前言
今年由SDN转向Docker的学习，学习Docker必会接触到一些容器编排工具如K8S和Docker Swarm的项目。下面我会总结一下Cent OS 7.5安装K8S 1.10的具体步骤，其中参照k8s中文社区和各博客。希望对大家有用。
集群由2 Master 和1 Worker组成。
开始
192.168.0.101 Master1
192.168.0.102 Master2
192.168.0.103 Worker1
软件版本：
docker17.03.2-ce
socat-1.7.3.2-2.el7.x86_64
kubelet-1.10.0-0.x86_64‘
kubernetes-cni-0.6.0-0.x86_64
kubectl-1.10.0-0.x86_64
kubeadm-1.10.0-0.x86_64
初始化环境
1.分别设置主机名
hostnamectl set-hostname master1
hostnamectl set-hostname master2
hostnamectl set-hostname node1
2.主机映射
cat < /etc/hosts
192.168.0.101 Master1
192.168.0.102 Master2
192.168.0.103 node1
3.master1免密码登录
ssh-keygen #一路回车即可
ssh-copy-id node02
ssh-copy-id node03
ssh-copy-id node04
4.四台主机配置、停防火墙、关闭Swap、关闭Selinux、设置内核、K8S的yum源、安装依赖包、配置ntp（配置完后建议重启一次）
systemctl stop firewalld
systemctl disable firewalld
swapoff -a
sed -i 's/.*swap.*/#&/' /etc/fstab
setenforce 0
sed -i "s/^SELINUX=enforcing/SELINUX=disabled/g" /etc/sysconfig/selinux
sed -i "s/^SELINUX=enforcing/SELINUX=disabled/g" /etc/selinux/config
sed -i "s/^SELINUX=permissive/SELINUX=disabled/g" /etc/sysconfig/selinux
sed -i "s/^SELINUX=permissive/SELINUX=disabled/g" /etc/selinux/config
modprobe br_netfilter
cat < /etc/sysctl.d/k8s.conf
net.bridge.bridge-nf-call-ip6tables = 1net.bridge.bridge-nf-call-iptables = 1EOF
sysctl -p /etc/sysctl.d/k8s.conf
ls /proc/sys/net/bridge
cat < /etc/yum.repos.d/kubernetes.repo[kubernetes]name=Kubernetesbaseurl=https://mirrors.aliyun.com/kubernetes/yum/repos/kubernetes-el7-x86_64/enabled=1gpgcheck=1repo_gpgcheck=1gpgkey=https://mirrors.aliyun.com/kubernetes/yum/doc/yum-key.gpg https://mirrors.aliyun.com/kubernetes/yum/doc/rpm-package-key.gpgEOF
yum install -y epel-release
yum install -y yum-utils device-mapper-persistent-data lvm2 net-tools conntrack-tools wget vim ntpdate libseccomp libtool-ltdl
systemctl enable ntpdate.service
echo '*/30 * * * * /usr/sbin/ntpdate time7.aliyun.com >/dev/null 2>&1' > /tmp/crontab2.tmp
crontab /tmp/crontab2.tmp
systemctl start ntpdate.service
echo "* soft nofile 65536" >> /etc/security/limits.conf
echo "* hard nofile 65536" >> /etc/security/limits.conf
echo "* soft nproc 65536" >> /etc/security/limits.conf
echo "* hard nproc 65536" >> /etc/security/limits.conf
echo "* soft memlock unlimited" >> /etc/security/limits.conf
echo "* hard memlock unlimited" >> /etc/security/limits.conf
2：安装、配置keepalived（主节点）(负载均衡)
1:安装keepalived
yum install -y keepalived
systemctl enable keepalived
master1的keepalived.conf
cat < /etc/keepalived/keepalived.conf
global_defs {
router_id LVS_k8s
}
vrrp_script CheckK8sMaster {
script "curl -k https://192.168.0.200:6443"
interval 3
timeout 9
fall 2
rise 2
}
vrrp_instance VI_1 {
state MASTER
interface <网卡名>
virtual_router_id 61
priority 100
advert_int 1
mcast_src_ip 192.168.0.101
nopreempt
authentication {
auth_type PASS
auth_pass sqP05dQgMSlzrxHj
}
unicast_peer {
192.168.0.102
}
virtual_ipaddress {
192.168.0.200/24
}
track_script {
CheckK8sMaster
}
}
EOF
master2的keepalived.conf
cat < /etc/keepalived/keepalived.conf
global_defs {
router_id LVS_k8s
}
global_defs {
router_id LVS_k8s
}
vrrp_script CheckK8sMaster {
script "curl -k https://192.168.0.200:6443"
interval 3
timeout 9
fall 2
rise 2
}
vrrp_instance VI_1 {
state BACKUP
interface <网卡名>
virtual_router_id 61
priority 90
advert_int 1
mcast_src_ip 192.168.0.102
nopreempt
authentication {
auth_type PASS
auth_pass sqP05dQgMSlzrxHj
}
unicast_peer {
192.168.0.101
}
virtual_ipaddress {
192.168.0.200/24
}
track_script {
CheckK8sMaster
}
}
EOF
2：启动keepalived
systemctl restart keepalived
在Master1上ip addr 看到ip下存在虚拟IP即成功，master2上没有虚拟IP
3：创建etcd证书(master1上执行即可)
1：设置cfssl环境
wget https://pkg.cfssl.org/R1.2/cfssl_linux-amd64
wget https://pkg.cfssl.org/R1.2/cfssljson_linux-amd64
wget https://pkg.cfssl.org/R1.2/cfssl-certinfo_linux-amd64
chmod +x cfssl_linux-amd64
mv cfssl_linux-amd64 /usr/local/bin/cfssl
chmod +x cfssljson_linux-amd64
mv cfssljson_linux-amd64 /usr/local/bin/cfssljson
chmod +x cfssl-certinfo_linux-amd64
mv cfssl-certinfo_linux-amd64 /usr/local/bin/cfssl-certinfo
export PATH=/usr/local/bin:$PATH
2：创建 CA 配置文件（下面配置的IP为etc节点的IP）
mkdir /root/ssl
cd /root/ssl
cat > ca-config.json < ca-csr.json < etcd-csr.json < 3:master1分发etcd证书到master2上面
mkdir -p /etc/etcd/ssl
cp etcd.pem etcd-key.pem ca.pem /etc/etcd/ssl/
ssh -n master2 "mkdir -p /etc/etcd/ssl && exit"
scp -r /etc/etcd/ssl/*.pem master2:/etc/etcd/ssl/
4：安装配置etcd (三主节点）
1:安装etcd
yum install etcd -y
mkdir -p /var/lib/etcd
master1的etcd.service
cat </etc/systemd/system/etcd.service
[Unit]
Description=Etcd Server
After=network.target
After=network-online.target
Wants=network-online.target
Documentation=https://github.com/coreos
[Service]
Type=notify
WorkingDirectory=/var/lib/etcd/
ExecStart=/usr/bin/etcd \
--name master1 \
--cert-file=/etc/etcd/ssl/etcd.pem \
--key-file=/etc/etcd/ssl/etcd-key.pem \
--peer-cert-file=/etc/etcd/ssl/etcd.pem \
--peer-key-file=/etc/etcd/ssl/etcd-key.pem \
--trusted-ca-file=/etc/etcd/ssl/ca.pem \
--peer-trusted-ca-file=/etc/etcd/ssl/ca.pem \
--initial-advertise-peer-urls https://192.168.0.101:2380 \
--listen-peer-urls https://192.168.0.101:2380 \
--listen-client-urls https://192.168.0.101:2379,http://127.0.0.1:2379 \
--advertise-client-urls https://192.168.0.101:2379 \
--initial-cluster-token etcd-cluster-0 \
--initial-cluster master1=https://192.168.0.101:2380,master2=https://192.168.0.102:2380 \
--initial-cluster-state new \
--data-dir=/var/lib/etcd
Restart=on-failure
RestartSec=5
LimitNOFILE=65536
[Install]
WantedBy=multi-user.target
EOF
master2的etcd.service
cat </etc/systemd/system/etcd.service
[Unit]
Description=Etcd Server
After=network.target
After=network-online.target
Wants=network-online.target
Documentation=https://github.com/coreos
[Service]
Type=notify
WorkingDirectory=/var/lib/etcd/
ExecStart=/usr/bin/etcd \
--name master2 \
--cert-file=/etc/etcd/ssl/etcd.pem \
--key-file=/etc/etcd/ssl/etcd-key.pem \
--peer-cert-file=/etc/etcd/ssl/etcd.pem \
--peer-key-file=/etc/etcd/ssl/etcd-key.pem \
--trusted-ca-file=/etc/etcd/ssl/ca.pem \
--peer-trusted-ca-file=/etc/etcd/ssl/ca.pem \
--initial-advertise-peer-urls https://192.168.0.102:2380 \
--listen-peer-urls https://192.168.0.102:2380 \
--listen-client-urls https://192.168.0.102:2379,http://127.0.0.1:2379 \
--advertise-client-urls https://192.168.0.102:2379 \
--initial-cluster-token etcd-cluster-0 \
--initial-cluster master1=https://192.168.0.101:2380,master2=https://192.168.0.102:2380 \
--initial-cluster-state new \
--data-dir=/var/lib/etcd
Restart=on-failure
RestartSec=5
LimitNOFILE=65536
[Install]
WantedBy=multi-user.target
EOF
2：添加自启动（etcd集群最少2个节点才能启动，启动报错看mesages日志）
mv etcd.service /usr/lib/systemd/system/
systemctl daemon-reload
systemctl enable etcd
systemctl start etcd
systemctl status etcd
3：在三个etcd节点执行一下命令检查
etcdctl --endpoints=https://192.168.0.101:2379,https://192.168.0.102:2379 \
--ca-file=/etc/etcd/ssl/ca.pem \
--cert-file=/etc/etcd/ssl/etcd.pem \
--key-file=/etc/etcd/ssl/etcd-key.pem cluster-health
5：所有节点安装配置docker
1:安装docker17.03
yum install https://mirrors.aliyun.com/docker-ce/linux/centos/7/x86_64/stable/Packages/docker-ce-selinux-17.03.2.ce-1.el7.centos.noarch.rpm -y
yum install https://mirrors.aliyun.com/docker-ce/linux/centos/7/x86_64/stable/Packages/docker-ce-17.03.2.ce-1.el7.centos.x86_64.rpm -y
修改配置文件 vim /usr/lib/systemd/system/docker.service
ExecStart=/usr/bin/dockerd -H tcp://0.0.0.0:2375 -H unix:///var/run/docker.sock --registry-mirror=https://ms3cfraz.mirror.aliyuncs.com
启动docker
systemctl daemon-reload
systemctl restart docker
systemctl enable docker
systemctl status docker
6: 安装、配置kubeadm
1：所有节点安装kubelet kubeadm kubectl
yum install -y kubelet kubeadm kubectl
systemctl enable kubelet
2: 所有节点修改kubelet配置文件
vim /etc/systemd/system/kubelet.service.d/10-kubeadm.conf
#修改这一行
Environment="KUBELET_CGROUP_ARGS=--cgroup-driver=cgroupfs"
#添加这一行
Environment="KUBELET_EXTRA_ARGS=--v=2 --fail-swap-on=false --pod-infra-container-image=registry.cn-hangzhou.aliyuncs.com/k8sth/pause-amd64:3.0"
3：所有节点修改完配置文件一定要重新加载配置
systemctl daemon-reload
systemctl enable kubelet
4: 命令补全
yum install -y bash-completion
source /usr/share/bash-completion/bash_completion
source <(kubectl completion bash)
echo "source <(kubectl completion bash)" >> ~/.bashrc
7：初始化集群
1：master1、master2、添加集群初始配置文件（集群配置文件一样）
cat < config.yaml
apiVersion: kubeadm.k8s.io/v1alpha1
kind: MasterConfiguration
etcd:
endpoints:
- https://192.168.0.101:2379
- https://192.168.0.102:2379
caFile: /etc/etcd/ssl/ca.pem
certFile: /etc/etcd/ssl/etcd.pem
keyFile: /etc/etcd/ssl/etcd-key.pem
dataDir: /var/lib/etcd
networking:
podSubnet: 10.244.0.0/16
kubernetesVersion: 1.10.0
api:
advertiseAddress: "192.168.0.200"
token: "b99a00.a144ef80536d4344"
tokenTTL: "0s"
apiServerCertSANs:
- node01
- node02
- 192.168.0.101
- 192.168.0.102
- 192.168.0.103
- 192.168.0.200
featureGates:
CoreDNS: true
imageRepository: "registry.cn-hangzhou.aliyuncs.com/k8sth"
EOF
2：首先master1初始化集群
kubeadm init --config config.yaml
初始化失败后处理办法
kubeadm reset
#或
rm -rf /etc/kubernetes/*.conf
rm -rf /etc/kubernetes/manifests/*.yaml
docker ps -a |awk '{print $1}' |xargs docker rm -f
systemctl stop kubelet
3：master1上面执行如下命令
mkdir -p HOME/.kube/config
sudo chown (id -g) $HOME/.kube/config
4.kubeadm生成证书密码文件分发到master2上面去
scp -r /etc/kubernetes/pki master2:/etc/kubernetes/
5：此时kubectl get node节点为notready的状态，原因是没有cni插件。部署flannel网络，只需要在master1执行就行
wget https://raw.githubusercontent.com/coreos/flannel/master/Documentation/kube-flannel.yml
#版本信息：quay.io/coreos/flannel:v0.10.0-amd64
kubectl create -f kube-flannel.yml
6：部署dashboard
kubernetes-dashboard.yaml文件内容如下
# Copyright 2017 The Kubernetes Authors.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# Configuration to deploy release version of the Dashboard UI compatible with
# Kubernetes 1.8.
#
# Example usage: kubectl create -f
# ------------------- Dashboard Secret ------------------- #
apiVersion: v1
kind: Secret
metadata:
labels:
k8s-app: kubernetes-dashboard
name: kubernetes-dashboard-certs
namespace: kube-system
type: Opaque
---
# ------------------- Dashboard Service Account ------------------- #
apiVersion: v1
kind: ServiceAccount
metadata:
labels:
k8s-app: kubernetes-dashboard
name: kubernetes-dashboard
namespace: kube-system
---
# ------------------- Dashboard Role & Role Binding ------------------- #
kind: Role
apiVersion: rbac.authorization.k8s.io/v1
metadata:
name: kubernetes-dashboard-minimal
namespace: kube-system
rules:
# Allow Dashboard to create 'kubernetes-dashboard-key-holder' secret.
- apiGroups: [""]
resources: ["secrets"]
verbs: ["create"]
# Allow Dashboard to create 'kubernetes-dashboard-settings' config map.
- apiGroups: [""]
resources: ["configmaps"]
verbs: ["create"]
# Allow Dashboard to get, update and delete Dashboard exclusive secrets.
- apiGroups: [""]
resources: ["secrets"]
resourceNames: ["kubernetes-dashboard-key-holder", "kubernetes-dashboard-certs"]
verbs: ["get", "update", "delete"]
# Allow Dashboard to get and update 'kubernetes-dashboard-settings' config map.
- apiGroups: [""]
resources: ["configmaps"]
resourceNames: ["kubernetes-dashboard-settings"]
verbs: ["get", "update"]
# Allow Dashboard to get metrics from heapster.
- apiGroups: [""]
resources: ["services"]
resourceNames: ["heapster"]
verbs: ["proxy"]
- apiGroups: [""]
resources: ["services/proxy"]
resourceNames: ["heapster", "http:heapster:", "https:heapster:"]
verbs: ["get"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
name: kubernetes-dashboard-minimal
namespace: kube-system
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: Role
name: kubernetes-dashboard-minimal
subjects:
- kind: ServiceAccount
name: kubernetes-dashboard
namespace: kube-system
---
# ------------------- Dashboard Deployment ------------------- #
kind: Deployment
apiVersion: apps/v1beta2
metadata:
labels:
k8s-app: kubernetes-dashboard
name: kubernetes-dashboard
namespace: kube-system
spec:
replicas: 1
revisionHistoryLimit: 10
selector:
matchLabels:
k8s-app: kubernetes-dashboard
template:
metadata:
labels:
k8s-app: kubernetes-dashboard
spec:
nodeSelector:
node-role.kubernetes.io/master: ""
containers:
- name: kubernetes-dashboard
image: registry.cn-hangzhou.aliyuncs.com/k8sth/kubernetes-dashboard-amd64:v1.8.3
ports:
- containerPort: 8443
protocol: TCP
args:
- --auto-generate-certificates
# Uncomment the following line to manually specify Kubernetes API server Host
# If not specified, Dashboard will attempt to auto discover the API server and connect
# to it. Uncomment only if the default does not work.
# - --apiserver-host=http://my-address:port
volumeMounts:
- name: kubernetes-dashboard-certs
mountPath: /certs
# Create on-disk volume to store exec logs
- mountPath: /tmp
name: tmp-volume
livenessProbe:
httpGet:
scheme: HTTPS
path: /
port: 8443
initialDelaySeconds: 30
timeoutSeconds: 30
volumes:
- name: kubernetes-dashboard-certs
secret:
secretName: kubernetes-dashboard-certs
- name: tmp-volume
emptyDir: {}
serviceAccountName: kubernetes-dashboard
# Comment the following tolerations if Dashboard must not be deployed on master
tolerations:
- key: node-role.kubernetes.io/master
effect: NoSchedule
---
# ------------------- Dashboard Service ------------------- #
kind: Service
apiVersion: v1
metadata:
labels:
k8s-app: kubernetes-dashboard
name: kubernetes-dashboard
namespace: kube-system
spec:
type: NodePort
ports:
- port: 443
targetPort: 8443
nodePort: 30000
selector:
k8s-app: kubernetes-dashboard
---
apiVersion: v1
kind: ServiceAccount
metadata:
name: admin-user
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1beta1
kind: ClusterRoleBinding
metadata:
name: admin-user
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: cluster-admin
subjects:
- kind: ServiceAccount
name: admin-user
namespace: kube-system
部署
kubectl create -f kubernetes-dashboard.yaml
7：安装heapster
mkdir heap
cd heap
heapster.yaml
apiVersion: v1
kind: ServiceAccount
metadata:
name: heapster
namespace: kube-system
---
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
name: heapster
namespace: kube-system
spec:
replicas: 1
template:
metadata:
labels:
task: monitoring
k8s-app: heapster
spec:
serviceAccountName: heapster
nodeSelector:
node-role.kubernetes.io/master: ""
containers:
- name: heapster
image: registry.cn-hangzhou.aliyuncs.com/k8sth/heapster-amd64:v1.4.2
imagePullPolicy: IfNotPresent
command:
- /heapster
- --source=kubernetes:https://kubernetes.default
- --sink=influxdb:http://monitoring-influxdb.kube-system.svc:8086
---
apiVersion: v1
kind: Service
metadata:
labels:
task: monitoring
# 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: Heapster
name: heapster
namespace: kube-system
spec:
ports:
- port: 80
targetPort: 8082
selector:
k8s-app: heapster
influxdb.yaml
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
name: monitoring-influxdb
namespace: kube-system
spec:
replicas: 1
template:
metadata:
labels:
task: monitoring
k8s-app: influxdb
spec:
nodeSelector:
node-role.kubernetes.io/master: ""
containers:
- name: influxdb
image: registry.cn-hangzhou.aliyuncs.com/k8sth/heapster-influxdb-amd64:v1.3.3
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /data
name: influxdb-storage
volumes:
- name: influxdb-storage
emptyDir: {}
---
apiVersion: v1
kind: Service
metadata:
labels:
task: monitoring
# 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-influxdb
name: monitoring-influxdb
namespace: kube-system
spec:
ports:
- port: 8086
targetPort: 8086
selector:
k8s-app: influxdb
heapster-rbac.yaml
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1beta1
metadata:
name: heapster
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: system:heapster
subjects:
- kind: ServiceAccount
name: heapster
namespace: kube-system
grafana.yaml
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
name: monitoring-grafana
namespace: kube-system
spec:
replicas: 1
template:
metadata:
labels:
task: monitoring
k8s-app: grafana
spec:
nodeSelector:
node-role.kubernetes.io/master: ""
containers:
- name: grafana
image: registry.cn-hangzhou.aliyuncs.com/k8sth/heapster-grafana-amd64:v4.4.3
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
kubectl create -f .
9：在master2上面分别执行初始化
scp config.yaml master2:/home
kubeadm init --config config.yaml
初始化的结果和node01的结果完全一样
mkdir -p $HOME/.kube
sudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
sudo chown $(id -u):$(id -g) $HOME/.kube/config
11：让master也运行pod（默认master不运行pod）
kubectl taint nodes --all node-role.kubernetes.io/master-
八：添加node1节点到集群
粘贴master1 init成功后的kubeadm join这一长句。
在node上kubectl get node可能会出现http://192.168.0.200:8080 connection refused的问题
解决方法：
出现这个问题的原因是kubectl命令需要使用kubernetes-admin来运行，解决方法如下，将主节点中的【/etc/kubernetes/admin.conf】文件拷贝到从节点相同目录下，然后配置环境变量：
echo "export KUBECONFIG=/etc/kubernetes/admin.conf" >> ~/.bash_profile
source ~/.bash_profile
即可运行
九.部署容器监控
mkdir prom
vim cluster-role.yaml
apiVersion: rbac.authorization.k8s.io/v1beta1
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: rbac.authorization.k8s.io/v1beta1
kind: ClusterRoleBinding
metadata:
name: prometheus
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: prometheus
subjects:
- kind: ServiceAccount
name: default
namespace: monitoring
vim config-map.yaml
apiVersion: v1
kind: ConfigMap
metadata:
name: prometheus-server-conf
labels:
name: prometheus-server-conf
namespace: monitoring
data:
prometheus.yml: |-
global:
scrape_interval: 5s
evaluation_interval: 5s
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'
scheme: https
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
- 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:$2
target_label: __address__
- action: labelmap
regex: __meta_kubernetes_pod_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: kubernetes_namespace
- source_labels: [__meta_kubernetes_pod_name]
action: replace
target_label: kubernetes_pod_name
- job_name: 'kubernetes-cadvisor'
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
kubernetes_sd_configs:
- role: node
relabel_configs:
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
- target_label: __address__
replacement: kubernetes.default.svc:443
- source_labels: [__meta_kubernetes_node_name]
regex: (.+)
target_label: __metrics_path__
replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
- 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
vim prometheus-deploymnet.yaml
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
name: prometheus-deployment
namespace: monitoring
spec:
replicas: 1
template:
metadata:
labels:
app: prometheus-server
spec:
containers:
- name: prometheus
image: prom/prometheus:v2.3.2
args:
- "--config.file=/etc/prometheus/prometheus.yml"
- "--storage.tsdb.path=/prometheus/"
ports:
- containerPort: 9090
volumeMounts:
- name: prometheus-config-volume
mountPath: /etc/prometheus/
- name: prometheus-storage-volume
mountPath: /prometheus/
volumes:
- name: prometheus-config-volume
configMap:
defaultMode: 420
name: prometheus-server-conf
- name: prometheus-storage-volume
emptyDir: {}
vim prometheus-service.yaml
apiVersion: v1
kind: Service
metadata:
name: prometheus-service
spec:
selector:
app: prometheus-server
type: NodePort
ports:
- port: 9090
targetPort: 9090
nodePort: 30909
Prometheus：
2018-12-05 16-31-49屏幕截图.png
2018-12-05 18-26-59屏幕截图.png