10.1.0.2数据库在启动的时候报ORA-00600[3004]错误

SQL> startup
ORACLE 例程已经启动。
Total System Global Area 1042254360 bytes
Fixed Size 743960 bytes
Variable Size 503316480 bytes
Database Buffers 536870912 bytes
Redo Buffers 1323008 bytes
数据库装载完毕。
ORA-00600: 内部错误代码，参数: [3004], [1], [0], [0], [], [], [], []

alert日志信息

Tue Jul 15 10:57:11 2014
Database mounted in Exclusive Mode.
Completed: ALTER DATABASE   MOUNT
Tue Jul 15 10:57:12 2014
ALTER DATABASE OPEN
Tue Jul 15 10:57:12 2014
Beginning crash recovery of 1 threads
 attempting to start a parallel recovery with 3 processes
 parallel recovery started with 3 processes
Tue Jul 15 10:57:12 2014
Started first pass scan
Tue Jul 15 10:57:12 2014
Errors in file d:\oracle\product\10.1.0\admin\orcl\udump\orcl_ora_1084.trc:
ORA-00600: 内部错误代码, 参数: [3004], [1], [0], [0], [], [], [], []
Tue Jul 15 10:57:13 2014
Errors in file d:\oracle\product\10.1.0\admin\orcl\bdump\orcl_p000_3780.trc:
ORA-10388: parallel query server interrupt (failure)
Tue Jul 15 10:57:13 2014
Errors in file d:\oracle\product\10.1.0\admin\orcl\bdump\orcl_p002_3420.trc:
ORA-10388: parallel query server interrupt (failure)
Tue Jul 15 10:57:14 2014
Errors in file d:\oracle\product\10.1.0\admin\orcl\bdump\orcl_p001_3784.trc:
ORA-10388: parallel query server interrupt (failure)
Tue Jul 15 10:57:14 2014
Aborting crash recovery due to error 600
Tue Jul 15 10:57:14 2014
Errors in file d:\oracle\product\10.1.0\admin\orcl\udump\orcl_ora_1084.trc:
ORA-00600: 内部错误代码, 参数: [3004], [1], [0], [0], [], [], [], []
ORA-600 signalled during: ALTER DATABASE OPEN...

根据老杨的blog,出现该问题，很可能是crontrolfile异常导致,所以这里可以考虑通过重建控制文件或者把当前控制文件当作备份控制文件来使用

Tue Jul 15 13:42:31 2014
ALTER DATABASE RECOVER  database using backup controlfile
Tue Jul 15 13:42:31 2014
Media Recovery Start
WARNING! Recovering data file 1 from a fuzzy file. If not the current file
it might be an online backup taken without entering the begin backup command.
WARNING! Recovering data file 2 from a fuzzy file. If not the current file
it might be an online backup taken without entering the begin backup command.
WARNING! Recovering data file 3 from a fuzzy file. If not the current file
it might be an online backup taken without entering the begin backup command.
WARNING! Recovering data file 4 from a fuzzy file. If not the current file
it might be an online backup taken without entering the begin backup command.
WARNING! Recovering data file 5 from a fuzzy file. If not the current file
it might be an online backup taken without entering the begin backup command.
WARNING! Recovering data file 6 from a fuzzy file. If not the current file
it might be an online backup taken without entering the begin backup command.
WARNING! Recovering data file 7 from a fuzzy file. If not the current file
it might be an online backup taken without entering the begin backup command.
WARNING! Recovering data file 8 from a fuzzy file. If not the current file
it might be an online backup taken without entering the begin backup command.
WARNING! Recovering data file 9 from a fuzzy file. If not the current file
it might be an online backup taken without entering the begin backup command.
WARNING! Recovering data file 10 from a fuzzy file. If not the current file
it might be an online backup taken without entering the begin backup command.
WARNING! Recovering data file 11 from a fuzzy file. If not the current file
it might be an online backup taken without entering the begin backup command.
 attempting to start a parallel recovery with 3 processes
 parallel recovery started with 3 processes
Starting datafile 1 with incarnation depth 0 in thread 1 sequence 794
Datafile 1: 'D:\ORACLE\PRODUCT\10.1.0\ORADATA\ORCL\SYSTEM01.DBF'
Starting datafile 2 with incarnation depth 0 in thread 1 sequence 794
Datafile 2: 'D:\ORACLE\PRODUCT\10.1.0\ORADATA\ORCL\UNDOTBS01.DBF'
Starting datafile 3 with incarnation depth 0 in thread 1 sequence 794
Datafile 3: 'D:\ORACLE\PRODUCT\10.1.0\ORADATA\ORCL\SYSAUX01.DBF'
Starting datafile 4 with incarnation depth 0 in thread 1 sequence 794
Datafile 4: 'D:\ORACLE\PRODUCT\10.1.0\ORADATA\ORCL\USERS01.DBF'
Starting datafile 5 with incarnation depth 0 in thread 1 sequence 794
Datafile 5: 'E:\ORADB\USER1_1.ORA'
Starting datafile 6 with incarnation depth 0 in thread 1 sequence 794
Datafile 6: 'E:\ORADB\USER1_2.ORA'
Starting datafile 7 with incarnation depth 0 in thread 1 sequence 794
Datafile 7: 'E:\ORADB\USER1_3.ORA'
Starting datafile 8 with incarnation depth 0 in thread 1 sequence 794
Datafile 8: 'E:\ORADB\USER1_4.ORA'
Starting datafile 9 with incarnation depth 0 in thread 1 sequence 794
Datafile 9: 'E:\ORADB\INDEX1_1.ORA'
Starting datafile 10 with incarnation depth 0 in thread 1 sequence 794
Datafile 10: 'E:\ORADB\INDEX1_2.ORA'
Starting datafile 11 with incarnation depth 0 in thread 1 sequence 794
Datafile 11: 'E:\ORADB\TEMP1_1.ORA'
Media Recovery Log
ORA-279 signalled during: ALTER DATABASE RECOVER  database using backup cont...
Tue Jul 15 13:43:03 2014
ALTER DATABASE RECOVER    LOGFILE 'D:\ORACLE\PRODUCT\10.1.0\ORADATA\ORCL\REDO01.LOG'
Tue Jul 15 13:43:03 2014
Media Recovery Log D:\ORACLE\PRODUCT\10.1.0\ORADATA\ORCL\REDO01.LOG
Completed: ALTER DATABASE RECOVER    LOGFILE 'D:\ORACLE\PRODU
Tue Jul 15 13:43:17 2014
alter database open resetlogs
RESETLOGS after complete recovery through change 3142208
Resetting resetlogs activation ID 1378452168 (0x522982c8)
Setting recovery target incarnation to 3
Tue Jul 15 13:43:18 2014
Setting recovery target incarnation to 3
Tue Jul 15 13:43:18 2014
Flashback Database Disabled
Tue Jul 15 13:43:19 2014
Assigning activation ID 1380750902 (0x524c9636)
Maximum redo generation record size = 120832 bytes
Maximum redo generation change vector size = 116476 bytes
Private_strands 7 at log switch
Thread 1 opened at log sequence 1
  Current log# 1 seq# 1 mem# 0: D:\ORACLE\PRODUCT\10.1.0\ORADATA\ORCL\REDO01.LOG
Successful open of redo thread 1
Tue Jul 15 13:43:19 2014
MTTR advisory is disabled because FAST_START_MTTR_TARGET is not set
Tue Jul 15 13:43:19 2014
SMON: enabling cache recovery
Tue Jul 15 13:43:20 2014
Errors in file d:\oracle\product\10.1.0\admin\orcl\udump\orcl_ora_1484.trc:
ORA-00600: 内部错误代码, 参数: [2662], [0], [3142214], [0], [3142438], [8388617], [], []
Tue Jul 15 13:43:21 2014
Errors in file d:\oracle\product\10.1.0\admin\orcl\udump\orcl_ora_1484.trc:
ORA-00600: 内部错误代码, 参数: [2662], [0], [3142214], [0], [3142438], [8388617], [], []
Tue Jul 15 13:43:21 2014
Error 600 happened during db open, shutting down database
USER: terminating instance due to error 600

这里出现ORA-600[2662]因为scn相差较小,直接重启几次,然后数据库出现如下启动正常但是出现ORA-01595和ORA-00600[4194]错误

Tue Jul 15 13:48:26 2014
Starting background process MMON
Starting background process MMNL
MMON started with pid=17, OS id=2896
MMNL started with pid=18, OS id=3828
Tue Jul 15 13:48:26 2014
Block recovery completed at rba 2.90.16, scn 0.3162303
Tue Jul 15 13:48:26 2014
Errors in file d:\oracle\product\10.1.0\admin\orcl\bdump\orcl_smon_3724.trc:
ORA-01595: error freeing extent (3) of rollback segment (1))
ORA-00607: Internal error occurred while making a change to a data block
ORA-00600: internal error code, arguments: [4194], [57], [6], [], [], [], [], []
Tue Jul 15 13:48:26 2014
Completed: alter database open
Tue Jul 15 13:48:27 2014
Errors in file d:\oracle\product\10.1.0\admin\orcl\bdump\orcl_j000_2956.trc:
ORA-00600: internal error code, arguments: [4193], [1375], [1379], [], [], [], [], []

通过设置undo_management=manual,重建undo表空间解决,至此本数据库恢复完成,建议对其进行逻辑方式重建

某个客户在一台机器上装3个oracle数据库，机器蓝屏后，使用pe拷贝出来所有数据文件，redo文件，控制文件等，在尝试恢复过程中，三个库都出现同样的ORA-600[3705]错误,在以前的数据库恢复中对于redo异常，使用过N次类似方法出来都未出问题，但是在ORACLE 9.2.0.1版本中确实出现诡异现象，这里记录处理过程和大家分享
尝试恢复数据库

C:\Documents and Settings\Administrator>set oracle_sid=telnet
C:\Documents and Settings\Administrator>sqlplus/nolog
SQL*Plus: Release 9.2.0.1.0 - Production on 星期日 5月 25 13:04:29 2014
Copyright (c) 1982, 2002, Oracle Corporation.  All rights reserved.
SQL> conn / as sysdba
已连接。
SQL> select open_mode from v$database;
OPEN_MODE
----------
MOUNTED
SQL> alter database open;
alter database open
*
ERROR 位于第 1 行:
ORA-01113: 文件 2 需要介质恢复
ORA-01110: 数据文件 2: 'E:\ORACLE\ORADATA\TELNET\UNDOTBS01.DBF'
SQL> recover database;
ORA-00283: 恢复会话因错误而取消
ORA-00322: 日志 2 (线程 1) 不是当前副本
ORA-00312: 联机日志 2 线程 1: 'E:\ORACLE\ORADATA\TELNET\REDO02.LOG'

redo异常,尝试使用_allow_resetlogs_corruption参数启动数据库

SQL> startup mount pfile='c:\pfile.txt'
ORACLE 例程已经启动。
Total System Global Area  126950220 bytes
Fixed Size                   453452 bytes
Variable Size             109051904 bytes
Database Buffers           16777216 bytes
Redo Buffers                 667648 bytes
数据库装载完毕。
SQL> recover database until cancel;
ORA-00279: 更改 66763056 (在 05/12/2014 09:50:10 生成) 对于线程 1 是必需的
ORA-00289: 建议: E:\ORACLE\ORA92\RDBMS\ARC00312.001
ORA-00280: 更改 66763056 对于线程 1 是按序列 # 312 进行的
指定日志: {<RET>=suggested | filename | AUTO | CANCEL}
cancel
ORA-01547: 警告: RECOVER 成功但 OPEN RESETLOGS 将出现如下错误
ORA-01194: 文件1需要更多的恢复来保持一致性
ORA-01110: 数据文件 1: 'E:\ORACLE\ORADATA\TELNET\SYSTEM01.DBF'
ORA-01112: 未启动介质恢复
SQL> alter database open resetlogs;
alter database open resetlogs
*
ERROR 位于第 1 行:
ORA-03113: 通信通道的文件结束

查看alert日志

Sun May 25 15:35:02 2014
ALTER DATABASE RECOVER    CANCEL
ORA-1547 signalled during: ALTER DATABASE RECOVER    CANCEL  ...
Sun May 25 15:35:02 2014
ALTER DATABASE RECOVER CANCEL
ORA-1112 signalled during: ALTER DATABASE RECOVER CANCEL ...
Sun May 25 15:35:09 2014
alter database open resetlogs
RESETLOGS is being done without consistancy checks. This may result
in a corrupted database. The database should be recreated.
RESETLOGS after incomplete recovery UNTIL CHANGE 66763056
Resetting resetlogs activation ID 0 (0x0)
Sun May 25 15:35:20 2014
Assigning activation ID 2117757301 (0x7e3a6975)
Sun May 25 15:35:20 2014
Errors in file e:\oracle\admin\telnet\bdump\telnet_lgwr_12140.trc:
ORA-00600: internal error code, arguments: [3705], [1], [1], [1], [1], [], [], []
Sun May 25 15:35:56 2014
Errors in file e:\oracle\admin\telnet\bdump\telnet_lgwr_12140.trc:
ORA-00600: internal error code, arguments: [3705], [1], [1], [1], [1], [], [], []
LGWR: terminating instance due to error 600
Instance terminated by LGWR, pid = 12140

创建控制文件继续恢复

SQL> recover database until cancel;
ORA-00283: 恢复会话因错误而取消
ORA-00600: 内部错误代码，参数: [2130], [0], [1], [2], [], [], [], []
SQL> alter database backup controlfile to trace as 'c:\ctl.txt';
数据库已更改。
SQL> alter database open;
alter database open
*
ERROR 位于第 1 行:
ORA-03113: 通信通道的文件结束
SQL> startup nomount
ORACLE 例程已经启动。
Total System Global Area  126950220 bytes
Fixed Size                   453452 bytes
Variable Size             109051904 bytes
Database Buffers           16777216 bytes
Redo Buffers                 667648 bytes
SQL> CREATE CONTROLFILE REUSE DATABASE "TELNET" NORESETLOGS  NOARCHIVELOG
  2      MAXLOGFILES 50
  3      MAXLOGMEMBERS 5
  4      MAXDATAFILES 100
  5      MAXINSTANCES 1
  6      MAXLOGHISTORY 226
  7  LOGFILE
  8    GROUP 1 'E:\ORACLE\ORADATA\TELNET\REDO01.LOG'  SIZE 100M,
  9    GROUP 2 'E:\ORACLE\ORADATA\TELNET\REDO02.LOG'  SIZE 100M,
 10    GROUP 3 'E:\ORACLE\ORADATA\TELNET\REDO03.LOG'  SIZE 100M
 11  DATAFILE
 12    'E:\ORACLE\ORADATA\TELNET\SYSTEM01.DBF',
 13    'E:\ORACLE\ORADATA\TELNET\UNDOTBS01.DBF',
 14    'E:\ORACLE\ORADATA\TELNET\CWMLITE01.DBF',
 15    'E:\ORACLE\ORADATA\TELNET\DRSYS01.DBF',
 16    'E:\ORACLE\ORADATA\TELNET\EXAMPLE01.DBF',
 17    'E:\ORACLE\ORADATA\TELNET\INDX01.DBF',
 18    'E:\ORACLE\ORADATA\TELNET\ODM01.DBF',
 19    'E:\ORACLE\ORADATA\TELNET\TOOLS01.DBF',
 20    'E:\ORACLE\ORADATA\TELNET\USERS01.DBF',
 21    'E:\ORACLE\ORADATA\TELNET\XDB01.DBF'
 22  CHARACTER SET ZHS16GBK
 23  ;
控制文件已创建
SQL> recover database;
ORA-00283: 恢复会话因错误而取消
ORA-00264: 不要求恢复
SQL> alter database open;
数据库已更改。