84 DBMS_LOGMNR

Syntax

DBMS_LOGMNR.ADD_LOGFILE ( 
   LogFileName     IN VARCHAR2,
   options         IN BINARY_INTEGER default ADDFILE );

Parameters

Exceptions

Usage Notes

• Before querying the V$LOGMNR_CONTENTS view, you must make a successful call to the DBMS_LOGMNR.START_LOGMNR procedure (within the current LogMiner session).

• Unless you specify the CONTINUOUS_MINE option, the LogMiner session must be set up with a list of redo log files to be analyzed. Use the ADD_LOGFILE procedure to specify the list of redo log files to analyze.

• If you are not using the CONTINUOUS_MINE option and you want to analyze more than one redo log file, you must call the ADD_LOGFILE procedure separately for each redo log file. The redo log files do not need to be registered in any particular order.

• Both archived and online redo log files can be mined.

• After you have added the first redo log file to the list, each additional redo log file that you add to the list must be associated with the same database and database RESETLOGS SCN as the first redo log file. (The database RESETLOGS SCN uniquely identifies each execution of an ALTER DATABASE OPEN RESETLOGS statement. When the online redo logs are reset, Oracle creates a new and unique incarnation of the database.)

• To analyze the redo log files from a different database (or a database incarnation with a different database RESETLOGS SCN) than that with which the current list of redo log files is associated, use the END_LOGMNR procedure to end the current LogMiner session, and then build a new list using the ADD_LOGFILE procedure.

• LogMiner matches redo log files by the log sequence number. Thus, two redo log files with different names but with the same log sequence number will return the ORA-01289 exception. For instance, the online counterpart of an archived redo log file has a different name from the archived redo log file, but attempting to register it with LogMiner after registering the archived counterpart will result in the ORA-01289 exception being returned.

Syntax

DBMS_LOGMNR.COLUMN_PRESENT (
     sql_redo_undo      IN  RAW,
     column_name        IN  VARCHAR2 default '') RETURN NUMBER;

Parameters

Return Values

Table 84-7 describes the return values for the COLUMN_PRESENT function. The COLUMN_PRESENT function returns 1 if the self-describing record (the first parameter) contains the column specified in the second parameter. This can be used to determine the meaning of NULL values returned by the DBMS_LOGMNR.MINE_VALUE function.

Exceptions

Usage Notes

• To use the COLUMN_PRESENT function, you must have successfully started LogMiner.

• The COLUMN_PRESENT function must be invoked in the context of a select operation on the V$LOGMNR_CONTENTS view.

• The COLUMN_PRESENT function does not support LONG, LOB, ADT, or COLLECTION datatypes.

• The value for the sql_redo_undo parameter depends on the operation performed and the data of interest:

  • If an update operation was performed and you want to know what the value was prior to the update operation, specify UNDO_VALUE.

  • If an update operation was performed and you want to know what the value is after the update operation, specify REDO_VALUE.

  • If an insert operation was performed, typically you would specify REDO_VALUE (because the value of a column prior to an insert operation will always be NULL).

  • If a delete operation was performed, typically you would specify UNDO_VALUE (because the value of a column after a delete operation will always be NULL).

Syntax

DBMS_LOGMNR.END_LOGMNR;

Exceptions

Syntax

DBMS_LOGMNR.MINE_VALUE (
     sql_redo_undo      IN  RAW,
     column_name        IN  VARCHAR2 default '') RETURN VARCHAR2;

Parameters

Return Values

Exceptions

Usage Notes

• To use the MINE_VALUE function, you must have successfully started LogMiner.

• The MINE_VALUE function must be invoked in the context of a select operation from the V$LOGMNR_CONTENTS view.

• The MINE_VALUE function does not support LONG, LOB, ADT, or COLLECTION datatypes.

• The value for the sql_redo_undo parameter depends on the operation performed and the data of interest:

  • If an update operation was performed and you want to know what the value was prior to the update operation, specify UNDO_VALUE.

  • If an update operation was performed and you want to know what the value is after the update operation, specify REDO_VALUE.

  • If an insert operation was performed, typically you would specify REDO_VALUE (because the value of a column prior to an insert operation will always be null).

  • If a delete operation was performed, typically you would specify UNDO_VALUE (because the value of a column after a delete operation will always be null).

Syntax

DBMS_LOGMNR.REMOVE_LOGFILE ( 
   LogFileName     IN VARCHAR2);

Parameters

Exceptions

Usage Notes

• Before querying the V$LOGMNR_CONTENTS view, you must make a successful call to the DBMS_LOGMNR.START_LOGMNR procedure (within the current LogMiner session).

• You can use this procedure to remove a redo log file from the list of redo log files for LogMiner to process if you know that redo log file does not contain any data of interest.

• Multiple redo log files can be removed by calling this procedure repeatedly.

• The redo log files do not need to be removed in any particular order.

• To start a new list of redo log files for analysis, use the END_LOGMNR procedure to end the current LogMiner session, and then build a new list using the ADD_LOGFILE procedure.

• Even if you remove all redo log files from the list, any subsequent calls you make to the ADD_LOGFILE procedure must match the database ID and RESETLOGS SCN of the removed redo log files. Therefore, to analyze the redo log files from a different database (or a database incarnation with a different database RESETLOGS SCN) than that with which the current list of redo log files is associated, use the END_LOGMNR procedure to end the current LogMiner session, and then build a new list using the ADD_LOGFILE procedure.

Syntax

DBMS_LOGMNR.START_LOGMNR ( 
   startScn           IN NUMBER default 0,
   endScn             IN NUMBER default 0,
   startTime          IN DATE default '01-jan-1988',
   endTime            IN DATE default '31-dec-2110',
   DictFileName       IN VARCHAR2 default '',
   Options            IN BINARY_INTEGER default 0 );

Parameters

Exceptions

Usage Notes

• LogMiner can use a dictionary that you previously extracted to the redo log files or to a flat file, or you can specify that LogMiner use the online catalog if LogMiner is mining data from the source system. See Oracle Database Utilities and Chapter 85, "DBMS_LOGMNR_D" in this manual for more information about the LogMiner dictionary.

• After executing the START_LOGMNR procedure, you can query the following views:

  • V$LOGMNR_CONTENTS - contains history of information in redo log files

  • V$LOGMNR_DICTIONARY - contains current information about the LogMiner dictionary file extracted to a flat file

  • V$LOGMNR_PARAMETERS - contains information about the LogMiner session

  (You can query the V$LOGMNR_LOGS view after a redo log file list has been added to the list of files that LogMiner is to mine.)

• Parameters and options are not persistent across calls to DBMS_LOGMNR.START_LOGMNR. You must specify all desired parameters and options (including SCN and time ranges) each time you call DBMS_LOGMNR.START_LOGMNR

• Be aware that specifying redo log files using a timestamp is not precise.

• The CONTINUOUS_MINE option directs LogMiner to automatically add redo log files, as needed, to find the data of interest. You need to specify only the first log to start mining, or just the starting SCN or date to indicate to LogMiner where to begin mining logs. Keep the following in mind when using the CONTINUOUS_MINE option:

  • The database control file will hold information about a limited number of archived redo log files, although the number of entries can be quite large. Query the V$ARCHIVED_LOGS view to determine which redo log file entries will be found by LogMiner.

    Even if an entry is listed in the database control file (and the V$ARCHIVED_LOGS view), the archived redo log file may not be accessible by LogMiner for various reasons. For example, the archived redo log file may have been deleted or moved from its location (maybe because of a backup operation to tape), or the directory where it resides may not be not available.

  • If you specify the CONTINUOUS_MINE option and an ending time or SCN that will occur in the future (or you do not specify an end time or SCN), a query of the V$LOGMNR_CONTENTS view will not finish until the database has generated redo log files beyond the specified time or SCN. In this scenario, LogMiner will automatically add archived redo log files to the LogMiner redo log file list as they are generated. In addition, in this scenario only, LogMiner may automatically remove redo log files from the list to keep it at 50 processed redo files. This is to save PGA memory as LogMiner automatically adds redo log files to the list. If LogMiner did not perform automated removal, memory could eventually be exhausted.

  • LogMiner can mine online redo logs. However, if the CONTINUOUS_MINE option is not specified, it is possible that the database is writing to the online redo log file at the same time that LogMiner is reading the online redo log file. If a log switch occurs while LogMiner is reading an online redo log file, the database will overwrite what LogMiner is attempting to read. The data that LogMiner returns if the file it is trying to read gets overwritten by the database is unpredictable.

• Keep the following in mind regarding starting and ending times or SCN ranges:

  • If you specify neither a startTime nor a startScn parameter, LogMiner will set the startScn parameter to use the lowest SCN value from the redo log file that contains the oldest changes.

  • If you specify both time and SCN values, LogMiner uses the SCN value or values and ignores the time values.

  • If you specify starting and ending time or SCN values and they are found in the LogMiner redo log file list, then LogMiner mines the logs indicated by those values.

  • If you specify starting and ending times or SCN values that are not in the LogMiner redo log file list, and you specify DBMS_LOGMNR.START_LOGMNR without the CONTINUOUS_MINE option, and you specify:

    • 0 for the startTime or startScn value, then the lowest SCN in the LogMiner redo log file list will be used as the startScn

    • A nonzero number for the startTime or startScn value, then an error is returned

    • 0 or a nonzero number for the endTime or endScn value, then the highest SCN in the LogMiner redo log file list will be used as the endScn

  • If you specify starting and ending times or SCN values and they are not found in the LogMiner redo log file list, and you specify DBMS_LOGMNR.START_LOGMNR with the CONTINUOUS_MINE option, and you specify:

    • 0 for the startTime or startScn value, then an error is returned.

    • A startTime or startScn value that is greater than any value in the database's archived redo log files, then LogMiner starts mining in the online redo log file. LogMiner will continue to process the online redo log file until it finds a change at, or beyond, the requested starting point before it returns rows from the V$LOGMNR_CONTENTS view.

    • An endTime or endScn parameter value that indicates a time or SCN in the future, then LogMiner includes the online redo log files when it mines. When you query the V$LOGMNR_CONTENTS view, rows will be returned from this view as changes are made to the database, and will not stop until LogMiner sees a change beyond the requested ending point.

    • 0 for the endTime or endScn parameter value, then LogMiner includes the online redo log files when it mines. When you query the V$LOGMNR_CONTENTS view, rows will be returned from this view as changes are made to the database, and will not stop until you enter CTL+C or you terminate the PL/SQL cursor.