ubuntu 16.04快速安装ceph集群

准备工作

1. 假设集群: 选一台作管理机
   注意: ceph集群引用hostname,而非ip.

   172.17.4.16 test16 #hostname必须是test16
   172.17.4.17 test17 #hostname必须是test17
   172.17.4.18 test18 #hostname必须是test18
   172.17.4.19 test19 #hostname必须是test19, 选作管理机
   172.17.4.20 test20 #hostname必须是test20
   172.17.4.21 test21 #hostname必须是test21
   172.17.4.22 test22 #hostname必须是test22
   

2. 安装用户
   注意: 建议不要使用"ceph",因为"apt install ceph"需要使用ceph. 用root最省事 ^_

   root@test19:~# ssh-keygen #创建安装用rsa,安装完记得删除
   
   root@test19:~# less .ssh/id_rsa.pub 
   ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQDZAQ8ikono13kGzRLpyx1BCRfzICieEKg27WABW+2eFkYXmbvzLSu8XkmC3a0x7M0ADd2aW2FGv8ZtxPgHMRFzyaeoXwGZUFU5zmd9CASglHibKlWzdUgl5sW/DSdSxFYs+ooQvZcKSMmbFYlo70Ndv5kHja2FEMKnLexJpox4fFb9Rv1KEez0p1j28iICc3nHXLAZigezKkaFiv/Wfk/g59nk6ZCNAr1UnDvTdQOnVTIu6Q6UkpoiDx3+R5oeWRynI2l6T/bhrMpubO5PaluFKvas0DF3eGZLf2XQPR8sYzt7PkOGC1QANi7D11UxTqurZF8Meb0LdH0KEqE1kH7z root@cadmin
   
   # 在各台机执行,authorized_keys必须是600
   mkdir /root/.ssh
   echo -n 'ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQDZAQ8ikono13kGzRLpyx1BCRfzICieEKg27WABW+2eFkYXmbvzLSu8XkmC3a0x7M0ADd2aW2FGv8ZtxPgHMRFzyaeoXwGZUFU5zmd9CASglHibKlWzdUgl5sW/DSdSxFYs+ooQvZcKSMmbFYlo70Ndv5kHja2FEMKnLexJpox4fFb9Rv1KEez0p1j28iICc3nHXLAZigezKkaFiv/Wfk/g59nk6ZCNAr1UnDvTdQOnVTIu6Q6UkpoiDx3+R5oeWRynI2l6T/bhrMpubO5PaluFKvas0DF3eGZLf2XQPR8sYzt7PkOGC1QANi7D11UxTqurZF8Meb0LdH0KEqE1kH7z' > /root/.ssh/authorized_keys && chmod 600 /root/.ssh/authorized_keys
   

测试用户
```
#在test19无密ssh
for node in 16 17 18 19 20 21 22; do
ssh test$node echo 123;
done;

    #确认yes
    The authenticity of host 'test22 (172.17.4.22)' can't be established.
    ECDSA key fingerprint is SHA256:6S9mp0m8bV15bKX9RugP2CflINUvxORw82yCwJqVyrE.
    Are you sure you want to continue connecting (yes/no)? yes
    
```
完成后记得将/root/.ssh/id_rsa从test19移除并妥善保管,以后可以用来维护集群.

2. 更新源

   root@test19: for node in 16 17 18 19 20 21 22; do
   ssh test$node \
   wget -q -O- https://download.ceph.com/keys/release.asc | sudo apt-key add -;\
   echo deb https://download.ceph.com/debian-jewel/ $(lsb_release -sc) main | sudo tee /etc/apt/sources.list.d/ceph.list;\
   apt update && apt -y dist-upgrade && apt -y autoremove;
   done
   
   #apt使用-y默认Yes
   

3. 安装ceph-deploy

   root@test19: apt install ceph-deploy
   

   注意: 16.04下这二个版本都有bug.

   • 1.5.32在执行ceph-deploy mon create-initial命令后生成的ceph.client.admin.keyring文件是空的!
   • 1.5.34则在重装时不会替换/var/lib/ceph/bootstrap-osd/ceph.keyring, 造成ceph-deploy osd activate失败.

   root@test19:~# apt-cache policy ceph-deploy
   ceph-deploy:
     Installed: 1.5.34
     Candidate: 1.5.34
     Version table:
    *** 1.5.34 999
           999 https://download.ceph.com/debian-jewel xenial/main amd64 Packages
           999 https://download.ceph.com/debian-jewel xenial/main i386 Packages
           100 /var/lib/dpkg/status
        1.5.32-0ubuntu1 500
           500 http://hk.archive.ubuntu.com/ubuntu xenial/universe amd64 Packages
           500 http://hk.archive.ubuntu.com/ubuntu xenial/universe i386 Packages
   

安装过程

参考: INSTALLATION (QUICK)

1. 创建管理目录

   root@test19:~# mkdir ceph-admin
   root@test19:~# cd ceph-admin/
   

2. 初始配置

   root@test19:~/ceph-admin# ceph-deploy new test16 test17
       
   drwxr-xr-x 2 root root 4096 Sep 14 10:28 ./
   drwx------ 6 root root 4096 Sep 14 10:28 ../
   -rw-r--r-- 1 root root  215 Sep 14 10:28 ceph.conf
   -rw-r--r-- 1 root root 4080 Sep 14 10:28 ceph-deploy-ceph.log
   -rw------- 1 root root   73 Sep 14 10:28 ceph.mon.keyring
   
   root@test19:~/ceph-admin# vi ceph.conf 
   [global]
   fsid = c96ee478-4df7-4100-9792-c078cf44b3c4
   mon_initial_members = test16, test17
   mon_host = 172.17.4.16,172.17.4.17
   auth_cluster_required = cephx
   auth_service_required = cephx
   auth_client_required = cephx
   
   public_network = 172.17.4.0/24
   cluster_network = 172.17.4.0/24
   # 以下是针对ext4的bug
   osd_max_object_name_len = 256
   osd_max_object_namespace_len = 64
   osd_check_max_object_name_len_on_startup = false
   

   需要注意: jewel 10.2.1对EXT4格式有个文件名长度BUG!

3. 安装ceph

    root@test19:~/ceph-admin# for node in 16 17 18 19 20 21 22; do ceph-deploy install test$node; done;
   

4. 创建初始mon结点

   root@test19:~/ceph-admin# ceph-deploy mon create-initial
   

5. 创建激活osd结点, 去掉16,17

   root@test19:~/ceph-admin# for node in 18 19 20 21 22; do ssh  test$node 'mkdir -R /data/ceph/osd; chown ceph:ceph -R /data/ceph; rm -rf /data/ceph/osd/*'; ceph-deploy osd prepare test$node:/data/ceph/osd; ceph-deploy osd activate test$node:/data/ceph/osd; done;
   

6. 分发管理配置

   root@test19:~/ceph-admin# for node in 16 17 18 19 20 21 22; do ceph-deploy admin test$node; ssh test$node 'chmod a+r /etc/ceph/ceph.client.admin.keyring'; done;
   

如果上述步骤需要重试,可以执行下述清理:
root@test19:~/ceph-admin# ceph-deploy purgedata test16 test17 test18 test19 test20 test21 test22 root@test19:~/ceph-admin# ceph-deploy forgetkeys root@test19:~/ceph-admin# for node in 16 17 18 19 20 21 22; do ssh test$node rm -rf /data/ceph/osd/*; done;
另外, 重试命令需要带上"--overwrite-conf"选项!

7. 测试集群是否安装成功

   root@test19:~/ceph-admin# ceph -s
   
   root@test19:~/ceph-admin# ceph osd tree
   
   root@test19:~/ceph-admin# ceph osd perf