从故障ceph cluster中恢复rbd

r囧r小猫 2022-08-06 17:19 322阅读 0赞

# 操作环境 #

centos 6.5 x86\_64

ceph 0.87

# 操作步骤 #

本文主要介绍从故障ceph cluster中恢复rbd方法步骤：

1.创建rbd，并记录rbd信息，一定要预先保存rbd信息主要是size、block\_name\_prefix信息，这些信息用于恢复rbd使用，否则无法恢复rbd；

root@ceph-osd-2 recovery]# rbd create -s 10240 bobtest
    [root@ceph-osd-2 recovery]# rbd info bobtest
    rbd image 'bobtest':
            size 10240 MB in 2560 objects
            order 22 (4096 kB objects)
            block_name_prefix: rb.0.bcb9.238e1f29
            format: 1

2.将bobtest rbd映射到client端，写入测试数据

[root@linux-nfs ~]# rbd -p rbd map bobtest
    /dev/rbd0
    [root@linux-nfs ~]# rbd showmapped
    id pool image   snap device    
    0  rbd  bobtest -    /dev/rbd0 
    [root@linux-nfs ~]# mkfs.xfs /dev/rbd0
    log stripe unit (4194304 bytes) is too large (maximum is 256KiB)
    log stripe unit adjusted to 32KiB
    meta-data=/dev/rbd0              isize=256    agcount=17, agsize=162816 blks
             =                       sectsz=512   attr=2, projid32bit=0
    data     =                       bsize=4096   blocks=2621440, imaxpct=25
             =                       sunit=1024   swidth=1024 blks
    naming   =version 2              bsize=4096   ascii-ci=0
    log      =internal log           bsize=4096   blocks=2560, version=2
             =                       sectsz=512   sunit=8 blks, lazy-count=1
    realtime =none                   extsz=4096   blocks=0, rtextents=0
    [root@linux-nfs ~]# mount /dev/rbd0 /mnt/
    [root@linux-nfs ~]# touch /mnt/test
    [root@linux-nfs ~]# echo recovery test > /mnt/test
    [root@linux-nfs ~]# cat /mnt/test
    recovery test

3.将bobtest rbd从client端卸载掉

[root@linux-nfs ~]# umount /mnt/
    [root@linux-nfs ~]# rbd unmap /dev/rbd0

4.在osd server中对bobtest rbd进行恢复（ceph cluster中必须有1个可用的osd server）

下载恢复rbd所需的脚本

#wget -O rbd_restore https://raw.githubusercontent.com/smmoore/ceph/master/rbd_restore.sh
    #chmod a+x rbd_restore

脚本具体如下：

#!/bin/sh
    #
    # AUTHORS
    # Shawn Moore <smmoore@catawba.edu>
    # Rodney Rymer <rrr@catawba.edu>
    #
    #
    # REQUIREMENTS
    # GNU Awk (gawk)
    #
    #
    # NOTES
    # This utility assumes one copy of all object files needed to construct the rbd
    # are located in the present working direcory at the time of execution.
    # For example all the rb.0.1032.5e69c215.* files.
    #
    # When listing the "RBD_SIZE_IN_BYTES", be sure you list the full potential size,
    # not just what it appears to be. If you do not know the true size of the rbd,
    # you can input a size in bytes that you know is larger than the disk could be
    # and it will be a large sparse file with un-partioned space at the end of the
    # disk.  In our tests, this doesn't occupy any more space/objects in the cluster
    # but the rbd could be resized from within the rbd (VM) to grow.  Once you bring
    # it up and are able to find the true size, you can resize with "rbd resize ..".
    "recovery/rbd_restore" 73L, 2771C
    #!/bin/sh
    #
    # AUTHORS
    # Shawn Moore <smmoore@catawba.edu>
    # Rodney Rymer <rrr@catawba.edu>
    #
    #
    # REQUIREMENTS
    # GNU Awk (gawk)
    #
    #
    # NOTES
    # This utility assumes one copy of all object files needed to construct the rbd
    # are located in the present working direcory at the time of execution.
    # For example all the rb.0.1032.5e69c215.* files.
    #
    # When listing the "RBD_SIZE_IN_BYTES", be sure you list the full potential size,
    # not just what it appears to be. If you do not know the true size of the rbd,
    # you can input a size in bytes that you know is larger than the disk could be
    # and it will be a large sparse file with un-partioned space at the end of the
    # disk.  In our tests, this doesn't occupy any more space/objects in the cluster
    # but the rbd could be resized from within the rbd (VM) to grow.  Once you bring
    # it up and are able to find the true size, you can resize with "rbd resize ..".
    #
    # To obtain needed utility input information if not already known run:
    # rbd info RBD
    #
    # To find needed files we run the following command on all nodes that might have
    # copies of the rbd objects:
    # find /${CEPH} -type f -name rb.0.1032.5e69c215.*
    # Then copy the files to a single location from all nodes.  If using btrfs be
    # sure to pay attention to the btrfs snapshots that ceph takes on it's own.
    # You may want the "current" or one of the "snaps".
    #
    # We are actually taking our own btrfs snapshots cluster osd wide at the same
    # time with parallel ssh and then using "btrfs subvolume find-new" command to
    # merge them all together for disaster recovery and also outside of ceph rbd
    # versioning.
    #
    # Hopefully once the btrfs send/recv functionality is stable we can switch to it.
    #
    #
    # This utility works for us but may not for you.  Always test with non-critical
    # data first.
    #
    
    # Rados object size
    obj_size=4194304
    
    # DD bs value
    rebuild_block_size=512
    
    rbd="${1}"
    base="${2}"
    rbd_size="${3}"
    if [ "${1}" = "-h" -o "${1}" = "--help" -o "${rbd}" = "" -o "${base}" = "" -o "${rbd_size}" = "" ]; then
      echo "USAGE: $(echo ${0} | awk -F/ '{print $NF}') RESTORE_RBD BLOCK_PREFIX RBD_SIZE_IN_BYTES"
      exit 1
    fi
    base_files=$(ls -1 ${base}.* 2>/dev/null | wc -l | awk '{print $1}')
    if [ ${base_files} -lt 1 ]; then
      echo "COULD NOT FIND FILES FOR ${base} IN $(pwd)"
      exit
    fi
    
    # Create full size sparse image.  Could use truncate, but wanted
    # as few required files and dd what a must.
    dd if=/dev/zero of=${rbd} bs=1 count=0 seek=${rbd_size} 2>/dev/null
    
    for file_name in $(ls -1 ${base}.* 2>/dev/null); do
      seek_loc=$(echo ${file_name} | awk -F_ '{print $1}' | awk -v os=${obj_size} -v rs=${rebuild_block_size} -F. '{print os*strtonum("0x" $NF)/rs}')
      dd conv=notrunc if=${file_name} of=${rbd} seek=${seek_loc} bs=${rebuild_block_size} 2>/dev/null
    done

开始恢复rbd

[root@ceph-osd-2 recovery]# for block in $(find / -type f -name  rb.0.bcb9.238e1f29.*); do cp $block . ; done
    [root@ceph-osd-2 recovery]# ./rbd_restore bobtest  rb.0.bcb9.238e1f29 10737418240      #这两个参数是rbd信息，前者为block_name_prefix，后者为rbd大小（单位KB)
    [root@ceph-osd-2 recovery]# file bobtest
    bobtest: SGI XFS filesystem data (blksz 4096, inosz 256, v2 dirs)
    [root@ceph-osd-2 recovery]# du -h bobtest
    15M     bobtest

通过loop挂载bobtest

[root@ceph-osd-2 recovery]# losetup -f
    /dev/loop1
    [root@ceph-osd-2 recovery]# losetup /dev/loop1 bobtest                                                                                                    [root@ceph-osd-2 recovery]# mount /dev/loop1 /mnt/
    [root@ceph-osd-2 recovery]# ls /mnt/
    test
    [root@ceph-osd-2 recovery]# cat /mnt/test 
    recovery test

ok~~~以上就完成了在故障ceph cluster中（必须有1个可用的osd server），rbd恢复的全过程。