|exception|fail|timeout)\"[5m])) * 60"
+        }
+      ]
+    }
+  ]
+}

observabilite/observability/vm_observabilite/observability/grafana/dashboards/ops/00_infra_overview.json

@@ -0,0 +1,49 @@
+{
+  "title": "Infra Overview (Ops)",
+  "uid": "ops-infra-overview",
+  "tags": ["ops","infrastructure"],
+  "time": { "from": "now-1h", "to": "now" },
+  "schemaVersion": 42,
+  "panels": [
+    {
+      "type": "timeseries",
+      "title": "CPU Utilization (%)",
+      "gridPos": {"x":0,"y":0,"w":12,"h":8},
+      "datasource": "prometheus",
+      "fieldConfig": { "defaults": { "unit": "percent" }, "overrides": [] },
+      "targets": [
+        { "refId": "A", "expr": "100 - (avg by(instance)(rate(node_cpu_seconds_total{mode=\"idle\"}[2m]))*100)" }
+      ]
+    },
+    {
+      "type": "timeseries",
+      "title": "Memory Utilization (%)",
+      "gridPos": {"x":12,"y":0,"w":12,"h":8},
+      "datasource": "prometheus",
+      "fieldConfig": { "defaults": { "unit": "percent" }, "overrides": [] },
+      "targets": [
+        { "refId": "A", "expr": "((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes) * 100" }
+      ]
+    },
+    {
+      "type": "timeseries",
+      "title": "Disk Space Used (bytes)",
+      "gridPos": {"x":0,"y":8,"w":12,"h":8},
+      "datasource": "prometheus",
+      "fieldConfig": { "defaults": { "unit": "bytes" }, "overrides": [] },
+      "targets": [
+        { "refId": "A", "expr": "node_filesystem_size_bytes{fstype!~\"tmpfs|overlay\"} - node_filesystem_avail_bytes{fstype!~\"tmpfs|overlay\"}" }
+      ]
+    },
+    {
+      "type": "timeseries",
+      "title": "Host Power (Watts) - Scaphandre",
+      "gridPos": {"x":12,"y":8,"w":12,"h":8},
+      "datasource": "prometheus",
+      "fieldConfig": { "defaults": { "unit": "watt" }, "overrides": [] },
+      "targets": [
+        { "refId": "A", "expr": "scaph_host_power_microwatts / 1e6" }
+      ]
+    }
+  ]
+}

observabilite/observability/vm_observabilite/observability/grafana/dashboards/ops/03_prometheus_health.json

@@ -0,0 +1,86 @@
+{
+  "title": "Prometheus Health (Ops)",
+  "uid": "ops-prom-health",
+  "tags": ["ops","prometheus","health"],
+  "time": { "from": "now-1h", "to": "now" },
+  "schemaVersion": 42,
+  "panels": [
+    {
+      "type": "stat",
+      "title": "Targets DOWN (total)",
+      "gridPos": { "x": 0, "y": 0, "w": 6, "h": 4 },
+      "datasource": "prometheus",
+      "fieldConfig": { "defaults": { "unit": "none" }, "overrides": [] },
+      "options": { "reduceOptions": { "calcs": ["lastNotNull"], "fields": "" } },
+      "targets": [
+        { "refId": "A", "expr": "sum(1 - up)" }
+      ]
+    },
+    {
+      "type": "stat",
+      "title": "Alerts firing",
+      "gridPos": { "x": 6, "y": 0, "w": 6, "h": 4 },
+      "datasource": "prometheus",
+      "fieldConfig": { "defaults": { "unit": "none" }, "overrides": [] },
+      "options": { "reduceOptions": { "calcs": ["lastNotNull"], "fields": "" } },
+      "targets": [
+        { "refId": "A", "expr": "count(ALERTS{alertstate=\"firing\"})" }
+      ]
+    },
+    {
+      "type": "stat",
+      "title": "Ingest rate (samples/s)",
+      "gridPos": { "x": 12, "y": 0, "w": 12, "h": 4 },
+      "datasource": "prometheus",
+      "fieldConfig": { "defaults": { "unit": "ops" }, "overrides": [] },
+      "options": { "reduceOptions": { "calcs": ["lastNotNull"] } },
+      "targets": [
+        { "refId": "A", "expr": "rate(prometheus_tsdb_head_samples_appended_total[5m])" }
+      ]
+    },
+    {
+      "type": "timeseries",
+      "title": "Targets UP by job",
+      "gridPos": { "x": 0, "y": 4, "w": 12, "h": 8 },
+      "datasource": "prometheus",
+      "fieldConfig": { "defaults": { "unit": "none" }, "overrides": [] },
+      "options": { "legend": { "showLegend": true, "placement": "bottom" } },
+      "targets": [
+        { "refId": "A", "expr": "sum by(job)(up)" }
+      ]
+    },
+    {
+      "type": "timeseries",
+      "title": "Scrape duration (s) by job",
+      "gridPos": { "x": 12, "y": 4, "w": 12, "h": 8 },
+      "datasource": "prometheus",
+      "fieldConfig": { "defaults": { "unit": "s" }, "overrides": [] },
+      "options": { "legend": { "showLegend": true, "placement": "bottom" } },
+      "targets": [
+        { "refId": "A", "expr": "avg by(job)(scrape_duration_seconds)" }
+      ]
+    },
+    {
+      "type": "timeseries",
+      "title": "Rule group eval duration (s)",
+      "gridPos": { "x": 0, "y": 12, "w": 12, "h": 8 },
+      "datasource": "prometheus",
+      "fieldConfig": { "defaults": { "unit": "s" }, "overrides": [] },
+      "options": { "legend": { "showLegend": true, "placement": "bottom" } },
+      "targets": [
+        { "refId": "A", "expr": "max by(rule_group) (prometheus_rule_group_last_duration_seconds)" }
+      ]
+    },
+    {
+      "type": "timeseries",
+      "title": "TSDB head chunks",
+      "gridPos": { "x": 12, "y": 12, "w": 12, "h": 8 },
+      "datasource": "prometheus",
+      "fieldConfig": { "defaults": { "unit": "short" }, "overrides": [] },
+      "options": { "legend": { "showLegend": true, "placement": "bottom" } },
+      "targets": [
+        { "refId": "A", "expr": "prometheus_tsdb_head_chunks" }
+      ]
+    }
+  ]
+}

observabilite/observability/vm_observabilite/observability/grafana/dashboards/ops/04_logs_loki_ops.json

@@ -0,0 +1,65 @@
+{
+  "title": "Logs – Ops (Errors & System)",
+  "uid": "ops-logs-errors",
+  "tags": ["ops","logs","loki"],
+  "time": { "from": "now-2h", "to": "now" },
+  "schemaVersion": 42,
+  "templating": {
+    "list": [
+      {
+        "name": "job",
+        "label": "Job",
+        "type": "query",
+        "datasource": "loki",
+        "query": "label_values(job)",
+        "includeAll": true,
+        "multi": true,
+        "refresh": 2
+      },
+      {
+        "name": "instance",
+        "label": "Instance",
+        "type": "query",
+        "datasource": "loki",
+        "query": "label_values({job=~\"$job\"}, instance)",
+        "includeAll": true,
+        "multi": true,
+        "refresh": 2
+      }
+    ]
+  },
+  "panels": [
+    {
+      "type": "timeseries",
+      "title": "Error rate by instance (logs/min)",
+      "gridPos": { "x": 0, "y": 0, "w": 24, "h": 8 },
+      "datasource": "loki",
+      "fieldConfig": { "defaults": { "unit": "ops" }, "overrides": [] },
+      "options": { "legend": { "showLegend": true, "placement": "bottom" } },
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "sum by (instance)(rate({job=~\"$job\", instance=~\"$instance\"} |~ \"(?i)(critical|error|err)\"[5m])) * 60"
+        }
+      ]
+    },
+    {
+      "type": "logs",
+      "title": "Recent critical & errors – $job / $instance",
+      "gridPos": { "x": 0, "y": 8, "w": 24, "h": 14 },
+      "datasource": "loki",
+      "options": {
+        "showLabels": true,
+        "showTime": true,
+        "wrapLogMessage": true,
+        "prettifyLogMessage": true
+      },
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "{job=~\"$job\", instance=~\"$instance\"} |~ \"(?i)(critical|error|err|panic|oom)\""
+        }
+      ]
+    }
+  ]
+}

observabilite/observability/vm_observabilite/observability/grafana/provisioning/dashboards/folders.yaml

@@ -0,0 +1,7 @@
+apiVersion: 1
+
+folders:
+  - uid: ops-folder
+    title: "Ops – Infrastructure & Plateforme"
+  - uid: dev-folder
+    title: "Dev – Application & Qualité"

observabilite/observability/vm_observabilite/observability/grafana/provisioning/dashboards/provider-dev.yaml

@@ -0,0 +1,12 @@
+apiVersion: 1
+providers:
+  - name: "dev-dashboards"
+    orgId: 1
+    folderUid: "dev-folder"
+    type: file
+    disableDeletion: false
+    editable: true
+    updateIntervalSeconds: 30
+    options:
+      path: /var/lib/grafana/dashboards/dev
+      foldersFromFilesStructure: true

observabilite/observability/vm_observabilite/observability/grafana/provisioning/dashboards/provider-ops.yaml

@@ -0,0 +1,12 @@
+apiVersion: 1
+providers:
+  - name: "ops-dashboards"
+    orgId: 1
+    folderUid: "ops-folder"
+    type: file
+    disableDeletion: false
+    editable: true
+    updateIntervalSeconds: 30
+    options:
+      path: /var/lib/grafana/dashboards/ops
+      foldersFromFilesStructure: true

observabilite/observability/vm_observabilite/observability/grafana/provisioning/datasources/prometheus.yaml

@@ -0,0 +1,8 @@
+apiVersion: 1
+datasources:
+  - name: prometheus
+    type: prometheus
+    access: proxy
+    url: http://prometheus:9090
+    isDefault: true
+    editable: true