故障環境還原
GlusterFS叢集系統一共有4個節點，叢集資訊如下
# 分别在各個節點上配置hosts、同步好系統時間，關閉防火牆和selinux
[root@glusterfs-master-8 ~]# tail -4 /etc/hosts
192.168.0.9 glusterfs-slave-9
192.168.0.6 k8s-node-6
192.168.0.7 k8s-node-7
192.168.0.10 client
------------------------------------------------------------------------------------
# 分别在四個節點機上使用df建立一個虛拟分區，然後在這個分區上建立存儲目錄
# dd指令建立一個虛拟分區出來，格式化并挂載到/data目錄下
[root@glusterfs-master-8 ~]# dd if=/dev/sda2 of=/dev/vdb1
[root@glusterfs-master-8 ~]# mkfs.xfs -f /dev/vdb1 //這裡格式成xfs格式檔案，也可以格式化成ext4格式的。
meta-data=/dev/vdb1 isize=512 agcount=4, agsize=65536 blks
= sectsz=512 attr=2, projid32bit=1
= crc=1 finobt=0, sparse=0
data = bsize=4096 blocks=262144, imaxpct=25
= sunit=0 swidth=0 blks
naming =version 2 bsize=4096 ascii-ci=0 ftype=1
log =internal log bsize=4096 blocks=2560, version=2
= sectsz=512 sunit=0 blks, lazy-count=1
realtime =none extsz=4096 blocks=0, rtextents=0
[root@glusterfs-master-8 ~]# mkdir /data
[root@glusterfs-master-8 ~]# mount /dev/vdb1 /data
[root@glusterfs-master-8 ~]# df -h |grep data
/dev/loop0 979M 33M 947M 4% /data
# 設定開機自動挂載
[root@GlusterFS-master ~]# echo '/dev/loop0 /data xfs defaults 1 2' >> /etc/fstab
記住：以上操作要在四台節點機器上都要執行一遍，即建立存儲目錄環境！
----------------------------------------------------------------------------------
# 部署glusterfs叢集的中間部分操作在此省略,可看資料存儲的glusterfs目錄
# 建立叢集，在GlusterFS-master節點上操作：
[root@GlusterFS-master ~]# gluster peer probe 192.168.0.9
peer probe: success.
[root@GlusterFS-master ~]# gluster peer probe 192.168.0.7
peer probe: success.
[root@GlusterFS-master ~]# gluster peer probe 192.168.0.6
peer probe: success.
# 檢視叢集情況
[root@glusterfs-master-8 ~]# gluster peer status
Number of Peers: 3
Hostname: glusterfs-slave-9
Uuid: e8a38fe1-aa9c-4330-9508-eed66b8f3da6
State: Peer in Cluster (Connected)
Hostname: 192.168.0.6
Uuid: 853633be-32e8-44bd-ba17-6a687f86d59b
State: Peer in Cluster (Connected)
Hostname: 192.168.0.7
Uuid: ee258b68-4e58-4757-8398-1e520c49b734
State: Peer in Cluster (Connected)
#建立副本卷
[root@GlusterFS-master ~]# gluster volume info
No volumes present
[root@GlusterFS-master ~]# gluster volume create models replica 2 192.168.0.8:/data/gluster 192.168.0.9:/data/gluster force
[root@GlusterFS-master ~]# gluster volume list
models
[root@glusterfs-master-8 ~]# gluster volume info
Volume Name: models
Type: Distributed-Replicate
Volume ID: ef9816b9-8b40-4c31-b10f-c2898656e5b1
Status: Started
Number of Bricks: 2 x 2 = 4
Transport-type: tcp
Bricks:
Brick1: 192.168.0.8:/opt/gluster/data
Brick2: 192.168.0.9:/opt/gluster/data
Brick3: 192.168.0.6:/opt/gluster/data
Brick4: 192.168.0.7:/opt/gluster/data
Options Reconfigured:
performance.write-behind: on
performance.io-thread-count: 32
performance.flush-behind: on
performance.cache-size: 128MB
features.quota: on
#啟動models卷
[root@GlusterFS-master ~]# gluster volume start models
volume start: models: success
[root@glusterfs-master-8 ~]# gluster volume status models
Status of volume: models
Gluster process Port Online Pid
------------------------------------------------------------------------------
Brick 192.168.0.8:/opt/gluster/data 49152 Y 40994
Brick 192.168.0.9:/opt/gluster/data 49152 Y 40666
Brick 192.168.0.6:/opt/gluster/data 49152 Y 19081
Brick 192.168.0.7:/opt/gluster/data 49152 Y 17882
NFS Server on localhost N/A N N/A
Self-heal Daemon on localhost N/A Y 41013
Quota Daemon on localhost N/A Y 41020
NFS Server on glusterfs-slave-9 N/A N N/A
Self-heal Daemon on glusterfs-slave-9 N/A Y 40687
Quota Daemon on glusterfs-slave-9 N/A Y 40688
NFS Server on 192.168.0.7 2049 Y 17895
Self-heal Daemon on 192.168.0.7 N/A Y 17901
Quota Daemon on 192.168.0.7 N/A Y 17908
NFS Server on 192.168.0.6 2049 Y 19094
Self-heal Daemon on 192.168.0.6 N/A Y 19100
Quota Daemon on 192.168.0.6 N/A Y 19107
Task Status of Volume models
------------------------------------------------------------------------------
Task : Rebalance
ID : 1ad408fc-7a3b-4b3a-b7f5-27ea696e592c
Status : completed
#将另外兩個節點追加到叢集中。即卷擴容
[root@GlusterFS-master ~]# gluster volume add-brick models 192.168.0.6:/data/gluster 192.168.0.7:/data/gluster force
[root@glusterfs-master-8 ~]# gluster volume info
Volume Name: models
Type: Distributed-Replicate
Volume ID: ef9816b9-8b40-4c31-b10f-c2898656e5b1
Status: Started
Number of Bricks: 2 x 2 = 4
Transport-type: tcp
Bricks:
Brick1: 192.168.0.8:/opt/gluster/data
Brick2: 192.168.0.9:/opt/gluster/data
Brick3: 192.168.0.6:/opt/gluster/data
Brick4: 192.168.0.7:/opt/gluster/data
Options Reconfigured:
performance.write-behind: on
performance.io-thread-count: 32
performance.flush-behind: on
performance.cache-size: 128MB
features.quota: on
測試Gluster卷
#用戶端挂載glusterfs
[root@Client ~]# mount -t glusterfs 192.168.0.8:models /opt/gfsmount
[root@Client gfsmount]# df -h
........
192.168.10.239:models 2.0G 65M 2.0G 4% /opt/gfsmount
[root@Client ~]# cd /opt/gfsmount/
[root@Client gfsmount]# ls
[root@Client gfsmount]#
#寫入測試資料
[root@Client gfsmount]# for i in `seq -w 1 100`; do cp -rp /var/log/messages /opt/gfsmount/copy-test-$i; done
[root@Client gfsmount]# ls /opt/gfsmount/
copy-test-001 copy-test-014 copy-test-027 copy-test-040 copy-test-053 copy-test-066 copy-test-079 copy-test-092
copy-test-002 copy-test-015 copy-test-028 copy-test-041 copy-test-054 copy-test-067 copy-test-080 copy-test-093
copy-test-003 copy-test-016 copy-test-029 copy-test-042 copy-test-055 copy-test-068 copy-test-081 copy-test-094
copy-test-004 copy-test-017 copy-test-030 copy-test-043 copy-test-056 copy-test-069 copy-test-082 copy-test-095
copy-test-005 copy-test-018 copy-test-031 copy-test-044 copy-test-057 copy-test-070 copy-test-083 copy-test-096
copy-test-006 copy-test-019 copy-test-032 copy-test-045 copy-test-058 copy-test-071 copy-test-084 copy-test-097
copy-test-007 copy-test-020 copy-test-033 copy-test-046 copy-test-059 copy-test-072 copy-test-085 copy-test-098
copy-test-008 copy-test-021 copy-test-034 copy-test-047 copy-test-060 copy-test-073 copy-test-086 copy-test-099
copy-test-009 copy-test-022 copy-test-035 copy-test-048 copy-test-061 copy-test-074 copy-test-087 copy-test-100
copy-test-010 copy-test-023 copy-test-036 copy-test-049 copy-test-062 copy-test-075 copy-test-088
copy-test-011 copy-test-024 copy-test-037 copy-test-050 copy-test-063 copy-test-076 copy-test-089
copy-test-012 copy-test-025 copy-test-038 copy-test-051 copy-test-064 copy-test-077 copy-test-090
copy-test-013 copy-test-026 copy-test-039 copy-test-052 copy-test-065 copy-test-078 copy-test-091
[root@Client gfsmount]# ls -lA /opt/gfsmount|wc -l
101
在各節點機器上也确認下，發現這100個檔案随機地各自分為了兩個50份的檔案（均衡），分别同步到了第1-2節點和第3-4節點上了。
[root@GlusterFS-master ~]# ls /data/gluster
copy-test-001 copy-test-016 copy-test-028 copy-test-038 copy-test-054 copy-test-078 copy-test-088 copy-test-100
copy-test-004 copy-test-017 copy-test-029 copy-test-039 copy-test-057 copy-test-079 copy-test-090
copy-test-006 copy-test-019 copy-test-030 copy-test-041 copy-test-060 copy-test-081 copy-test-093
copy-test-008 copy-test-021 copy-test-031 copy-test-046 copy-test-063 copy-test-082 copy-test-094
copy-test-011 copy-test-022 copy-test-032 copy-test-048 copy-test-065 copy-test-083 copy-test-095
copy-test-012 copy-test-023 copy-test-033 copy-test-051 copy-test-073 copy-test-086 copy-test-098
copy-test-015 copy-test-024 copy-test-034 copy-test-052 copy-test-077 copy-test-087 copy-test-099
[root@GlusterFS-master ~]# ll /data/gluster|wc -l
51
[root@GlusterFS-slave ~]# ls /data/gluster/
copy-test-001 copy-test-016 copy-test-028 copy-test-038 copy-test-054 copy-test-078 copy-test-088 copy-test-100
copy-test-004 copy-test-017 copy-test-029 copy-test-039 copy-test-057 copy-test-079 copy-test-090
copy-test-006 copy-test-019 copy-test-030 copy-test-041 copy-test-060 copy-test-081 copy-test-093
copy-test-008 copy-test-021 copy-test-031 copy-test-046 copy-test-063 copy-test-082 copy-test-094
copy-test-011 copy-test-022 copy-test-032 copy-test-048 copy-test-065 copy-test-083 copy-test-095
copy-test-012 copy-test-023 copy-test-033 copy-test-051 copy-test-073 copy-test-086 copy-test-098
copy-test-015 copy-test-024 copy-test-034 copy-test-052 copy-test-077 copy-test-087 copy-test-099
[root@GlusterFS-slave ~]# ll /data/gluster/|wc -l
51
[root@GlusterFS-slave2 ~]# ls /data/gluster/
copy-test-002 copy-test-014 copy-test-036 copy-test-047 copy-test-059 copy-test-069 copy-test-080 copy-test-097
copy-test-003 copy-test-018 copy-test-037 copy-test-049 copy-test-061 copy-test-070 copy-test-084
copy-test-005 copy-test-020 copy-test-040 copy-test-050 copy-test-062 copy-test-071 copy-test-085
copy-test-007 copy-test-025 copy-test-042 copy-test-053 copy-test-064 copy-test-072 copy-test-089
copy-test-009 copy-test-026 copy-test-043 copy-test-055 copy-test-066 copy-test-074 copy-test-091
copy-test-010 copy-test-027 copy-test-044 copy-test-056 copy-test-067 copy-test-075 copy-test-092
copy-test-013 copy-test-035 copy-test-045 copy-test-058 copy-test-068 copy-test-076 copy-test-096
[root@GlusterFS-slave2 ~]# ll /data/gluster/|wc -l
51
[root@GlusterFS-slave3 ~]# ls /data/gluster/
copy-test-002 copy-test-014 copy-test-036 copy-test-047 copy-test-059 copy-test-069 copy-test-080 copy-test-097
copy-test-003 copy-test-018 copy-test-037 copy-test-049 copy-test-061 copy-test-070 copy-test-084
copy-test-005 copy-test-020 copy-test-040 copy-test-050 copy-test-062 copy-test-071 copy-test-085
copy-test-007 copy-test-025 copy-test-042 copy-test-053 copy-test-064 copy-test-072 copy-test-089
copy-test-009 copy-test-026 copy-test-043 copy-test-055 copy-test-066 copy-test-074 copy-test-091
copy-test-010 copy-test-027 copy-test-044 copy-test-056 copy-test-067 copy-test-075 copy-test-092
copy-test-013 copy-test-035 copy-test-045 copy-test-058 copy-test-068 copy-test-076 copy-test-096
[root@GlusterFS-slave3 ~]# ll /data/gluster/|wc -l
51
模拟brick故障
1）檢視目前存儲狀态
在GlusterFS-slave3節點機器上操作
[root@GlusterFS-slave3 ~]# gluster volume status
Status of volume: models
Gluster process Port Online Pid
------------------------------------------------------------------------------
Brick 192.168.10.239:/data/gluster 49156 Y 16040
Brick 192.168.10.212:/data/gluster 49157 Y 5544
Brick 192.168.10.204:/data/gluster 49157 Y 12432
Brick 192.168.10.220:/data/gluster 49158 Y 17678
NFS Server on localhost N/A N N/A
Self-heal Daemon on localhost N/A Y 17697
NFS Server on GlusterFS-master N/A N N/A
Self-heal Daemon on GlusterFS-master N/A Y 16104
NFS Server on 192.168.10.204 N/A N N/A
Self-heal Daemon on 192.168.10.204 N/A Y 12451
NFS Server on 192.168.10.212 N/A N N/A
Self-heal Daemon on 192.168.10.212 N/A Y 5593
Task Status of Volume models
------------------------------------------------------------------------------
There are no active volume tasks
注：注意到Online項全部為"Y"
2）制造故障（注意這裡模拟的是檔案系統故障，假設實體硬碟沒有問題或已經更換陣列中的硬碟）
在GlusterFS-slave3節點機器上操作
[root@GlusterFS-slave3 ~]# vim /etc/fstab //注釋掉如下行
......
#/dev/loop0 /data xfs defaults 1 2
#重新開機伺服器
[root@GlusterFS-slave3 ~]# reboot
#重新開機後，發現GlusterFS-slave3節點的/data沒有挂載上
[root@GlusterFS-slave3 ~]# df -h
#重新開機後，發現GlusterFS-slave3節點的存儲目錄不在了，資料沒有了。
[root@GlusterFS-slave3 ~]# ls /data/
[root@GlusterFS-slave3 ~]#
#重新開機伺服器後，記得啟動glusterd服務
[root@GlusterFS-slave3 ~]# /usr/local/glusterfs/sbin/glusterd
[root@GlusterFS-slave3 ~]# ps -ef|grep gluster
root 11122 1 4 23:13 ? 00:00:00 /usr/local/glusterfs/sbin/glusterd
root 11269 1 2 23:13 ? 00:00:00 /usr/local/glusterfs/sbin/glusterfs -s localhost --volfile-id gluster/glustershd -p /usr/local/glusterfs/var/lib/glusterd/glustershd/run/glustershd.pid -l /usr/local/glusterfs/var/log/glusterfs/glustershd.log -S /var/run/98e3200bc6620c9d920e9dc65624dbe0.socket --xlator-option *replicate*.node-uuid=dd99743a-285b-4aed-b3d6-e860f9efd965
root 11280 5978 0 23:13 pts/0 00:00:00 grep --color=auto gluster
3）檢視目前存儲狀态
[root@GlusterFS-slave3 ~]# gluster volume status
Status of volume: models
Gluster process Port Online Pid
------------------------------------------------------------------------------
Brick 192.168.10.239:/data/gluster 49156 Y 16040
Brick 192.168.10.212:/data/gluster 49157 Y 5544
Brick 192.168.10.204:/data/gluster 49157 Y 12432
Brick 192.168.10.220:/data/gluster N/A N N/A
NFS Server on localhost N/A N N/A
Self-heal Daemon on localhost N/A Y 11269
NFS Server on GlusterFS-master N/A N N/A
Self-heal Daemon on GlusterFS-master N/A Y 16104
NFS Server on 192.168.10.212 N/A N N/A
Self-heal Daemon on 192.168.10.212 N/A Y 5593
NFS Server on 192.168.10.204 N/A N N/A
Self-heal Daemon on 192.168.10.204 N/A Y 12451
Task Status of Volume models
------------------------------------------------------------------------------
There are no active volume tasks
注意：發現GlusterFS-slave3節點（192.168.10.220）的Online項狀态為"N"了！
4）恢複故障brick方法
4.1）結束故障brick的程序
如上通過"gluster volume status"指令，如果檢視到狀态Online項為"N"的GlusterFS-slave3節點存在PID号（不顯示N/A）,則應當使用"kill -15 pid"殺死它！
一般當Online項為"N"時就不顯示pid号了。
4.2）建立新的資料目錄（注意絕不可以與之前目錄一樣）
[root@GlusterFS-slave3 ~]# dd if=/dev/vda1 of=/dev/vdb1
2097152+0 records in
2097152+0 records out
1073741824 bytes (1.1 GB) copied, 2.05684 s, 522 MB/s
[root@GlusterFS-slave3 ~]# du -sh /dev/vdb1
1.0G /dev/vdb1
[root@GlusterFS-slave3 ~]# mkfs.xfs -f /dev/vdb1
meta-data=/dev/vdb1 isize=512 agcount=4, agsize=65536 blks
= sectsz=512 attr=2, projid32bit=1
= crc=1 finobt=0, sparse=0
data = bsize=4096 blocks=262144, imaxpct=25
= sunit=0 swidth=0 blks
naming =version 2 bsize=4096 ascii-ci=0 ftype=1
log =internal log bsize=4096 blocks=2560, version=2
= sectsz=512 sunit=0 blks, lazy-count=1
realtime =none extsz=4096 blocks=0, rtextents=0
重新挂載
[root@GlusterFS-slave3 ~]# mount /dev/vdb1 /data
[root@GlusterFS-slave3 ~]# vim /etc/fstab //去掉下面注釋
......
/dev/loop0 /data xfs defaults 1 2
4.3）查詢故障節點的備份節點(GlusterFS-slave2)目錄的擴充屬性（使用"yum search getfattr"指令getfattr工具的安裝途徑）
[root@GlusterFS-slave2 ~]# yum install -y attr.x86_64
[root@GlusterFS-slave2 ~]# getfattr -d -m. -e hex /data/gluster
getfattr: Removing leading '/' from absolute path names
# file: data/gluster
trusted.gfid=0x00000000000000000000000000000001
trusted.glusterfs.dht=0x00000001000000007fffffffffffffff
trusted.glusterfs.volume-id=0x8eafb261e0d24f3b8e0905475c63dcc6
4.4）挂載卷并觸發自愈
在用戶端先解除安裝掉之前的挂載
[root@Client ~]# umount /data/gluster
然後重新挂載GlusterFS-slave3（其實挂載哪一個節點的都可以）
[root@Client ~]# mount -t glusterfs 192.168.10.220:models /opt/gfsmount
[root@Client ~]# df -h
.......
192.168.10.220:models 2.0G 74M 2.0G 4% /opt/gfsmount
建立一個卷中不存在的目錄并删除
[root@Client ~]# cd /opt/gfsmount/
[root@Client gfsmount]# mkdir testDir001
[root@Client gfsmount]# rm -rf testDir001
設定擴充屬性觸發自愈
[root@Client gfsmount]# setfattr -n trusted.non-existent-key -v abc /opt/gfsmount
[root@Client gfsmount]# setfattr -x trusted.non-existent-key /opt/gfsmount
4.5）檢查目前節點是否挂起xattrs
再次查詢故障節點的備份節點(GlusterFS-slave2)目錄的擴充屬性
[root@GlusterFS-slave2 ~]# getfattr -d -m. -e hex /data/gluster
getfattr: Removing leading '/' from absolute path names
# file: data/gluster
trusted.afr.dirty=0x000000000000000000000000
trusted.afr.models-client-2=0x000000000000000000000000
trusted.afr.models-client-3=0x000000000000000200000002
trusted.gfid=0x00000000000000000000000000000001
trusted.glusterfs.dht=0x00000001000000007fffffffffffffff
trusted.glusterfs.volume-id=0x8eafb261e0d24f3b8e0905475c63dcc6
注意：留意第5行,表示xattrs已經将源标記為GlusterFS-slave3:/data/gluster
4.6）檢查卷的狀态是否顯示需要替換
[root@GlusterFS-slave3 ~]# gluster volume heal models info
Brick GlusterFS-master:/data/gluster/
Number of entries: 0
Brick GlusterFS-slave:/data/gluster/
Number of entries: 0
Brick GlusterFS-slave2:/data/gluster/
/
Number of entries: 1
Brick 192.168.10.220:/data/gluster
Status: Transport endpoint is not connected
注：狀态提示傳輸端點未連接配接（最後一行）
4.7）使用強制送出完成操作
[root@GlusterFS-slave3 ~]# gluster volume replace-brick models 192.168.10.220:/data/gluster 192.168.10.220:/data/gluster1 commit force
提示如下表示正常完成：
volume replace-brick: success: replace-brick commit force operation successful
-------------------------------------------------------------------------------------
注意：也可以将資料恢複到另外一台伺服器，詳細指令如下（192.168.10.230為新增的另一個glusterfs節點）（可選）：
# gluster peer probe 192.168.10.230
# gluster volume replace-brick models 192.168.10.220:/data/gluster 192.168.10.230:/data/gluster commit force
-------------------------------------------------------------------------------------
4.8）檢查存儲的線上狀态
[root@GlusterFS-slave3 ~]# gluster volume status
Status of volume: models
Gluster process Port Online Pid
------------------------------------------------------------------------------
Brick 192.168.10.239:/data/gluster 49156 Y 16040
Brick 192.168.10.212:/data/gluster 49157 Y 5544
Brick 192.168.10.204:/data/gluster 49157 Y 12432
Brick 192.168.10.220:/data/gluster1 49159 Y 11363
NFS Server on localhost N/A N N/A
Self-heal Daemon on localhost N/A Y 11375
NFS Server on 192.168.10.204 N/A N N/A
Self-heal Daemon on 192.168.10.204 N/A Y 12494
NFS Server on 192.168.10.212 N/A N N/A
Self-heal Daemon on 192.168.10.212 N/A Y 5625
NFS Server on GlusterFS-master N/A N N/A
Self-heal Daemon on GlusterFS-master N/A Y 16161
Task Status of Volume models
------------------------------------------------------------------------------
There are no active volume tasks
從上面資訊可以看出，192.168.10.220（GlusterFS-slave3）節點的Online項的狀态為"Y"了，不過存儲目錄是/data/gluster1
這個時候，檢視GlusterFS-slave3節點的存儲目錄，發現資料已經恢複了
[root@GlusterFS-slave3 ~]# ls /data/gluster/
copy-test-002 copy-test-014 copy-test-036 copy-test-047 copy-test-059 copy-test-069 copy-test-080 copy-test-097
copy-test-003 copy-test-018 copy-test-037 copy-test-049 copy-test-061 copy-test-070 copy-test-084
copy-test-005 copy-test-020 copy-test-040 copy-test-050 copy-test-062 copy-test-071 copy-test-085
copy-test-007 copy-test-025 copy-test-042 copy-test-053 copy-test-064 copy-test-072 copy-test-089
copy-test-009 copy-test-026 copy-test-043 copy-test-055 copy-test-066 copy-test-074 copy-test-091
copy-test-010 copy-test-027 copy-test-044 copy-test-056 copy-test-067 copy-test-075 copy-test-092
copy-test-013 copy-test-035 copy-test-045 copy-test-058 copy-test-068 copy-test-076 copy-test-096
[root@GlusterFS-slave3 ~]# ll /data/gluster/|wc -l
上面模拟的故障是gluster節點的存儲目錄所在的分區挂載失敗，導緻存儲目錄不在的資料修複方法。
如果存儲目錄删除了，還可以根據文檔：http://www.cnblogs.com/kevingrace/p/8778123.html中介紹的複制卷資料故障的相關方法進行資料恢複。
![GlusterFS 安裝與配置[圖]](data:image/gif;base64,R0lGODlhAQABAIAAAP///wAAACwAAAAAAQABAAACAkQBADs=)