kubernetes(k8s) Prometheus+grafana监控告警安装部署

{
  "endpoint" : {
    "protocol": "https",
    "port": 8000,
    "path": "/nginx_status"
  },
  "metrics_config"  : [
    { "name" : "activeConnections",
      "metric_type" : "gauge",
      "units" : "number of active connections",
      "data_type" : "int",
      "polling_frequency" : 10,
      "regex" : "Active connections: ([0-9]+)"
    },
    { "name" : "reading",
      "metric_type" : "gauge",
      "units" : "number of reading connections",
      "data_type" : "int",
      "polling_frequency" : 10,
      "regex" : "Reading: ([0-9]+) .*"
    },
    { "name" : "writing",
      "metric_type" : "gauge",
      "data_type" : "int",
      "units" : "number of writing connections",
      "polling_frequency" : 10,
      "regex" : ".*Writing: ([0-9]+).*"
    },
    { "name" : "waiting",
      "metric_type" : "gauge",
      "units" : "number of waiting connections",
      "data_type" : "int",
      "polling_frequency" : 10,
      "regex" : ".*Waiting: ([0-9]+)"
    }
  ]
}

apiVersion: v1
kind: Service
metadata:
  annotations:
    prometheus.io/scrape: 'true'
  labels:
    app: node-exporter
    name: node-exporter
  name: node-exporter
  namespace: kube-system
spec:
  clusterIP: None
  ports:
  - name: scrape
    port: 9100
    protocol: TCP
  selector:
    app: node-exporter
  type: ClusterIP
---
apiVersion: extensions/v1beta1
kind: DaemonSet
metadata:
  name: node-exporter
  namespace: kube-system
spec:
  template:
    metadata:
      labels:
        app: node-exporter
      name: node-exporter
    spec:
      containers:
      - image: prom/node-exporter:latest
        name: node-exporter
        ports:
        - containerPort: 9100
          hostPort: 9100
          name: scrape
      hostNetwork: true
      hostPID: true
      restartPolicy: Always

apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  name: prometheus
rules:
- apiGroups: [""]
  resources:
  - nodes
  - nodes/proxy
  - services
  - endpoints
  - pods
  verbs: ["get", "list", "watch"]
- apiGroups:
  - extensions
  resources:
  - ingresses
  verbs: ["get", "list", "watch"]
- nonResourceURLs: ["/metrics"]
  verbs: ["get"]
---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: prometheus
  namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: prometheus
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: prometheus
subjects:
- kind: ServiceAccount
  name: prometheus
  namespace: kube-system

# cat configmap.yaml 
apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-config
  namespace: kube-system
data:
  prometheus.yml: |
    global:
      scrape_interval:     15s
      evaluation_interval: 15s
    scrape_configs:

    - 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:
      - source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
        action: keep
        regex: default;kubernetes;https

    - job_name: 'kubernetes-nodes'
      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

    - 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-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

    - job_name: 'kubernetes-services'
      kubernetes_sd_configs:
      - role: service
      metrics_path: /probe
      params:
        module: [http_2xx]
      relabel_configs:
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_probe]
        action: keep
        regex: true
      - source_labels: [__address__]
        target_label: __param_target
      - target_label: __address__
        replacement: blackbox-exporter.example.com:9115
      - source_labels: [__param_target]
        target_label: instance
      - action: labelmap
        regex: __meta_kubernetes_service_label_(.+)
      - source_labels: [__meta_kubernetes_namespace]
        target_label: kubernetes_namespace
      - source_labels: [__meta_kubernetes_service_name]
        target_label: kubernetes_name

    - job_name: 'kubernetes-ingresses'
      kubernetes_sd_configs:
      - role: ingress
      relabel_configs:
      - source_labels: [__meta_kubernetes_ingress_annotation_prometheus_io_probe]
        action: keep
        regex: true
      - source_labels: [__meta_kubernetes_ingress_scheme,__address__,__meta_kubernetes_ingress_path]
        regex: (.+);(.+);(.+)
        replacement: ${1}://${2}${3}
        target_label: __param_target
      - target_label: __address__
        replacement: blackbox-exporter.example.com:9115
      - source_labels: [__param_target]
        target_label: instance
      - action: labelmap
        regex: __meta_kubernetes_ingress_label_(.+)
      - source_labels: [__meta_kubernetes_namespace]
        target_label: kubernetes_namespace
      - source_labels: [__meta_kubernetes_ingress_name]
        target_label: kubernetes_name

    - job_name: 'kubernetes-pods'
      kubernetes_sd_configs:
      - role: pod
      relabel_configs:
      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
        action: keep
        regex: true
      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
        action: replace
        target_label: __metrics_path__
        regex: (.+)
      - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
        action: replace
        regex: ([^:]+)(?::\d+)?;(\d+)
        replacement: $1:$2
        target_label: __address__
      - action: labelmap
        regex: __meta_kubernetes_pod_label_(.+)
      - source_labels: [__meta_kubernetes_namespace]
        action: replace
        target_label: kubernetes_namespace
      - source_labels: [__meta_kubernetes_pod_name]
        action: replace
        target_label: kubernetes_pod_name

---
apiVersion: apps/v1beta2
kind: Deployment
metadata:
  labels:
    name: prometheus-deployment
  name: prometheus
  namespace: kube-system
spec:
  replicas: 1
  selector:
    matchLabels:
      app: prometheus
  template:
    metadata:
      labels:
        app: prometheus
    spec:
      containers:
      - image: prom/prometheus:v2.0.0
        name: prometheus
        command:
        - "/bin/prometheus"
        args:
        - "--config.file=/etc/prometheus/prometheus.yml"
        - "--storage.tsdb.path=/prometheus"
        - "--storage.tsdb.retention=24h"
        ports:
        - containerPort: 9090
          protocol: TCP
        volumeMounts:
        - mountPath: "/prometheus"
          name: data
        - mountPath: "/etc/prometheus"
          name: config-volume
        resources:
          requests:
            cpu: 100m
            memory: 100Mi
          limits:
            cpu: 500m
            memory: 2500Mi
      serviceAccountName: prometheus    
      volumes:
      - name: data
        emptyDir: {}
      - name: config-volume
        configMap:
          name: prometheus-config 

---
kind: Service
apiVersion: v1
metadata:
  labels:
    app: prometheus
  name: prometheus
  namespace: kube-system
spec:
  type: NodePort
  ports:
  - port: 9090
    targetPort: 9090
    nodePort: 30003
  selector:
    app: prometheus

node_cpu

ALERT <alert name>
  IF <expression>
  [ FOR <duration> ]
  [ LABELS <label set> ]
  [ ANNOTATIONS <label set> ]

# To insert a firing element's label values:
{{ $labels.<labelname> }}
# To insert the numeric expression value of the firing element:
{{ $value }}

alerting:
  alertmanagers:
    - static_configs:
      - targets: ["alertManager域名:9093"]

# How frequently to evaluate rules.
[ evaluation_interval: <duration> | default = 1m ]

rule_files:
    - /etc/prometheus/rules.yml

rules.yml: |
    groups:
    - name: test-rule
      rules:
      - alert: NodeFilesystemUsage
        expr: (node_filesystem_size{device="rootfs"} - node_filesystem_free{device="rootfs"}) / node_filesystem_size{device="rootfs"} * 100 > 80
        for: 2m
        labels:
          team: node
        annotations:
          summary: "{{$labels.instance}}: High Filesystem usage detected"
          description: "{{$labels.instance}}: Filesystem usage is above 80% (current value is: {{ $value }}"
      - alert: NodeMemoryUsage
        expr: (node_memory_MemTotal - (node_memory_MemFree+node_memory_Buffers+node_memory_Cached )) / node_memory_MemTotal * 100 > 80
        for: 2m
        labels:
          team: node
        annotations:
          summary: "{{$labels.instance}}: High Memory usage detected"
          description: "{{$labels.instance}}: Memory usage is above 80% (current value is: {{ $value }}"
      - alert: NodeCPUUsage
        expr: (100 - (avg by (instance) (irate(node_cpu{job="kubernetes-node-exporter",mode="idle"}[5m])) * 100)) > 80
        for: 2m
        labels:
          team: node
        annotations:
          summary: "{{$labels.instance}}: High CPU usage detected"
          description: "{{$labels.instance}}: CPU usage is above 80% (current value is: {{ $value }}"

<duration> : 与正则表达式匹配的持续时间值,[0-9]+(ms|[smhdwy])
<labelname>: 与正则表达式匹配的字符串,[a-zA-Z_][a-zA-Z0-9_]*
<labelvalue>: unicode字符串
<filepath>: 有效的文件路径
<boolean>: boolean类型，true或者false
<string>: 字符串
<tmpl_string>: 模板变量字符串

global:
      resolve_timeout: 30s
      smtp_smarthost: "smtp.163.com:25"
      smtp_from: 'xiyanxiyan10@163.com'
      smtp_auth_username: "xiyanxiyan10@163.com" 
      smtp_auth_password: "xiyanxiyan10" 
      smtp_require_tls: false

    route:
      receiver: mailhook
      group_wait: 30s
      group_interval: 1m
      repeat_interval: 1m
      group_by: [NodeMemoryUsage, NodeCPUUsage, NodeFilesystemUsage]

      routes:
      - receiver: mailhook
        group_wait: 10s
        match:
          team: node

route:
  # The labels by which incoming alerts are grouped together. For example,
  # multiple alerts coming in for cluster=A and alertname=LatencyHigh would
  # be batched into a single group.
  group_by: ['alertname']

  # When a new group of alerts is created by an incoming alert, wait at
  # least 'group_wait' to send the initial notification.
  # This way ensures that you get multiple alerts for the same group that start
  # firing shortly after another are batched together on the first 
  # notification.
  group_wait: 5s

  # When the first notification was sent, wait 'group_interval' to send a batch
  # of new alerts that started firing for that group.
  group_interval: 1m

  # If an alert has successfully been sent, wait 'repeat_interval' to
  # resend them.
  repeat_interval: 3h 

  # A default receiver
  receiver: mengyuan

receivers:
- name: 'mengyuan'
  webhook_configs:
  - url: http://192.168.0.53:8080
  email_configs:
  - to: 'xiyanxiyan10@hotmail.com'

#报警接收器
[ receiver: <string> ]

#分组
[ group_by: '[' <labelname>, ... ']' ]

# Whether an alert should continue matching subsequent sibling nodes.
[ continue: <boolean> | default = false ]

# A set of equality matchers an alert has to fulfill to match the node.
#根据匹配的警报，指定接收器
match:
  [ <labelname>: <labelvalue>, ... ]

# A set of regex-matchers an alert has to fulfill to match the node.
match_re:
#根据匹配正则符合的警告，指定接收器
  [ <labelname>: <regex>, ... ]

# How long to initially wait to send a notification for a group
# of alerts. Allows to wait for an inhibiting alert to arrive or collect
# more initial alerts for the same group. (Usually ~0s to few minutes.)
[ group_wait: <duration> ]

# How long to wait before sending notification about new alerts that are
# in are added to a group of alerts for which an initial notification
# has already been sent. (Usually ~5min or more.)
[ group_interval: <duration> ]

# How long to wait before sending a notification again if it has already
# been sent successfully for an alert. (Usually ~3h or more).
[ repeat_interval: <duration> ]

# Zero or more child routes.
routes:
  [ - <route> ... ]

// Match does a depth-first left-to-right search through the route tree
// and returns the matching routing nodes.
func (r *Route) Match(lset model.LabelSet) []*Route {
Alert
Alert是alertmanager接收到的报警，类型如下。

// Alert is a generic representation of an alert in the Prometheus eco-system.
type Alert struct {
    // Label value pairs for purpose of aggregation, matching, and disposition
    // dispatching. This must minimally include an "alertname" label.
    Labels LabelSet `json:"labels"`

    // Extra key/value information which does not define alert identity.
    Annotations LabelSet `json:"annotations"`

    // The known time range for this alert. Both ends are optional.
    StartsAt     time.Time `json:"startsAt,omitempty"`
    EndsAt       time.Time `json:"endsAt,omitempty"`
    GeneratorURL string    `json:"generatorURL"`
}

# Matchers that have to be fulfilled in the alerts to be muted.
##必须在要需要静音的警报中履行的匹配者
target_match:
  [ <labelname>: <labelvalue>, ... ]
target_match_re:
  [ <labelname>: <regex>, ... ]

# Matchers for which one or more alerts have to exist for the
# inhibition to take effect.
#必须存在一个或多个警报以使抑制生效的匹配者。
source_match:
  [ <labelname>: <labelvalue>, ... ]
source_match_re:
  [ <labelname>: <regex>, ... ]

# Labels that must have an equal value in the source and target
# alert for the inhibition to take effect.
#在源和目标警报中必须具有相等值的标签才能使抑制生效
[ equal: '[' <labelname>, ... ']' ]

# The unique name of the receiver.
name: <string>

# Configurations for several notification integrations.
email_configs:
  [ - <email_config>, ... ]
pagerduty_configs:
  [ - <pagerduty_config>, ... ]
slack_config:
  [ - <slack_config>, ... ]
opsgenie_configs:
  [ - <opsgenie_config>, ... ]
webhook_configs:
  [ - <webhook_config>, ... ]
邮件接收器email_config

# Whether or not to notify about resolved alerts.
#警报被解决之后是否通知
[ send_resolved: <boolean> | default = false ]

# The email address to send notifications to.
to: <tmpl_string>
# The sender address.
[ from: <tmpl_string> | default = global.smtp_from ]
# The SMTP host through which emails are sent.
[ smarthost: <string> | default = global.smtp_smarthost ]

# The HTML body of the email notification.
[ html: <tmpl_string> | default = '{{ template "email.default.html" . }}' ] 

# Further headers email header key/value pairs. Overrides any headers
# previously set by the notification implementation.
[ headers: { <string>: <tmpl_string>, ... } ]

# Whether or not to notify about resolved alerts.
[ send_resolved: <boolean> | default = true ]

# The Slack webhook URL.
[ api_url: <string> | default = global.slack_api_url ]

# The channel or user to send notifications to.
channel: <tmpl_string>

# API request data as defined by the Slack webhook API.
[ color: <tmpl_string> | default = '{{ if eq .Status "firing" }}danger{{ else }}good{{ end }}' ]
[ username: <tmpl_string> | default = '{{ template "slack.default.username" . }}'
[ title: <tmpl_string> | default = '{{ template "slack.default.title" . }}' ]
[ title_link: <tmpl_string> | default = '{{ template "slack.default.titlelink" . }}' ]
[ pretext: <tmpl_string> | default = '{{ template "slack.default.pretext" . }}' ]
[ text: <tmpl_string> | default = '{{ template "slack.default.text" . }}' ]
[ fallback: <tmpl_string> | default = '{{ template "slack.default.fallback" . }}' ]

 # Whether or not to notify about resolved alerts.
[ send_resolved: <boolean> | default = true ]

 # The endpoint to send HTTP POST requests to.
url: <string>

{
  "version": "3",
  "groupKey": <number>     // key identifying the group of alerts (e.g. to deduplicate)
  "status": "<resolved|firing>",
  "receiver": <string>,
  "groupLabels": <object>,
  "commonLabels": <object>,
  "commonAnnotations": <object>,
  "externalURL": <string>,  // backling to the Alertmanager.
  "alerts": [
    {
      "labels": <object>,
      "annotations": <object>,
      "startsAt": "<rfc3339>",
      "endsAt": "<rfc3339>"
    },
    ...
  ]
}

 receivers:
    - name: mailhook
      email_configs:
      - to: "xiyanxiyan10@hotmail.com"
        html: '{{ template "alert.html" . }}'
        headers: { Subject: "[WARN] Warn Email" }

# cat grafana-deploy.yaml 

---
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
  name: grafana-core
  namespace: kube-system
  labels:
    app: grafana
    component: core
spec:
  replicas: 1
  template:
    metadata:
      labels:
        app: grafana
        component: core
    spec:
      containers:
      - image: grafana/grafana:4.2.0
        name: grafana-core
        imagePullPolicy: IfNotPresent
        # env:
        resources:
          # keep request = limit to keep this container in guaranteed class
          limits:
            cpu: 100m
            memory: 100Mi
          requests:
            cpu: 100m
            memory: 100Mi
        env:
          # The following env variables set up basic auth twith the default admin user and admin password.
          - name: GF_AUTH_BASIC_ENABLED
            value: "true"
          - name: GF_AUTH_ANONYMOUS_ENABLED
            value: "false"
          # - name: GF_AUTH_ANONYMOUS_ORG_ROLE
          #   value: Admin
          # does not really work, because of template variables in exported dashboards:
          # - name: GF_DASHBOARDS_JSON_ENABLED
          #   value: "true"
        readinessProbe:
          httpGet:
            path: /login
            port: 3000
          # initialDelaySeconds: 30
          # timeoutSeconds: 1
        volumeMounts:
        - name: grafana-persistent-storage
          mountPath: /var
      volumes:
      - name: grafana-persistent-storage
        emptyDir: {}
--- 
apiVersion: v1
kind: Service
metadata:
  name: grafana
  namespace: kube-system
  labels:
    app: grafana
    component: core
spec:
  type: NodePort
  ports:
    - port: 3000
      targetPort: 3000
      nodePort: 30009
  selector:
    app: grafana