diff --git a/readme.md b/readme.md index be8c3ed..3b48293 100644 --- a/readme.md +++ b/readme.md @@ -49,3 +49,4 @@ * [09.6. Gitlab](/src/homework/09-ci/9.6) * [10.1. Зачем и что нужно мониторить](/src/homework/10-monitoring/10.1) * [10.2. Системы мониторинга](/src/homework/10-monitoring/10.2) +* [10.3. Системы Grafana](/src/homework/10-monitoring/10.3) diff --git a/src/homework/10-monitoring/10.3/img/grafana_datasource.png b/src/homework/10-monitoring/10.3/img/grafana_datasource.png new file mode 100644 index 0000000..6d941b0 Binary files /dev/null and b/src/homework/10-monitoring/10.3/img/grafana_datasource.png differ diff --git a/src/homework/10-monitoring/10.3/readme.md b/src/homework/10-monitoring/10.3/readme.md new file mode 100644 index 0000000..f94af95 --- /dev/null +++ b/src/homework/10-monitoring/10.3/readme.md @@ -0,0 +1,62 @@ +Выполнение [домашнего задания](https://github.com/netology-code/mnt-homeworks/blob/MNT-13/10-monitoring-03-grafana/README.md) +по теме "10.3. Системы Grafana" + +## Q/A + +### Задание 1 + +> Cамостоятельно разверните grafana, где в роли источника данных будет выступать prometheus, а сборщиком данных node-exporter: +> +> * `grafana` +> * `prometheus-server` +> * `prometheus node-exporter` +> +> Запустите связку prometheus-grafana. +> Зайдите в веб-интерфейс Grafana, используя авторизационные данные, указанные в манифесте docker-compose. +> Подключите поднятый вами prometheus как источник данных. +> Решение домашнего задания - скриншот веб-интерфейса grafana со списком подключенных Datasource. +> В решении к домашнему заданию приведите также все конфигурации/скрипты/манифесты, которые вы использовали в процессе решения задания. + +`docker-compose` и остальная конфигурация расположена в директории [stack](./stack). +При поднятии контейнеров в `grafana` автоматически создаётся `data-source` к `prometheus`, +а так же dashboard по мониторингу контейнера `prometheus`. + +![grafana_datasource](./img/grafana_datasource.png) + +### Задание 2 + +> Изучите самостоятельно ресурсы: +> - [promql-for-humans](https://timber.io/blog/promql-for-humans/#cpu-usage-by-instance) +> - [understanding prometheus cpu metrics](https://www.robustperception.io/understanding-machine-cpu-usage) +> +> Создайте Dashboard и в ней создайте следующие Panels: +> - Утилизация CPU для nodeexporter (в процентах, 100-idle) +> - CPULA 1/5/15 +> - Количество свободной оперативной памяти +> - Количество места на файловой системе +> +> Для решения данного ДЗ приведите promql запросы для выдачи этих метрик, а также скриншот получившейся Dashboard. + +Метрики и текст запросов для них + +- Утилизация CPU для nodeexporter (в процентах, 100-idle) + +```text +100 * (1 - avg by(instance)(irate(node_cpu_seconds_total{mode="idle"}[1m]))) +``` + +- CPULA 1/5/15 + +```text +avg(node_load1{}) +avg(node_load5{}) +avg(node_load15{}) +``` + +- Количество свободной оперативной памяти + +// todo + +- Количество места на файловой системе + +// todo diff --git a/src/homework/10-monitoring/10.3/stack/docker-compose.yml b/src/homework/10-monitoring/10.3/stack/docker-compose.yml new file mode 100644 index 0000000..df212a2 --- /dev/null +++ b/src/homework/10-monitoring/10.3/stack/docker-compose.yml @@ -0,0 +1,44 @@ +--- +version: "3.9" + +services: + node-exporter: + image: prom/node-exporter:v1.4.0 + container_name: node-exporter + volumes: + - /proc:/host/proc:ro + - /sys:/host/sys:ro + - /:/rootfs:ro + command: + - "--path.procfs=/host/proc" + - "--path.rootfs=/rootfs" + - "--path.sysfs=/host/sys" + - "--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)" + expose: + - 9100 + + prometheus: + image: prom/prometheus:v2.37.1 + container_name: prometheus + volumes: + - ./prometheus/:/etc/prometheus/ + 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" + expose: + - 9090 + depends_on: + node-exporter: + condition: service_completed_successfully + + grafana: + image: grafana/grafana:9.1.7 + expose: + - 3000 + ports: + - "3000:3000" + volumes: + - ./grafana/provisioning/:/etc/grafana/provisioning/ diff --git a/src/homework/10-monitoring/10.3/stack/grafana/dashboard_backup.json b/src/homework/10-monitoring/10.3/stack/grafana/dashboard_backup.json new file mode 100644 index 0000000..407e8d3 --- /dev/null +++ b/src/homework/10-monitoring/10.3/stack/grafana/dashboard_backup.json @@ -0,0 +1,298 @@ +{ + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": { + "type": "grafana", + "uid": "-- Grafana --" + }, + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "target": { + "limit": 100, + "matchAny": false, + "tags": [], + "type": "dashboard" + }, + "type": "dashboard" + } + ] + }, + "editable": true, + "fiscalYearStartMonth": 0, + "graphTooltip": 0, + "id": 2, + "links": [], + "liveNow": false, + "panels": [ + { + "datasource": { + "type": "prometheus", + "uid": "PBFA97CFB590B2093" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "semi-dark-yellow", + "value": 1 + }, + { + "color": "semi-dark-orange", + "value": 4 + }, + { + "color": "semi-dark-red", + "value": 11 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "avg(node_load1{})" + }, + "properties": [ + { + "id": "displayName", + "value": "loadavg1" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "avg(node_load5{})" + }, + "properties": [ + { + "id": "displayName", + "value": "loadavg5" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "avg(node_load15{})" + }, + "properties": [ + { + "id": "displayName", + "value": "loadavg15" + } + ] + } + ] + }, + "gridPos": { + "h": 6, + "w": 13, + "x": 0, + "y": 0 + }, + "id": 4, + "options": { + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showThresholdLabels": true, + "showThresholdMarkers": true + }, + "pluginVersion": "9.1.7", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "PBFA97CFB590B2093" + }, + "editorMode": "code", + "expr": "avg(node_load1{})", + "legendFormat": "__auto", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "PBFA97CFB590B2093" + }, + "editorMode": "code", + "expr": "avg(node_load5{})", + "hide": false, + "legendFormat": "__auto", + "range": true, + "refId": "B" + }, + { + "datasource": { + "type": "prometheus", + "uid": "PBFA97CFB590B2093" + }, + "editorMode": "code", + "expr": "avg(node_load15{})", + "hide": false, + "legendFormat": "__auto", + "range": true, + "refId": "C" + } + ], + "title": "CPU Load Average", + "type": "gauge" + }, + { + "datasource": { + "type": "prometheus", + "uid": "PBFA97CFB590B2093" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 71, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "smooth", + "lineStyle": { + "fill": "solid" + }, + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "dashed" + } + }, + "displayName": "средняя нагрузка", + "mappings": [], + "max": 1, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 0.8 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "средняя нагрузка" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "red", + "mode": "fixed" + } + } + ] + } + ] + }, + "gridPos": { + "h": 8, + "w": 13, + "x": 0, + "y": 6 + }, + "id": 2, + "options": { + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": false + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "PBFA97CFB590B2093" + }, + "editorMode": "code", + "expr": "100 * (1 - avg by(instance)(irate(node_cpu_seconds_total{mode=\"idle\"}[1m])))", + "legendFormat": "__auto", + "range": true, + "refId": "A" + } + ], + "title": "Нагрузка на node", + "type": "timeseries" + } + ], + "refresh": false, + "schemaVersion": 37, + "style": "dark", + "tags": [], + "templating": { + "list": [] + }, + "time": { + "from": "now-30m", + "to": "now" + }, + "timepicker": {}, + "timezone": "", + "title": "node-exporter", + "uid": "NwsNrL44z", + "version": 1, + "weekStart": "" +} diff --git a/src/homework/10-monitoring/10.3/stack/grafana/provisioning/dashboards/Docker Prometheus Monitoring-1571332751387.json b/src/homework/10-monitoring/10.3/stack/grafana/provisioning/dashboards/Docker Prometheus Monitoring-1571332751387.json new file mode 100644 index 0000000..57715cc --- /dev/null +++ b/src/homework/10-monitoring/10.3/stack/grafana/provisioning/dashboards/Docker Prometheus Monitoring-1571332751387.json @@ -0,0 +1,1831 @@ +{ + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "description": "Docker Monitoring Template", + "editable": true, + "gnetId": 179, + "graphTooltip": 1, + "id": 1, + "iteration": 1571330223815, + "links": [], + "panels": [ + { + "collapsed": false, + "datasource": null, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 17, + "panels": [], + "title": "Host Info", + "type": "row" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "Prometheus", + "decimals": null, + "format": "s", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 7, + "w": 3, + "x": 0, + "y": 1 + }, + "id": 15, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "options": {}, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "time() - process_start_time_seconds{job=\"prometheus\"}", + "format": "time_series", + "intervalFactor": 1, + "refId": "A" + } + ], + "thresholds": "", + "title": "Uptime", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "Prometheus", + "format": "short", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 4, + "w": 3, + "x": 3, + "y": 1 + }, + "id": 35, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "options": {}, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false, + "ymax": null, + "ymin": null + }, + "tableColumn": "", + "targets": [ + { + "expr": "count(count(node_cpu_seconds_total{instance=~\"$node\", mode='system'}) by (cpu))", + "instant": true, + "refId": "A" + } + ], + "thresholds": "", + "timeFrom": null, + "timeShift": null, + "title": "CPU Cores", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": true, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "Prometheus", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 7, + "w": 5, + "x": 6, + "y": 1 + }, + "id": 13, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "options": {}, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(ALERTS)", + "format": "time_series", + "intervalFactor": 1, + "refId": "A" + } + ], + "thresholds": "0,1", + "title": "Alerts", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "0" + } + ], + "valueName": "avg" + }, + { + "cacheTimeout": null, + "colorBackground": true, + "colorValue": false, + "colors": [ + "#d44a3a", + "rgba(237, 129, 40, 0.89)", + "#299c46" + ], + "datasource": "Prometheus", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 7, + "w": 4, + "x": 11, + "y": 1 + }, + "id": 11, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "options": {}, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(up)", + "format": "time_series", + "intervalFactor": 1, + "refId": "A" + } + ], + "thresholds": "0,1", + "title": "Targets Online", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#d44a3a", + "rgba(237, 129, 40, 0.89)", + "#299c46" + ], + "datasource": "Prometheus", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 7, + "w": 4, + "x": 15, + "y": 1 + }, + "id": 31, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "options": {}, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": true + }, + "tableColumn": "", + "targets": [ + { + "expr": "count(rate(container_last_seen{job=\"cadvisor\", name!=\"\"}[5m]))", + "format": "time_series", + "intervalFactor": 1, + "refId": "A" + } + ], + "thresholds": "0,1", + "title": "Running Containers", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": null, + "decimals": null, + "format": "decbytes", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 3, + "w": 3, + "x": 3, + "y": 5 + }, + "id": 37, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "options": {}, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false, + "ymax": null, + "ymin": null + }, + "tableColumn": "", + "targets": [ + { + "expr": "node_memory_MemTotal_bytes{instance=~\"$node\"}", + "refId": "A" + } + ], + "thresholds": "", + "timeFrom": null, + "timeShift": null, + "title": "Host Memory", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "Prometheus", + "editable": true, + "error": false, + "format": "percent", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 6, + "w": 6, + "x": 0, + "y": 8 + }, + "id": 4, + "interval": null, + "isNew": true, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "options": {}, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "(sum(node_memory_MemTotal_bytes) - sum(node_memory_MemFree_bytes +node_memory_Buffers_bytes + node_memory_Cached_bytes) ) / sum(node_memory_MemTotal_bytes) * 100", + "format": "time_series", + "interval": "10s", + "intervalFactor": 1, + "refId": "A", + "step": 10 + } + ], + "thresholds": "65, 90", + "title": "Memory usage", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "Prometheus", + "decimals": 2, + "editable": true, + "error": false, + "format": "percent", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 6, + "w": 6, + "x": 6, + "y": 8 + }, + "id": 6, + "interval": null, + "isNew": true, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "options": {}, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "100 - (avg(irate(node_cpu_seconds_total{instance=~\"$node\",mode=\"idle\"}[5m])) * 100)", + "format": "time_series", + "interval": "1m", + "intervalFactor": 1, + "legendFormat": "", + "refId": "A", + "step": 10 + } + ], + "thresholds": "65, 90", + "title": "CPU usage", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "Prometheus", + "decimals": 2, + "editable": true, + "error": false, + "format": "percent", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 6, + "w": 7, + "x": 12, + "y": 8 + }, + "id": 7, + "interval": null, + "isNew": true, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "options": {}, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "avg( node_filesystem_avail_bytes {mountpoint=\"/\"} / node_filesystem_size_bytes{mountpoint=\"/\"})", + "interval": "10s", + "intervalFactor": 1, + "metric": "", + "refId": "A", + "step": 10 + } + ], + "thresholds": "65, 90", + "title": "Filesystem usage", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "aliasColors": { + "RECEIVE": "#ea6460", + "SENT": "#1f78c1", + "TRANSMIT": "#1f78c1" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "Prometheus", + "fill": 4, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 6, + "x": 0, + "y": 14 + }, + "id": 25, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(container_network_receive_bytes_total{id=\"/\"}[$interval])) by (id)", + "format": "time_series", + "interval": "2m", + "intervalFactor": 2, + "legendFormat": "RECEIVE", + "refId": "A" + }, + { + "expr": "- sum(rate(container_network_transmit_bytes_total{id=\"/\"}[$interval])) by (id)", + "format": "time_series", + "interval": "2m", + "intervalFactor": 2, + "legendFormat": "TRANSMIT", + "refId": "B" + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Node Network Traffic", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "Available Memory": "#508642", + "Used Memory": "#bf1b00" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "Prometheus", + "fill": 3, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 6, + "x": 6, + "y": 14 + }, + "id": 27, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(node_memory_MemTotal_bytes) - sum(node_memory_MemAvailable_bytes)", + "format": "time_series", + "interval": "2m", + "intervalFactor": 2, + "legendFormat": "Used Memory", + "refId": "B" + }, + { + "expr": "sum(node_memory_MemAvailable_bytes)", + "format": "time_series", + "interval": "2m", + "intervalFactor": 2, + "legendFormat": "Available Memory", + "refId": "A" + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Node Mermory", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "decbytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + "Available Memory": "#508642", + "Free Storage": "#447ebc", + "Total Storage Available": "#508642", + "Used Memory": "#bf1b00", + "Used Storage": "#bf1b00" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "Prometheus", + "fill": 3, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 7, + "x": 12, + "y": 14 + }, + "id": 28, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(node_filesystem_free_bytes {job=\"node-exporter\", instance=~\".*9100\", device=~\"/dev/.*\", mountpoint!=\"/var/lib/docker/aufs\"}) ", + "format": "time_series", + "interval": "2m", + "intervalFactor": 2, + "legendFormat": "Free Storage", + "refId": "A" + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Filesystem Available", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "decimals": null, + "format": "decbytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "collapsed": false, + "datasource": null, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 23 + }, + "id": 19, + "panels": [], + "repeat": null, + "title": "Container Performance", + "type": "row" + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "Prometheus", + "decimals": 3, + "editable": true, + "error": false, + "fill": 0, + "fillGradient": 0, + "grid": {}, + "gridPos": { + "h": 10, + "w": 6, + "x": 0, + "y": 24 + }, + "id": 3, + "isNew": true, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(container_cpu_usage_seconds_total{image!=\"\"}[1m])) by (id,name)", + "format": "time_series", + "interval": "10s", + "intervalFactor": 1, + "legendFormat": "{{ name }}", + "metric": "container_cpu_user_seconds_total", + "refId": "A", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Container CPU usage", + "tooltip": { + "msResolution": true, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "Prometheus", + "decimals": 2, + "editable": true, + "error": false, + "fill": 0, + "fillGradient": 0, + "grid": {}, + "gridPos": { + "h": 10, + "w": 6, + "x": 6, + "y": 24 + }, + "id": 2, + "isNew": true, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "container_memory_max_usage_bytes{image!=\"\"}", + "format": "time_series", + "interval": "10s", + "intervalFactor": 1, + "legendFormat": "{{ name }}", + "metric": "container_memory_usage:sort_desc", + "refId": "A", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Container Memory Usage", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "columns": [], + "datasource": "Prometheus", + "fontSize": "100%", + "gridPos": { + "h": 13, + "w": 10, + "x": 12, + "y": 24 + }, + "id": 23, + "links": [], + "options": {}, + "pageSize": null, + "scroll": true, + "showHeader": true, + "sort": { + "col": 0, + "desc": true + }, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "date" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "decimals": 2, + "pattern": "/.*/", + "thresholds": [], + "type": "number", + "unit": "short" + } + ], + "targets": [ + { + "expr": "ALERTS", + "format": "table", + "intervalFactor": 1, + "refId": "A" + } + ], + "title": "Alerts", + "transform": "table", + "type": "table" + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "Prometheus", + "decimals": 2, + "editable": true, + "error": false, + "fill": 0, + "fillGradient": 0, + "grid": {}, + "gridPos": { + "h": 14, + "w": 6, + "x": 0, + "y": 34 + }, + "id": 8, + "isNew": true, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum by (name) (rate(container_network_receive_bytes_total{image!=\"\"}[1m] ) ))", + "interval": "10s", + "intervalFactor": 1, + "legendFormat": "{{ name }}", + "metric": "container_network_receive_bytes_total", + "refId": "A", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Container Network Input", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "Prometheus", + "decimals": 2, + "editable": true, + "error": false, + "fill": 0, + "fillGradient": 0, + "grid": {}, + "gridPos": { + "h": 14, + "w": 6, + "x": 6, + "y": 34 + }, + "id": 9, + "isNew": true, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum by (name) (rate(container_network_transmit_bytes_total{image!=\"\"}[1m] ) ))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ name }}", + "metric": "container_network_transmit_bytes_total", + "refId": "B", + "step": 4 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Container Network Output", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "columns": [], + "datasource": "Prometheus", + "fontSize": "100%", + "gridPos": { + "h": 10, + "w": 10, + "x": 12, + "y": 37 + }, + "id": 30, + "links": [], + "options": {}, + "pageSize": 10, + "scroll": true, + "showHeader": true, + "sort": { + "col": 0, + "desc": true + }, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "link": false, + "linkUrl": "", + "pattern": "Time", + "type": "date" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "decimals": 2, + "pattern": "/.*/", + "thresholds": [], + "type": "number", + "unit": "short" + } + ], + "targets": [ + { + "expr": "cadvisor_version_info", + "format": "table", + "instant": false, + "interval": "15m", + "intervalFactor": 2, + "legendFormat": "cAdvisor Version: {{cadvisorVersion}}", + "refId": "A" + }, + { + "expr": "prometheus_build_info", + "format": "table", + "interval": "15m", + "intervalFactor": 2, + "legendFormat": "Prometheus Version: {{version}}", + "refId": "B" + }, + { + "expr": "node_exporter_build_info", + "format": "table", + "interval": "15m", + "intervalFactor": 2, + "legendFormat": "Node-Exporter Version: {{version}}", + "refId": "C" + } + ], + "title": "Running Versions", + "transform": "table", + "type": "table" + } + ], + "refresh": "10s", + "schemaVersion": 20, + "style": "dark", + "tags": [ + "docker", + "prometheus, ", + "node-exporter", + "cadvisor" + ], + "templating": { + "list": [ + { + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "1m", + "value": "1m" + }, + "hide": 0, + "label": "interval", + "name": "interval", + "options": [ + { + "selected": true, + "text": "1m", + "value": "1m" + }, + { + "selected": false, + "text": "10m", + "value": "10m" + }, + { + "selected": false, + "text": "30m", + "value": "30m" + }, + { + "selected": false, + "text": "1h", + "value": "1h" + }, + { + "selected": false, + "text": "6h", + "value": "6h" + }, + { + "selected": false, + "text": "12h", + "value": "12h" + }, + { + "selected": false, + "text": "1d", + "value": "1d" + }, + { + "selected": false, + "text": "7d", + "value": "7d" + }, + { + "selected": false, + "text": "14d", + "value": "14d" + }, + { + "selected": false, + "text": "30d", + "value": "30d" + } + ], + "query": "1m,10m,30m,1h,6h,12h,1d,7d,14d,30d", + "refresh": 2, + "skipUrlSync": false, + "type": "interval" + }, + { + "allValue": null, + "current": { + "text": "All", + "value": "$__all" + }, + "datasource": "Prometheus", + "definition": "label_values(node_exporter_build_info{name=~'$name'},instance)", + "hide": 0, + "includeAll": true, + "label": "IP", + "multi": true, + "name": "node", + "options": [], + "query": "label_values(node_exporter_build_info{name=~'$name'},instance)", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "All", + "value": "$__all" + }, + "datasource": "Prometheus", + "definition": "label_values(node_exporter_build_info,env)", + "hide": 0, + "includeAll": true, + "label": "Env", + "multi": true, + "name": "env", + "options": [], + "query": "label_values(node_exporter_build_info,env)", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 0, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "All", + "value": "$__all" + }, + "datasource": "Prometheus", + "definition": "label_values(node_exporter_build_info{env=~'$env'},name)", + "hide": 0, + "includeAll": true, + "label": "CPU Name", + "multi": true, + "name": "name", + "options": [], + "query": "label_values(node_exporter_build_info{env=~'$env'},name)", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 0, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-5m", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "browser", + "title": "Docker Prometheus Monitoring", + "uid": "64nrElFmk", + "version": 2 +} diff --git a/src/homework/10-monitoring/10.3/stack/grafana/provisioning/dashboards/dashboard.yml b/src/homework/10-monitoring/10.3/stack/grafana/provisioning/dashboards/dashboard.yml new file mode 100644 index 0000000..e1f37c7 --- /dev/null +++ b/src/homework/10-monitoring/10.3/stack/grafana/provisioning/dashboards/dashboard.yml @@ -0,0 +1,12 @@ +--- +apiVersion: 1 + +providers: + - name: 'Prometheus' + orgId: 1 + folder: '' + type: file + disableDeletion: false + editable: true + options: + path: /etc/grafana/provisioning/dashboards diff --git a/src/homework/10-monitoring/10.3/stack/grafana/provisioning/datasources/datasource.yml b/src/homework/10-monitoring/10.3/stack/grafana/provisioning/datasources/datasource.yml new file mode 100644 index 0000000..e198148 --- /dev/null +++ b/src/homework/10-monitoring/10.3/stack/grafana/provisioning/datasources/datasource.yml @@ -0,0 +1,51 @@ +--- +# 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: + # name of the datasource. Required + - name: Prometheus + # datasource type. Required + type: prometheus + # access mode. direct or proxy. Required + access: proxy + # org id. will default to orgId 1 if not specified + orgId: 1 + # url + url: http://prometheus:9090 + # database password, if used + password: + # database user, if used + user: + # database name, if used + database: + # enable/disable basic auth + basicAuth: false + # basic auth username, if used + basicAuthUser: + # basic auth password, if used + basicAuthPassword: + # enable/disable with credentials headers + withCredentials: + # mark as default datasource. Max one per org + isDefault: true + # fields that will be converted to json and stored in json_data + jsonData: + graphiteVersion: "1.1" + tlsAuth: false + tlsAuthWithCACert: false + # json object of data that will be encrypted. + secureJsonData: + tlsCACert: "..." + tlsClientCert: "..." + tlsClientKey: "..." + version: 1 + # allow users to edit datasources from the UI. + editable: true diff --git a/src/homework/10-monitoring/10.3/stack/prometheus/prometheus.yml b/src/homework/10-monitoring/10.3/stack/prometheus/prometheus.yml new file mode 100644 index 0000000..9920bf7 --- /dev/null +++ b/src/homework/10-monitoring/10.3/stack/prometheus/prometheus.yml @@ -0,0 +1,13 @@ +--- +global: + scrape_interval: 15s + +scrape_configs: + - job_name: "prometheus" + scrape_interval: 30s + static_configs: + - targets: ["localhost:9090"] + + - job_name: "node" + static_configs: + - targets: ["node-exporter:9100"]