From 82f3dae6ab3d1b40ae3913917bac48d9eb8d8d0c Mon Sep 17 00:00:00 2001 From: nkozobrod Date: Fri, 31 Jul 2026 15:24:11 +0300 Subject: [PATCH] Initial: Prometheus + Grafana monitoring stack - Prometheus with 9 scrape targets - Grafana with Home Server Overview dashboard - Exporters: node_exporter, cadvisor, postgres_exporter (x3), qbittorrent - Traefik and Gitea metrics enabled --- .gitignore | 4 + docker-compose.yml | 140 ++++++++++++++ grafana/provisioning/dashboards/default.yml | 11 ++ .../dashboards/home-overview.json | 173 ++++++++++++++++++ .../provisioning/datasources/prometheus.yml | 9 + prometheus.yml | 40 ++++ 6 files changed, 377 insertions(+) create mode 100644 .gitignore create mode 100644 docker-compose.yml create mode 100644 grafana/provisioning/dashboards/default.yml create mode 100644 grafana/provisioning/dashboards/home-overview.json create mode 100644 grafana/provisioning/datasources/prometheus.yml create mode 100644 prometheus.yml diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..b2d8eb7 --- /dev/null +++ b/.gitignore @@ -0,0 +1,4 @@ +.env +prometheus_data/ +grafana_data/ +*.log diff --git a/docker-compose.yml b/docker-compose.yml new file mode 100644 index 0000000..a2f7938 --- /dev/null +++ b/docker-compose.yml @@ -0,0 +1,140 @@ +name: monitoring + +services: + prometheus: + image: prom/prometheus:latest + container_name: prometheus + restart: always + user: "0:0" + ports: + - "127.0.0.1:9090:9090" + command: + - '--config.file=/etc/prometheus/prometheus.yml' + - '--storage.tsdb.path=/prometheus' + - '--web.console.libraries=/etc/prometheus/console_libraries' + - '--web.console.templates=/etc/prometheus/consoles' + - '--web.enable-lifecycle' + volumes: + - ./prometheus.yml:/etc/prometheus/prometheus.yml:ro + - prometheus_data:/prometheus + networks: + - monitoring + - traefik_proxy + extra_hosts: + - 'host.docker.internal:192.168.1.80' + + grafana: + image: grafana/grafana:latest + container_name: grafana + restart: always + user: "0:0" + environment: + - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD} + - GF_SERVER_ROOT_URL=https://grafana.kzbrd.ru + - GF_INSTALL_PLUGINS=grafana-piechart-panel + volumes: + - grafana_data:/var/lib/grafana + - ./grafana/provisioning:/etc/grafana/provisioning:ro + labels: + - "traefik.enable=true" + - "traefik.docker.network=traefik_proxy" + - "traefik.http.routers.grafana.rule=Host(`grafana.kzbrd.ru`)" + - "traefik.http.routers.grafana.entrypoints=websecure" + - "traefik.http.routers.grafana.tls=true" + - "traefik.http.routers.grafana.tls.certresolver=myresolver" + - "traefik.http.services.grafana.loadbalancer.server.port=3000" + - "com.centurylinklabs.watchtower.enable=true" + networks: + - monitoring + - traefik_proxy + + node_exporter: + image: prom/node-exporter:latest + container_name: node_exporter + restart: always + command: + - '--path.rootfs=/host' + pid: host + volumes: + - /:/host:ro,rslave + networks: + - monitoring + + cadvisor: + image: gcr.io/cadvisor/cadvisor:latest + container_name: cadvisor + restart: always + privileged: true + command: + - '--port=8081' + devices: + - /dev/kmsg + volumes: + - /:/rootfs:ro + - /var/run:/var/run:ro + - /sys:/sys:ro + - /var/lib/docker/:/var/lib/docker:ro + - /dev/disk/:/dev/disk:ro + networks: + - monitoring + + postgres_exporter_pgvector: + image: prometheuscommunity/postgres-exporter:latest + container_name: postgres_exporter_pgvector + restart: always + environment: + - DATA_SOURCE_NAME=postgresql://postgres:${PGVECTOR_PASSWORD}@host.docker.internal:5432/postgres?sslmode=disable + networks: + - monitoring + extra_hosts: + - 'host.docker.internal:192.168.1.80' + + postgres_exporter_langfuse: + image: prometheuscommunity/postgres-exporter:latest + container_name: postgres_exporter_langfuse + restart: always + command: + - '--web.listen-address=:9188' + environment: + - DATA_SOURCE_NAME=postgresql://postgres:${LANGFUSE_DB_PASSWORD}@langfuse-postgres-1:5432/langfuse?sslmode=disable + networks: + - monitoring + - langfuse_default + + postgres_exporter_mcpjungle: + image: prometheuscommunity/postgres-exporter:latest + container_name: postgres_exporter_mcpjungle + restart: always + command: + - '--web.listen-address=:9189' + environment: + - DATA_SOURCE_NAME=postgresql://mcpjungle:${MCPJUNGLE_DB_PASSWORD}@mcpjungle-db:5432/mcpjungle?sslmode=disable + networks: + - monitoring + - mcpjungle_internal + + qbittorrent_exporter: + image: ghcr.io/esanchezm/prometheus-qbittorrent-exporter:latest + container_name: qbittorrent_exporter + restart: always + environment: + - QBITTORRENT_HOST=qbittorrent + - QBITTORRENT_PORT=8080 + - QBITTORRENT_API_KEY=${QBIT_PASSWORD} + networks: + - monitoring + - traefik_proxy + +networks: + monitoring: + driver: bridge + traefik_proxy: + external: true + langfuse_default: + external: true + mcpjungle_internal: + external: true + +volumes: + prometheus_data: + grafana_data: diff --git a/grafana/provisioning/dashboards/default.yml b/grafana/provisioning/dashboards/default.yml new file mode 100644 index 0000000..f4b3078 --- /dev/null +++ b/grafana/provisioning/dashboards/default.yml @@ -0,0 +1,11 @@ +apiVersion: 1 + +providers: + - name: 'default' + orgId: 1 + folder: '' + type: file + disableDeletion: false + editable: true + options: + path: /etc/grafana/provisioning/dashboards diff --git a/grafana/provisioning/dashboards/home-overview.json b/grafana/provisioning/dashboards/home-overview.json new file mode 100644 index 0000000..137b505 --- /dev/null +++ b/grafana/provisioning/dashboards/home-overview.json @@ -0,0 +1,173 @@ +{ + "annotations": { + "list": [] + }, + "editable": true, + "fiscalYearStartMonth": 0, + "graphTooltip": 1, + "id": null, + "links": [], + "panels": [ + { + "datasource": {"type": "prometheus", "uid": "${DS_PROMETHEUS}"}, + "fieldConfig": { + "defaults": { + "color": {"mode": "palette-classic"}, + "custom": {"axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", "fillOpacity": 10, "gradientMode": "none", "hideFrom": {"legend": false, "tooltip": false, "viz": false}, "lineInterpolation": "linear", "lineWidth": 2, "pointSize": 5, "scaleDistribution": {"type": "linear"}, "showPoints": "auto", "spanNulls": false, "stacking": {"group": "A", "mode": "none"}, "thresholdsStyle": {"mode": "off"}}, + "mappings": [], + "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]}, + "unit": "percent" + }, + "overrides": [] + }, + "gridPos": {"h": 8, "w": 12, "x": 0, "y": 0}, + "id": 1, + "options": {"legend": {"calcs": ["mean", "max"], "displayMode": "table", "placement": "bottom", "showLegend": true}, "tooltip": {"mode": "multi", "sort": "desc"}}, + "targets": [ + {"datasource": {"type": "prometheus", "uid": "${DS_PROMETHEUS}"}, "expr": "100 - (avg by (instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100)", "legendFormat": "{{instance}}", "refId": "A"} + ], + "title": "CPU Usage", + "type": "timeseries" + }, + { + "datasource": {"type": "prometheus", "uid": "${DS_PROMETHEUS}"}, + "fieldConfig": { + "defaults": { + "color": {"mode": "palette-classic"}, + "custom": {"axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", "fillOpacity": 10, "gradientMode": "none", "hideFrom": {"legend": false, "tooltip": false, "viz": false}, "lineInterpolation": "linear", "lineWidth": 2, "pointSize": 5, "scaleDistribution": {"type": "linear"}, "showPoints": "auto", "spanNulls": false, "stacking": {"group": "A", "mode": "none"}, "thresholdsStyle": {"mode": "off"}}, + "mappings": [], + "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]}, + "unit": "bytes" + }, + "overrides": [] + }, + "gridPos": {"h": 8, "w": 12, "x": 12, "y": 0}, + "id": 2, + "options": {"legend": {"calcs": ["lastNotNull"], "displayMode": "table", "placement": "bottom", "showLegend": true}, "tooltip": {"mode": "multi", "sort": "desc"}}, + "targets": [ + {"datasource": {"type": "prometheus", "uid": "${DS_PROMETHEUS}"}, "expr": "node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes", "legendFormat": "Used", "refId": "A"}, + {"datasource": {"type": "prometheus", "uid": "${DS_PROMETHEUS}"}, "expr": "node_memory_MemTotal_bytes", "legendFormat": "Total", "refId": "B"} + ], + "title": "Memory Usage", + "type": "timeseries" + }, + { + "datasource": {"type": "prometheus", "uid": "${DS_PROMETHEUS}"}, + "fieldConfig": { + "defaults": { + "color": {"mode": "thresholds"}, + "mappings": [], + "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}, {"color": "yellow", "value": 50}, {"color": "red", "value": 80}]}, + "unit": "percent" + }, + "overrides": [] + }, + "gridPos": {"h": 5, "w": 6, "x": 0, "y": 8}, + "id": 3, + "options": {"orientation": "auto", "reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false}, "showThresholdLabels": false, "showThresholdMarkers": true}, + "targets": [ + {"datasource": {"type": "prometheus", "uid": "${DS_PROMETHEUS}"}, "expr": "100 - ((node_filesystem_avail_bytes{mountpoint=\"/\"} / node_filesystem_size_bytes{mountpoint=\"/\"}) * 100)", "legendFormat": "Root", "refId": "A"} + ], + "title": "Disk Usage /", + "type": "gauge" + }, + { + "datasource": {"type": "prometheus", "uid": "${DS_PROMETHEUS}"}, + "fieldConfig": { + "defaults": { + "color": {"mode": "palette-classic"}, + "custom": {"axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", "fillOpacity": 10, "gradientMode": "none", "hideFrom": {"legend": false, "tooltip": false, "viz": false}, "lineInterpolation": "linear", "lineWidth": 2, "pointSize": 5, "scaleDistribution": {"type": "linear"}, "showPoints": "auto", "spanNulls": false, "stacking": {"group": "A", "mode": "none"}, "thresholdsStyle": {"mode": "off"}}, + "mappings": [], + "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]}, + "unit": "Bps" + }, + "overrides": [] + }, + "gridPos": {"h": 8, "w": 12, "x": 0, "y": 13}, + "id": 4, + "options": {"legend": {"calcs": ["mean", "max"], "displayMode": "table", "placement": "bottom", "showLegend": true}, "tooltip": {"mode": "multi", "sort": "desc"}}, + "targets": [ + {"datasource": {"type": "prometheus", "uid": "${DS_PROMETHEUS}"}, "expr": "rate(node_network_receive_bytes_total{device!=\"lo\"}[5m])", "legendFormat": "{{device}} RX", "refId": "A"}, + {"datasource": {"type": "prometheus", "uid": "${DS_PROMETHEUS}"}, "expr": "-rate(node_network_transmit_bytes_total{device!=\"lo\"}[5m])", "legendFormat": "{{device}} TX", "refId": "B"} + ], + "title": "Network Traffic", + "type": "timeseries" + }, + { + "datasource": {"type": "prometheus", "uid": "${DS_PROMETHEUS}"}, + "fieldConfig": { + "defaults": { + "color": {"mode": "palette-classic"}, + "custom": {"axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", "fillOpacity": 10, "gradientMode": "none", "hideFrom": {"legend": false, "tooltip": false, "viz": false}, "lineInterpolation": "linear", "lineWidth": 2, "pointSize": 5, "scaleDistribution": {"type": "linear"}, "showPoints": "auto", "spanNulls": false, "stacking": {"group": "A", "mode": "none"}, "thresholdsStyle": {"mode": "off"}}, + "mappings": [], + "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]}, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": {"h": 8, "w": 12, "x": 12, "y": 13}, + "id": 5, + "options": {"legend": {"calcs": ["lastNotNull"], "displayMode": "table", "placement": "bottom", "showLegend": true}, "tooltip": {"mode": "multi", "sort": "desc"}}, + "targets": [ + {"datasource": {"type": "prometheus", "uid": "${DS_PROMETHEUS}"}, "expr": "count(count by (name) (container_last_seen{name=~\".+\"}))", "legendFormat": "Running containers", "refId": "A"} + ], + "title": "Docker Containers", + "type": "timeseries" + }, + { + "datasource": {"type": "prometheus", "uid": "${DS_PROMETHEUS}"}, + "fieldConfig": { + "defaults": { + "color": {"mode": "palette-classic"}, + "custom": {"axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", "fillOpacity": 10, "gradientMode": "none", "hideFrom": {"legend": false, "tooltip": false, "viz": false}, "lineInterpolation": "linear", "lineWidth": 2, "pointSize": 5, "scaleDistribution": {"type": "linear"}, "showPoints": "auto", "spanNulls": false, "stacking": {"group": "A", "mode": "none"}, "thresholdsStyle": {"mode": "off"}}, + "mappings": [], + "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]}, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": {"h": 8, "w": 12, "x": 0, "y": 21}, + "id": 6, + "options": {"legend": {"calcs": ["mean"], "displayMode": "table", "placement": "bottom", "showLegend": true}, "tooltip": {"mode": "multi", "sort": "desc"}}, + "targets": [ + {"datasource": {"type": "prometheus", "uid": "${DS_PROMETHEUS}"}, "expr": "rate(traefik_service_requests_total{service=~\"grafana.*|gitea.*|langfuse.*|pingvin.*\"}[5m])", "legendFormat": "{{service}}", "refId": "A"} + ], + "title": "Traefik HTTP Requests (by service)", + "type": "timeseries" + }, + { + "datasource": {"type": "prometheus", "uid": "${DS_PROMETHEUS}"}, + "fieldConfig": { + "defaults": { + "color": {"mode": "palette-classic"}, + "custom": {"axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", "fillOpacity": 10, "gradientMode": "none", "hideFrom": {"legend": false, "tooltip": false, "viz": false}, "lineInterpolation": "linear", "lineWidth": 2, "pointSize": 5, "scaleDistribution": {"type": "linear"}, "showPoints": "auto", "spanNulls": false, "stacking": {"group": "A", "mode": "none"}, "thresholdsStyle": {"mode": "off"}}, + "mappings": [], + "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]}, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": {"h": 8, "w": 12, "x": 12, "y": 21}, + "id": 7, + "options": {"legend": {"calcs": ["lastNotNull"], "displayMode": "table", "placement": "bottom", "showLegend": true}, "tooltip": {"mode": "multi", "sort": "desc"}}, + "targets": [ + {"datasource": {"type": "prometheus", "uid": "${DS_PROMETHEUS}"}, "expr": "gitea_repositories", "legendFormat": "Repositories", "refId": "A"}, + {"datasource": {"type": "prometheus", "uid": "${DS_PROMETHEUS}"}, "expr": "gitea_issues", "legendFormat": "Issues", "refId": "B"} + ], + "title": "Gitea Stats", + "type": "timeseries" + } + ], + "refresh": "30s", + "schemaVersion": 39, + "tags": ["overview"], + "templating": { + "list": [] + }, + "time": {"from": "now-1h", "to": "now"}, + "timepicker": {}, + "timezone": "browser", + "title": "Home Server Overview", + "uid": "home-overview", + "version": 1 +} diff --git a/grafana/provisioning/datasources/prometheus.yml b/grafana/provisioning/datasources/prometheus.yml new file mode 100644 index 0000000..1a57b69 --- /dev/null +++ b/grafana/provisioning/datasources/prometheus.yml @@ -0,0 +1,9 @@ +apiVersion: 1 + +datasources: + - name: Prometheus + type: prometheus + access: proxy + url: http://prometheus:9090 + isDefault: true + editable: true diff --git a/prometheus.yml b/prometheus.yml new file mode 100644 index 0000000..5e5b7a8 --- /dev/null +++ b/prometheus.yml @@ -0,0 +1,40 @@ +global: + scrape_interval: 15s + evaluation_interval: 15s + +scrape_configs: + - job_name: prometheus + static_configs: + - targets: ['localhost:9090'] + + - job_name: traefik + static_configs: + - targets: ['traefik:8080'] + + - job_name: gitea + static_configs: + - targets: ['gitea:3000'] + + - job_name: node + static_configs: + - targets: ['node_exporter:9100'] + + - job_name: cadvisor + static_configs: + - targets: ['cadvisor:8081'] + + - job_name: postgres_pgvector + static_configs: + - targets: ['postgres_exporter_pgvector:9187'] + + - job_name: postgres_langfuse + static_configs: + - targets: ['postgres_exporter_langfuse:9188'] + + - job_name: postgres_mcpjungle + static_configs: + - targets: ['postgres_exporter_mcpjungle:9189'] + + - job_name: qbittorrent + static_configs: + - targets: ['qbittorrent_exporter:8000']