rancher证书是否过期解决方案

临时方案

一、证书过期，导致不能登录

版本：v2.3.6

2.3 +

[root@localhost ~]# docker ps -a | grep 8443
17a1d1cf97fc        harbor.jettech.com/rancher/rancher:v2.3.6   "entrypoint.sh"     about an hour ago   Up about an hour    0.0.0.0:80->80/tcp, 0.0.0.0:8443->443/tcp   heuristic_shannon
[root@localhost ~]# docker exec -it 17a1d1cf97fc bash
root@17a1d1cf97fc:/var/lib/rancher# ls
k3s  management-state
root@17a1d1cf97fc:/var/lib/rancher# cp -r k3s/server/tls k3s/server/tls_bak
root@17a1d1cf97fc:/var/lib/rancher# rm -f k3s/server/tls
    properties([
            pipelineTriggers([
                    cron('H 9 * * 1')
            ])
    ])
    node('master') {
        rancherIP = "192.168.1.2"
        rancherSshUser = "admin"        
        rancherSshPwd = "123456"
        scriptDir = "${WORKSPACE}/devops/shell/k8s"      //脚本所在目录
        vxUrl = "https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=8d4432c9-d15c-4803-879a-73xdasfads32"	//机器人API

        try {
            stage("git pull") {
                gitClone()
            }
            stage("check ${rancherIP} rancher cert time") {
                sh """
                    sshpass -p ${rancherSshPwd} scp -o StrictHostKeyChecking=no ${scriptDir}/{check_rancher_cert.sh,check_cert_time.py} ${rancherSshUser}@${rancherIP}:.
                    sshpass -p ${rancherSshPwd} ssh -o StrictHostKeyChecking=no ${rancherSshUser}@${rancherIP} "sudo bash check_rancher_cert.sh ${vxUrl}"
                """
            }
        } catch (e) {
            throw e
        } finally {

        }
    }
}

def gitClone(){
    sh """
        if [[ -d devops ]];then
            cd devops && git pull
        else
            git clone --depth=1 -b devops https://lvhy@192.168.2.3/devops/devops.git devops
        fi
    """
}

check_rancher_cert.sh

#!/bin/bash
# vim:sw=4:ts=4:et
< ${EXCEED_CERT_PATH}
    for name in `ls *.crt`
    do
        local cert_time_info=$(openssl x509 -enddate -noout -in ${name})    #如notAfter=May 26 06:27:49 2022 GMT
        local cert_exceed_time=$(echo ${cert_time_info} | awk -F'[ =]' '{printf"%s %s %sn",$2,$3,$5}')     #获取到证书过期时间，如May 26 2022
        python ${WORKDIR}/check_cert_time.py ${EXCEED_CERT_PATH} ${name} ${BEFORE_MONTH} "${cert_exceed_time}"
    done
    # python ${WORKDIR}/check_cert_time.py ${EXCEED_CERT_PATH} "a.crt" ${BEFORE_MONTH} "Mar 18 2022"
    # python ${WORKDIR}/check_cert_time.py ${EXCEED_CERT_PATH} "b.crt" ${BEFORE_MONTH} "Mar 18 2022"
}

#企业微信通知
Vx_Notice(){
    local vx_url=$1
    local exceed_time=$2
    local host_ip=$(ip addr |awk '/inet /' |sed -n '2p' |awk -F' ' '{print $2}' |awk -F'/' '{print $1}')
    curl "${vx_url}" 
        -H 'Content-Type: application/json' 
        -d '{"msgtype": "text",
            "text": {
                "content": "'${host_ip}' Rancher following certificates will expire in '${exceed_time}'nPlease Check '${EXCEED_CERT_PATH}'",
                "mentioned_mobile_list":["@all"]}
            }'
}

#检查证书
Check_Cert_Time(){
    echo "INFO:Begin Check Rancher Cert Exceed Time..."
    Check_Env
    Get_Exceed_Cert
    [[ ! -f ${EXCEED_CERT_PATH} ]] && echo "ERROR:${EXCEED_CERT_PATH} Not Found" && exit 1
    if [[ $(cat ${EXCEED_CERT_PATH} | wc -l) -gt 1 ]];then
        if [[ -n $1 ]];then
            local vx_url=$1
            if ! echo ${vx_url} | grep "https://qyapi.weixin.qq.com/" &> /dev/null;then
                echo "ERROR:Vx Url ${vx_url} Is Error" && exit 1
            fi
            local exceed_time=$(cat ${EXCEED_CERT_PATH} | awk -F'[ :]' '/crt/{print $3}' | sed -n '1p')
            Vx_Notice ${vx_url} ${exceed_time}
        fi
        echo -e "33[33mWARN:The following certificates will expire in ${BEFORE_MONTH} months33[0m"
        cat ${EXCEED_CERT_PATH}
        exit 1
    else
        echo "INFO:Rancher Cert Is Ok" | tee -a ${EXCEED_CERT_PATH} && exit 0
    fi
}

[[ $# -gt 1 ]] && echo "ERROR:Invalid Param!!!,Please Excute:bash $0 " && exit 1
Check_Cert_Time $1

check_cert_time.py

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# @FileName  :check_cert.py
# @Time      :2021/12/17
# @Author    :运维@小兵
# @Function  :检查证书过期时间，如果在n个月后过期，则把证书和过期时间写入到文件中
# @Excute    :python check_cert.py 保存过期证书信息的文件 证书文件 几个月后 证书过期时间

from datetime import datetime
import sys

# 环境检查
def check_env():
    ex = Exception('Invalid Param!!! eg:python %s 保存过期证书信息的文件 证书文件 几个月后 证书过期时间' % sys.argv[0])
    if len(sys.argv) != 5:
        raise ex
'''
    param mon: 获取当前时间X月之后的时间
    return: YYYY-MM-DD
'''
def get_date_month(mon=0):
    now = datetime.now()  # 当前时间
    # 当前时间n个月后
    last_y = int((int(now.year) * 12 + int(now.month) + mon) / 12)
    last_m = (int(now.year) * 12 + int(now.month) + mon) % 12
    if last_m < 10:
        last_m = "0" + str(last_m)
    last_d = int(now.day)
    last_date = '%s-%s-%s' % (last_y, last_m, last_d)
    return last_date

# 将GMT时间转为标准时间
def trans_gmt(gmt_time):
    GMT_FORMAT = '%b %d %Y'
    standard_time = datetime.strptime(gmt_time, GMT_FORMAT)
    standard_time = standard_time.strftime("%Y-%m-%d")      # 把转为str
    return standard_time

#检查k8s证书时间
def check_k8s_cert():
    exceed_cert_file = sys.argv[1]      # 保存过期证书信息文件
    cert_file = sys.argv[2]             # 证书名
    after_mon = int(sys.argv[3])        # n个月后
    cert_exceed_time = sys.argv[4]      # 证书过期时间(GMT格式)

    cert_exceed_time = trans_gmt(cert_exceed_time)
    cert_exceed_time = int(cert_exceed_time.replace('-', ''))       # 转成整型，如20220318
    after_mon_time = get_date_month(after_mon)                      
    after_mon_time = int(after_mon_time.replace('-', ''))           # n个月后的时间
    if cert_exceed_time <= after_mon_time:
        with open(exceed_cert_file, 'a') as f:
            f.write("%s 过期时间:%sn" % (cert_file, cert_exceed_time))
        # print('WARN:证书%s将在%s过期' % (cert_file,cert_exceed_time))
if __name__ == '__main__':
    try:
        check_env()
        check_k8s_cert()
    except Exception as e:
        print('ERROR:%s' % e)

去Jenkins上创建一个pipeline的流水线即可

方案3. 调整服务器日期

将服务器时间同步服务关闭，调整系统日期提前到证书有效期内，然后打开 UI 页面进行证书更新。

可以手动设置节点的时间，把时间往后调整一些。因为Agent只与K8S master和Rancher Server通信，如果 Rancher Server 证书未过期，那就只需调整K8S master节点时间。

调整命令，物理机操作：

# 关闭ntp同步，不然时间会自动更新
timedatectl set-ntp false
# 修改节点时间
timedatectl set-time '2019-01-01 00:00:00'

然后再对 Rancher Server 进行升级，接着按照证书轮换步骤进行证书轮换，等到证书轮换完成后再把时间同步回来

timedatectl set-ntp true

检查证书有效期

openssl x509 -in /etc/kubernetes/ssl/kube-apiserver.pem -noout -dates

方案4.按照官方文档进行证书轮换

轮换证书 | Rancher文档

# 进入 server 容器
docker exec -it rancher /bin/sh
kubectl --insecure-skip-tls-verify -n kube-system delete secrets k3s-serving
kubectl --insecure-skip-tls-verify delete secret serving-cert -n cattle-system
rm -f /var/lib/rancher/k3s/server/tls/dynamic-cert.json

# 重启 server 容器
docker restart rancher

# 执行以下命令刷新参数
curl --insecure -sfL https://localhost:8443/v3

# 重启 server 容器
docker restart rancher

然后在进入页面跟新证书

因为证书改变，相应的token也会变化，所以在完成集群证书更新后，需要对连接API SERVER的 Pod 进行重建，以获取新的token。

cattle-system/cattle-cluster-agent

cattle-system/cattle-node-agent

cattle-system/kube-api-auth

ingress-nginx/nginx-ingress-controller

kube-system/canal

kube-system/kube-dns

kube-system/kube-dns-autoscaler

其他应用 Pod

rancher证书是否过期解决方案

Java相关栏目本月热门文章