k8s 主控节点的介绍以及安装

3. 主控节点安装

etcd 的leader选举机制，要求至少为3台或以上的奇数台。本次安装涉及：hdss7-12，hdss7-21，hdss7-22

3.1.1. 签发etcd证书

证书签发服务器 hdss7-200:

• 创建ca的json配置: /opt/certs/ca-config.json

• • server 表示服务端连接客户端时携带的证书，用于客户端验证服务端身份
  • client 表示客户端连接服务端时携带的证书，用于服务端验证客户端身份
  • peer 表示相互之间连接时使用的证书，如etcd节点之间验证

{
    "signing": {
        "default": {
            "expiry": "175200h"
        },
        "profiles": {
            "server": {
                "expiry": "175200h",
                "usages": [
                    "signing",
                    "key encipherment",
                    "server auth"
                ]
            },
            "client": {
                "expiry": "175200h",
                "usages": [
                    "signing",
                    "key encipherment",
                    "client auth"
                ]
            },
            "peer": {
                "expiry": "175200h",
                "usages": [
                    "signing",
                    "key encipherment",
                    "server auth",
                    "client auth"
                ]
            }
        }
    }
}

• 创建etcd证书配置：/opt/certs/etcd-peer-csr.json

重点在hosts上，将所有可能的etcd服务器添加到host列表，不能使用网段，新增etcd服务器需要重新签发证书

{
    "CN": "k8s-etcd",
    "hosts": [
        "10.4.7.11",
        "10.4.7.12",
        "10.4.7.21",
        "10.4.7.22"
    ],
    "key": {
        "algo": "rsa",
        "size": 2048
    },
    "names": [
        {
            "C": "CN",
            "ST": "beijing",
            "L": "beijing",
            "O": "od",
            "OU": "ops"
        }
    ]
}

签发证书

[root@hdss7-200 ~]# cd /opt/certs/
[root@hdss7-200 certs]# cfssl gencert -ca=ca.pem -ca-key=ca-key.pem -config=ca-config.json -profile=peer etcd-peer-csr.json |cfssl-json -bare etcd-peer
[root@hdss7-200 certs]# ll etcd-peer*
-rw-r--r-- 1 root root 1062 Jan  5 17:01 etcd-peer.csr
-rw-r--r-- 1 root root  363 Jan  5 16:59 etcd-peer-csr.json
-rw------- 1 root root 1675 Jan  5 17:01 etcd-peer-key.pem
-rw-r--r-- 1 root root 1428 Jan  5 17:01 etcd-peer.pem

3.1.2. 安装etcd

etcd地址：https://github.com/etcd-io/etcd/

实验使用版本: etcd-v3.1.20-linux-amd64.tar.gz

本次安装涉及：hdss7-12，hdss7-21，hdss7-22

下载etcd

[root@hdss7-12 ~]# useradd -s /sbin/nologin -M etcd
[root@hdss7-12 ~]# cd /opt/src/
[root@hdss7-12 src]# wget https://github.com/etcd-io/etcd/releases/download/v3.1.20/etcd-v3.1.20-linux-amd64.tar.gz
[root@hdss7-12 src]# tar -xf etcd-v3.1.20-linux-amd64.tar.gz 
[root@hdss7-12 src]# mv etcd-v3.1.20-linux-amd64 /opt/release/etcd-v3.1.20
[root@hdss7-12 src]# ln -s /opt/release/etcd-v3.1.20 /opt/apps/etcd
[root@hdss7-12 src]# ll /opt/apps/etcd
lrwxrwxrwx 1 root root 25 Jan  5 17:56 /opt/apps/etcd -> /opt/release/etcd-v3.1.20
[root@hdss7-12 src]# mkdir -p /opt/apps/etcd/certs /data/etcd /data/logs/etcd-server

下发证书到各个etcd上

[root@hdss7-12 src] cd  /opt/apps/etcd/certs
[root@hdss7-12 src] scp hdss7-200:/opt/certs/ca.pem .
[root@hdss7-12 src] scp hdss7-200:/opt/certs/etcd-peer.pem .
[root@hdss7-12 src] scp hdss7-200:/opt/certs/etcd-peer-key.pem .
###或者 在hdss-200 上
[root@hdss7-200 ~]# cd /opt/certs/
[root@hdss7-200 certs]# for i in 12 21 22;do scp ca.pem etcd-peer.pem etcd-peer-key.pem hdss7-${i}:/opt/apps/etcd/certs/ ;done

使用MD5校验信息

[root@hdss7-12 src]# md5sum /opt/apps/etcd/certs/*
8778d0c3411891af61a287e49a70c89a  /opt/apps/etcd/certs/ca.pem
7918783c2f6bf69e96edf03e67d04983  /opt/apps/etcd/certs/etcd-peer-key.pem
d4d849751a834c7727d42324fdedf92d  /opt/apps/etcd/certs/etcd-peer.pem

创建启动脚本(部分参数每台机器不同

[root@hdss7-12 ~]# vim /opt/apps/etcd/etcd-server-startup.sh
#!/bin/sh
# listen-peer-urls etcd节点之间通信端口
# listen-client-urls 客户端与etcd通信端口
# quota-backend-bytes 配额大小
# 需要修改的参数：name,listen-peer-urls,listen-client-urls,initial-advertise-peer-urls

WORK_DIR=$(dirname $(readlink -f $0))
[ $? -eq 0 ] && cd $WORK_DIR || exit

/opt/apps/etcd/etcd --name etcd-server-7-12 \
    --data-dir /data/etcd/etcd-server \
    --listen-peer-urls https://10.4.7.12:2380 \
    --listen-client-urls https://10.4.7.12:2379,http://127.0.0.1:2379 \
    --quota-backend-bytes 8000000000 \
    --initial-advertise-peer-urls https://10.4.7.12:2380 \
    --advertise-client-urls https://10.4.7.12:2379,http://127.0.0.1:2379 \
    --initial-cluster  etcd-server-7-12=https://10.4.7.12:2380,etcd-server-7-21=https://10.4.7.21:2380,etcd-server-7-22=https://10.4.7.22:2380 \
    --ca-file ./certs/ca.pem \
    --cert-file ./certs/etcd-peer.pem \
    --key-file ./certs/etcd-peer-key.pem \
    --client-cert-auth  \
    --trusted-ca-file ./certs/ca.pem \
    --peer-ca-file ./certs/ca.pem \
    --peer-cert-file ./certs/etcd-peer.pem \
    --peer-key-file ./certs/etcd-peer-key.pem \
    --peer-client-cert-auth \
    --peer-trusted-ca-file ./certs/ca.pem \
    --log-output stdout

[root@hdss7-12 ~]# chmod u+x /opt/apps/etcd/etcd-server-startup.sh
[root@hdss7-12 ~]# chown -R etcd.etcd /opt/apps/etcd/ /data/etcd /data/logs/etcd-server 

3.1.3. 启动etcd

因为这些进程都是要启动为后台进程，要么手动启动，要么采用后台进程管理工具，实验中使用后台管理工具

[root@hdss7-12 ~]# yum install -y supervisor
[root@hdss7-12 ~]# systemctl start supervisord ; systemctl enable supervisord
[root@hdss7-12 ~]# vim /etc/supervisord.d/etcd-server.ini
[program:etcd-server-7-12]
command=/opt/apps/etcd/etcd-server-startup.sh         ; the program (relative uses PATH, can take args)
numprocs=1                                            ; number of processes copies to start (def 1)
directory=/opt/apps/etcd                              ; directory to cwd to before exec (def no cwd)
autostart=true                                        ; start at supervisord start (default: true)
autorestart=true                                      ; retstart at unexpected quit (default: true)
startsecs=30                                          ; number of secs prog must stay running (def. 1)
startretries=3                                        ; max # of serial start failures (default 3)
exitcodes=0,2                                         ; 'expected' exit codes for process (default 0,2)
stopsignal=QUIT                                       ; signal used to kill process (default TERM)
stopwaitsecs=10                                       ; max num secs to wait b4 SIGKILL (default 10)
user=etcd                                             ; setuid to this UNIX account to run the program
redirect_stderr=true                                  ; redirect proc stderr to stdout (default false)
stdout_logfile=/data/logs/etcd-server/etcd.stdout.log ; stdout log path, NONE for none; default AUTO
stdout_logfile_maxbytes=64MB                          ; max # logfile bytes b4 rotation (default 50MB)
stdout_logfile_backups=5                              ; # of stdout logfile backups (default 10)
stdout_capture_maxbytes=1MB                           ; number of bytes in 'capturemode' (default 0)
stdout_events_enabled=false                           ; emit events on stdout writes (default false)
[root@hdss7-12 ~]# supervisorctl update
etcd-server-7-12: added process group

etcd 进程状态查看

[root@hdss7-12 ~]# supervisorctl status  # supervisorctl 状态
etcd-server-7-12                 RUNNING   pid 22375, uptime 0:00:39

[root@hdss7-12 ~]# netstat -lntp|grep etcd
tcp        0      0 10.4.7.12:2379          0.0.0.0:*               LISTEN      22379/etcd          
tcp        0      0 127.0.0.1:2379          0.0.0.0:*               LISTEN      22379/etcd          
tcp        0      0 10.4.7.12:2380          0.0.0.0:*               LISTEN      22379/etcd

[root@hdss7-12 ~]# /opt/apps/etcd/etcdctl member list # 随着etcd重启，leader会变化
988139385f78284: name=etcd-server-7-22 peerURLs=https://10.4.7.22:2380 clientURLs=http://127.0.0.1:2379,https://10.4.7.22:2379 isLeader=false
5a0ef2a004fc4349: name=etcd-server-7-21 peerURLs=https://10.4.7.21:2380 clientURLs=http://127.0.0.1:2379,https://10.4.7.21:2379 isLeader=true
f4a0cb0a765574a8: name=etcd-server-7-12 peerURLs=https://10.4.7.12:2380 clientURLs=http://127.0.0.1:2379,https://10.4.7.12:2379 isLeader=false

[root@hdss7-12 ~]# /opt/apps/etcd/etcdctl cluster-health
member 988139385f78284 is healthy: got healthy result from http://127.0.0.1:2379
member 5a0ef2a004fc4349 is healthy: got healthy result from http://127.0.0.1:2379
member f4a0cb0a765574a8 is healthy: got healthy result from http://127.0.0.1:2379
cluster is healthy

3.2. apiserver 安装

3.2.1. 下载kubernetes服务端

aipserver 涉及的服务器：hdss7-21，hdss7-22

下载 kubernetes 二进制版本包需要不可描述工具下载

• 进入kubernetes的github页面: https://github.com/kubernetes/kubernetes
• 进入tags页签: https://github.com/kubernetes/kubernetes/tags
• 选择要下载的版本: https://github.com/kubernetes/kubernetes/releases/tag/v1.15.2
• 点击 CHANGELOG-${version}.md 进入说明页面: https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG-1.15.md#downloads-for-v1152
• 下载Server Binaries: https://dl.k8s.io/v1.15.2/kubernetes-server-linux-amd64.tar.gz

[root@hdss7-21 ~]# cd /opt/src
[root@hdss7-21 src]# wget https://dl.k8s.io/v1.15.2/kubernetes-server-linux-amd64.tar.gz

[root@hdss7-21 src]# tar -xf kubernetes-server-linux-amd64.tar.gz 
[root@hdss7-21 src]# mv kubernetes /opt/release/kubernetes-v1.15.2
[root@hdss7-21 src]# ln -s /opt/release/kubernetes-v1.15.2 /opt/apps/kubernetes
[root@hdss7-21 src]# ll /opt/apps/kubernetes
lrwxrwxrwx 1 root root 31 Jan  6 12:59 /opt/apps/kubernetes -> /opt/release/kubernetes-v1.15.2

[root@hdss7-21 src]# cd /opt/apps/kubernetes
[root@hdss7-21 kubernetes]# rm -f kubernetes-src.tar.gz 
[root@hdss7-21 kubernetes]# cd server/bin/
[root@hdss7-21 bin]# rm -f *.tar *_tag  # *.tar *_tag 镜像文件
[root@hdss7-21 bin]# ll
total 884636
-rwxr-xr-x 1 root root  43534816 Aug  5 18:01 apiextensions-apiserver
-rwxr-xr-x 1 root root 100548640 Aug  5 18:01 cloud-controller-manager
-rwxr-xr-x 1 root root 200648416 Aug  5 18:01 hyperkube
-rwxr-xr-x 1 root root  40182208 Aug  5 18:01 kubeadm
-rwxr-xr-x 1 root root 164501920 Aug  5 18:01 kube-apiserver
-rwxr-xr-x 1 root root 116397088 Aug  5 18:01 kube-controller-manager
-rwxr-xr-x 1 root root  42985504 Aug  5 18:01 kubectl
-rwxr-xr-x 1 root root 119616640 Aug  5 18:01 kubelet
-rwxr-xr-x 1 root root  36987488 Aug  5 18:01 kube-proxy
-rwxr-xr-x 1 root root  38786144 Aug  5 18:01 kube-scheduler
-rwxr-xr-x 1 root root   1648224 Aug  5 18:01 mounter

3.2.2. 签发证书

签发证书 涉及的服务器：hdss7-200

• 签发client证书（apiserver和etcd通信证书）

  [root@hdss7-200 ~]# cd /opt/certs/
  [root@hdss7-200 certs]# vim /opt/certs/client-csr.json
  {
      "CN": "k8s-node",
      "hosts": [
      ],
      "key": {
          "algo": "rsa",
          "size": 2048
      },
      "names": [
          {
              "C": "CN",
              "ST": "beijing",
              "L": "beijing",
              "O": "od",
              "OU": "ops"
          }
      ]
  }
  [root@hdss7-200 certs]# cfssl gencert -ca=ca.pem -ca-key=ca-key.pem -config=ca-config.json -profile=client client-csr.json |cfssl-json -bare client
  2020/01/06 13:42:47 [INFO] generate received request
  2020/01/06 13:42:47 [INFO] received CSR
  2020/01/06 13:42:47 [INFO] generating key: rsa-2048
  2020/01/06 13:42:47 [INFO] encoded CSR
  2020/01/06 13:42:47 [INFO] signed certificate with serial number 268276380983442021656020268926931973684313260543
  2020/01/06 13:42:47 [WARNING] This certificate lacks a "hosts" field. This makes it unsuitable for
  websites. For more information see the Baseline Requirements for the Issuance and Management
  of Publicly-Trusted Certificates, v.1.1.6, from the CA/Browser Forum (https://cabforum.org);
  specifically, section 10.2.3 ("Information Requirements").
  [root@hdss7-200 certs]# ls client* -l
  -rw-r--r-- 1 root root  993 Jan  6 13:42 client.csr
  -rw-r--r-- 1 root root  280 Jan  6 13:42 client-csr.json
  -rw------- 1 root root 1679 Jan  6 13:42 client-key.pem
  -rw-r--r-- 1 root root 1363 Jan  6 13:42 client.pem
  

签发server证书（apiserver和其它k8s组件通信使用）

# hosts中将所有可能作为apiserver的ip添加进去，VIP 10.4.7.10 也要加入
[root@hdss7-200 certs]# vim /opt/certs/apiserver-csr.json
{
    "CN": "k8s-apiserver",
    "hosts": [
        "127.0.0.1",
        "192.168.0.1",
        "kubernetes.default",
        "kubernetes.default.svc",
        "kubernetes.default.svc.cluster",
        "kubernetes.default.svc.cluster.local",
        "10.4.7.10",
        "10.4.7.21",
        "10.4.7.22",
        "10.4.7.23"
    ],
    "key": {
        "algo": "rsa",
        "size": 2048
    },
    "names": [
        {
            "C": "CN",
            "ST": "beijing",
            "L": "beijing",
            "O": "od",
            "OU": "ops"
        }
    ]
}
[root@hdss7-200 certs]# cfssl gencert -ca=ca.pem -ca-key=ca-key.pem -config=ca-config.json -profile=server apiserver-csr.json |cfssl-json -bare apiserver
2020/01/06 13:46:56 [INFO] generate received request
2020/01/06 13:46:56 [INFO] received CSR
2020/01/06 13:46:56 [INFO] generating key: rsa-2048
2020/01/06 13:46:56 [INFO] encoded CSR
2020/01/06 13:46:56 [INFO] signed certificate with serial number 573076691386375893093727554861295529219004473872
2020/01/06 13:46:56 [WARNING] This certificate lacks a "hosts" field. This makes it unsuitable for
websites. For more information see the Baseline Requirements for the Issuance and Management
of Publicly-Trusted Certificates, v.1.1.6, from the CA/Browser Forum (https://cabforum.org);
specifically, section 10.2.3 ("Information Requirements").
[root@hdss7-200 certs]# ls apiserver* -l
-rw-r--r-- 1 root root 1249 Jan  6 13:46 apiserver.csr
-rw-r--r-- 1 root root  566 Jan  6 13:45 apiserver-csr.json
-rw------- 1 root root 1675 Jan  6 13:46 apiserver-key.pem
-rw-r--r-- 1 root root 1598 Jan  6 13:46 apiserver.pem

证书下发

 [root@hdss7-200 certs]# for i in 21 22;do echo hdss7-$i;ssh hdss7-$i "mkdir /opt/apps/kubernetes/server/bin/certs";scp apiserver-key.pem apiserver.pem ca-key.pem ca.pem client-key.pem client.pem hdss7-$i:/opt/apps/kubernetes/server/bin/certs/;done 

3.2.3. 配置apiserver日志审计

aipserver 涉及的服务器：hdss7-21，hdss7-22

[root@hdss7-21 bin]# mkdir /opt/apps/kubernetes/conf
[root@hdss7-21 bin]# vim /opt/apps/kubernetes/conf/audit.yaml # 打开文件后，设置 :set paste，避免自动缩进
apiVersion: audit.k8s.io/v1beta1 # This is required.
kind: Policy
# Don't generate audit events for all requests in RequestReceived stage.
omitStages:
  - "RequestReceived"
rules:
  # Log pod changes at RequestResponse level
  - level: RequestResponse
    resources:
    - group: ""
      # Resource "pods" doesn't match requests to any subresource of pods,
      # which is consistent with the RBAC policy.
      resources: ["pods"]
  # Log "pods/log", "pods/status" at Metadata level
  - level: Metadata
    resources:
    - group: ""
      resources: ["pods/log", "pods/status"]

  # Don't log requests to a configmap called "controller-leader"
  - level: None
    resources:
    - group: ""
      resources: ["configmaps"]
      resourceNames: ["controller-leader"]

  # Don't log watch requests by the "system:kube-proxy" on endpoints or services
  - level: None
    users: ["system:kube-proxy"]
    verbs: ["watch"]
    resources:
    - group: "" # core API group
      resources: ["endpoints", "services"]

  # Don't log authenticated requests to certain non-resource URL paths.
  - level: None
    userGroups: ["system:authenticated"]
    nonResourceURLs:
    - "/api*" # Wildcard matching.
    - "/version"

  # Log the request body of configmap changes in kube-system.
  - level: Request
    resources:
    - group: "" # core API group
      resources: ["configmaps"]
    # This rule only applies to resources in the "kube-system" namespace.
    # The empty string "" can be used to select non-namespaced resources.
    namespaces: ["kube-system"]

  # Log configmap and secret changes in all other namespaces at the Metadata level.
  - level: Metadata
    resources:
    - group: "" # core API group
      resources: ["secrets", "configmaps"]

  # Log all other resources in core and extensions at the Request level.
  - level: Request
    resources:
    - group: "" # core API group
    - group: "extensions" # Version of group should NOT be included.

  # A catch-all rule to log all other requests at the Metadata level.
  - level: Metadata
    # Long-running requests like watches that fall under this rule will not
    # generate an audit event in RequestReceived.
    omitStages:
      - "RequestReceived"

3.2.4. 配置启动脚本

aipserver 涉及的服务器：hdss7-21，hdss7-22

• 创建启动脚本

[root@hdss7-21 bin]# vim /opt/apps/kubernetes/server/bin/kube-apiserver-startup.sh
#!/bin/bash

WORK_DIR=$(dirname $(readlink -f $0))
[ $? -eq 0 ] && cd $WORK_DIR || exit

/opt/apps/kubernetes/server/bin/kube-apiserver \
    --apiserver-count 2 \
    --audit-log-path /data/logs/kubernetes/kube-apiserver/audit-log \
    --audit-policy-file ../../conf/audit.yaml \
    --authorization-mode RBAC \
    --client-ca-file ./certs/ca.pem \
    --requestheader-client-ca-file ./certs/ca.pem \
    --enable-admission-plugins NamespaceLifecycle,LimitRanger,ServiceAccount,DefaultStorageClass,DefaultTolerationSeconds,MutatingAdmissionWebhook,ValidatingAdmissionWebhook,ResourceQuota \
    --etcd-cafile ./certs/ca.pem \
    --etcd-certfile ./certs/client.pem \
    --etcd-keyfile ./certs/client-key.pem \
    --etcd-servers https://10.4.7.12:2379,https://10.4.7.21:2379,https://10.4.7.22:2379 \
    --service-account-key-file ./certs/ca-key.pem \
    --service-cluster-ip-range 192.168.0.0/16 \
    --service-node-port-range 3000-29999 \
    --target-ram-mb=1024 \
    --kubelet-client-certificate ./certs/client.pem \
    --kubelet-client-key ./certs/client-key.pem \
    --log-dir  /data/logs/kubernetes/kube-apiserver \
    --tls-cert-file ./certs/apiserver.pem \
    --tls-private-key-file ./certs/apiserver-key.pem \
    --v 2

配置supervisor启动配置

[root@hdss7-21 bin]# vim /etc/supervisord.d/kube-apiserver.ini
[program:kube-apiserver-7-21]
command=/opt/apps/kubernetes/server/bin/kube-apiserver-startup.sh
numprocs=1
directory=/opt/apps/kubernetes/server/bin
autostart=true
autorestart=true
startsecs=30
startretries=3
exitcodes=0,2
stopsignal=QUIT
stopwaitsecs=10
user=root
redirect_stderr=true
stdout_logfile=/data/logs/kubernetes/kube-apiserver/apiserver.stdout.log
stdout_logfile_maxbytes=64MB
stdout_logfile_backups=5
stdout_capture_maxbytes=1MB
stdout_events_enabled=false
[root@hdss7-21 bin]# mkdir -p /data/logs/kubernetes/kube-apiserver
[root@hdss7-21 bin]# chmod +x /opt/apps/kubernetes/server/bin/kube-apiserver-startup.sh 
[root@hdss7-21 bin]# supervisorctl update
[root@hdss7-21 bin]# supervisorctl status
etcd-server-7-21                 RUNNING   pid 23637, uptime 22:26:08
kube-apiserver-7-21              RUNNING   pid 32591, uptime 0:05:37

启停apiserver

[root@hdss7-12 ~]# supervisorctl start kube-apiserver-7-21
[root@hdss7-12 ~]# supervisorctl stop kube-apiserver-7-21
[root@hdss7-12 ~]# supervisorctl restart kube-apiserver-7-21
[root@hdss7-12 ~]# supervisorctl status kube-apiserver-7-21

• 查看进程

[root@hdss7-21 bin]# netstat -lntp|grep api
tcp        0      0 127.0.0.1:8080          0.0.0.0:*               LISTEN      32595/kube-apiserve 
tcp6       0      0 :::6443                 :::*                    LISTEN      32595/kube-apiserve 
[root@hdss7-21 bin]# ps uax|grep kube-apiserver|grep -v grep
root      32591  0.0  0.0 115296  1476 ?        S    20:17   0:00 /bin/bash /opt/apps/kubernetes/server/bin/kube-apiserver-startup.sh
root      32595  3.0  2.3 402720 184892 ?       Sl   20:17   0:16 /opt/apps/kubernetes/server/bin/kube-apiserver --apiserver-count 2 --audit-log-path /data/logs/kubernetes/kube-apiserver/audit-log --audit-policy-file ../../conf/audit.yaml --authorization-mode RBAC --client-ca-file ./certs/ca.pem --requestheader-client-ca-file ./certs/ca.pem --enable-admission-plugins NamespaceLifecycle,LimitRanger,ServiceAccount,DefaultStorageClass,DefaultTolerationSeconds,MutatingAdmissionWebhook,ValidatingAdmissionWebhook,ResourceQuota --etcd-cafile ./certs/ca.pem --etcd-certfile ./certs/client.pem --etcd-keyfile ./certs/client-key.pem --etcd-servers https://10.4.7.12:2379,https://10.4.7.21:2379,https://10.4.7.22:2379 --service-account-key-file ./certs/ca-key.pem --service-cluster-ip-range 192.168.0.0/16 --service-node-port-range 3000-29999 --target-ram-mb=1024 --kubelet-client-certificate ./certs/client.pem --kubelet-client-key ./certs/client-key.pem --log-dir /data/logs/kubernetes/kube-apiserver --tls-cert-file ./certs/apiserver.pem --tls-private-key-file ./certs/apiserver-key.pem --v 2

配置apiserver L4代理

3.3.1. nginx配置

L4 代理涉及的服务器：hdss7-11，hdss7-12

[root@hdss7-11 ~]# yum install -y nginx
[root@hdss7-11 ~]# vim /etc/nginx/nginx.conf  
# 末尾加上以下内容，stream 只能加在 main 中
# 此处只是简单配置下nginx，实际生产中，建议进行更合理的配置
stream {
    log_format proxy '$time_local|$remote_addr|$upstream_addr|$protocol|$status|'
                     '$session_time|$upstream_connect_time|$bytes_sent|$bytes_received|'
                     '$upstream_bytes_sent|$upstream_bytes_received' ;

    upstream kube-apiserver {
        server 10.4.7.21:6443     max_fails=3 fail_timeout=30s;
        server 10.4.7.22:6443     max_fails=3 fail_timeout=30s;
    }
    server {
        listen 7443;
        proxy_connect_timeout 2s;
        proxy_timeout 900s;
        proxy_pass kube-apiserver;
        access_log /var/log/nginx/proxy.log proxy;
    }
}
[root@hdss7-11 ~]# systemctl start nginx; systemctl enable nginx
[root@hdss7-11 ~]# curl 127.0.0.1:7443  # 测试几次
Client sent an HTTP request to an HTTPS server.
[root@hdss7-11 ~]# cat /var/log/nginx/proxy.log 
06/Jan/2020:21:00:27 +0800|127.0.0.1|10.4.7.21:6443|TCP|200|0.001|0.000|76|78|78|76
06/Jan/2020:21:05:03 +0800|127.0.0.1|10.4.7.22:6443|TCP|200|0.020|0.019|76|78|78|76
06/Jan/2020:21:05:04 +0800|127.0.0.1|10.4.7.21:6443|TCP|200|0.001|0.001|76|78|78|76

3.3.2. keepalived配置

[root@hdss7-11 ~]# yum install -y keepalived
[root@hdss7-11 ~]# vim /etc/keepalived/check_port.sh # 配置检查脚本
#!/bin/bash
#keepalived 监控端口脚本
#使用方法：
#在keepalived的配置文件中
#vrrp_script check_port {#创建一个vrrp_script脚本,检查配置
#    script "/etc/keepalived/check_port.sh 6379" #配置监听的端口
#    interval 2 #检查脚本的频率,单位（秒）
#}
CHK_PORT=$1
if [ -n "$CHK_PORT" ];then
        PORT_PROCESS=`ss -lnt|grep $CHK_PORT|wc -l`
        if [ $PORT_PROCESS -eq 0 ];then
                echo "Port $CHK_PORT Is Not Used,End."
                exit 1
        fi
else
        echo "Check Port Cant Be Empty!"
fi
[root@hdss7-11 ~]# chmod +x /etc/keepalived/check_port.sh

配置主节点：/etc/keepalived/keepalived.conf

主节点中，必须加上 **nopreempt **非抢占式

因为一旦因为网络抖动导致VIP漂移，不能让它自动飘回来，必须要分析原因后手动迁移VIP到主节点！如主节点确认正常后，重启备节点的keepalive，让VIP飘到主节点.

keepalived 的日志输出配置此处省略，生产中需要进行处理。

! Configuration File for keepalived
global_defs {
   router_id 10.4.7.11
}
vrrp_script chk_nginx {
    script "/etc/keepalived/check_port.sh 7443"
    interval 2
    weight -20
}
vrrp_instance VI_1 {
    state MASTER
    interface eth0
    virtual_router_id 251
    priority 100
    advert_int 1
    mcast_src_ip 10.4.7.11
    nopreempt

    authentication {
        auth_type PASS
        auth_pass 11111111
    }
    track_script {
         chk_nginx
    }
    virtual_ipaddress {
        10.4.7.10
    }
}

• 配置备节点：/etc/keepalived/keepalived.conf

! Configuration File for keepalived
global_defs {
        router_id 10.4.7.12
}
vrrp_script chk_nginx {
        script "/etc/keepalived/check_port.sh 7443"
        interval 2
        weight -20
}
vrrp_instance VI_1 {
        state BACKUP
        interface eth0
        virtual_router_id 251
        mcast_src_ip 10.4.7.12
        priority 90
        advert_int 1
        authentication {
                auth_type PASS
                auth_pass 11111111
        }
        track_script {
                chk_nginx
        }
        virtual_ipaddress {
                10.4.7.10
   

• 启动keepalived

[root@hdss7-11 ~]# systemctl start keepalived ; systemctl enable keepalived
[root@hdss7-11 ~]# ip addr show ens32
2: ens32: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP group default qlen 1000
    link/ether 00:0c:29:6d:b8:82 brd ff:ff:ff:ff:ff:ff
    inet 10.4.7.11/24 brd 10.4.7.255 scope global noprefixroute ens32
       valid_lft forever preferred_lft forever
    inet 10.4.7.10/32 scope global ens32
       valid_lft forever preferred_lft forever
......
生产环境不要让vip飘来飘去

3.4. controller-manager 安装

controller-manager 涉及的服务器：hdss7-21，hdss7-22

controller-manager 设置为只调用当前机器的 apiserver，走127.0.0.1网卡，因此不配制SSL证书

[root@hdss7-21 ~]# vim /opt/apps/kubernetes/server/bin/kube-controller-manager-startup.sh
#!/bin/sh
WORK_DIR=$(dirname $(readlink -f $0))
[ $? -eq 0 ] && cd $WORK_DIR || exit

/opt/apps/kubernetes/server/bin/kube-controller-manager \
    --cluster-cidr 172.7.0.0/16 \
    --leader-elect true \
    --log-dir /data/logs/kubernetes/kube-controller-manager \
    --master http://127.0.0.1:8080 \
    --service-account-private-key-file ./certs/ca-key.pem \
    --service-cluster-ip-range 192.168.0.0/16 \
    --root-ca-file ./certs/ca.pem \
    --v 2

[root@hdss7-21 ~]# chmod u+x /opt/apps/kubernetes/server/bin/kube-controller-manager-startup.sh 
[root@hdss7-21 ~]# mkdir -p /data/logs/kubernetes/kube-controller-manager

[root@hdss7-21 ~]# vim /etc/supervisord.d/kube-controller-manager.ini
[program:kube-controller-manager-7-21]
command=/opt/apps/kubernetes/server/bin/kube-controller-manager-startup.sh                     ; the program (relative uses PATH, can take args)
numprocs=1                                                                        ; number of processes copies to start (def 1)
directory=/opt/apps/kubernetes/server/bin                                              ; directory to cwd to before exec (def no cwd)
autostart=true                                                                    ; start at supervisord start (default: true)
autorestart=true                                                                  ; retstart at unexpected quit (default: true)
startsecs=30                                                                      ; number of secs prog must stay running (def. 1)
startretries=3                                                                    ; max # of serial start failures (default 3)
exitcodes=0,2                                                                     ; 'expected' exit codes for process (default 0,2)
stopsignal=QUIT                                                                   ; signal used to kill process (default TERM)
stopwaitsecs=10                                                                   ; max num secs to wait b4 SIGKILL (default 10)
user=root                                                                         ; setuid to this UNIX account to run the program
redirect_stderr=true                                                              ; redirect proc stderr to stdout (default false)
stdout_logfile=/data/logs/kubernetes/kube-controller-manager/controller.stdout.log  ; stderr log path, NONE for none; default AUTO
stdout_logfile_maxbytes=64MB                                                      ; max # logfile bytes b4 rotation (default 50MB)
stdout_logfile_backups=4                                                          ; # of stdout logfile backups (default 10)
stdout_capture_maxbytes=1MB                                                       ; number of bytes in 'capturemode' (default 0)
stdout_events_enabled=false                                                       ; emit events on stdout writes (default false)

[root@hdss7-21 ~]# supervisorctl update
kube-controller-manager-7-21: stopped
kube-controller-manager-7-21: updated process group
[root@hdss7-21 ~]# supervisorctl status
etcd-server-7-21                 RUNNING   pid 23637, uptime 1 day, 0:16:54
kube-apiserver-7-21              RUNNING   pid 32591, uptime 1:56:23
kube-controller-manager-7-21     RUNNING   pid 33357, uptime 0:00:38

3.5. kube-scheduler安装

kube-scheduler 涉及的服务器：hdss7-21，hdss7-22

kube-scheduler 设置为只调用当前机器的 apiserver，走127.0.0.1网卡，因此不配制SSL证书

[root@hdss7-21 ~]# vim /opt/apps/kubernetes/server/bin/kube-scheduler-startup.sh
#!/bin/sh
WORK_DIR=$(dirname $(readlink -f $0))
[ $? -eq 0 ] && cd $WORK_DIR || exit

/opt/apps/kubernetes/server/bin/kube-scheduler \
    --leader-elect  \
    --log-dir /data/logs/kubernetes/kube-scheduler \
    --master http://127.0.0.1:8080 \
    --v 2
[root@hdss7-21 ~]# chmod u+x /opt/apps/kubernetes/server/bin/kube-scheduler-startup.sh
[root@hdss7-21 ~]# mkdir -p /data/logs/kubernetes/kube-scheduler

[root@hdss7-21 ~]# vim /etc/supervisord.d/kube-scheduler.ini
[program:kube-scheduler-7-21]
command=/opt/apps/kubernetes/server/bin/kube-scheduler-startup.sh                     
numprocs=1                                                               
directory=/opt/apps/kubernetes/server/bin                                     
autostart=true                                                           
autorestart=true                                                         
startsecs=30                                                             
startretries=3                                                           
exitcodes=0,2                                                            
stopsignal=QUIT                                                          
stopwaitsecs=10                                                          
user=root                                                                
redirect_stderr=true                                                     
stdout_logfile=/data/logs/kubernetes/kube-scheduler/scheduler.stdout.log 
stdout_logfile_maxbytes=64MB                                             
stdout_logfile_backups=4                                                 
stdout_capture_maxbytes=1MB                                              
stdout_events_enabled=false 

[root@hdss7-21 ~]# supervisorctl update
kube-scheduler-7-21: stopped
kube-scheduler-7-21: updated process group
[root@hdss7-21 ~]# supervisorctl status 
etcd-server-7-21                 RUNNING   pid 23637, uptime 1 day, 0:26:53
kube-apiserver-7-21              RUNNING   pid 32591, uptime 2:06:22
kube-controller-manager-7-21     RUNNING   pid 33357, uptime 0:10:37
kube-scheduler-7-21              RUNNING   pid 33450, uptime 0:01:18

3.6. 检查主控节点状态

[root@hdss7-21 ~]# ln -s /opt/apps/kubernetes/server/bin/kubectl /usr/local/bin/
[root@hdss7-21 ~]# kubectl get cs
NAME                 STATUS    MESSAGE              ERROR
scheduler            Healthy   ok                   
controller-manager   Healthy   ok                   
etcd-1               Healthy   {"health": "true"}   
etcd-0               Healthy   {"health": "true"}   
etcd-2               Healthy   {"health": "true"}   

[root@hdss7-22 ~]# ln -s /opt/apps/kubernetes/server/bin/kubectl /usr/local/bin/
[root@hdss7-22 ~]# kubectl get cs
NAME                 STATUS    MESSAGE              ERROR
controller-manager   Healthy   ok                   
scheduler            Healthy   ok                   
etcd-2               Healthy   {"health": "true"}   
etcd-1               Healthy   {"health": "true"}   
etcd-0               Healthy   {"health": "true"}