Because Oracle OLAP is contained in the database and its resources are managed using the same tools, the management tasks of Oracle OLAP and the database converge. Nonetheless, you should address tasks such as database tuning in the specific context of data warehousing.
This chapter contains the following topics:
Table 7-1 identifies the parameters that affect the performance of Oracle OLAP. Alter your server parameter file or init.ora file to these values, then restart your database instance. You can monitor the effectiveness of these settings and adjust them as necessary.
See Also:
Oracle Database Performance Tuning Guide for information about tuning parameter settings
Oracle Database Reference for descriptions of individual parameters
Table 7-1 Initial Settings for Database Parameters
| Parameter | Default Value | Recommended Setting | Description |
|---|---|---|---|
|
|
If you reduce this value to limit the maximum number of job slaves running on an instance, then calculate the following number of processes for use by OLAP: Number of CPUs, plus one additional process for every three CPUs; in a multi-core CPU, each core counts as a CPU For example, |
Controls the degree of parallelism in OLAP builds, as described in "Parallelism" |
|
|
|
|
|
Controls how the degree of parallelism is determined When set to |
|
Derived |
2.5 * maximum number of simultaneous OLAP users |
Provides sufficient background processes for each user |
|
|
( |
|
Specifies use of an undo tablespace |
|
|
Derived |
Name of the undo tablespace, which must be defined previously |
Identifies the undo tablespace defined for OLAP use, as shown in "Creating an Undo Tablespace" |
To set the system parameters:
Open the init.ora initialization file in a text editor.
Add or change the settings in the file, as described in Table 7-1.
Stop and restart the database.
On Windows, use the Services utility to stop and restart OracleService.
On Linux, use commands like the following. Be sure to identify the initialization file in the STARTUP command.
SQLPLUS '/ AS SYSDBA' SHUTDOWN IMMEDIATE STARTUP pfile=$ORACLE_BASE/admin/orcl/pfile/init.ora.724200516420
Analytic workspaces are stored in the owner's default tablespace, unless the owner specifies otherwise. All tablespaces for OLAP use should specify EXTENT MANAGEMENT LOCAL. Tablespaces created using default parameters may use resources inefficiently. You should create undo, permanent, and temporary tablespaces that are appropriate for storing analytic workspaces.
Create an undo tablespace with the EXTENT MANAGEMENT LOCAL clause, as shown in this example:
CREATE UNDO TABLESPACE olapundo DATAFILE '$ORACLE_BASE/oradata/undo.dbf'
SIZE 64M REUSE AUTOEXTEND ON NEXT 8M
MAXSIZE UNLIMITED EXTENT MANAGEMENT LOCAL;
After creating the undo tablespace, change your system parameter file to include the following settings, then restart the database as described in "Setting Database Initialization Parameters".
UNDO_TABLESPACE=tablespace
UNDO_MANAGEMENT=AUTO
Each dimensional object occupies at least one extent. A fixed extent size may waste most of the allocated space. For example, if an object is 64K and the extents are set to a uniform size of 1M (the default), then only a small portion of the extent is used.
Create permanent tablespaces with the EXTENT MANAGEMENT LOCAL and SEGMENT SPACE MANAGEMENT AUTO clauses, as shown in this example:
CREATE TABLESPACE glo DATAFILE '$ORACLE_BASE/oradata/glo.dbf'
SIZE 64M REUSE AUTOEXTEND ON NEXT 8M MAXSIZE UNLIMITED
EXTENT MANAGEMENT LOCAL SEGMENT SPACE MANAGEMENT AUTO;
Oracle OLAP uses the temporary tablespace to store all changes to the data in a cube, whether the changes are the result of a data load or data analysis. Saving the cube moves the changes into the permanent tablespace and clears the temporary tablespace.
This usage creates numerous extents within the tablespace. A temporary tablespace suitable for use by Oracle OLAP should specify the EXTENT MANAGEMENT LOCAL clause and a UNIFORM SIZE clause with a small size, as shown in this example:
CREATE TEMPORARY TABLESPACE glotmp TEMPFILE '$ORACLE_BASE/oradata/glotmp.tmp'
SIZE 50M REUSE AUTOEXTEND ON NEXT 5M MAXSIZE UNLIMITED
EXTENT MANAGEMENT LOCAL UNIFORM SIZE 256K;
Oracle Database provides excellent storage management tools to simplify routine tasks. Automatic Storage Management (ASM) provides a simple storage management interface that virtualizes database storage into disk groups. You can manage a small set of disk groups, and ASM automates the placement of the database files within those disk groups.
ASM spreads data evenly across all available storage resources to optimize performance and utilization. After you add or drop disks, ASM automatically rebalances files across the disk group.
Because OLAP is part of Oracle Database, you can use ASM to manage both relational and dimensional data.
ASM is highly recommended for analytic workspaces. A system managed with ASM is faster than a file system and easier to manage than raw devices. ASM optimizes the performance of analytic workspaces both on systems with Oracle RAC and those without Oracle RAC.
However, you do not need ASM to use Oracle OLAP. You can still spread your data across multiple disks, just by defining the tablespaces like in this example:
CREATE TABLESPACE glo DATAFILE
'disk1/oradata/glo1.dbf' SIZE 64M REUSE AUTOEXTEND ON NEXT 8M MAXSIZE 1024M
EXTENT MANAGEMENT LOCAL SEGMENT SPACE MANAGEMENT AUTO;
ALTER TABLESPACE glo ADD DATAFILE
'disk2/oradata/glo2.dbf' SIZE 64M REUSE AUTOEXTEND ON NEXT 8M MAXSIZE 1024M,
'disk3/oradata/glo3.dbf' SIZE 64M REUSE AUTOEXTEND ON NEXT 8M
MAXSIZE UNLIMITED;
Oracle Database data dictionary views and system tables contain extensive information about analytic workspaces.
Among the static views of the database data dictionary are several that provide information about analytic workspaces. Table 7-2 provides brief descriptions of them. All data dictionary views have corresponding DBA and USER views.
Table 7-2 Static Data Dictionary Views for OLAP
| View | Description |
|---|---|
|
Describes all analytic workspaces accessible to the current user. |
|
|
Describes the current objects in all analytic workspaces accessible to the current user. |
|
|
Describes the properties defined in all analytic workspaces accessible to the current user. |
|
|
Describes the page spaces currently in use by all analytic workspaces accessible to the current user. |
See Also:
"Querying the Data Dictionary" for a list of data dictionary views that describe OLAP dimensional objects
Oracle Database Reference for full descriptions of all data dictionary views
The SYS user owns several tables associated with analytic workspaces. Table 7-3 provides brief descriptions.
Important:
These tables are vital for the operation of Oracle OLAP. Do not delete them or attempt to modify them directly without being fully aware of the consequences.Table 7-3 OLAP Tables Owned By SYS
Analytic workspaces are stored in tables in the Oracle database. The names of these tables always begin with AW$.
For example, if the GLOBAL user creates two analytic workspaces, one named FINANCIALS and the other named MARKETING, then these tables are created in the GLOBAL schema:
AW$FINANCIALS AW$MARKETING
The tables store all of the object definitions and data.
The first time you load data into a cube or dimension using Analytic Workspace Manager, it creates several logs. These logs are stored in tables in the same schema as the analytic workspace:
Cube Build Log: Contains information about what happened during a build. Use this log to determine whether the build produced the results you were expecting, and if not, why not. The log is continually updated whenever a cube or dimension is refreshed, whether by Analytic Workspace Manager, the database materialized view refresh subsystem, or a PL/SQL procedure. You can query the log at any time to evaluate the progress of the build and to estimate the time to completion. The default table name is CUBE_BUILD_LOG.
Cube Dimension Compile Log: Contains errors that occur during the validation of the dimension hierarchies when OLAP is aggregating a cube. The default table name is CUBE_DIMENSION_COMPILE.
Cube Operations Log: Contains messages and debugging information for all OLAP engine events. The default table name is CUBE_OPERATIONS_LOG.
Cube Rejected Records Log: Identifies any records that were rejected because they did not meet the expected format. The default table name is CUBE_DIMENSION_COMPILE.
These logs enable you to track the progress of long running processes, then use the results to profile performance characteristics. They provide information to help you diagnose and remedy problems that may occur during development and maintenance of a cube. They also help diagnose performance problems in querying cubes.
You can also run the $ORACLE_HOME/olap/admin/utlolaplog.sql script to create the build log with some useful views.
The Maintenance Wizard in Analytic Workspace Manager displays the relevant rows from these tables during every build on the Maintenance Log page. You can query the tables directly in any SQL interface.
See Also:
DBMS_CUBE_LOG entry in Oracle Database PL/SQL Packages and Types Reference.Cubes are often partitioned to improve build and maintenance times. For information about creating a partitioned cube, refer to "Choosing a Partitioning Strategy".
To discover the current partitioning, query the ALL_CUBES data dictionary view. The PARTITION_DIMENSION_NAME, PARTITION_HIERARCHY_NAME, and PARTITION_LEVEL_NAME columns display partitioning information. For example, the following query shows that the Units Cube is partitioned on the Time dimension, the Calendar hierarchy, and the Calendar Year level.
SELECT partition_dimension_name, partition_hierarchy_name,
partition_level_name FROM all_cubes
WHERE owner='GLOBAL' AND cube_name='UNITS_CUBE';
PARTITION_DIMENSION_NAME PARTITION_HIERARCHY_NAME PARTITION_LEVEL_NAME
------------------------- ------------------------- --------------------
TIME CALENDAR CALENDAR_YEAR
The OLAP engine automatically creates and drops partitions as part of data maintenance, as members are added and deleted from the partitioning dimension.
For example, assume that in the sample Global analytic workspace, the Units cube is partitioned on the Time dimension, using the Calendar hierarchy, and at the Calendar Quarter level. The OLAP engine creates a partition for each Calendar Quarter and its children. The default top partition contains Calendar Years and all members of the Fiscal hierarchy. If Global has three years of data, then the Units cube has 13 partitions: Four bottom partitions for each Calendar Year, plus the top partition.
A data refresh typically creates new time periods and deletes old ones. Whenever a Calendar Quarter value is loaded into the Time dimension, a corresponding partition is added to the cube. Whenever a Calendar Quarter value is deleted from the Time dimension, the corresponding empty partition is deleted from the cube.
You can improve the performance of data maintenance by enabling parallel processing. There are two levels of parallelism:
Parallel job execution: Loading and aggregating the data using multiple processes.
Parallel update: Moving the data from temporary to permanent tablespaces using multiple processes.
This number of parallel processes is controlled by these factors:
The number of objects that can be aggregated in parallel. Each cube and each partition (including the top partition) can use a separate process.
You can control the number of partitions in a cube on the Partitioning tab of the cube property sheet in Analytic Workspace Manager.
The number of simultaneous database processes the user is authorized to run.
This number is controlled by the JOB_QUEUE_PROCESSES parameter. If you have SYS privileges, you can obtain the current parameter setting with the following SQL command:
SHOW PARAMETER JOB_QUEUE_PROCESSES
For parallel update, the number of processes you allocate to the job. You can specify the number of processes in the Maintenance Wizard of Analytic Workspace Manager when specifying the task processing options, or on the Materialized View tab of the cube.
The number of processes allocated to SQL to fetch rows from the relational source tables. When PARALLEL_DEGREE_POLICY is set to AUTO or LIMITED, the database can allocate additional processes for executing SQL statements.
Suppose that a cube is partitioned on the Quarter level of Time, and the cube contains three years of data. The cube has 3*4=12 bottom partitions, JOB_QUEUE_PROCESSES is set to 8, and you set the parallelism option to 4 for the build. Oracle Database processes the cube in this way when PARALLEL_DEGREE_POLICY is set to its default value of MANUAL:
Load and build the dimensions of the cube serially using a single process.
Load and build the 12 bottom partitions in parallel using 4 processes. As soon as one process finishes, another begins until all 12 are complete.
This cube could use the 8 processes allowed by JOB_QUEUE_PROCESSES, but it is limited to 4 by the build setting.
Load and build the top partition.
When PARALLEL_DEGREE_POLICY is set to AUTO or LIMITED, Oracle Database may allocate more than the designated processes.
Example 7-1 shows excerpts from CUBE_BUILD_LOG for a build of the Units cube and its dimensions. Partitioning on the Calendar Year level of the Time dimension created 10 bottom partitions for 1998 to 2007. JOB_QUEUE_PROCESSES is set to 2 and the parallelism option is set to 2 for the build also. The log shows that Oracle Database processed the Global in this way:
Processed the four dimensions serially.
Processed each partition of the Units cube
Example 7-1 Build Log for Global Units Cube
SLAVE_NUMBER STATUS COMMAND BUILD_OBJECT PARTITION
------------ ---------- -------------------- --------------- ---------------
0 STARTED BUILD
0 STARTED ATTACH AW RW WAIT
0 COMPLETED ATTACH AW RW WAIT
0 STARTED FREEZE
0 COMPLETED FREEZE
0 STARTED LOAD NO SYNCH TIME
0 SQL LOAD NO SYNCH TIME
.
.
.
0 SQL LOAD NO SYNCH PRODUCT
0 SQL LOAD NO SYNCH PRODUCT
0 COMPLETED LOAD NO SYNCH PRODUCT
0 STARTED COMPILE PRODUCT
0 COMPLETED COMPILE PRODUCT
0 STARTED COMPILE AGGMAP UNITS_CUBE
0 COMPLETED COMPILE AGGMAP UNITS_CUBE
0 STARTED COMPILE AGGMAP PRICE_CUBE
0 COMPLETED COMPILE AGGMAP PRICE_CUBE
0 STARTED UPDATE/COMMIT PRODUCT
0 COMPLETED UPDATE/COMMIT PRODUCT
0 STARTED UPDATE/COMMIT
0 COMPLETED UPDATE/COMMIT
0 STARTED REATTACH AW MULTI TH
AW
0 COMPLETED REATTACH AW MULTI TH
AW
0 STARTED SLAVE UNITS_CUBE P10:CY2007
0 STARTED SLAVE UNITS_CUBE P9:CY2006
1 STARTED BUILD P10:CY2007
1 STARTED ATTACH AW MULTI THAW UNITS_CUBE P10:CY2007
1 COMPLETED ATTACH AW MULTI THAW UNITS_CUBE P10:CY2007
1 STARTED ACQUIRE UNITS_CUBE P10:CY2007
1 COMPLETED ACQUIRE UNITS_CUBE P10:CY2007
1 STARTED LOAD UNITS_CUBE P10:CY2007
1 SQL LOAD UNITS_CUBE P10:CY2007
1 COMPLETED LOAD UNITS_CUBE P10:CY2007
1 STARTED UPDATE/COMMIT UNITS_CUBE P10:CY2007
1 COMPLETED UPDATE/COMMIT UNITS_CUBE P10:CY2007
.
.
.
10 STARTED BUILD P1:CY1998
10 STARTED ATTACH AW MULTI THAW UNITS_CUBE P1:CY1998
10 COMPLETED ATTACH AW MULTI THAW UNITS_CUBE P1:CY1998
10 STARTED ACQUIRE UNITS_CUBE P1:CY1998
10 COMPLETED ACQUIRE UNITS_CUBE P1:CY1998
10 STARTED LOAD UNITS_CUBE P1:CY1998
10 SQL LOAD UNITS_CUBE P1:CY1998
10 COMPLETED LOAD UNITS_CUBE P1:CY1998
10 STARTED SOLVE UNITS_CUBE P1:CY1998
10 COMPLETED SOLVE UNITS_CUBE P1:CY1998
10 STARTED UPDATE/COMMIT UNITS_CUBE P1:CY1998
10 COMPLETED UPDATE/COMMIT UNITS_CUBE P1:CY1998
10 STARTED DETACH AW UNITS_CUBE P1:CY1998
10 COMPLETED DETACH AW UNITS_CUBE P1:CY1998
10 COMPLETED BUILD P1:CY1998
0 COMPLETED SLAVE UNITS_CUBE P1:CY1998
0 STARTED REATTACH AW MULTI TH
AW
0 COMPLETED REATTACH AW MULTI TH
AW
0 STARTED SLAVE UNITS_CUBE P0
11 STARTED BUILD P0
11 STARTED ATTACH AW MULTI THAW UNITS_CUBE P0
11 COMPLETED ATTACH AW MULTI THAW UNITS_CUBE P0
11 STARTED ACQUIRE UNITS_CUBE P0
11 COMPLETED ACQUIRE UNITS_CUBE P0
11 STARTED LOAD UNITS_CUBE P0
11 COMPLETED LOAD UNITS_CUBE P0
11 STARTED SOLVE UNITS_CUBE P0
11 COMPLETED SOLVE UNITS_CUBE P0
11 STARTED UPDATE/COMMIT UNITS_CUBE P0
11 COMPLETED UPDATE/COMMIT UNITS_CUBE P0
11 STARTED DETACH AW UNITS_CUBE P0
11 COMPLETED DETACH AW UNITS_CUBE P0
11 COMPLETED BUILD P0
0 COMPLETED SLAVE UNITS_CUBE P0
0 STARTED REATTACH AW RW WAIT
0 COMPLETED REATTACH AW RW WAIT
0 STARTED ANALYZE UNITS_CUBE
0 COMPLETED ANALYZE UNITS_CUBE
0 STARTED THAW
0 COMPLETED THAW
0 STARTED DETACH AW
0 COMPLETED DETACH AW
0 COMPLETED BUILD
268 rows selected.
Oracle Database allocates the specified number of processes regardless of whether all of them can be used simultaneously at any point in the job. For example, if your job can use up to three processes, but you specify five, then two of the processes allocated to your job cannot be used by it or by any other job.
If Oracle Database is installed with Real Application Clusters (Oracle RAC), then a script submitted to the job queue is distributed across all nodes in the cluster. The performance gains can be significant. For example, a job running on four nodes in a cluster may run up to four times faster than the same job running on a single computer.
If your application executes queries directly against a single cube, you do not need to generate optimizer statistics for the cube. These queries are automatically optimized within the analytic workspace.
Optimizer statistics are used to create execution plans for queries that join two cube views or join a cube view to a table or a view of a table. They are also used for cost-based rewrite to cube materialized views. You must generate the statistics only for these types of queries.
To generate optimizer statistics, use the DBMS_AW_STATS PL/SQL package. You can run this package in Analytic Workspace Manager as part of a cube script, in SQL*Plus, or in any other SQL interface. Generating the statistics does not have a significant performance cost.
DBMS_AW_STATS has the following syntax:
DBMS_AW_STATS.ANALYZE
(object IN VARCHAR2);
The argument can be either a cube or a dimension. Example 7-2 shows a sample script for generating statistics on the Units cube and its dimensions.
Example 7-2 Generating Statistics for the Units Cube
BEGIN
DBMS_AW_STATS.ANALYZE('units_cube');
DBMS_AW_STATS.ANALYZE('time');
DBMS_AW_STATS.ANALYZE('customer');
DBMS_AW_STATS.ANALYZE('product');
DBMS_AW_STATS.ANALYZE('channel');
END;
/
Although you cannot view the statistics directly, you can examine the execution plans, as described in "Viewing Execution Plans".
See Also:
Oracle Database Performance Tuning GuideOracle Database provides various tools to help you diagnose performance problems. As an Oracle DBA, you may find these tools useful in tuning the database:
Oracle Enterprise Manager Database Control (Database Control) is a general database management and administration tool. In addition to facilitating basic tasks like adding users and modifying datafiles, Database Control presents a graphic overview of a database's current status. It also provides an interface to troubleshooting and performance tuning utilities.
Automatic Workload Repository collects database performance statistics and metrics for analysis and tuning, shows the exact time spent in the database, and saves session information.
Automatic Database Diagnostic Monitor watches database performance statistics to identify bottlenecks, analyze SQL statements, and offer suggestions to improve performance.
Oracle Database also provides system views to help you diagnose performance problems. The following topics identify views that are either specific to OLAP or provide database information that is pertinent to OLAP.
Each Oracle Database instance maintains fixed tables that record current database activity. These tables collect data on internal disk structures and memory structures. Among them are tables that collect data on Oracle OLAP.
These tables are available to users through a set of dynamic performance views. By monitoring these views, you can detect usage trends and diagnose system bottlenecks. Table 7-4 provides a brief description of each view. Global dynamic performance views (GV$) are also provided.
See Also:
Oracle Database Reference for full descriptions of the OLAP dynamic performance views.Table 7-4 OLAP Dynamic Performance Views
| View | Description |
|---|---|
|
Lists the aggregation operators available in analytic workspaces. |
|
|
Lists the allocation operators available in analytic workspaces. |
|
|
Collects information about the use of cache space and the status of dynamic aggregation. |
|
|
Collects status information about SQL fetches. |
|
|
Collects information about each active session. |
|
|
Collects information about the status of active analytic workspaces. |
Table 7-5 describes some other dynamic performance views that are not specific to OLAP, but which you may want to use when tuning your database for OLAP.
Table 7-5 Selected Database Performance Views
| View | Description |
|---|---|
|
|
Displays log file information from the control file. |
|
|
Contains information about redo log files. |
|
|
Provides PGA memory usage statistics and statistics about the automatic PGA memory manager when |
|
|
Displays statistics for data dictionary activity. Each row contains statistics for one data dictionary cache. |
|
|
Lists system statistics. |
The following queries extract OLAP information from the data dictionary. You must have a privileged account to query the DBA views.
More complex queries are provided in a script that you can download from the Oracle OLAP Web site on the Oracle Technology Network. For descriptions of these scripts and download instructions, refer to "OLAP DBA Scripts".
The OLAP option is provided with Oracle Database Enterprise Edition. To verify that the OLAP components have been installed, issue this SQL command:
SELECT comp_name, version, status FROM DBA_REGISTRY
WHERE comp_name LIKE '%OLAP%';
COMP_NAME VERSION STATUS
------------------------ ------------------------------ -----------
OLAP Analytic Workspace 11.2.0.1.0 VALID
Oracle OLAP API 11.2.0.1.0 VALID
OLAP Catalog 11.2.0.1.0 VALID
The DBA_AWS view provides information about all analytic workspaces. Use the following SQL command to get a list of names, their owners, and the version:
SELECT owner, aw_name, aw_version FROM DBA_AWS; OWNER AW_NAME AW_VERSION ---------- ------------------------------ ---------- SYS EXPRESS 11.2 GLOBAL GLOBAL 11.2 SYS AWCREATE 11.2 SH SH 11.2 SYS AWMD 11.2 SYS AWXML 11.2 SYS AWREPORT 11.2 SYS AWCREATE10G 11.2
To find out the size in bytes of the tablespace extents for a particular analytic workspace, use the following SQL statements, replacing GLOBAL with the name of your analytic workspace.
SELECT extnum, SUM(dbms_lob.getlength(awlob)) bytes FROM global.aw$global
GROUP BY extnum;
EXTNUM BYTES
---------- ----------
0 191776956
To see the size of the LOB table containing an analytic workspace, use a SQL command like the following, replacing GLOBAL.AW$GLOBAL with the qualified name of your analytic workspace.
SELECT ROUND(SUM(dbms_lob.getlength(awlob))/1024,0) kb
FROM global.aw$global;
KB
----------
187282
The DBA_OBJECTS view provides the creation date of the objects in your database. The following SQL command generates an easily readable report for analytic workspaces.
SELECT owner, object_name, created, status FROM dba_objects
WHERE object_name LIKE 'AW$%' AND object_name!='AW$'
GROUP BY owner, object_name, created, status
ORDER BY owner, object_name;
OWNER OBJECT_NAME CREATED STATUS
---------- --------------- --------- -------
GLOBAL AW$GLOBAL 01-APR-09 VALID
SYS AW$AWCREATE 26-MAR-09 VALID
SYS AW$AWCREATE10G 26-MAR-09 VALID
SYS AW$AWMD 26-MAR-09 VALID
SYS AW$AWREPORT 26-MAR-09 VALID
SYS AW$AWXML 26-MAR-09 VALID
SYS AW$EXPRESS 26-MAR-09 VALID
7 rows selected.
You can download a file that contains several SQL scripts from the Oracle OLAP Web site on the Oracle Technology Network. These scripts typically extract information from two or more system views and generate a report that may be useful in monitoring and tuning a database. To download the file, use this URL:
http://www.oracle.com/technology/products/bi/olap/olap_dba_scripts.zip
Table 7-6 describes these scripts. For more information, refer to the README file provided with the scripts.
| SQL Script | Description |
|---|---|
|
|
Identifies the objects in the buffer cache that are related to analytic workspaces. |
|
|
Tallies the reads from temporary and permanent tablespaces, the writes to cache, and the rows processed in analytic workspaces. |
|
|
Displays the amount of disk space used by each analytic workspace. |
|
|
Provides extensive information about the tablespaces used by analytic workspaces. |
|
|
Identifies the users of analytic workspaces. |
|
|
Describes the wait events experienced by users of analytic workspaces over the previous hour. |
|
|
Calculates the buffer cache hit ratio. |
|
|
Indicates whether the database parameters that limit the number of open cursors are set too low. |
|
|
Determines how much PGA is in use, the size of the OLAP page pool, and the hit/miss ratio for OLAP pages for each user. |
|
|
Determines how much PGA is consumed by the OLAP page pool to perform operations on analytic workspaces. |
|
|
Identifies the use of cursors, PGA, and UGA for each open session. |
|
|
Calculates the shared pool hit ratio. |
Several of the scripts listed in "OLAP DBA Scripts" provide detailed information about the use of memory and other database resources by OLAP sessions. You can use these scripts as is, or you can use them as the starting point for developing your own scripts.
Example 7-3 shows the information returned by the session_resources script. It lists the use of resources such as cursors, PGA, and UGA.
Example 7-3 Querying Session Resources
@session_resources
USERNAME NAME VALUE
-------------------- ------------------------------ ----------
GLOBAL:86 opened cursors cumulative 621
opened cursors current 18
session cursor cache count 50
session cursor cache hits 432
session pga memory 5356368
session pga memory max 10468176
session stored procedure space 0
session uga memory 4230692
session uga memory max 7049780
9 rows selected.
Several of the scripts listed in "OLAP DBA Scripts" provide detailed information about the use of disk space by analytic workspaces. Example 7-4 shows the information returned by the aw_size script. It lists all of the analytic workspaces in the database, the disk space they consume, and the tablespaces in which they are stored.
Example 7-4 Querying the Use of Disk Space By Analytic Workspaces
@aw_size
Analytic Workspace On Disk MB Tablespace
---------------------------------------- --------------- --------------------
GLOBAL.GLOBAL 249.31 GLOBAL
SYS.AWCREATE 7.81 SYSAUX
SYS.AWCREATE10G 1.63 SYSAUX
SYS.AWMD 8.00 SYSAUX
SYS.AWREPORT 1.63 SYSAUX
SYS.AWXML 18.00 SYSAUX
SYS.EXPRESS 2.25 SYSAUX
---------------
Total Disk: 288.63
7 rows selected.
You can backup and recover analytic workspaces using the same tools and procedures as the rest of your database.
Oracle Recovery Manager (RMAN) is a powerful tool that simplifies, automates, and improves the performance of backup and recovery operations. RMAN enables one time backup configuration, automatic management of backups, and archived logs based on a user-specified recovery window, restartable backups and restores, and test restore/recovery.
RMAN implements a recovery window to control when backups expire. This lets you establish a period of time during which it is possible to discover logical errors and fix the affected objects by doing a database or tablespace point-in-time recovery. RMAN also automatically expires backups that are no longer required to restore the database to a point-in-time within the recovery window. Control file auto backup also allows for restoring or recovering a database, even when an RMAN repository is not available.
You can copy analytic workspaces in several different ways, either to replicate them on another computer or to back them up.
Data Pump. Analytic workspaces are copied with the other objects in a schema or database export. Use the expdp/impdp database utilities.
Tip:
Verify that the target schema of an import has the OLAP_XS_ADMIN privilege. Otherwise, the analytic workspace will not be created with the necessary permissions.Transportable Tablespaces. Analytic workspaces are copied with the other objects to a transportable tablespace. However, you can only transport the tablespace to the same platform (for example, from Linux to Linux, Solaris to Solaris, or Windows to Windows) because the OLAP DECIMAL data type is hardware dependent. Use the expdp/impdp database utilities. Transportable tablespaces are much faster than dump files.
XML Templates. A template saves the XML definition of objects in an analytic workspace. You can save the entire analytic workspace, or individual cubes, dimensions, and calculated measures. Using a saved template, you can create an analytic workspace exactly like an existing one. The template does not save any data, nor does it save any customizations to the analytic workspace. You can copy a template to a different platform.
The owner of an analytic workspace can create an XML template, or export the schema to a dump file. Only users with the EXP_FULL_DATABASE privilege or a privileged user (such as SYS or a user with the DBA role) can export the full database or create a transportable tablespace.
See Also:
"Using Templates to Re-Create Dimensional Objects" for information about XML templates
Oracle Database Utilitiesor information about Oracle Data Pump and the expdp/impdp commands
A cube materialized view is an Oracle OLAP cube that has been enhanced with the capabilities of a materialized view at build time.
The data dictionary contains numerous static views that provide information about materialized views. They list cube materialized views along with all other materialized views.
See Also:
Oracle Database Reference for complete descriptions of the data dictionary viewsUSER_MVIEWS contains a row for each materialized view owned by the current user. The following query lists the materialized views owned by the GLOBAL user. The CB$ prefix identifies a cube materialized view.
SELECT mview_name, refresh_mode "MODE", refresh_method "METHOD",
last_refresh_date "DATE", staleness FROM user_mviews;
MVIEW_NAME MODE METHOD DATE STALENESS
------------------------ -------- -------- --------------- ----------
CB$CUSTOMER_MARKET DEMAND COMPLETE 20-MAR-09 UNKNOWN
CB$CHANNEL_PRIMARY DEMAND COMPLETE 20-MAR-09 UNKNOWN
CB$CUSTOMER_SHIPMENTS DEMAND COMPLETE 20-MAR-09 UNKNOWN
CB$PRODUCT_PRIMARY DEMAND COMPLETE 20-MAR-09 UNKNOWN
CB$TIME_CALENDAR DEMAND COMPLETE 20-MAR-09 UNKNOWN
CB$TIME_FISCAL DEMAND COMPLETE 20-MAR-09 UNKNOWN
CB$UNITS_CUBE DEMAND FORCE 20-MAR-09 UNKNOWN
7 rows selected.
The example shows the cube materialized views defined by Analytic Workspace Manager: One for each dimension hierarchy and one for each cube.
Oracle Database can maintain a set of logs on the master tables for the cube materialized views. These logs support incremental (fast) refresh of the cube. The script generated by the Relational Schema Advisor creates a log for each fact and dimension table to record any changes to the data. The following query lists the materialized view logs owned by the GLOBAL user:
SELECT master, log_table FROM user_mview_logs; MASTER LOG_TABLE ------------------------------ ------------------------------ CHANNEL_DIM MLOG$_CHANNEL_DIM CUSTOMER_DIM MLOG$_CUSTOMER_DIM PRODUCT_DIM MLOG$_PRODUCT_DIM TIME_DIM MLOG$_TIME_DIM UNITS_FACT MLOG$_UNITS_FACT
You can initiate a data refresh of a cube materialized view in several different ways using Analytic Workspace Manager or a PL/SQL package:
Automatic Refresh: On the Materialized View tab for a cube, you can create a regular schedule for the materialized view refresh subsystem, as described in "Adding Materialized View Capability to a Cube".
Maintenance Wizard: The Maintenance Wizard is available for refreshing all cubes and dimensions, including cube materialized views.
DBMS_CUBE: The DBMS_CUBE PL/SQL package is available for refreshing all cubes, cube dimensions, and cube materialized views.
DBMS_MVIEW: The DBMS_MVIEW PL/SQL package contains several procedures for use with cube materialized views.
DBMS_CUBE can be used to create and populate an analytic workspace. You can use it to maintain any cube, including cube materialized views.
The following command initiates a complete refresh of UNITS_CUBE, which is enabled as a cube materialized view. It automatically refreshes any stale dimensions before refreshing the cube.
EXECUTE dbms_cube.build('GLOBAL.UNITS_CUBE');
You can determine the refresh method from USER_MVIEWS, as shown in "Identifying Cube Materialized Views".
DBMS_MVIEW can be used to refresh all types of materialized views. These refresh procedures can be used with cube materialized views:
REFRESH refreshes a list of one or more materialized views.
REFRESH_ALL_MVIEWS refreshes all materialized views that meet certain criteria.
REFRESH_DEPENDENT refreshes all materialized views that depend on a particular master table and meet certain criteria.
Dimensions must be refreshed before the cube. An error is raised during refresh of a cube materialized view if any of its associated dimension materialized views are stale. The procedures in DBMS_MVIEW can refresh multiple materialized views in one call, but they do not guarantee the refresh order. To control the refresh order, call DBMS_MVIEW.REFRESH for the cube materialized view separately from its dimension materialized views.
The following command initiates a refresh of the materialized view for the CHANNEL_PRIMARY hierarchy.
EXECUTE dbms_mview.refresh('CB$CHANNEL_PRIMARY', 'C');
In Analytic Workspace Manager, you can specify the COMPLETE, FAST, or FORCE methods for refreshing a cube. Two additional methods, FAST_PCT and FAST_SOLVE, are invoked by the materialized view subsystem. They are not separate choices.
Table 7-7 describes the refresh methods that are supported on cube materialized views.
Table 7-7 Refresh Methods For Cube Materialized Views
| Refresh Method | Description |
|---|---|
|
|
Deletes and recreates the cube. This option supports arbitrarily complex mappings from the source tables to the cube. |
|
|
Loads and re-aggregates only changed values, based on the materialized view logs or, after direct path loading, on the ALL_SUMDELTA data dictionary view. The source for the refresh is the incremental differences that have been captured in the materialized view logs, rather than the original mapped sources. These differences are used to incrementally rebuild the cube. Only cells that are affected by the changed values are re-aggregated. This option supports only simple mappings for cube materialized views, that is, where no expressions (other than table.column), views, or aggregations occur in the query defining the mapping. The materialized view subsystem determines whether to perform a |
|
|
Loads and re-aggregates data only from changed partitions. This method works best when the source table and the cube are partitioned on the same dimension.
|
|
|
Loads and re-aggregates only changed values, based on the original mapped data source.
This option is supported for arbitrarily complex mappings from the source tables to the cube. To discover whether a |
|
|
Loads and re-aggregates values using the best method possible. When a |
The build log lists the CLEAR LEAVES command when the FAST SOLVE method was used. Example 7-5 shows the rows of CUBE_BUILD_LOG concerned with building UNITS_CUBE.
See Also:
"Maintenance Logs"Example 7-5 Identifying a FAST SOLVE Refresh
SELECT build_object, status, command FROM cube_build_log
WHERE build_object='UNITS_CUBE'
AND build_id=8;
BUILD_OBJECT STATUS COMMAND
------------ ---------- -------------------------
UNITS_CUBE STARTED COMPILE AGGMAP
UNITS_CUBE COMPLETED COMPILE AGGMAP
UNITS_CUBE STARTED UPDATE
UNITS_CUBE COMPLETED UPDATE
UNITS_CUBE STARTED CLEAR LEAVES
UNITS_CUBE COMPLETED CLEAR LEAVES
UNITS_CUBE STARTED LOAD
UNITS_CUBE COMPLETED LOAD
UNITS_CUBE STARTED SOLVE
UNITS_CUBE COMPLETED SOLVE
UNITS_CUBE STARTED UPDATE
UNITS_CUBE COMPLETED UPDATE
UNITS_CUBE STARTED ANALYZE
UNITS_CUBE COMPLETED ANALYZE
14 rows selected.
Query rewrite changes a query to select data from the materialized views instead of calculating the result set from the master tables. The transformation is fully transparent to the client, and requires no mention of the materialized views in the SQL statement. In the case of cube materialized views, the query is written against the tables or views of a star or snowflake schema, and it is transformed into a query against a cube materialized view. This transformation can result in significant improvements in run-time performance.
Query rewrite requires optimizer statistics on the cubes and dimensions. You can discover whether a query is rewritten by generating and examining its execution plan.
Oracle Database uses two initialization parameters to control query rewrite:
QUERY_REWRITE_ENABLED: Enables or disables query rewrite globally for the database.
QUERY_REWRITE_INTEGRITY: Determines the degree to which query rewrite monitors the consistency of materialized views with the source data. The trusted or stale tolerated settings are recommended when using rewrite to cube materialized views.
Administration of cube materialized views is the same as any other materialized view except that the cube materialized views must be in the same schema as the analytic workspace. Users require the GLOBAL QUERY REWRITE privilege to have rewrite to materialized views that are in schemas other than their own. However, the owner can access the materialized views from any schema without additional privileges.
See Also:
"Analyzing Cubes and Dimensions" for information about optimizer statistics
Viewing Execution Plans for information about execution plans
Oracle Database Reference for complete descriptions of the initialization parameters
Oracle Database has numerous PL/SQL packages for managing materialized views. Cube materialized views are optimized to provide the best performance, so you have no need to use most of these packages. Few design decisions remain for you to make. For this reason, the TUNE_MVIEW procedure of DBMS_ADVISOR is disabled for cube materialized views.
However, there are a few packages that you may find useful, as shown in Table 7-8.
Table 7-8 PL/SQL Packages for Cube Materialized Views
| Package | Description |
|---|---|
|
Executes data refreshes. See "Initiating a Data Refresh". You can use the |
|
|
Displays an execution plan. See "Viewing Execution Plans". |