1 Grafana介绍
Grafana是一个跨平台的开源的度量分析和可视化工具，可以将采集的数据可视化的展示，并及时通知给告警接收方。它主要有以下六大特点：
1、展示方式：快速灵活的客户端图表，面板插件有许多不同方式的可视化指标和日志，官方库中具有丰富的仪表盘插件，比如热图、折线图、图表等多种展示方式；
2、数据源：Graphite，InfluxDB，OpenTSDB，Prometheus，Elasticsearch，CloudWatch和KairosDB等；
3、通知提醒：以可视方式定义最重要指标的警报规则，Grafana将不断计算并发送通知，在数据达到阈值时通过Slack、PagerDuty等获得通知；
4、混合展示：在同一图表中混合使用不同的数据源，可以基于每个查询指定数据源，甚至自定义数据源；
5、注释：使用来自不同数据源的丰富事件注释图表，将鼠标悬停在事件上会显示完整的事件元数据和标记。
编写yaml 部署文件
[root@k8s-master cka]# cat grafana.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
name: monitoring-grafana
namespace: kube-system
spec:
replicas: 1
selector:
matchLabels:
task: monitoring
k8s-app: grafana
template:
metadata:
labels:
task: monitoring
k8s-app: grafana
spec:
containers:
- name: grafana
image: k8s.gcr.io/heapster-grafana-amd64:v5.0.4
imagePullPolicy: IfNotPresent
ports:
- containerPort: 3000
protocol: TCP
volumeMounts:
- mountPath: /etc/ssl/certs
name: ca-certificates
readOnly: true
- mountPath: /var
name: grafana-storage
env:
- name: INFLUXDB_HOST
value: monitoring-influxdb
- name: GF_SERVER_HTTP_PORT
value: "3000"
# The following env variables are required to make Grafana accessible via
# the kubernetes api-server proxy. On production clusters, we recommend
# removing these env variables, setup auth for grafana, and expose the grafana
# service using a LoadBalancer or a public IP.
- name: GF_AUTH_BASIC_ENABLED
value: "false"
- name: GF_AUTH_ANONYMOUS_ENABLED
value: "true"
- name: GF_AUTH_ANONYMOUS_ORG_ROLE
value: Admin
- name: GF_SERVER_ROOT_URL
# If you're only using the API Server proxy, set this value instead:
# value: /api/v1/namespaces/kube-system/services/monitoring-grafana/proxy
value: /
volumes:
- name: ca-certificates
hostPath:
path: /etc/ssl/certs
- name: grafana-storage
emptyDir: {}
---
apiVersion: v1
kind: Service
metadata:
labels:
# For use as a Cluster add-on (https://github.com/kubernetes/kubernetes/tree/master/cluster/addons)
# If you are NOT using this as an addon, you should comment out this line.
kubernetes.io/cluster-service: 'true'
kubernetes.io/name: monitoring-grafana
name: monitoring-grafana
namespace: kube-system
spec:
# In a production setup, we recommend accessing Grafana through an external Loadbalancer
# or through a public IP.
# type: LoadBalancer
# You could also use NodePort to expose the service at a randomly-generated port
# type: NodePort
ports:
- port: 80
targetPort: 3000
selector:
k8s-app: grafana
type: NodePort
创建
[root@k8s-master cka]# kubectl apply -f grafana.yaml deployment.apps/monitoring-grafana created service/monitoring-grafana created
查看
[root@k8s-master cka]# kubectl get pod -n kube-system -owide NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES calico-kube-controllers-677cd97c8d-tcjfs 1/1 Running 0 23h 10.244.169.129 k8s-node2 <none> <none> calico-node-29wxx 1/1 Running 0 23h 192.168.10.50 k8s-master <none> <none> calico-node-8vv57 1/1 Running 0 23h 192.168.10.51 k8s-node1 <none> <none> calico-node-nf6qv 1/1 Running 0 23h 192.168.10.52 k8s-node2 <none> <none> coredns-6d8c4cb4d-f6vbx 1/1 Running 0 23h 10.244.169.130 k8s-node2 <none> <none> coredns-6d8c4cb4d-gvkt5 1/1 Running 0 23h 10.244.169.131 k8s-node2 <none> <none> etcd-k8s-master 1/1 Running 0 23h 192.168.10.50 k8s-master <none> <none> kube-apiserver-k8s-master 1/1 Running 0 23h 192.168.10.50 k8s-master <none> <none> kube-controller-manager-k8s-master 1/1 Running 0 23h 192.168.10.50 k8s-master <none> <none> kube-proxy-fmwch 1/1 Running 0 23h 192.168.10.51 k8s-node1 <none> <none> kube-proxy-tt9ts 1/1 Running 0 23h 192.168.10.52 k8s-node2 <none> <none> kube-proxy-xdxsx 1/1 Running 0 23h 192.168.10.50 k8s-master <none> <none> kube-scheduler-k8s-master 1/1 Running 0 23h 192.168.10.50 k8s-master <none> <none> monitoring-grafana-7948df75d9-fdxs2 1/1 Running 0 31s 10.244.36.66 k8s-node1 <none> <none> [root@k8s-master cka]# [root@k8s-master cka]# kubectl get svc -n kube-system -owide NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE SELECTOR kube-dns ClusterIP 10.96.0.10 <none> 53/UDP,53/TCP,9153/TCP 23h k8s-app=kube-dns monitoring-grafana NodePort 10.108.3.145 <none> 80:31945/TCP 2m k8s-app=grafana
配置数据源
导入的监控模板，可在如下链接搜索
https://grafana.com/dashboards?dataSource=prometheus&search=kubernetes
可直接导入node_exporter.json监控模板，这个可以把node节点指标显示出来
安装kube-state-metrics组件
kube-state-metrics通过监听API Server生成有关资源对象的状态指标，比如Node、Pod，需要注意的是kube-state-metrics只是简单的提供一个metrics数据，并不会存储这些指标数据，所以我们可以使用Prometheus来抓取这些数据然后存储，主要关注的是业务相关的一些元数据，比如Pod副本状态等；
安装kube-state-metrics组件
1）创建sa，并对sa授权
在k8s的控制节点生成一个kube-state-metrics-rbac.yaml文件
[root@k8s-master cka]# cat kube-state-metrics-rbac.yaml --- apiVersion: v1 kind: ServiceAccount metadata: name: kube-state-metrics namespace: kube-system --- apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRole metadata: name: kube-state-metrics rules: - apiGroups: [""] resources: ["nodes", "pods", "services", "resourcequotas", "replicationcontrollers", "limitranges", "persistentvolumeclaims", "persistentvolumes", "namespaces", "endpoints"] verbs: ["list", "watch"] - apiGroups: ["extensions"] resources: ["daemonsets", "deployments", "replicasets"] verbs: ["list", "watch"] - apiGroups: ["apps"] resources: ["statefulsets"] verbs: ["list", "watch"] - apiGroups: ["batch"] resources: ["cronjobs", "jobs"] verbs: ["list", "watch"] - apiGroups: ["autoscaling"] resources: ["horizontalpodautoscalers"] verbs: ["list", "watch"] --- apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRoleBinding metadata: name: kube-state-metrics roleRef: apiGroup: rbac.authorization.k8s.io kind: ClusterRole name: kube-state-metrics subjects: - kind: ServiceAccount name: kube-state-metrics namespace: kube-system [root@k8s-master cka]# kubectl apply -f kube-state-metrics-rbac.yaml serviceaccount/kube-state-metrics created clusterrole.rbac.authorization.k8s.io/kube-state-metrics created clusterrolebinding.rbac.authorization.k8s.io/kube-state-metrics created
通过kubectl apply更新资源清单yaml文件
[root@k8s-master cka]# cat kube-state-metrics-deploy.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
name: kube-state-metrics
namespace: kube-system
spec:
replicas: 1
selector:
matchLabels:
app: kube-state-metrics
template:
metadata:
labels:
app: kube-state-metrics
spec:
serviceAccountName: kube-state-metrics
containers:
- name: kube-state-metrics
image: quay.io/coreos/kube-state-metrics:v1.9.0
imagePullPolicy: IfNotPresent
ports:
- containerPort: 8080
[root@k8s-master cka]# kubectl apply -f kube-state-metrics-deploy.yaml
deployment.apps/kube-state-metrics created
创建service
在8s的控制节点生成一个kube-state-metrics-svc.yaml文件
[root@k8s-master cka]# cat kube-state-metrics-svc.yaml
apiVersion: v1
kind: Service
metadata:
annotations:
prometheus.io/scrape: 'true'
name: kube-state-metrics
namespace: kube-system
labels:
app: kube-state-metrics
spec:
ports:
- name: kube-state-metrics
port: 8080
protocol: TCP
selector:
app: kube-state-metrics
[root@k8s-master cka]# kubectl apply -f kube-state-metrics-svc.yaml
service/kube-state-metrics created
配置alertmanager-发送报警到qq邮箱
报警：指prometheus将监测到的异常事件发送给alertmanager
通知：alertmanager将报警信息发送到邮件、微信、钉钉等
创建alertmanager配置文件
在k8s的控制节点创建alertmanager-cm.yaml文件
[root@k8s-master cka]# cat alertmanager-cm.yaml
kind: ConfigMap
apiVersion: v1
metadata:
name: alertmanager
namespace: monitor-sa
data:
alertmanager.yml: |-
global:
resolve_timeout: 1m
smtp_smarthost: 'smtp.163.com:25'
smtp_from: 'rdchenxi@163.com'
smtp_auth_username: 'rdchenxi@163.com'
smtp_auth_password: 'DHTTKBPNMYSGTWAW'
smtp_require_tls: false
route:
group_by: [alertname]
group_wait: 10s
group_interval: 10s
repeat_interval: 10m
receiver: default-receiver
receivers:
- name: 'default-receiver'
email_configs:
- to: 'ruidongchenxi@163.com'
send_resolved: true
alertmanager配置文件解释说明：
smtp_smarthost: 'smtp.163.com:25'
#163邮箱的SMTP服务器地址+端口
smtp_from: '15011572657@163.com'
#这是指定从哪个邮箱发送报警
smtp_auth_username: '15011572657@163.com'
smtp_auth_password: ' BGWHYUOSOOHWEUJM'
#这是发送邮箱的授权码而不是登录密码，你们需要用自己的，不要用我的，用我的你会发不出来报警
email_configs:
- to: '1980570647@qq.com'
#to后面指定发送到哪个邮箱，我发送到我的qq邮箱，大家需要写自己的邮箱地址，不应该跟smtp_from的邮箱名字重复
route: #用于设置告警的分发策略
group_by: [alertname]
#alertmanager会根据group_by配置将Alert分组
group_wait: 10s
# 分组等待时间。也就是告警产生后等待10s，如果有同组告警一起发出
group_interval: 10s # 上下两组发送告警的间隔时间
repeat_interval: 10m # 重复发送告警的时间，减少相同邮件的发送频率，默认是1h
receiver: default-receiver #定义谁来收告警
报警处理流程如下：
1. Prometheus Server监控目标主机上暴露的http接口（这里假设接口A），通过Promethes配置的'scrape_interval'定义的时间间隔，定期采集目标主机上监控数据。
2. 当接口A不可用的时候，Server端会持续的尝试从接口中取数据，直到"scrape_timeout"时间后停止尝试。这时候把接口的状态变为“DOWN”。
3. Prometheus同时根据配置的"evaluation_interval"的时间间隔，定期（默认1min）的对Alert Rule进行评估；当到达评估周期的时候，发现接口A为DOWN，即UP=0为真，激活Alert，进入“PENDING”状态，并记录当前active的时间；
4. 当下一个alert rule的评估周期到来的时候，发现UP=0继续为真，然后判断警报Active的时间是否已经超出rule里的‘for’ 持续时间，如果未超出，则进入下一个评估周期；如果时间超出，则alert的状态变为“FIRING”；同时调用Alertmanager接口，发送相关报警数据。
5. AlertManager收到报警数据后，会将警报信息进行分组，然后根据alertmanager配置的“group_wait”时间先进行等待。等wait时间过后再发送报警信息。
6. 属于同一个Alert Group的警报，在等待的过程中可能进入新的alert，如果之前的报警已经成功发出，那么间隔“group_interval”的时间间隔后再重新发送报警信息。比如配置的是邮件报警，那么同属一个group的报警信息会汇总在一个邮件里进行发送。
7. 如果Alert Group里的警报一直没发生变化并且已经成功发送，等待‘repeat_interval’时间间隔之后再重复发送相同的报警邮件；如果之前的警报没有成功发送，则相当于触发第6条条件，则需要等待group_interval时间间隔后重复发送。
编辑prometheus-alertmanager-cfg.yaml
[root@k8s-master cka]# cat prometheus-alertmanager-cfg.yaml
kind: ConfigMap
apiVersion: v1
metadata:
labels:
app: prometheus
name: prometheus-config
namespace: monitor-sa
data:
prometheus.yml: |
rule_files:
- /etc/prometheus/rules.yml
alerting:
alertmanagers:
- static_configs:
- targets: ["localhost:9093"]
global:
scrape_interval: 15s
scrape_timeout: 10s
evaluation_interval: 1m
scrape_configs:
- job_name: 'kubernetes-node'
kubernetes_sd_configs:
- role: node
relabel_configs:
- source_labels: [__address__]
regex: '(.*):10250'
replacement: '${1}:9100'
target_label: __address__
action: replace
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
- job_name: 'kubernetes-node-cadvisor'
kubernetes_sd_configs:
- role: node
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
relabel_configs:
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
- target_label: __address__
replacement: kubernetes.default.svc:443
- source_labels: [__meta_kubernetes_node_name]
regex: (.+)
target_label: __metrics_path__
replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
- job_name: 'kubernetes-apiserver'
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-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-pods'
kubernetes_sd_configs:
- role: pod
relabel_configs:
- action: keep
regex: true
source_labels:
- __meta_kubernetes_pod_annotation_prometheus_io_scrape
- action: replace
regex: (.+)
source_labels:
- __meta_kubernetes_pod_annotation_prometheus_io_path
target_label: __metrics_path__
- action: replace
regex: ([^:]+)(?::\d+)?;(\d+)
replacement: $1:$2
source_labels:
- __address__
- __meta_kubernetes_pod_annotation_prometheus_io_port
target_label: __address__
- action: labelmap
regex: __meta_kubernetes_pod_label_(.+)
- action: replace
source_labels:
- __meta_kubernetes_namespace
target_label: kubernetes_namespace
- action: replace
source_labels:
- __meta_kubernetes_pod_name
target_label: kubernetes_pod_name
- job_name: 'kubernetes-etcd'
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/k8s-certs/etcd/ca.crt
cert_file: /var/run/secrets/kubernetes.io/k8s-certs/etcd/server.crt
key_file: /var/run/secrets/kubernetes.io/k8s-certs/etcd/server.key
scrape_interval: 5s
static_configs:
- targets: ['192.168.40.180:2379']
rules.yml: |
groups:
- name: example
rules:
- alert: apiserver的cpu使用率大于80%
expr: rate(process_cpu_seconds_total{job=~"kubernetes-apiserver"}[1m]) * 100 > 80
for: 2s
labels:
severity: warnning
annotations:
description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过80%"
- alert: apiserver的cpu使用率大于90%
expr: rate(process_cpu_seconds_total{job=~"kubernetes-apiserver"}[1m]) * 100 > 90
for: 2s
labels:
severity: critical
annotations:
description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过90%"
- alert: etcd的cpu使用率大于80%
expr: rate(process_cpu_seconds_total{job=~"kubernetes-etcd"}[1m]) * 100 > 80
for: 2s
labels:
severity: warnning
annotations:
description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过80%"
- alert: etcd的cpu使用率大于90%
expr: rate(process_cpu_seconds_total{job=~"kubernetes-etcd"}[1m]) * 100 > 90
for: 2s
labels:
severity: critical
annotations:
description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过90%"
- alert: kube-state-metrics的cpu使用率大于80%
expr: rate(process_cpu_seconds_total{k8s_app=~"kube-state-metrics"}[1m]) * 100 > 80
for: 2s
labels:
severity: warnning
annotations:
description: "{{$labels.instance}}的{{$labels.k8s_app}}组件的cpu使用率超过80%"
value: "{{ $value }}%"
threshold: "80%"
- alert: kube-state-metrics的cpu使用率大于90%
expr: rate(process_cpu_seconds_total{k8s_app=~"kube-state-metrics"}[1m]) * 100 > 0
for: 2s
labels:
severity: critical
annotations:
description: "{{$labels.instance}}的{{$labels.k8s_app}}组件的cpu使用率超过90%"
value: "{{ $value }}%"
threshold: "90%"
- alert: coredns的cpu使用率大于80%
expr: rate(process_cpu_seconds_total{k8s_app=~"kube-dns"}[1m]) * 100 > 80
for: 2s
labels:
severity: warnning
annotations:
description: "{{$labels.instance}}的{{$labels.k8s_app}}组件的cpu使用率超过80%"
value: "{{ $value }}%"
threshold: "80%"
- alert: coredns的cpu使用率大于90%
expr: rate(process_cpu_seconds_total{k8s_app=~"kube-dns"}[1m]) * 100 > 90
for: 2s
labels:
severity: critical
annotations:
description: "{{$labels.instance}}的{{$labels.k8s_app}}组件的cpu使用率超过90%"
value: "{{ $value }}%"
threshold: "90%"
- alert: kube-proxy打开句柄数>600
expr: process_open_fds{job=~"kubernetes-kube-proxy"} > 600
for: 2s
labels:
severity: warnning
annotations:
description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>600"
value: "{{ $value }}"
- alert: kube-proxy打开句柄数>1000
expr: process_open_fds{job=~"kubernetes-kube-proxy"} > 1000
for: 2s
labels:
severity: critical
annotations:
description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>1000"
value: "{{ $value }}"
- alert: kubernetes-schedule打开句柄数>600
expr: process_open_fds{job=~"kubernetes-schedule"} > 600
for: 2s
labels:
severity: warnning
annotations:
description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>600"
value: "{{ $value }}"
- alert: kubernetes-schedule打开句柄数>1000
expr: process_open_fds{job=~"kubernetes-schedule"} > 1000
for: 2s
labels:
severity: critical
annotations:
description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>1000"
value: "{{ $value }}"
- alert: kubernetes-controller-manager打开句柄数>600
expr: process_open_fds{job=~"kubernetes-controller-manager"} > 600
for: 2s
labels:
severity: warnning
annotations:
description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>600"
value: "{{ $value }}"
- alert: kubernetes-controller-manager打开句柄数>1000
expr: process_open_fds{job=~"kubernetes-controller-manager"} > 1000
for: 2s
labels:
severity: critical
annotations:
description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>1000"
value: "{{ $value }}"
- alert: kubernetes-apiserver打开句柄数>600
expr: process_open_fds{job=~"kubernetes-apiserver"} > 600
for: 2s
labels:
severity: warnning
annotations:
description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>600"
value: "{{ $value }}"
- alert: kubernetes-apiserver打开句柄数>1000
expr: process_open_fds{job=~"kubernetes-apiserver"} > 1000
for: 2s
labels:
severity: critical
annotations:
description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>1000"
value: "{{ $value }}"
- alert: kubernetes-etcd打开句柄数>600
expr: process_open_fds{job=~"kubernetes-etcd"} > 600
for: 2s
labels:
severity: warnning
annotations:
description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>600"
value: "{{ $value }}"
- alert: kubernetes-etcd打开句柄数>1000
expr: process_open_fds{job=~"kubernetes-etcd"} > 1000
for: 2s
labels:
severity: critical
annotations:
description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>1000"
value: "{{ $value }}"
- alert: coredns
expr: process_open_fds{k8s_app=~"kube-dns"} > 600
for: 2s
labels:
severity: warnning
annotations:
description: "插件{{$labels.k8s_app}}({{$labels.instance}}): 打开句柄数超过600"
value: "{{ $value }}"
- alert: coredns
expr: process_open_fds{k8s_app=~"kube-dns"} > 1000
for: 2s
labels:
severity: critical
annotations:
description: "插件{{$labels.k8s_app}}({{$labels.instance}}): 打开句柄数超过1000"
value: "{{ $value }}"
- alert: kube-proxy
expr: process_virtual_memory_bytes{job=~"kubernetes-kube-proxy"} > 2000000000
for: 2s
labels:
severity: warnning
annotations:
description: "组件{{$labels.job}}({{$labels.instance}}): 使用虚拟内存超过2G"
value: "{{ $value }}"
- alert: scheduler
expr: process_virtual_memory_bytes{job=~"kubernetes-schedule"} > 2000000000
for: 2s
labels:
severity: warnning
annotations:
description: "组件{{$labels.job}}({{$labels.instance}}): 使用虚拟内存超过2G"
value: "{{ $value }}"
- alert: kubernetes-controller-manager
expr: process_virtual_memory_bytes{job=~"kubernetes-controller-manager"} > 2000000000
for: 2s
labels:
severity: warnning
annotations:
description: "组件{{$labels.job}}({{$labels.instance}}): 使用虚拟内存超过2G"
value: "{{ $value }}"
- alert: kubernetes-apiserver
expr: process_virtual_memory_bytes{job=~"kubernetes-apiserver"} > 2000000000
for: 2s
labels:
severity: warnning
annotations:
description: "组件{{$labels.job}}({{$labels.instance}}): 使用虚拟内存超过2G"
value: "{{ $value }}"
- alert: kubernetes-etcd
expr: process_virtual_memory_bytes{job=~"kubernetes-etcd"} > 2000000000
for: 2s
labels:
severity: warnning
annotations:
description: "组件{{$labels.job}}({{$labels.instance}}): 使用虚拟内存超过2G"
value: "{{ $value }}"
- alert: kube-dns
expr: process_virtual_memory_bytes{k8s_app=~"kube-dns"} > 2000000000
for: 2s
labels:
severity: warnning
annotations:
description: "插件{{$labels.k8s_app}}({{$labels.instance}}): 使用虚拟内存超过2G"
value: "{{ $value }}"
- alert: HttpRequestsAvg
expr: sum(rate(rest_client_requests_total{job=~"kubernetes-kube-proxy|kubernetes-kubelet|kubernetes-schedule|kubernetes-control-manager|kubernetes-apiservers"}[1m])) > 1000
for: 2s
labels:
team: admin
annotations:
description: "组件{{$labels.job}}({{$labels.instance}}): TPS超过1000"
value: "{{ $value }}"
threshold: "1000"
- alert: Pod_restarts
expr: kube_pod_container_status_restarts_total{namespace=~"kube-system|default|monitor-sa"} > 0
for: 2s
labels:
severity: warnning
annotations:
description: "在{{$labels.namespace}}名称空间下发现{{$labels.pod}}这个pod下的容器{{$labels.container}}被重启,这个监控指标是由{{$labels.instance}}采集的"
value: "{{ $value }}"
threshold: "0"
- alert: Pod_waiting
expr: kube_pod_container_status_waiting_reason{namespace=~"kube-system|default"} == 1
for: 2s
labels:
team: admin
annotations:
description: "空间{{$labels.namespace}}({{$labels.instance}}): 发现{{$labels.pod}}下的{{$labels.container}}启动异常等待中"
value: "{{ $value }}"
threshold: "1"
- alert: Pod_terminated
expr: kube_pod_container_status_terminated_reason{namespace=~"kube-system|default|monitor-sa"} == 1
for: 2s
labels:
team: admin
annotations:
description: "空间{{$labels.namespace}}({{$labels.instance}}): 发现{{$labels.pod}}下的{{$labels.container}}被删除"
value: "{{ $value }}"
threshold: "1"
- alert: Etcd_leader
expr: etcd_server_has_leader{job="kubernetes-etcd"} == 0
for: 2s
labels:
team: admin
annotations:
description: "组件{{$labels.job}}({{$labels.instance}}): 当前没有leader"
value: "{{ $value }}"
threshold: "0"
- alert: Etcd_leader_changes
expr: rate(etcd_server_leader_changes_seen_total{job="kubernetes-etcd"}[1m]) > 0
for: 2s
labels:
team: admin
annotations:
description: "组件{{$labels.job}}({{$labels.instance}}): 当前leader已发生改变"
value: "{{ $value }}"
threshold: "0"
- alert: Etcd_failed
expr: rate(etcd_server_proposals_failed_total{job="kubernetes-etcd"}[1m]) > 0
for: 2s
labels:
team: admin
annotations:
description: "组件{{$labels.job}}({{$labels.instance}}): 服务失败"
value: "{{ $value }}"
threshold: "0"
- alert: Etcd_db_total_size
expr: etcd_debugging_mvcc_db_total_size_in_bytes{job="kubernetes-etcd"} > 10000000000
for: 2s
labels:
team: admin
annotations:
description: "组件{{$labels.job}}({{$labels.instance}})：db空间超过10G"
value: "{{ $value }}"
threshold: "10G"
- alert: Endpoint_ready
expr: kube_endpoint_address_not_ready{namespace=~"kube-system|default"} == 1
for: 2s
labels:
team: admin
annotations:
description: "空间{{$labels.namespace}}({{$labels.instance}}): 发现{{$labels.endpoint}}不可用"
value: "{{ $value }}"
threshold: "1"
- name: 物理节点状态-监控告警
rules:
- alert: 物理节点cpu使用率
expr: 100-avg(irate(node_cpu_seconds_total{mode="idle"}[5m])) by(instance)*100 > 90
for: 2s
labels:
severity: ccritical
annotations:
summary: "{{ $labels.instance }}cpu使用率过高"
description: "{{ $labels.instance }}的cpu使用率超过90%,当前使用率[{{ $value }}],需要排查处理"
- alert: 物理节点内存使用率
expr: (node_memory_MemTotal_bytes - (node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes)) / node_memory_MemTotal_bytes * 100 > 90
for: 2s
labels:
severity: critical
annotations:
summary: "{{ $labels.instance }}内存使用率过高"
description: "{{ $labels.instance }}的内存使用率超过90%,当前使用率[{{ $value }}],需要排查处理"
- alert: InstanceDown
expr: up == 0
for: 2s
labels:
severity: critical
annotations:
summary: "{{ $labels.instance }}: 服务器宕机"
description: "{{ $labels.instance }}: 服务器延时超过2分钟"
- alert: 物理节点磁盘的IO性能
expr: 100-(avg(irate(node_disk_io_time_seconds_total[1m])) by(instance)* 100) < 60
for: 2s
labels:
severity: critical
annotations:
summary: "{{$labels.mountpoint}} 流入磁盘IO使用率过高！"
description: "{{$labels.mountpoint }} 流入磁盘IO大于60%(目前使用:{{$value}})"
- alert: 入网流量带宽
expr: ((sum(rate (node_network_receive_bytes_total{device!~'tap.*|veth.*|br.*|docker.*|virbr*|lo*'}[5m])) by (instance)) / 100) > 102400
for: 2s
labels:
severity: critical
annotations:
summary: "{{$labels.mountpoint}} 流入网络带宽过高！"
description: "{{$labels.mountpoint }}流入网络带宽持续5分钟高于100M. RX带宽使用率{{$value}}"
- alert: 出网流量带宽
expr: ((sum(rate (node_network_transmit_bytes_total{device!~'tap.*|veth.*|br.*|docker.*|virbr*|lo*'}[5m])) by (instance)) / 100) > 102400
for: 2s
labels:
severity: critical
annotations:
summary: "{{$labels.mountpoint}} 流出网络带宽过高！"
description: "{{$labels.mountpoint }}流出网络带宽持续5分钟高于100M. RX带宽使用率{{$value}}"
- alert: TCP会话
expr: node_netstat_Tcp_CurrEstab > 1000
for: 2s
labels:
severity: critical
annotations:
summary: "{{$labels.mountpoint}} TCP_ESTABLISHED过高！"
description: "{{$labels.mountpoint }} TCP_ESTABLISHED大于1000%(目前使用:{{$value}}%)"
- alert: 磁盘容量
expr: 100-(node_filesystem_free_bytes{fstype=~"ext4|xfs"}/node_filesystem_size_bytes {fstype=~"ext4|xfs"}*100) > 80
for: 2s
labels:
severity: critical
annotations:
summary: "{{$labels.mountpoint}} 磁盘分区使用率过高！"
description: "{{$labels.mountpoint }} 磁盘分区使用大于80%(目前使用:{{$value}}%)"
创建
[root@k8s-master cka]# kubectl apply -f prometheus-alertmanager-cfg.yaml configmap/prometheus-config unchanged
生成一个etcd-certs，这个在部署prometheus需要
[root@k8s-master cka]# kubectl -n monitor-sa create secret generic etcd-certs --from-file=/etc/kubernetes/pki/etcd/server.key --from-file=/etc/kubernetes/pki/etcd/server.crt --from-file=/etc/kubernetes/pki/et cd/ca.crt
编写prometheus-alertmanager-deploy.yaml
[root@k8s-master cka]# cat prometheus-alertmanager-deploy.yaml
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: prometheus-server
namespace: monitor-sa
labels:
app: prometheus
spec:
replicas: 1
selector:
matchLabels:
app: prometheus
component: server
#matchExpressions:
#- {key: app, operator: In, values: [prometheus]}
#- {key: component, operator: In, values: [server]}
template:
metadata:
labels:
app: prometheus
component: server
annotations:
prometheus.io/scrape: 'false'
spec:
nodeName: xianchaonode1
serviceAccountName: monitor
containers:
- name: prometheus
image: prom/prometheus:v2.2.1
imagePullPolicy: IfNotPresent
command:
- "/bin/prometheus"
args:
- "--config.file=/etc/prometheus/prometheus.yml"
- "--storage.tsdb.path=/prometheus"
- "--storage.tsdb.retention=24h"
- "--web.enable-lifecycle"
ports:
- containerPort: 9090
protocol: TCP
volumeMounts:
- mountPath: /etc/prometheus
name: prometheus-config
- mountPath: /prometheus/
name: prometheus-storage-volume
- name: k8s-certs
mountPath: /var/run/secrets/kubernetes.io/k8s-certs/etcd/
- name: alertmanager
image: prom/alertmanager:v0.14.0
imagePullPolicy: IfNotPresent
args:
- "--config.file=/etc/alertmanager/alertmanager.yml"
- "--log.level=debug"
ports:
- containerPort: 9093
protocol: TCP
name: alertmanager
volumeMounts:
- name: alertmanager-config
mountPath: /etc/alertmanager
- name: alertmanager-storage
mountPath: /alertmanager
- name: localtime
mountPath: /etc/localtime
volumes:
- name: prometheus-config
configMap:
name: prometheus-config
- name: prometheus-storage-volume
hostPath:
path: /data
type: Directory
- name: k8s-certs
secret:
secretName: etcd-certs
- name: alertmanager-config
configMap:
name: alertmanager
- name: alertmanager-storage
hostPath:
path: /data/alertmanager
type: DirectoryOrCreate
- name: localtime
hostPath:
path: /usr/share/zoneinfo/Asia/Shanghai
创建
[root@k8s-master cka]# kubectl apply -f prometheus-alertmanager-deploy.yaml deployment.apps/prometheus-server configured
编写创建svc
[root@k8s-master cka]# kubectl apply -f alertmanager-svc.yaml
service/alertmanager created
[root@k8s-master cka]# cat alertmanager-svc.yaml
---
apiVersion: v1
kind: Service
metadata:
labels:
name: prometheus
kubernetes.io/cluster-service: 'true'
name: alertmanager
namespace: monitor-sa
spec:
ports:
- name: alertmanager
nodePort: 30066
port: 9093
protocol: TCP
targetPort: 9093
selector:
app: prometheus
sessionAffinity: None
type: NodePort
http://192.168.10.50:30194/targets
