[add] 添加 Grafana 文章

SUMMARY.md

@@ -85,3 +85,4 @@
 * [监控 Kubernetes 集群应用](docs/53.监控Kubernetes集群应用.md)
 * [监控 Kubernetes 集群节点](docs/54.监控Kubernetes集群节点.md)
 * [监控 Kubernetes 常用资源对象](docs/55.监控Kubernetes常用资源对象.md)
+* [Grafana 的安装使用](docs/56.Grafana的安装使用.md)
\ No newline at end of file

docs/files/grafana-k8s-cluster-dashboard.json

+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": "-- Grafana --",
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "description": "Monitor a Kubernetes cluster using Prometheus TSDB.  Shows overall cluster CPU / Memory / Disk usage as well as individual pod statistics. ",
+  "editable": true,
+  "gnetId": 162,
+  "graphTooltip": 1,
+  "id": 2,
+  "links": [],
+  "panels": [
+    {
+      "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-ds",
+      "editable": true,
+      "error": false,
+      "format": "percent",
+      "gauge": {
+        "maxValue": 100,
+        "minValue": 0,
+        "show": true,
+        "thresholdLabels": false,
+        "thresholdMarkers": true
+      },
+      "gridPos": {
+        "h": 7,
+        "w": 8,
+        "x": 0,
+        "y": 0
+      },
+      "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,
+      "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": "Cluster 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-ds",
+      "decimals": 2,
+      "editable": true,
+      "error": false,
+      "format": "percent",
+      "gauge": {
+        "maxValue": 100,
+        "minValue": 0,
+        "show": true,
+        "thresholdLabels": false,
+        "thresholdMarkers": true
+      },
+      "gridPos": {
+        "h": 7,
+        "w": 8,
+        "x": 8,
+        "y": 0
+      },
+      "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,
+      "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(sum by (container_name)( rate(container_cpu_usage_seconds_total{image!=\"\"}[1m] ) )) / count(node_cpu_seconds_total{mode=\"system\"}) * 100",
+          "format": "time_series",
+          "interval": "10s",
+          "intervalFactor": 1,
+          "refId": "A",
+          "step": 10
+        }
+      ],
+      "thresholds": "65, 90",
+      "title": "Cluster 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-ds",
+      "decimals": 2,
+      "editable": true,
+      "error": false,
+      "format": "percent",
+      "gauge": {
+        "maxValue": 100,
+        "minValue": 0,
+        "show": true,
+        "thresholdLabels": false,
+        "thresholdMarkers": true
+      },
+      "gridPos": {
+        "h": 7,
+        "w": 8,
+        "x": 16,
+        "y": 0
+      },
+      "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,
+      "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_filesystem_size_bytes{device=\"rootfs\"}) - sum(node_filesystem_free_bytes{device=\"rootfs\"}) ) / sum(node_filesystem_size_bytes{device=\"rootfs\"}) * 100",
+          "format": "time_series",
+          "interval": "10s",
+          "intervalFactor": 1,
+          "metric": "",
+          "refId": "A",
+          "step": 10
+        }
+      ],
+      "thresholds": "65, 90",
+      "title": "Cluster Filesystem usage",
+      "type": "singlestat",
+      "valueFontSize": "80%",
+      "valueMaps": [
+        {
+          "op": "=",
+          "text": "N/A",
+          "value": "null"
+        }
+      ],
+      "valueName": "current"
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": "prometheus-ds",
+      "decimals": 3,
+      "editable": true,
+      "error": false,
+      "fill": 0,
+      "grid": {},
+      "gridPos": {
+        "h": 7,
+        "w": 24,
+        "x": 0,
+        "y": 7
+      },
+      "id": 3,
+      "isNew": true,
+      "legend": {
+        "alignAsTable": true,
+        "avg": true,
+        "current": true,
+        "max": false,
+        "min": false,
+        "rightSide": true,
+        "show": true,
+        "sort": "current",
+        "sortDesc": true,
+        "total": false,
+        "values": true
+      },
+      "lines": true,
+      "linewidth": 2,
+      "links": [],
+      "nullPointMode": "connected",
+      "percentage": false,
+      "pointradius": 5,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "expr": "sum by (pod_name)(rate(container_cpu_usage_seconds_total{image!=\"\", pod_name!=\"\"}[1m] ))",
+          "format": "time_series",
+          "interval": "10s",
+          "intervalFactor": 1,
+          "legendFormat": "{{ pod_name }}",
+          "metric": "container_cpu",
+          "refId": "A",
+          "step": 10
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeShift": null,
+      "title": "Pod 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": "percent",
+          "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-ds",
+      "decimals": 2,
+      "editable": true,
+      "error": false,
+      "fill": 0,
+      "grid": {},
+      "gridPos": {
+        "h": 7,
+        "w": 24,
+        "x": 0,
+        "y": 14
+      },
+      "id": 2,
+      "isNew": true,
+      "legend": {
+        "alignAsTable": true,
+        "avg": true,
+        "current": true,
+        "max": false,
+        "min": false,
+        "rightSide": true,
+        "show": true,
+        "sideWidth": 200,
+        "sort": "current",
+        "sortDesc": true,
+        "total": false,
+        "values": true
+      },
+      "lines": true,
+      "linewidth": 2,
+      "links": [],
+      "nullPointMode": "connected",
+      "percentage": false,
+      "pointradius": 5,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "expr": "sort_desc(sum (container_memory_usage_bytes{image!=\"\", pod_name!=\"\"}) by(pod_name))",
+          "format": "time_series",
+          "interval": "10s",
+          "intervalFactor": 1,
+          "legendFormat": "{{ pod_name }}",
+          "metric": "container_memory_usage:sort_desc",
+          "refId": "A",
+          "step": 10
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeShift": null,
+      "title": "Pod 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
+      }
+    },
+    {
+      "aliasColors": {},
+      "bars": false,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": "prometheus-ds",
+      "decimals": 2,
+      "editable": true,
+      "error": false,
+      "fill": 0,
+      "grid": {},
+      "gridPos": {
+        "h": 7,
+        "w": 24,
+        "x": 0,
+        "y": 21
+      },
+      "id": 8,
+      "isNew": true,
+      "legend": {
+        "alignAsTable": true,
+        "avg": true,
+        "current": true,
+        "max": false,
+        "min": false,
+        "rightSide": true,
+        "show": true,
+        "sideWidth": 200,
+        "sort": "current",
+        "sortDesc": true,
+        "total": false,
+        "values": true
+      },
+      "lines": true,
+      "linewidth": 2,
+      "links": [],
+      "nullPointMode": "connected",
+      "percentage": false,
+      "pointradius": 5,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "expr": "sort_desc(sum by (pod_name) (rate (container_network_receive_bytes_total{name!=\"\"}[1m]) ))",
+          "format": "time_series",
+          "interval": "10s",
+          "intervalFactor": 1,
+          "legendFormat": "{{ pod_name }}",
+          "metric": "network",
+          "refId": "A",
+          "step": 10
+        },
+        {
+          "expr": "sort_desc(sum by (pod_name) (rate (container_network_transmit_bytes_total{name!=\"\"}[1m]) ))",
+          "format": "time_series",
+          "interval": "10s",
+          "intervalFactor": 1,
+          "legendFormat": "{{ pod_name }}",
+          "metric": "network",
+          "refId": "B",
+          "step": 10
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeShift": null,
+      "title": "Pod Network i/o",
+      "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
+      }
+    }
+  ],
+  "refresh": "10s",
+  "schemaVersion": 16,
+  "style": "dark",
+  "tags": [
+    "kubernetes"
+  ],
+  "templating": {
+    "list": []
+  },
+  "time": {
+    "from": "now-1h",
+    "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": "Kubernetes cluster monitoring (via Prometheus)",
+  "uid": "wM-Athfmz",
+  "version": 3
+}
\ No newline at end of file

grafana/grafana-chown-job.yaml

+apiVersion: batch/v1
+kind: Job
+metadata: 
+  name: grafana-chown
+  namespace: kube-ops
+spec:
+  template:
+    spec:
+      restartPolicy: Never
+      containers:
+      - name: grafana-chown
+        command: ["chown", "-R", "472:472", "/var/lib/grafana"]
+        image: busybox
+        imagePullPolicy: IfNotPresent
+        volumeMounts:
+        - name: storage
+          subPath: grafana
+          mountPath: /var/lib/grafana
+      volumes:
+      - name: storage
+        persistentVolumeClaim:
+          claimName: grafana
\ No newline at end of file

grafana/grafana-cm.yaml

+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: grafana-config
+  namespace: kube-ops
+data:
+  grafana.ini: |
+    [smtp]
+    enabled = true
+    host = smtp.163.com:25
+    user = ych_1024@163.com
+    password = <password>
+    skip_verify = true
+    from_address = ych_1024@163.com
+    [alerting]
+    enabled = true
+    execute_alerts = true

grafana/grafana-deploy.yaml

@@ -14,11 +14,9 @@ spec:
     spec:
       containers:
       - name: grafana
-        image: grafana/grafana:5.3.1
+        image: grafana/grafana:5.3.4
         imagePullPolicy: IfNotPresent
         ports:
-        - containerPort: 80
-          name: service
         - containerPort: 3000
           name: grafana
         env:
@@ -48,16 +46,23 @@ spec:
         resources:
           limits:
             cpu: 100m
-            memory: 128Mi
+            memory: 256Mi
           requests:
             cpu: 100m
-            memory: 128Mi
+            memory: 256Mi
         volumeMounts:
         - mountPath: /var/lib/grafana
+          subPath: grafana
           name: storage
+        - mountPath: "/etc/grafana"
+          name: config
       securityContext:
         fsGroup: 472
         runAsUser: 472
       volumes:
-      - emptyDir: {}
-        name: storage
+      - name: storage
+        persistentVolumeClaim:
+          claimName: grafana
+      - name: config
+        configMap:
+          name: grafana-config
\ No newline at end of file

grafana/grafana-volume.yaml

+apiVersion: v1
+kind: PersistentVolume
+metadata:
+  name: grafana
+spec:
+  capacity:
+    storage: 1Gi
+  accessModes:
+  - ReadWriteOnce
+  persistentVolumeReclaimPolicy: Recycle
+  nfs:
+    server: 10.151.30.57
+    path: /data/k8s
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: grafana
+  namespace: kube-ops
+spec:
+  accessModes:
+  - ReadWriteOnce
+  resources:
+    requests:
+      storage: 1Gi
\ No newline at end of file

grafana/grafana.ini

+##################### 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 = conf/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 = localhost
+
+# 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 = http://localhost:3000
+
+# 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 =
+
+#################################### 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 = false
+;allow_sign_up = true
+;client_id = some_client_id
+;client_secret = some_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 = smtp.163.com:25
+user = ych_1024@163.com
+password = OTFych88198900
+skip_verify = true
+from_address = ych_1024@163.com
+;enabled = false
+;host = localhost:25
+;user =
+# If the password contains # or ; you have to wrap it with trippel quotes. Ex """#password;"""
+;password =
+;cert_file =
+;key_file =
+;skip_verify = false
+;from_address = admin@grafana.localhost
+;from_name = Grafana
+# 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 =
\ No newline at end of file

prome/prome-cm.yaml

@@ -40,4 +40,58 @@ data:
           action: replace
         - action: labelmap
           regex: __meta_kubernetes_node_label_(.+)
-          
+      - job_name: 'kubernetes-cadvisor'
+        kubernetes_sd_configs:
+        - role: node
+        scheme: https
+        tls_config:
+          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+        relabel_configs:
+        - action: labelmap
+          regex: __meta_kubernetes_node_label_(.+)
+        - target_label: __address__
+          replacement: kubernetes.default.svc:443
+        - source_labels: [__meta_kubernetes_node_name]
+          regex: (.+)
+          target_label: __metrics_path__
+          replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
+      - job_name: 'kubernetes-apiservers'
+        kubernetes_sd_configs:
+        - role: endpoints
+        scheme: https
+        tls_config:
+          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+        relabel_configs:
+        - action: keep
+          source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
+          regex: default;kubernetes;https
+      - job_name: 'kubernetes-service-endpoints'
+        kubernetes_sd_configs:
+        - role: endpoints
+        relabel_configs:
+        - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
+          action: keep
+          regex: true
+        - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
+          action: replace
+          target_label: __scheme__
+          regex: (https?)
+        - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
+          action: replace
+          target_label: __metrics_path__
+          regex: (.+)
+        - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
+          action: replace
+          target_label: __address__
+          regex: ([^:]+)(?::\d+)?;(\d+)
+          replacement: $1:$2
+        - action: labelmap
+          regex: __meta_kubernetes_service_label_(.+)
+        - source_labels: [__meta_kubernetes_namespace]
+          action: replace
+          target_label: kubernetes_namespace
+        - source_labels: [__meta_kubernetes_service_name]
+          action: replace
+          target_label: kubernetes_name

prome/prome-redis-exporter.yaml

@@ -32,6 +32,9 @@ apiVersion: v1
 metadata:
   name: redis
   namespace: kube-ops
+  annotations:
+    prometheus.io/scrape: "true"
+    prometheus.io/port: "9121"
 spec:
   selector:
     app: redis