一、ICMP监控¶
```yaml #添加如下配置 ########## ICMP 监控配置 ########## - job_name: icmp-status metrics_path: /probe params: module: [icmp] static_configs: - targets: - 10.0.0.61 labels: group: icmp relabel_configs: - source_labels: [address] target_label: param_target - source_labels: [__param_target] target_label: instance - target_label: __address replacement: blackbox-exporter.monitor:9115
#完整配置文件 [root@master01 7]# cat prometheus-config.yaml apiVersion: v1 kind: ConfigMap metadata: name: prometheus-config namespace: monitor data: prometheus.yml: | global: scrape_interval: 15s evaluation_interval: 15s external_labels: cluster: "kubernetes"
############ 数据采集job ###################
scrape_configs:
########## prometheus 监控配置 ##########
- job_name: prometheus
static_configs:
- targets: ['127.0.0.1:9090']
labels:
instance: prometheus
########## kube-apiserver 监控配置 ##########
- job_name: kube-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]
action: keep
regex: default;kubernetes
- source_labels: [__meta_kubernetes_endpoints_name]
action: replace
target_label: endpoint
- source_labels: [__meta_kubernetes_pod_name]
action: replace
target_label: pod
- source_labels: [__meta_kubernetes_service_name]
action: replace
target_label: service
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: namespace
########## kube-controller-manager 监控配置 ##########
- job_name: 'kube-controller-manager'
# 使用 Kubernetes Pod 发现机制
kubernetes_sd_configs:
- role: pod
# 强制使用 HTTPS 协议
scheme: https
# TLS 配置（测试环境跳过验证）
tls_config:
insecure_skip_verify: true
# 使用 ServiceAccount 的 Token 认证
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
relabel_configs:
# 保留标签为 component=kube-controller-manager 的 Pod
- source_labels: [__meta_kubernetes_pod_label_component]
regex: kube-controller-manager
action: keep
# 重写目标地址为 Pod IP + 10257 端口
- source_labels: [__meta_kubernetes_pod_ip]
regex: (.+)
target_label: __address__
replacement: "${1}:10257"
# 强制使用 HTTPS 协议（冗余但明确）
- source_labels: []
regex: .*
target_label: __scheme__
replacement: https
# 附加元数据标签
- source_labels: [__meta_kubernetes_endpoints_name]
action: replace
target_label: endpoint
- source_labels: [__meta_kubernetes_pod_name]
action: replace
target_label: pod
- source_labels: [__meta_kubernetes_service_name]
action: replace
target_label: service
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: namespace
########## kube-scheduler 监控配置 ##########
- job_name: 'kube-scheduler'
kubernetes_sd_configs:
- role: pod
scheme: https
tls_config:
insecure_skip_verify: true
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
relabel_configs:
- source_labels: [__meta_kubernetes_pod_label_component]
regex: kube-scheduler
action: keep
- source_labels: [__meta_kubernetes_pod_ip]
regex: (.+)
target_label: __address__
replacement: "${1}:10259"
- source_labels: []
regex: .*
target_label: __scheme__
replacement: https
- source_labels: [__meta_kubernetes_endpoints_name]
action: replace
target_label: endpoint
- source_labels: [__meta_kubernetes_pod_name]
action: replace
target_label: pod
- source_labels: [__meta_kubernetes_service_name]
action: replace
target_label: service
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: namespace
########## kube-state-metrics 监控配置 ##########
- job_name: kube-state-metrics
kubernetes_sd_configs:
- role: endpoints
relabel_configs:
- source_labels: [__meta_kubernetes_service_name]
regex: kube-state-metrics
action: keep
- source_labels: [__meta_kubernetes_pod_ip]
regex: (.+)
target_label: __address__
replacement: ${1}:8080
- source_labels: [__meta_kubernetes_endpoints_name]
action: replace
target_label: endpoint
- source_labels: [__meta_kubernetes_pod_name]
action: replace
target_label: pod
- source_labels: [__meta_kubernetes_service_name]
action: replace
target_label: service
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: namespace
########## coredns 监控配置 ##########
- job_name: coredns
kubernetes_sd_configs:
- role: endpoints
relabel_configs:
- source_labels:
- __meta_kubernetes_service_label_k8s_app
regex: kube-dns
action: keep
- source_labels: [__meta_kubernetes_pod_ip]
regex: (.+)
target_label: __address__
replacement: ${1}:9153
- source_labels: [__meta_kubernetes_endpoints_name]
action: replace
target_label: endpoint
- source_labels: [__meta_kubernetes_pod_name]
action: replace
target_label: pod
- source_labels: [__meta_kubernetes_service_name]
action: replace
target_label: service
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: namespace
########## etcd 监控配置 ##########
- job_name: etcd
kubernetes_sd_configs:
- role: pod
relabel_configs:
- source_labels:
- __meta_kubernetes_pod_label_component
regex: etcd
action: keep
- source_labels: [__meta_kubernetes_pod_ip]
regex: (.+)
target_label: __address__
replacement: ${1}:2381
- source_labels: [__meta_kubernetes_endpoints_name]
action: replace
target_label: endpoint
- source_labels: [__meta_kubernetes_pod_name]
action: replace
target_label: pod
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: namespace
########## kubelet 监控配置 ##########
- job_name: kubelet
metrics_path: /metrics/cadvisor
scheme: https
tls_config:
insecure_skip_verify: true
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
kubernetes_sd_configs:
- role: node
relabel_configs:
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
- source_labels: [__meta_kubernetes_endpoints_name]
action: replace
target_label: endpoint
- source_labels: [__meta_kubernetes_pod_name]
action: replace
target_label: pod
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: namespace
########## k8s-node 监控配置 ##########
- job_name: k8s-nodes
kubernetes_sd_configs:
- role: node
relabel_configs:
- source_labels: [__address__]
regex: '(.*):10250'
replacement: '${1}:9100'
target_label: __address__
action: replace
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
- source_labels: [__meta_kubernetes_endpoints_name]
action: replace
target_label: endpoint
- source_labels: [__meta_kubernetes_pod_name]
action: replace
target_label: pod
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: namespace
########## DNS 监控配置 ##########
- job_name: "kubernetes-dns"
metrics_path: /probe # 不是metrics，是probe
params:
module: [dns_tcp] # 使用DNS TCP模块
static_configs:
- targets:
- kube-dns.kube-system:53 #不要省略端口号
- 8.8.4.4:53
- 8.8.8.8:53
- 223.5.5.5:53
relabel_configs:
- source_labels: [__address__]
target_label: __param_target
- source_labels: [__param_target]
target_label: instance
- target_label: __address__
replacement: blackbox-exporter.monitor:9115 # 服务地址，和上面的 Service 定义保持一致
########## ICMP 监控配置 ##########
- job_name: icmp-status
metrics_path: /probe
params:
module: [icmp]
static_configs:
- targets:
- 10.0.0.61
labels:
group: icmp
relabel_configs:
- source_labels: [__address__]
target_label: __param_target
- source_labels: [__param_target]
target_label: instance
- target_label: __address__
replacement: blackbox-exporter.monitor:9115
############ 指定告警规则文件路径位置 ###################
rule_files:
- /etc/prometheus/rules/*.rules
#应用 [root@master01 7]# kaf prometheus-config.yaml ```
按上面方法重载 Prometheus，打开 Prometheus 的 Target 页面，就会看到 上面定义的 blackbox-k8s-http-services 任务
curl -XPOST http://prometheus.zhang-qing.com/-/reload