PrometheusK8S中部署Alertmanager

# Prometheus configuration format https://prometheus.io/docs/prometheus/latest/configuration/configuration/
apiVersion: v1
kind: ConfigMap
metadata:
name: prometheus-config
namespace: kube-system
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: EnsureExists
data:
# 存放prometheus配置文件
prometheus.yml: |
# 配置采集目标
scrape_configs:
- job_name: prometheus
static_configs:
- targets:
# 采集自身
- localhost:9090
prometheus.yml: |
# 配置采集目标
scrape_configs:
- job_name: kubernetes-nodes
static_configs:
- targets:
# 采集自身
- 192.168.1.110:9100
- 192.168.1.111:9100

# 采集：Apiserver 生存指标
# 创建的job name 名称为 kubernetes-apiservers
- job_name: kubernetes-apiservers
# 基于k8s的服务发现
kubernetes_sd_configs:
- role: endpoints
# 使用通信标记标签
relabel_configs:
# 保留正则匹配标签
- action: keep
# 已经包含
regex: default;kubernetes;https
source_labels:
- __meta_kubernetes_namespace
- __meta_kubernetes_service_name
- __meta_kubernetes_endpoint_port_name
# 使用方法为https、默认http
scheme: https
tls_config:
# promethus访问Apiserver使用认证
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
# 跳过https认证
insecure_skip_verify: true
# promethus访问Apiserver使用认证
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
# 采集：Kubelet 生存指标
- job_name: kubernetes-nodes-kubelet
kubernetes_sd_configs:
# 发现集群中所有的Node
- role: node
relabel_configs:
# 通过regex获取关键信息
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
insecure_skip_verify: true
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
# 采集：nodes-cadvisor 信息
- job_name: kubernetes-nodes-cadvisor
kubernetes_sd_configs:
- role: node
relabel_configs:
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
# 重命名标签
- target_label: __metrics_path__
replacement: /metrics/cadvisor
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
insecure_skip_verify: true
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
# 采集：service-endpoints 信息
- job_name: kubernetes-service-endpoints
# 选定指标
kubernetes_sd_configs:
- role: endpoints
relabel_configs:
- action: keep
regex: true
# 指定源标签
source_labels:
- __meta_kubernetes_service_annotation_prometheus_io_scrape
- action: replace
regex: (https?)
source_labels:
- __meta_kubernetes_service_annotation_prometheus_io_scheme
# 重命名标签采集
target_label: __scheme__
- action: replace
regex: (.+)
source_labels:
- __meta_kubernetes_service_annotation_prometheus_io_path
target_label: __metrics_path__
- action: replace
regex: ([^:]+)(?::\d+)?;(\d+)
replacement: $1:$2
source_labels:
- __address__
- __meta_kubernetes_service_annotation_prometheus_io_port
target_label: __address__
- action: labelmap
regex: __meta_kubernetes_service_label_(.+)
- action: replace
source_labels:
- __meta_kubernetes_namespace
target_label: kubernetes_namespace
- action: replace
source_labels:
- __meta_kubernetes_service_name
target_label: kubernetes_name
# 采集：kubernetes-services 服务指标
- job_name: kubernetes-services
kubernetes_sd_configs:
- role: service
# 黑盒探测，探测IP与端口是否可用
metrics_path: /probe
params:
module:
- http_2xx
relabel_configs:
- action: keep
regex: true
source_labels:
- __meta_kubernetes_service_annotation_prometheus_io_probe
- source_labels:
- __address__
target_label: __param_target
# 使用 blackbox进行黑盒探测
- replacement: blackbox
target_label: __address__
- 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
# 采集： kubernetes-pods 信息
- job_name: kubernetes-pods
kubernetes_sd_configs:
- role: pod
relabel_configs:
- action: keep
regex: true
source_labels:
# 只保留采集的信息
- __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:
# 采集地址
- __address__
# 采集端口
- __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
alerting:
# 告警配置文件
alertmanagers:
# 修改：使用静态绑定
- static_configs:
# 修改：targets、指定地址与端口
- targets: ["alertmanager:80"]

apiVersion: v1
kind: ConfigMap
metadata:
name: prometheus-config
namespace: kube-system
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: EnsureExists
data:
prometheus.yml: |
# 添加：指定读取rules配置
rules_files:
- /etc/config/rules/*.rules
......

apiVersion: v1
kind: ConfigMap
metadata:
name: prometheus-rules
namespace: kube-system
data:
# 通用角色
general.rules: |
groups:
- name: general.rules
rules:
- alert: InstanceDown
expr: up == 0
for: 1m
labels:
severity: error
annotations:
summary: "Instance {{ $labels.instance }} 停止工作"
description: "{{ $labels.instance }} job {{ $labels.job }} 已经停止5分钟以上."
# Node对所有资源的监控
node.rules: |
groups:
- name: node.rules
rules:
- alert: NodeFilesystemUsage
expr: 100 - (node_filesystem_free_bytes{fstype=~"ext4|xfs"} / node_filesystem_size_bytes{fstype=~"ext4|xfs"} * 100) > 80
for: 1m
labels:
severity: warning
annotations:
summary: "Instance {{ $labels.instance }} : {{ $labels.mountpoint }} 分区使用率过高"
description: "{{ $labels.instance }}: {{ $labels.mountpoint }} 分区使用大于80% (当前值: {{ $value }})"
- alert: NodeMemoryUsage
expr: 100 - (node_memory_MemFree_bytes+node_memory_Cached_bytes+node_memory_Buffers_bytes) / node_memory_MemTotal_bytes * 100 > 80
for: 1m
labels:
severity: warning
annotations:
summary: "Instance {{ $labels.instance }} 内存使用率过高"
description: "{{ $labels.instance }}内存使用大于80% (当前值: {{ $value }})"
- alert: NodeCPUUsage
expr: 100 - (avg(irate(node_cpu_seconds_total{mode="idle"}[5m])) by (instance) * 100) > 60
for: 1m
labels:
severity: warning
annotations:
summary: "Instance {{ $labels.instance }} CPU使用率过高"
description: "{{ $labels.instance }}CPU使用大于60% (当前值: {{ $value }})"

apiVersion: apps/v1
kind: StatefulSet
metadata:
name: prometheus
# 部署命名空间
namespace: kube-system
labels:
k8s-app: prometheus
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
version: v2.2.1
spec:
serviceName: "prometheus"
replicas: 1
podManagementPolicy: "Parallel"
updateStrategy:
type: "RollingUpdate"
selector:
matchLabels:
k8s-app: prometheus
template:
metadata:
labels:
k8s-app: prometheus
annotations:
scheduler.alpha.kubernetes.io/critical-pod: ‘‘
spec:
priorityClassName: system-cluster-critical
serviceAccountName: prometheus
# 初始化容器
initContainers:
- name: "init-chown-data"
image: "busybox:latest"
imagePullPolicy: "IfNotPresent"
command: ["chown", "-R", "65534:65534", "/data"]
volumeMounts:
- name: prometheus-data
mountPath: /data
subPath: ""
containers:
- name: prometheus-server-configmap-reload
image: "jimmidyson/configmap-reload:v0.1"
imagePullPolicy: "IfNotPresent"
args:
- --volume-dir=/etc/config
- --webhook-url=http://localhost:9090/-/reload
volumeMounts:
- name: config-volume
mountPath: /etc/config
readOnly: true
resources:
limits:
cpu: 10m
memory: 10Mi
requests:
cpu: 10m
memory: 10Mi
- name: prometheus-server
# 主要使用镜像
image: "prom/prometheus:v2.2.1"
imagePullPolicy: "IfNotPresent"
args:
- --config.file=/etc/config/prometheus.yml
- --storage.tsdb.path=/data
- --web.console.libraries=/etc/prometheus/console_libraries
- --web.console.templates=/etc/prometheus/consoles
- --web.enable-lifecycle
ports:
- containerPort: 9090
readinessProbe:
# 健康检查
httpGet:
path: /-/ready
port: 9090
initialDelaySeconds: 30
timeoutSeconds: 30
livenessProbe:
httpGet:
path: /-/healthy
port: 9090
initialDelaySeconds: 30
timeoutSeconds: 30
# based on 10 running nodes with 30 pods each
resources:
limits:
cpu: 200m
memory: 1000Mi
requests:
cpu: 200m
memory: 1000Mi
# 数据卷
volumeMounts:
- name: config-volume
mountPath: /etc/config
- name: prometheus-data
mountPath: /data
# 添加：指定rules的configmap配置文件名称
- name: prometheus-rules
mountPath: /etc/config/rules
subPath: ""
terminationGracePeriodSeconds: 300
volumes:
- name: config-volume
configMap:
name: prometheus-config
# 添加：name rules
- name: prometheus-rules
# 添加：配置文件
configMap:
# 添加：定义文件名称
name: prometheus-rules
volumeClaimTemplates:
- metadata:
name: prometheus-data
spec:
# 使用动态PV
storageClassName: managed-nfs-storage
accessModes:
- ReadWriteOnce
resources:
requests:
storage: "16Gi"