非归档模式，磁盘损坏，恢复后启动oracle 报01092错误，帮...

ALLSTARS_ORACLE

linux下，oracle9i的库，用的RAID5，非归档模式，磁盘损坏，恢复磁盘后启动oracle 报01092错误。
下面是我，startup mount;
alter database open;
后的日志文件，麻烦看下，我该怎么解决把库启起来，谢谢！
Thu Sep  7 16:03:17 2006
Starting ORACLE instance (normal)
Thu Sep  7 16:03:17 2006
WARNING: EINVAL creating segment of size 0x0000000044400000
fix shm parameters in /etc/system or equivalent
LICENSE_MAX_SESSION = 0
LICENSE_SESSIONS_WARNING = 0
SCN scheme 2
Using log_archive_dest parameter default value
LICENSE_MAX_USERS = 0
SYS auditing is disabled
Starting up ORACLE RDBMS Version: 9.2.0.4.0.
System parameters with non-default values:
  processes                = 150
  timed_statistics         = TRUE
  shared_pool_size         = 520093696
  large_pool_size          = 67108864
  java_pool_size           = 50331648
  control_files            = /oracle/oradata/game/control01.ctl, /oracle/oradata/game/control02.ctl, /oracle/oradata/game/control03.ctl
  db_block_size            = 8192
  db_cache_size            = 469762048
  compatible               = 9.2.0.0.0
  db_file_multiblock_read_count= 16
  fast_start_mttr_target   = 300
  undo_management          = AUTO
  undo_tablespace          = UNDOTBS1
  undo_retention           = 10800
  remote_login_passwordfile= EXCLUSIVE
  db_domain                =
  instance_name            = game
  dispatchers              = (PROTOCOL=TCP) (SERVICE=gameXDB)
  job_queue_processes      = 10
  hash_join_enabled        = TRUE
  background_dump_dest     = /oracle/admin/game/bdump
  user_dump_dest           = /oracle/admin/game/udump
  core_dump_dest           = /oracle/admin/game/cdump
  sort_area_size           = 2524288
  db_name                  = game
  open_cursors             = 300
  star_transformation_enabled= FALSE
  query_rewrite_enabled    = FALSE
  pga_aggregate_target     = 96000000
  aq_tm_processes          = 1
PMON started with pid=2
DBW0 started with pid=3
LGWR started with pid=4
CKPT started with pid=5
SMON started with pid=6
RECO started with pid=7
CJQ0 started with pid=8
QMN0 started with pid=9
Thu Sep  7 16:03:18 2006
starting up 1 shared server(s) ...
starting up 1 dispatcher(s) for network address '(ADDRESS=(PARTIAL=YES)(PROTOCOL=TCP))'...
Thu Sep  7 16:03:18 2006
ALTER DATABASE   MOUNT
Thu Sep  7 16:03:22 2006
Successful mount of redo thread 1, with mount id 4218342150.
Thu Sep  7 16:03:22 2006
Database mounted in Exclusive Mode.
Completed: ALTER DATABASE   MOUNT
Thu Sep  7 16:03:37 2006
alter database open
Thu Sep  7 16:03:37 2006
Beginning crash recovery of 1 threads
Thu Sep  7 16:03:37 2006
Started first pass scan
Thu Sep  7 16:03:37 2006
Completed first pass scan
1 redo blocks read, 0 data blocks need recovery
Thu Sep  7 16:03:37 2006
Started recovery at
Thread 1: logseq 27, block 2, scn 0.23773488
Recovery of Online Redo Log: Thread 1 Group 2 Seq 27 Reading mem 0
  Mem# 0 errs 0: /oracle/oradata/game/redo02.log
Thu Sep  7 16:03:37 2006
Completed redo application
Thu Sep  7 16:03:37 2006
Ended recovery at
Thread 1: logseq 27, block 3, scn 0.23793489
0 data blocks read, 0 data blocks written, 1 redo blocks read
Crash recovery completed successfully
Thu Sep  7 16:03:37 2006
Thread 1 advanced to log sequence 28
Thread 1 opened at log sequence 28
  Current log# 3 seq# 28 mem# 0: /oracle/oradata/game/redo03.log
Successful open of redo thread 1.
Thu Sep  7 16:03:37 2006
SMON: enabling cache recovery
Thu Sep  7 16:03:37 2006
Errors in file /oracle/admin/game/udump/game_ora_2135.trc:
ORA-01578: ORACLE data block corrupted (file # 2, block # 9)
ORA-01110: data file 2: '/oracle/oradata/game/undotbs01.dbf'
Thu Sep  7 16:03:37 2006
Error 1578 happened during db open, shutting down database
USER: terminating instance due to error 1578
Instance terminated by USER, pid = 2135
ORA-1092 signalled during: alter database open...


谢谢回复，库是正常shutdown的，是在启动startup的时候（还没有启动完毕），一块硬盘出问题，IBM的工程师也在，当时还有一块硬盘在做raid5的同步恢复，这个时候启动就报I/O的错误。等raid5的硬盘同步恢复好了，再启动就报01092的错误了，所以只要能启动，估计不会有数据丢失！



应该是undo 的block损坏了，不知道怎么忽略它，启动数据库