12 Managing the Redo Log

Redo Threads

When speaking in the context of multiple database instances, the redo log for each database instance is also referred to as a redo thread. In typical configurations, only one database instance accesses an Oracle Database, so only one thread is present. In an Oracle Real Application Clusters environment, however, two or more instances concurrently access a single database and each instance has its own thread of redo. A separate redo thread for each instance avoids contention for a single set of redo log files, thereby eliminating a potential performance bottleneck.

This chapter describes how to configure and manage the redo log on a standard single-instance Oracle Database. The thread number can be assumed to be 1 in all discussions and examples of statements. For information about redo log groups in an Oracle Real Application Clusters environment, see Oracle Real Application Clusters Administration and Deployment Guide.

Redo Log Contents

Redo log files are filled with redo records. A redo record, also called a redo entry, is made up of a group of change vectors, each of which is a description of a change made to a single block in the database. For example, if you change a salary value in an employee table, you generate a redo record containing change vectors that describe changes to the data segment block for the table, the undo segment data block, and the transaction table of the undo segments.

Redo entries record data that you can use to reconstruct all changes made to the database, including the undo segments. Therefore, the redo log also protects rollback data. When you recover the database using redo data, the database reads the change vectors in the redo records and applies the changes to the relevant blocks.

Redo records are buffered in a circular fashion in the redo log buffer of the SGA (see "How Oracle Database Writes to the Redo Log") and are written to one of the redo log files by the Log Writer (LGWR) database background process. Whenever a transaction is committed, LGWR writes the transaction redo records from the redo log buffer of the SGA to a redo log file, and assigns a system change number (SCN) to identify the redo records for each committed transaction. Only when all redo records associated with a given transaction are safely on disk in the online logs is the user process notified that the transaction has been committed.

Redo records can also be written to a redo log file before the corresponding transaction is committed. If the redo log buffer fills, or another transaction commits, LGWR flushes all of the redo log entries in the redo log buffer to a redo log file, even though some redo records may not be committed. If necessary, the database can roll back these changes.

How Oracle Database Writes to the Redo Log

The redo log of a database consists of two or more redo log files. The database requires a minimum of two files to guarantee that one is always available for writing while the other is being archived (if the database is in ARCHIVELOG mode). See "Managing Archived Redo Logs" for more information.

LGWR writes to redo log files in a circular fashion. When the current redo log file fills, LGWR begins writing to the next available redo log file. When the last available redo log file is filled, LGWR returns to the first redo log file and writes to it, starting the cycle again. Figure 12-1 illustrates the circular writing of the redo log file. The numbers next to each line indicate the sequence in which LGWR writes to each redo log file.

Filled redo log files are available to LGWR for reuse depending on whether archiving is enabled.

• If archiving is disabled (the database is in NOARCHIVELOG mode), a filled redo log file is available after the changes recorded in it have been written to the data files.

• If archiving is enabled (the database is in ARCHIVELOG mode), a filled redo log file is available to LGWR after the changes recorded in it have been written to the data files and the file has been archived.

Figure 12-1 Reuse of Redo Log Files by LGWR

Description of "Figure 12-1 Reuse of Redo Log Files by LGWR"

Multiplexing Redo Log Files

To protect against a failure involving the redo log itself, Oracle Database allows a multiplexed redo log, meaning that two or more identical copies of the redo log can be automatically maintained in separate locations. For the most benefit, these locations should be on separate disks. Even if all copies of the redo log are on the same disk, however, the redundancy can help protect against I/O errors, file corruption, and so on. When redo log files are multiplexed, LGWR concurrently writes the same redo log information to multiple identical redo log files, thereby eliminating a single point of redo log failure.

Multiplexing is implemented by creating groups of redo log files. A group consists of a redo log file and its multiplexed copies. Each identical copy is said to be a member of the group. Each redo log group is defined by a number, such as group 1, group 2, and so on.

Figure 12-2 Multiplexed Redo Log Files

Description of "Figure 12-2 Multiplexed Redo Log Files"

In Figure 12-2, A_LOG1 and B_LOG1 are both members of Group 1, A_LOG2 and B_LOG2 are both members of Group 2, and so forth. Each member in a group must be the same size.

Each member of a log file group is concurrently active—that is, concurrently written to by LGWR—as indicated by the identical log sequence numbers assigned by LGWR. In Figure 12-2, first LGWR writes concurrently to both A_LOG1 and B_LOG1. Then it writes concurrently to both A_LOG2 and B_LOG2, and so on. LGWR never writes concurrently to members of different groups (for example, to A_LOG1 and B_LOG2).

Legal and Illegal Configurations

In most cases, a multiplexed redo log should be symmetrical: all groups of the redo log should have the same number of members. However, the database does not require that a multiplexed redo log be symmetrical. For example, one group can have only one member, and other groups can have two members. This configuration protects against disk failures that temporarily affect some redo log members but leave others intact.

The only requirement for an instance redo log is that it have at least two groups. Figure 12-3 shows legal and illegal multiplexed redo log configurations. The second configuration is illegal because it has only one group.

Figure 12-3 Legal and Illegal Multiplexed Redo Log Configuration

Description of "Figure 12-3 Legal and Illegal Multiplexed Redo Log Configuration"

Placing Redo Log Members on Different Disks

When setting up a multiplexed redo log, place members of a group on different physical disks. If a single disk fails, then only one member of a group becomes unavailable to LGWR and other members remain accessible to LGWR, so the instance can continue to function.

If you archive the redo log, spread redo log members across disks to eliminate contention between the LGWR and ARCn background processes. For example, if you have two groups of multiplexed redo log members (a duplexed redo log), place each member on a different disk and set your archiving destination to a fifth disk. Doing so will avoid contention between LGWR (writing to the members) and ARCn (reading the members).

Data files should also be placed on different disks from redo log files to reduce contention in writing data blocks and redo records.

Planning the Size of Redo Log Files

When setting the size of redo log files, consider whether you will be archiving the redo log. Redo log files should be sized so that a filled group can be archived to a single unit of offline storage media (such as a tape or disk), with the least amount of space on the medium left unused. For example, suppose only one filled redo log group can fit on a tape and 49% of the tape storage capacity remains unused. In this case, it is better to decrease the size of the redo log files slightly, so that two log groups could be archived on each tape.

All members of the same multiplexed redo log group must be the same size. Members of different groups can have different sizes. However, there is no advantage in varying file size between groups. If checkpoints are not set to occur between log switches, make all groups the same size to guarantee that checkpoints occur at regular intervals.

The minimum size permitted for a redo log file is 4 MB.

Planning the Block Size of Redo Log Files

Unlike the database block size, which can be between 2K and 32K, redo log files always default to a block size that is equal to the physical sector size of the disk. Historically, this has typically been 512 bytes (512B).

Some newer high-capacity disk drives offer 4K byte (4K) sector sizes for both increased ECC capability and improved format efficiency. Most Oracle Database platforms are able to detect this larger sector size. The database then automatically creates redo log files with a 4K block size on those disks.

However, with a block size of 4K, there is increased redo wastage. In fact, the amount of redo wastage in 4K blocks versus 512B blocks is significant. You can determine the amount of redo wastage by viewing the statistics stored in the V$SESSTAT and V$SYSSTAT views.

SQL> SELECT name, value FROM v$sysstat WHERE name = 'redo wastage';
 
NAME                                  VALUE
-------------------------------- ----------
redo wastage                       17941684

To avoid the additional redo wastage, if you are using emulation-mode disks—4K sector size disk drives that emulate a 512B sector size at the disk interface—you can override the default 4K block size for redo logs by specifying a 512B block size or, for some platforms, a 1K block size. However, you will incur a significant performance degradation when a redo log write is not aligned with the beginning of the 4K physical sector. Because seven out of eight 512B slots in a 4K physical sector are not aligned, performance degradation typically does occur. Thus, you must evaluate the trade-off between performance and disk wastage when planning the redo log block size on 4K sector size emulation-mode disks.

Beginning with Oracle Database 11g Release 2, you can specify the block size of online redo log files with the BLOCKSIZE keyword in the CREATE DATABASE, ALTER DATABASE, and CREATE CONTROLFILE statements. The permissible block sizes are 512, 1024, and 4096.

The following statement adds a redo log file group with a block size of 512B. The BLOCKSIZE 512 clause is valid but not required for 512B sector size disks. For 4K sector size emulation-mode disks, the BLOCKSIZE 512 clause overrides the default 4K size.

ALTER DATABASE orcl ADD LOGFILE
  GROUP 4 ('/u01/logs/orcl/redo04a.log','/u01/logs/orcl/redo04b.log')
  SIZE 100M BLOCKSIZE 512 REUSE;

To ascertain the redo log file block size, run the following query:

SQL> SELECT BLOCKSIZE FROM V$LOG;

BLOCKSIZE
---------
      512

Choosing the Number of Redo Log Files

The best way to determine the appropriate number of redo log files for a database instance is to test different configurations. The optimum configuration has the fewest groups possible without hampering LGWR from writing redo log information.

In some cases, a database instance may require only two groups. In other situations, a database instance may require additional groups to guarantee that a recycled group is always available to LGWR. During testing, the easiest way to determine whether the current redo log configuration is satisfactory is to examine the contents of the LGWR trace file and the database alert log. If messages indicate that LGWR frequently has to wait for a group because a checkpoint has not completed or a group has not been archived, add groups.

Consider the parameters that can limit the number of redo log files before setting up or altering the configuration of an instance redo log. The following parameters limit the number of redo log files that you can add to a database:

• The MAXLOGFILES parameter used in the CREATE DATABASE statement determines the maximum number of groups of redo log files for each database. Group values can range from 1 to MAXLOGFILES. When the compatibility level is set earlier than 10.2.0, the only way to override this upper limit is to re-create the database or its control file. Therefore, it is important to consider this limit before creating a database. When compatibility is set to 10.2.0 or later, you can exceed the MAXLOGFILES limit, and the control files expand as needed. If MAXLOGFILES is not specified for the CREATE DATABASE statement, then the database uses an operating system specific default value.

• The MAXLOGMEMBERS parameter used in the CREATE DATABASE statement determines the maximum number of members for each group. As with MAXLOGFILES, the only way to override this upper limit is to re-create the database or control file. Therefore, it is important to consider this limit before creating a database. If no MAXLOGMEMBERS parameter is specified for the CREATE DATABASE statement, then the database uses an operating system default value.

  See Also:

  • Your operating system specific Oracle documentation for the default and legal values of the MAXLOGFILES and MAXLOGMEMBERS parameters

  • Oracle Database Performance Tuning Guide

Controlling Archive Lag

You can force all enabled redo log threads to switch their current logs at regular time intervals. In a primary/standby database configuration, changes are made available to the standby database by archiving redo logs at the primary site and then shipping them to the standby database. The changes that are being applied by the standby database can lag behind the changes that are occurring on the primary database, because the standby database must wait for the changes in the primary database redo log to be archived (into the archived redo log) and then shipped to it. To limit this lag, you can set the ARCHIVE_LAG_TARGET initialization parameter. Setting this parameter lets you specify in seconds how long that lag can be.

ARCHIVE_LAG_TARGET = 1800

Creating Redo Log Groups

To create a new group of redo log files, use the SQL statement ALTER DATABASE with the ADD LOGFILE clause.

The following statement adds a new group of redo logs to the database:

ALTER DATABASE
  ADD LOGFILE ('/oracle/dbs/log1c.rdo', '/oracle/dbs/log2c.rdo') SIZE 100M;

You can also specify the number that identifies the group using the GROUP clause:

ALTER DATABASE 
  ADD LOGFILE GROUP 10 ('/oracle/dbs/log1c.rdo', '/oracle/dbs/log2c.rdo')
      SIZE 100M BLOCKSIZE 512;

Using group numbers can make administering redo log groups easier. However, the group number must be between 1 and MAXLOGFILES. Do not skip redo log file group numbers (that is, do not number your groups 10, 20, 30, and so on), or you will consume unnecessary space in the control files of the database.

In the preceding statement, the BLOCKSIZE clause is optional. See "Planning the Block Size of Redo Log Files" for more information.

Creating Redo Log Members

In some cases, it might not be necessary to create a complete group of redo log files. A group could already exist, but not be complete because one or more members of the group were dropped (for example, because of a disk failure). In this case, you can add new members to an existing group.

To create new redo log members for an existing group, use the SQL statement ALTER DATABASE with the ADD LOGFILE MEMBER clause. The following statement adds a new redo log member to redo log group number 2:

ALTER DATABASE ADD LOGFILE MEMBER '/oracle/dbs/log2b.rdo' TO GROUP 2;

Notice that filenames must be specified, but sizes need not be. The size of the new members is determined from the size of the existing members of the group.

When using the ALTER DATABASE statement, you can alternatively identify the target group by specifying all of the other members of the group in the TO clause, as shown in the following example:

ALTER DATABASE ADD LOGFILE MEMBER '/oracle/dbs/log2c.rdo'
    TO ('/oracle/dbs/log2a.rdo', '/oracle/dbs/log2b.rdo'); 

Dropping Log Groups

To drop a redo log group, you must have the ALTER DATABASE system privilege. Before dropping a redo log group, consider the following restrictions and precautions:

• An instance requires at least two groups of redo log files, regardless of the number of members in the groups. (A group comprises one or more members.)

• You can drop a redo log group only if it is inactive. If you must drop the current group, then first force a log switch to occur.

• Make sure a redo log group is archived (if archiving is enabled) before dropping it. To see whether this has happened, use the V$LOG view.

  SELECT GROUP#, ARCHIVED, STATUS FROM V$LOG;
  
     GROUP# ARC STATUS
  --------- --- ----------------
          1 YES ACTIVE
          2 NO  CURRENT
          3 YES INACTIVE
          4 YES INACTIVE
  

Drop a redo log group with the SQL statement ALTER DATABASE with the DROP LOGFILE clause.

The following statement drops redo log group number 3:

ALTER DATABASE DROP LOGFILE GROUP 3;

When a redo log group is dropped from the database, and you are not using the Oracle Managed Files feature, the operating system files are not deleted from disk. Rather, the control files of the associated database are updated to drop the members of the group from the database structure. After dropping a redo log group, ensure that the drop completed successfully, and then use the appropriate operating system command to delete the dropped redo log files.

When using Oracle Managed Files, the cleanup of operating systems files is done automatically for you.

Dropping Redo Log Members

To drop a redo log member, you must have the ALTER DATABASE system privilege. Consider the following restrictions and precautions before dropping individual redo log members:

• It is permissible to drop redo log files so that a multiplexed redo log becomes temporarily asymmetric. For example, if you use duplexed groups of redo log files, you can drop one member of one group, even though all other groups have two members each. However, you should rectify this situation immediately so that all groups have at least two members, and thereby eliminate the single point of failure possible for the redo log.

• An instance always requires at least two valid groups of redo log files, regardless of the number of members in the groups. (A group comprises one or more members.) If the member you want to drop is the last valid member of the group, you cannot drop the member until the other members become valid. To see a redo log file status, use the V$LOGFILE view. A redo log file becomes INVALID if the database cannot access it. It becomes STALE if the database suspects that it is not complete or correct. A stale log file becomes valid again the next time its group is made the active group.

• You can drop a redo log member only if it is not part of an active or current group. To drop a member of an active group, first force a log switch to occur.

• Make sure the group to which a redo log member belongs is archived (if archiving is enabled) before dropping the member. To see whether this has happened, use the V$LOG view.

To drop specific inactive redo log members, use the ALTER DATABASE statement with the DROP LOGFILE MEMBER clause.

The following statement drops the redo log /oracle/dbs/log3c.rdo:

ALTER DATABASE DROP LOGFILE MEMBER '/oracle/dbs/log3c.rdo';

When a redo log member is dropped from the database, the operating system file is not deleted from disk. Rather, the control files of the associated database are updated to drop the member from the database structure. After dropping a redo log file, ensure that the drop completed successfully, and then use the appropriate operating system command to delete the dropped redo log file.

To drop a member of an active group, you must first force a log switch.