Shulou(Shulou.com)06/01 Report--

In this issue, the editor will bring you solutions to ORA-1172 errors caused by power outage. The article is rich in content and analyzed and described from a professional point of view. I hope you can get something after reading this article.

Due to UPS failure, the computer room lost power for many times in succession. After the problem was solved, it was found that a local test database was opened by Times error, ORA-1172, ORA-1151 error.

Try to open the database.

Let's try to open the database in EVENTS, but because the mechanism of the ORA-600 2662 error is different from that of the previous article, there is no need to set the implicit parameter _ allow_resetlogs_corruption. However, since the current version is 10g, you need to set the implicit parameter _ allow_error_simulation to true, which is the premise of using EVENTS to adjust SCN.

SQL > conn / as sysdba

Connected to an idle instance.

SQL > create pfile='/home/oracle/inittest08.ora' from spfile

File created.

Edit the initialization parameter file, add _ ALLOW_ERROR_SIMULATION=true to the file, and start the database to the mount state:

SQL > startup pfile=/home/oracle/inittest08.ora mount

ORACLE instance started.

Total System Global Area 2483027968 bytes

Fixed Size 2074760 bytes

Variable Size 1090520952 bytes

Database Buffers 1375731712 bytes

Redo Buffers 14700544 bytes

Database mounted.

Adjust the SCN through EVENTS:

SQL > alter session set events' 10015 trace name adjust_scn level 1'

Session altered.

Try to open the database below:

SQL > alter database open

Alter database open

*

ERROR at line 1:

ORA-01092: ORACLE instance terminated. Disconnection forced

Try to open it and still report an error, check the alert file again:

Errors in file / opt/ora10g/admin/test08/udump/test08_ora_6525.trc:

ORA-00600: internal error code, arguments: [2256], [0], [1073741824], [1], [2238656971], []

Thu Jun 5 16:32:01 2008

Errors in file / opt/ora10g/admin/test08/udump/test08_ora_6525.trc:

ORA-00600: internal error code, arguments: [2662], [1], [2238656973], [1], [2238756337], [8388637], [], []

Thu Jun 5 16:32:04 2008

Errors in file / opt/ora10g/admin/test08/udump/test08_ora_6525.trc:

ORA-00600: internal error code, arguments: [2662], [1], [2238656973], [1], [2238756337], [8388637], [], []

Thu Jun 5 16:32:04 2008

Error 600 happened during db open, shutting down database

USER: terminating instance due to error 600

Instance terminated by USER, pid = 6525

ORA-1092 signalled during: alter database open...

In addition to the ORA-600 2662 error just now, another 2256 error has been added. According to the description of the METALINK document Doc ID: Note:30681.1, the LEVEL of ADJUST_SCN needs to be adjusted at this time:

Multiply the value of parameter c by 4 and determine the value of LEVEL based on the range of SCN, set LEVEL to 7 as needed, and then try to open the database:

SQL > conn / as sysdba

Connected to an idle instance.

SQL > startup pfile=/home/oracle/inittest08.ora mount

ORACLE instance started.

Total System Global Area 2483027968 bytes

Fixed Size 2074760 bytes

Variable Size 1090520952 bytes

Database Buffers 1375731712 bytes

Redo Buffers 14700544 bytes

Database mounted.

SQL > alter session set events' 10015 trace name adjust_scn level 7'

Session altered.

SQL > alter database open

Alter database open

*

ERROR at line 1:

ORA-00603: ORACLE server session terminated by fatal error

The error message has changed this time. Check the alert file:

Errors in file / opt/ora10g/admin/test08/udump/test08_ora_6700.trc:

ORA-00600: internal error code, arguments: [4194], [30], [29], []

Thu Jun 5 16:43:30 2008

Errors in file / opt/ora10g/admin/test08/bdump/test08_smon_6686.trc:

ORA-00604: error occurred at recursive SQL level 1

ORA-01578: ORACLE data block corrupted (file # 1, block # 32529)

ORA-01110: data file 1:'/ data/oradata/test08/system01.dbf'

Thu Jun 5 16:43:31 2008

Errors in file / opt/ora10g/admin/test08/bdump/test08_smon_6686.trc:

ORA-00600: internal error code, arguments: [4194], [109], [98], []

Thu Jun 5 16:43:33 2008

Doing block recovery for file 2 block 133

Block recovery from logseq 531, block 60 to scn 7516192829

Thu Jun 5 16:43:33 2008

Recovery of Online Redo Log: Thread 1 Group 2 Seq 531 Reading mem 0

Mem# 0: / data/oradata/test08/redo02.log

Block recovery stopped at EOT rba 531.62.16

Block recovery completed at rba 531.62.16, scn 1.3221225531

Doing block recovery for file 2 block 5

Block recovery from logseq 531, block 60 to scn 7516192826

Thu Jun 5 16:43:33 2008

Recovery of Online Redo Log: Thread 1 Group 2 Seq 531 Reading mem 0

Mem# 0: / data/oradata/test08/redo02.log

Block recovery completed at rba 531.62.16, scn 1.3221225531

Thu Jun 5 16:43:33 2008

Errors in file / opt/ora10g/admin/test08/bdump/test08_smon_6686.trc:

ORA-01595: error freeing extent (2) of rollback segment (1))

ORA-00607: Internal error occurred while making a change to a data block

ORA-00600: internal error code, arguments: [4194], [109], [98], []

Thu Jun 5 16:43:34 2008

Doing block recovery for file 2 block 1102

Block recovery from logseq 531, block 58 to scn 7516192831

Thu Jun 5 16:43:34 2008

Recovery of Online Redo Log: Thread 1 Group 2 Seq 531 Reading mem 0

Mem# 0: / data/oradata/test08/redo02.log

Block recovery stopped at EOT rba 531.62.16

Block recovery completed at rba 531.62.16, scn 1.3221225531

Doing block recovery for file 2 block 61

Block recovery from logseq 531, block 58 to scn 7516192825

Thu Jun 5 16:43:34 2008

Recovery of Online Redo Log: Thread 1 Group 2 Seq 531 Reading mem 0

Mem# 0: / data/oradata/test08/redo02.log

Block recovery completed at rba 531.60.16, scn 1.3221225530

Thu Jun 5 16:43:34 2008

Errors in file / opt/ora10g/admin/test08/udump/test08_ora_6700.trc:

ORA-00600: internal error code, arguments: [4193], [4306], [4309], []

DEBUG: Replaying xcb 0xf0eba330, pmd 0xf3d4c360 for failed op 8

Doing block recovery for file 2 block 1085

No block recovery was needed

This time, there are ORA-600 4194 and 4193 errors, and according to the error message, there is a problem with Oracle's recovery process. Query METALINK and find that it is caused by the inconsistency between the rollback record in REDO and the UNDO. Try to open the database with the implicit parameter _ CORRUPTED_ROLLBACK_SEGMENTS. Add the following information to the inittest08.ora initialization file you just created:

Undo_management='MANUAL'

_ corrupted_rollback_segments= (_ SYSSMU1&,_SYSSMU2&,_SYSSMU3&,_SYSSMU4&,_SYSSMU5&,_SYSSMU6&,_SYSSMU7&,_SYSSMU8&,_SYSSMU9&,_SYSSMU10&,_SYSSMU11&,_SYSSMU12&,_SYSSMU13&,_SYSSMU14&,_SYSSMU15&,_SYSSMU16&,_SYSSMU17&,_SYSSMU18&,_SYSSMU19&,_SYSSMU20&,_SYSSMU21&,_SYSSMU22&,_SYSSMU23&,_SYSSMU24&,_SYSSMU25&,_SYSSMU26&,_SYSSMU27&,_SYSSMU28&,_SYSSMU29&,_SYSSMU30&,_SYSSMU31& _ SYSSMU32&,_SYSSMU33&,_SYSSMU34&,_SYSSMU35&,_SYSSMU36&,_SYSSMU37&,_SYSSMU38&,_SYSSMU39&,_SYSSMU40&,_SYSSMU41&)

Try to start the database:

SQL > conn / as sysdba

Connected to an idle instance.

SQL > startup pfile=/home/oracle/inittest08.ora

ORACLE instance started.

Total System Global Area 2483027968 bytes

Fixed Size 2074760 bytes

Variable Size 1090520952 bytes

Database Buffers 1375731712 bytes

Redo Buffers 14700544 bytes

Database mounted.

Database opened.

The successful opening of the important database, due to the use of the initialization parameter _ CORRUPTED_ROLLBACK_SEGMENTS, may lead to inconsistent state of the database, so it is likely to have caused the loss of data, but fortunately, the test database. Now you just need to export the non-system SCHEMA, build a clean database, and then import it.

In fact, the problem of record conflict between REDO and UNDO has not been solved at this time. If you close the database and try not to adapt to the implicit parameters, you will encounter the following error:

SQL > shutdown immediate

Database closed.

Database dismounted.

ORACLE instance shut down.

SQL > startup

ORACLE instance started.

Total System Global Area 2483027968 bytes

Fixed Size 2074760 bytes

Variable Size 1090520952 bytes

Database Buffers 1375731712 bytes

Redo Buffers 14700544 bytes

Database mounted.

ORA-00607: Internal error occurred while making a change to a data block

ORA-00600: internal error code, arguments: [4194], [30], [29], []

[]

SQL > shutdown immediate

ORA-03113: end-of-file on communication channel

SQL > conn / as sysdba

Connected to an idle instance.

SQL > startup pfile=/home/oracle/inittest08.ora

ORACLE instance started.

Total System Global Area 2483027968 bytes

Fixed Size 2074760 bytes

Variable Size 1090520952 bytes

Database Buffers 1375731712 bytes

Redo Buffers 14700544 bytes

Database mounted.

Database opened.

The above is the solution to the ORA-1172 error caused by the power outage shared by the editor. If you happen to have similar doubts, you might as well refer to the above analysis to understand. If you want to know more about it, you are welcome to follow the industry information channel.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.