来源：
https://juejin.im/post/5c36054251882525a50bbdf0
https://github.com/redhatxl/k8s-prometheus-grafana
Prometheus
master/node节点环境部署
git clone https://github.com/redhatxl/k8s-prometheus-grafana.git
在node节点下载监控所需镜像（在所有节点也下载了）
docker pull prom/node-exporter
docker pull prom/prometheus:v2.0.0
docker pull grafana/grafana:4.2.0
采用daemonset方式部署node-exporter组件
kubectl create -f node-exporter.yaml
部署prometheus组件
rbac文件
kubectl create -f k8s-prometheus-grafana/prometheus/rbac-setup.yaml
以configmap的形式管理prometheus组件的配置文件
kubectl create -f k8s-prometheus-grafana/prometheus/configmap.yaml
Prometheus deployment 文件
kubectl create -f k8s-prometheus-grafana/prometheus/prometheus.deploy.yml
Prometheus service文件
kubectl create -f k8s-prometheus-grafana/prometheus/prometheus.svc.yml
部署grafana组件
grafana deployment配置文件
kubectl create -f k8s-prometheus-grafana/grafana/grafana-deploy.yaml
grafana service配置文件
kubectl create -f k8s-prometheus-grafana/grafana/grafana-svc.yaml
grafana ingress配置文件
kubectl create -f k8s-prometheus-grafana/grafana/grafana-ing.yaml
访问
k get po -n kube-system -owide
NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES
coredns-5c98db65d4-j2925 1/1 Running 4 2d23h 10.244.0.13 k8s-master <none> <none>
coredns-5c98db65d4-k2rcj 1/1 Running 4 2d23h 10.244.0.12 k8s-master <none> <none>
etcd-k8s-master 1/1 Running 4 2d23h 192.168.190.140 k8s-master <none> <none>
grafana-core-6ff599bfdc-pbdzf 1/1 Running 0 99m 10.244.1.66 k8s-node1 <none> <none>
kube-apiserver-k8s-master 1/1 Running 4 2d23h 192.168.190.140 k8s-master <none> <none>
kube-controller-manager-k8s-master 1/1 Running 4 2d23h 192.168.190.140 k8s-master <none> <none>
kube-flannel-ds-amd64-6rq62 1/1 Running 5 2d23h 192.168.190.140 k8s-master <none> <none>
kube-flannel-ds-amd64-ctmdz 1/1 Running 4 2d23h 192.168.190.141 k8s-node1 <none> <none>
kube-proxy-kmgc5 1/1 Running 4 2d23h 192.168.190.140 k8s-master <none> <none>
kube-proxy-ss8jr 1/1 Running 4 2d23h 192.168.190.141 k8s-node1 <none> <none>
kube-scheduler-k8s-master 1/1 Running 4 2d23h 192.168.190.140 k8s-master <none> <none>
node-exporter-fsfkb 1/1 Running 0 102m 10.244.1.64 k8s-node1 <none> <none>
prometheus-68545d4fd8-hnltb 1/1 Running 0 101m 10.244.1.65 k8s-node1 <none> <none>
k get svc -n kube-system
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
grafana NodePort 10.106.70.200 <none> 3000:30592/TCP 98m
kube-dns ClusterIP 10.96.0.10 <none> 53/UDP,53/TCP,9153/TCP 2d23h
node-exporter NodePort 10.102.245.168 <none> 9100:31672/TCP 101m
prometheus NodePort 10.101.205.6 <none> 9090:30003/TCP 99m
访问prometheus ：
任一个节点的物理地址+暴露的端口（9090:30003/TCP ）
访问grafana:
任一个节点的物理地址+暴露的端口（3000:30592/TCP）
输入密码登录：
admin/admin
添加数据源
类型：prometheus
url: http://prometheus:9090
save& test
导入模板
模板下载地址https:///dashboards/315， 或在线导入315 /1621
各配置文件
daemonset方式部署的node-exporter
cat node-exporter.yaml
---
apiVersion: extensions/v1beta1
kind: DaemonSet
metadata:
name: node-exporter
namespace: kube-system
labels:
k8s-app: node-exporter
spec:
template:
metadata:
labels:
k8s-app: node-exporter
spec:
containers:
- image: prom/node-exporter
name: node-exporter
ports:
- containerPort: 9100
protocol: TCP
name: http
---
apiVersion: v1
kind: Service
metadata:
labels:
k8s-app: node-exporter
name: node-exporter
namespace: kube-system
spec:
ports:
- name: http
port: 9100
nodePort: 31672
protocol: TCP
type: NodePort
selector:
k8s-app: node-exporter
prometheus的rbac-setup.yaml
cat rbac-setup.yaml
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
prometheus的configmap
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
配置说明：来源官网
https://prometheus.io/docs/prometheus/latest/configuration/configuration/
<kubernetes_sd_config>
Kubernetes SD配置允许从Kubernetes的 REST API 检索抓取目标， 并始终与集群状态保持同步。
role可以将以下类型之一配置为发现目标：
1，node
该node角色为每个群集节点发现一个目标，其地址默认为Kubelet的HTTP端口。目标地址默认为的地址类型顺序Kubernetes节点对象的第一个现有地址NodeInternalIP，NodeExternalIP， NodeLegacyHostIP，和NodeHostName。
可用的元标签:
__meta_kubernetes_node_name：节点对象的名称。
_meta_kubernetes_node_label
_meta_kubernetes_node_labelpresent
_meta_kubernetes_node_annotation
_meta_kubernetes_node_annotationpresent
_meta_kubernetes_node_address<address_type>：每个节点地址类型的第一个地址（如果存在）。
此外，该instance节点的标签将设置为从API服务器检索到的节点名称
2,service
该service角色发现每一个服务端口为每个服务的目标。这通常用于监视服务的黑盒。该地址将设置为服务的Kubernetes DNS名称以及相应的服务端口
可用的元标签：
__meta_kubernetes_namespace：服务对象的名称空间。
_meta_kubernetes_service_annotation
_meta_kubernetes_service_annotationpresent
__meta_kubernetes_service_cluster_ip：服务的群集IP地址。（不适用于外部名称类型的服务）
__meta_kubernetes_service_external_name：服务的DNS名称。（适用于外部名称类型的服务）
_meta_kubernetes_service_label
_meta_kubernetes_service_labelpresent
__meta_kubernetes_service_name：服务对象的名称。
__meta_kubernetes_service_port_name：目标服务端口的名称。
__meta_kubernetes_service_port_protocol：目标服务端口的协议。
3,pod
该pod角色发现所有pods并将其内容器公开为目标。对于容器的每个声明的端口，将生成一个目标。如果容器没有指定的端口，则会为每个容器创建无端口目标，以通过重新标记手动添加端口
可用的元标签：
__meta_kubernetes_namespace：pod对象的名称空间。
__meta_kubernetes_pod_name：pod对象的名称。
__meta_kubernetes_pod_ip：pod对象的pod IP。
_meta_kubernetes_pod_label
_meta_kubernetes_pod_labelpresent
_meta_kubernetes_pod_annotation
_meta_kubernetes_pod_annotationpresent
__meta_kubernetes_pod_container_init：true如果容器是InitContainer
__meta_kubernetes_pod_container_name：目标地址指向的容器的名称。
__meta_kubernetes_pod_container_port_name：容器端口的名称。
__meta_kubernetes_pod_container_port_number：容器端口号。
__meta_kubernetes_pod_container_port_protocol：容器端口的协议。
__meta_kubernetes_pod_ready：设置为true或false吊舱的就绪状态。
__meta_kubernetes_pod_phase：设置为Pending，Running，Succeeded，Failed或Unknown 在生命周期。
__meta_kubernetes_pod_node_name：将Pod调度到的节点的名称。
__meta_kubernetes_pod_host_ip：pod对象的当前主机IP。
__meta_kubernetes_pod_uid：pod对象的UID。
__meta_kubernetes_pod_controller_kind：pod控制器的对象种类。
__meta_kubernetes_pod_controller_name：pod控制器的名称。
４，endpoints
该endpoints角色从服务的列表中的终端发现目标。对于每个端点地址，每个端口都发现一个目标。如果端点由Pod支持，则该Pod的所有其他未绑定到端点端口的容器端口也将被发现为目标
可用的元标签：
__meta_kubernetes_namespace：端点对象的名称空间。
__meta_kubernetes_endpoints_name：端点对象的名称。
对于直接从端点列表中发现的所有目标（未从基础容器额外推断出的所有目标），将附加以下标签：
__meta_kubernetes_endpoint_hostname：端点的主机名。
__meta_kubernetes_endpoint_node_name：托管端点的节点的名称。
__meta_kubernetes_endpoint_ready：设置为true或false为端点的就绪状态。
__meta_kubernetes_endpoint_port_name：端点端口的名称。
__meta_kubernetes_endpoint_port_protocol：端点端口的协议。
__meta_kubernetes_endpoint_address_target_kind：端点地址目标的种类。
__meta_kubernetes_endpoint_address_target_name：端点地址目标的名称。
如果端点属于服务，role: service则会附加发现的所有标签。
对于由Pod支持的所有目标，role: pod将附加发现的所有标签。
５，ingress
该ingress角色发现了一个目标，为每个进入的每个路径。这通常对黑盒监视入口很有用。该地址将设置为入口规范中指定的主机。
可用的元标签：
__meta_kubernetes_namespace：入口对象的名称空间。
__meta_kubernetes_ingress_name：入口对象的名称。
_meta_kubernetes_ingress_label
_meta_kubernetes_ingress_labelpresent
_meta_kubernetes_ingress_annotation
_meta_kubernetes_ingress_annotationpresent
__meta_kubernetes_ingress_scheme：https如果设置了TLS配置，则为入口的协议方案。默认为http。
__meta_kubernetes_ingress_path：来自入口规范的路径。默认为/
有关Kubernetes发现的配置选项：
# The information to access the Kubernetes API.
# The API server addresses. If left empty, Prometheus is assumed to run inside
# of the cluster and will discover API servers automatically and use the pod's
# CA certificate and bearer token file at /var/run/secrets/kubernetes.io/serviceaccount/.
[ api_server: <host> ]
# The Kubernetes role of entities that should be discovered.
role: <role>
# Optional authentication information used to authenticate to the API server.
# Note that `basic_auth`, `bearer_token` and `bearer_token_file` options are
# mutually exclusive.
# password and password_file are mutually exclusive.
# Optional HTTP basic authentication information.
basic_auth:
[ username: <string> ]
[ password: <secret> ]
[ password_file: <string> ]
# Optional bearer token authentication information.
[ bearer_token: <secret> ]
# Optional bearer token file authentication information.
[ bearer_token_file: <filename> ]
# Optional proxy URL.
[ proxy_url: <string> ]
# TLS configuration.
tls_config:
[ <tls_config> ]
# Optional namespace discovery. If omitted, all namespaces are used.
namespaces:
names:
[ - <string> ]
prometheus-kubernetes.yml:
来源：https://github.com/prometheus/prometheus/blob/release-2.14/documentation/examples/prometheus-kubernetes.yml
# A scrape configuration for running Prometheus on a Kubernetes cluster.
# This uses separate scrape configs for cluster components (i.e. API server, node)
# and services to allow each to use different authentication configs.
#
# Kubernetes labels will be added as Prometheus labels on metrics via the
# `labelmap` relabeling action.
#
# If you are using Kubernetes 1.7.2 or earlier, please take note of the comments
# for the kubernetes-cadvisor job; you will need to edit or remove this job.
# Scrape config for API servers.
#
# Kubernetes exposes API servers as endpoints to the default/kubernetes
# service so this uses `endpoints` role and uses relabelling to only keep
# the endpoints associated with the default/kubernetes service using the
# default named port `https`. This works for single API server deployments as
# well as HA API server deployments.
scrape_configs:
- job_name: 'kubernetes-apiservers'
kubernetes_sd_configs:
- role: endpoints
# Default to scraping over https. If required, just disable this or change to
# `http`.
scheme: https
# This TLS & bearer token file config is used to connect to the actual scrape
# endpoints for cluster components. This is separate to discovery auth
# configuration because discovery & scraping are two separate concerns in
# Prometheus. The discovery auth config is automatic if Prometheus runs inside
# the cluster. Otherwise, more config options have to be provided within the
# <kubernetes_sd_config>.
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
# If your node certificates are self-signed or use a different CA to the
# master CA, then disable certificate verification below. Note that
# certificate verification is an integral part of a secure infrastructure
# so this should only be disabled in a controlled environment. You can
# disable certificate verification by uncommenting the line below.
#
# insecure_skip_verify: true
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
# Keep only the default/kubernetes service endpoints for the https port. This
# will add targets for each API server which Kubernetes adds an endpoint to
# the default/kubernetes service.
relabel_configs:
- source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
action: keep
regex: default;kubernetes;https
# Scrape config for nodes (kubelet).
#
# Rather than connecting directly to the node, the scrape is proxied though the
# Kubernetes apiserver. This means it will work if Prometheus is running out of
# cluster, or can't connect to nodes for some other reason (e.g. because of
# firewalling).
- job_name: 'kubernetes-nodes'
# Default to scraping over https. If required, just disable this or change to
# `http`.
scheme: https
# This TLS & bearer token file config is used to connect to the actual scrape
# endpoints for cluster components. This is separate to discovery auth
# configuration because discovery & scraping are two separate concerns in
# Prometheus. The discovery auth config is automatic if Prometheus runs inside
# the cluster. Otherwise, more config options have to be provided within the
# <kubernetes_sd_config>.
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
kubernetes_sd_configs:
- role: node
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
# Scrape config for Kubelet cAdvisor.
#
# This is required for Kubernetes 1.7.3 and later, where cAdvisor metrics
# (those whose names begin with 'container_') have been removed from the
# Kubelet metrics endpoint. This job scrapes the cAdvisor endpoint to
# retrieve those metrics.
#
# In Kubernetes 1.7.0-1.7.2, these metrics are only exposed on the cAdvisor
# HTTP endpoint; use "replacement: /api/v1/nodes/${1}:4194/proxy/metrics"
# in that case (and ensure cAdvisor's HTTP server hasn't been disabled with
# the --cadvisor-port=0 Kubelet flag).
#
# This job is not necessary and should be removed in Kubernetes 1.6 and
# earlier versions, or it will cause the metrics to be scraped twice.
- job_name: 'kubernetes-cadvisor'
# Default to scraping over https. If required, just disable this or change to
# `http`.
scheme: https
# This TLS & bearer token file config is used to connect to the actual scrape
# endpoints for cluster components. This is separate to discovery auth
# configuration because discovery & scraping are two separate concerns in
# Prometheus. The discovery auth config is automatic if Prometheus runs inside
# the cluster. Otherwise, more config options have to be provided within the
# <kubernetes_sd_config>.
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
kubernetes_sd_configs:
- role: node
relabel_configs:
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
- target_label: __address__
replacement: kubernetes.default.svc:443
- source_labels: [__meta_kubernetes_node_name]
regex: (.+)
target_label: __metrics_path__
replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
# Example scrape config for service endpoints.
#
# The relabeling allows the actual service scrape endpoint to be configured
# for all or only some endpoints.
- job_name: 'kubernetes-service-endpoints'
kubernetes_sd_configs:
- role: endpoints
relabel_configs:
# Example relabel to scrape only endpoints that have
# "example.io/should_be_scraped = true" annotation.
# - source_labels: [__meta_kubernetes_service_annotation_example_io_should_be_scraped]
# action: keep
# regex: true
#
# Example relabel to customize metric path based on endpoints
# "example.io/metric_path = <metric path>" annotation.
# - source_labels: [__meta_kubernetes_service_annotation_example_io_metric_path]
# action: replace
# target_label: __metrics_path__
# regex: (.+)
#
# Example relabel to scrape only single, desired port for the service based
# on endpoints "example.io/scrape_port = <port>" annotation.
# - source_labels: [__address__, __meta_kubernetes_service_annotation_example_io_scrape_port]
# action: replace
# regex: ([^:]+)(?::d+)?;(d+)
# replacement: $1:$2
# target_label: __address__
#
# Example relabel to configure scrape scheme for all service scrape targets
# based on endpoints "example.io/scrape_scheme = <scheme>" annotation.
# - source_labels: [__meta_kubernetes_service_annotation_example_io_scrape_scheme]
# action: replace
# target_label: __scheme__
# regex: (https?)
- 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
# Example scrape config for probing services via the Blackbox Exporter.
#
# The relabeling allows the actual service scrape endpoint to be configured
# for all or only some services.
- job_name: 'kubernetes-services'
metrics_path: /probe
params:
module: [http_2xx]
kubernetes_sd_configs:
- role: service
relabel_configs:
# Example relabel to probe only some services that have "example.io/should_be_probed = true" annotation
# - source_labels: [__meta_kubernetes_service_annotation_example_io_should_be_probed]
# 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
# Example scrape config for probing ingresses via the Blackbox Exporter.
#
# The relabeling allows the actual ingress scrape endpoint to be configured
# for all or only some services.
- job_name: 'kubernetes-ingresses'
metrics_path: /probe
params:
module: [http_2xx]
kubernetes_sd_configs:
- role: ingress
relabel_configs:
# Example relabel to probe only some ingresses that have "example.io/should_be_probed = true" annotation
# - source_labels: [__meta_kubernetes_ingress_annotation_example_io_should_be_probed]
# 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
# Example scrape config for pods
#
# The relabeling allows the actual pod scrape to be configured
# for all the declared ports (or port-free target if none is declared)
# or only some ports.
- job_name: 'kubernetes-pods'
kubernetes_sd_configs:
- role: pod
relabel_configs:
# Example relabel to scrape only pods that have
# "example.io/should_be_scraped = true" annotation.
# - source_labels: [__meta_kubernetes_pod_annotation_example_io_should_be_scraped]
# action: keep
# regex: true
#
# Example relabel to customize metric path based on pod
# "example.io/metric_path = <metric path>" annotation.
# - source_labels: [__meta_kubernetes_pod_annotation_example_io_metric_path]
# action: replace
# target_label: __metrics_path__
# regex: (.+)
#
# Example relabel to scrape only single, desired port for the pod
# based on pod "example.io/scrape_port = <port>" annotation.
# Note that __address__ is modified here, so if pod containers' ports
# are declared, they all will be ignored.
# - source_labels: [__address__, __meta_kubernetes_pod_annotation_example_io_scrape_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
Prometheus deployment
cat prometheus.deploy.yml
---
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
prometheus的service
cat prometheus.svc.yml
---
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
grafana-deployment配置文件
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: {}
grafana service
cat grafana-svc.yaml
apiVersion: v1
kind: Service
metadata:
name: grafana
namespace: kube-system
labels:
app: grafana
component: core
spec:
type: NodePort
ports:
- port: 3000
selector:
app: grafana
component: core
grafana ingress
cat grafana-ing.yaml
apiVersion: extensions/v1beta1
kind: Ingress
metadata:
name: grafana
namespace: kube-system
spec:
rules:
- host: k8s.grafana
http:
paths:
- path: /
backend:
serviceName: grafana
servicePort: 3000