hello， 当我安装lustre的ost端的时候，出现这个问题

[root@de78 ~]# mkfs.lustre --fsname=hust --ost --mgsnode=192.168.2.78@o2ib0 /dev/sdc2

   Permanent disk data:
Target:     hust-OSTffff
Index:      unassigned
Lustre FS:  hust
Mount type: ldiskfs
Flags:      0x72
              (OST needs_index first_time update )
Persistent mount opts: errors=remount-ro,extents,mballoc
Parameters: mgsnode=192.168.2.78@o2ib

checking for existing Lustre data: not found
device size = 41362MB
2 6 18
formatting backing filesystem ldiskfs on /dev/sdc2
     target name  hust-OSTffff
     4k blocks     10588843
     options        -J size=400 -i 16384 -I 256 -q -O dir_index,extents,uninit_groups -F
mkfs_cmd = mke2fs -j -b 4096 -L hust-OSTffff  -J size=400 -i 16384 -I 256 -q -O dir_index,extents,uninit_groups -F /dev/sdc2 10588843
mkfs.lustre: Can't make configs dir /tmp/mntPiNPcO/CONFIGS: Input/output error

mkfs.lustre FATAL: failed to write local files
mkfs.lustre: exiting with -1 (Unknown error 18446744073709551615)

日志如下/var/log/messages:

2634 Jun 27 09:11:40 de78 kernel: kjournald starting.  Commit interval 5 seconds
2635 Jun 27 09:11:40 de78 kernel: LDISKFS FS on sdc2, internal journal
2636 Jun 27 09:11:40 de78 kernel: LDISKFS-fs: mounted filesystem with ordered data mode.
2637 Jun 27 09:11:40 de78 kernel: LDISKFS-fs: file extents enabled
2638 Jun 27 09:11:40 de78 kernel: LDISKFS-fs: mballoc enabled
2639 Jun 27 09:11:40 de78 kernel: LDISKFS-fs error (device sdc2): ldiskfs_ext_find_extent: :463     : bad header in inode #2305633: invalid magic - magic 0, entries 0, max 0(0), depth 0(0)
2640 Jun 27 09:11:40 de78 kernel: Remounting filesystem read-only
2641 Jun 27 09:11:40 de78 kernel: LDISKFS-fs error (device sdc2) in start_transaction: Readonly      filesystem
2642 Jun 27 09:11:40 de78 kernel: LDISKFS-fs: mballoc: 0 blocks 0 reqs (0 success)
2643 Jun 27 09:11:40 de78 kernel: LDISKFS-fs: mballoc: 0 extents scanned, 0 goal hits, 0 2^N hi     ts, 0 breaks, 0 lost
2644 Jun 27 09:11:40 de78 kernel: LDISKFS-fs: mballoc: 0 generated and it took 0
2645 Jun 27 09:11:40 de78 kernel: LDISKFS-fs: mballoc: 0 preallocated, 0 discarded

已经安装的软件：

[root@de78 lustre安装]#  rpm -qa | grep lustre
lustre-ldiskfs-3.1.6-2.6.18_194.17.1.el5_lustre.1.8.7
lustre-modules-1.8.7-2.6.18_194.17.1.el5_lustre.1.8.7
kernel-2.6.18-194.17.1.el5_lustre.1.8.7
lustre-1.8.7-2.6.18_194.17.1.el5_lustre.1.8.7
[root@de78 lustre安装]#  rpm -qa | grep e2fsprogs
e2fsprogs-devel-1.39-23.el5
e2fsprogs-libs-1.39-23.el5
e2fsprogs-1.42.ora1-0redhat

不知道为什么会出现-1的错误，lustre里面应该是权限不够的意思，但是指什么呢？我装mds是好好的，不知道为什么装ost就会出现问题 已经困扰了好几天了，真心求教啊~