Whenever a resumable statement is suspended in any session, this trigger can have either of two effects:

• If an undo segment has reached its space limit, then a message is sent to the DBA and the statement is terminated.

• If any other recoverable error has occurred, the timeout interval is reset to 8 hours.

Here are the statements for this example:

CREATE OR REPLACE TRIGGER resumable_default
AFTER SUSPEND
ON DATABASE
DECLARE
   /* declare transaction in this trigger is autonomous */
   /* this is not required because transactions within a trigger
      are always autonomous */
   PRAGMA AUTONOMOUS_TRANSACTION;
   cur_sid           NUMBER;
   cur_inst          NUMBER;
   errno             NUMBER;
   err_type          VARCHAR2;
   object_owner      VARCHAR2;
   object_type       VARCHAR2;
   table_space_name  VARCHAR2;
   object_name       VARCHAR2;
   sub_object_name   VARCHAR2;
   error_txt         VARCHAR2;
   msg_body          VARCHAR2;
   ret_value         BOOLEAN;
   mail_conn         UTL_SMTP.CONNECTION;
BEGIN
   -- Get session ID
   SELECT DISTINCT(SID) INTO cur_SID FROM V$MYSTAT;

   -- Get instance number
   cur_inst := userenv('instance');

   -- Get space error information
   ret_value := 
   DBMS_RESUMABLE.SPACE_ERROR_INFO(err_type,object_type,object_owner,
        table_space_name,object_name, sub_object_name);
   /*
   -- If the error is related to undo segments, log error, send email
   -- to DBA, and terminate the statement. Otherwise, set timeout to 8 hours.
   -- 
   -- sys.rbs_error is a table which is to be
   -- created by a DBA manually and defined as
   -- (sql_text VARCHAR2(1000), error_msg VARCHAR2(4000),
   -- suspend_time DATE)
   */

   IF OBJECT_TYPE = 'UNDO SEGMENT' THEN
       /* LOG ERROR */
       INSERT INTO sys.rbs_error (
           SELECT SQL_TEXT, ERROR_MSG, SUSPEND_TIME
           FROM DBMS_RESUMABLE
           WHERE SESSION_ID = cur_sid AND INSTANCE_ID = cur_inst
        );
       SELECT ERROR_MSG INTO error_txt FROM DBMS_RESUMABLE 
           WHERE SESSION_ID = cur_sid and INSTANCE_ID = cur_inst;

        -- Send email to receipient through UTL_SMTP package
        msg_body:='Subject: Space Error Occurred

                   Space limit reached for undo segment ' || object_name || 
                   on ' || TO_CHAR(SYSDATE, 'Month dd, YYYY, HH:MIam') ||
                   '. Error message was ' || error_txt;

        mail_conn := UTL_SMTP.OPEN_CONNECTION('localhost', 25);
        UTL_SMTP.HELO(mail_conn, 'localhost');
        UTL_SMTP.MAIL(mail_conn, 'sender@localhost');
        UTL_SMTP.RCPT(mail_conn, 'recipient@localhost');
        UTL_SMTP.DATA(mail_conn, msg_body);
        UTL_SMTP.QUIT(mail_conn);

        -- Terminate the statement
        DBMS_RESUMABLE.ABORT(cur_sid);
    ELSE
        -- Set timeout to 8 hours
        DBMS_RESUMABLE.SET_TIMEOUT(28800);
    END IF;

    /* commit autonomous transaction */
    COMMIT;   
END;
/

The benefits of segment shrink are these:

• Compaction of data leads to better cache utilization, which in turn leads to better online transaction processing (OLTP) performance.

• The compacted data requires fewer blocks to be scanned in full table scans, which in turns leads to better decision support system (DSS) performance.

Segment shrink is an online, in-place operation. DML operations and queries can be issued during the data movement phase of segment shrink. Concurrent DML operations are blocked for a short time at the end of the shrink operation, when the space is deallocated. Indexes are maintained during the shrink operation and remain usable after the operation is complete. Segment shrink does not require extra disk space to be allocated.

Segment shrink reclaims unused space both above and below the high water mark. In contrast, space deallocation reclaims unused space only above the high water mark. In shrink operations, by default, the database compacts the segment, adjusts the high water mark, and releases the reclaimed space.

Segment shrink requires that rows be moved to new locations. Therefore, you must first enable row movement in the object you want to shrink and disable any rowid-based triggers defined on the object. You enable row movement in a table with the ALTER TABLE ... ENABLE ROW MOVEMENT command.

Shrink operations can be performed only on segments in locally managed tablespaces with automatic segment space management (ASSM). Within an ASSM tablespace, all segment types are eligible for online segment shrink except these:

• IOT mapping tables

• Tables with rowid based materialized views

• Tables with function-based indexes

• SECUREFILE LOBs

• Tables compressed with the following compression methods:

  • Basic table compression using ROW STORE COMPRESS BASIC

  • Warehouse compression using COLUMN STORE COMPRESS FOR QUERY

  • Archive compression using COLUMN STORE COMPRESS FOR ARCHIVE

  However, tables compressed with advanced row compression using ROW STORE COMPRESS ADVANCED are eligible for online segment shrink. See "Consider Using Table Compression" for information about table compression methods.

Invoking Online Segment Shrink

Before invoking online segment shrink, view the findings and recommendations of the Segment Advisor. For more information, see "Using the Segment Advisor".

You invoke online segment shrink with Cloud Control or with SQL commands in SQL*Plus. The remainder of this section discusses the command line method.

You can shrink space in a table, index-organized table, index, partition, subpartition, materialized view, or materialized view log. You do this using ALTER TABLE, ALTER INDEX, ALTER MATERIALIZED VIEW, or ALTER MATERIALIZED VIEW LOG statement with the SHRINK SPACE clause.

Two optional clauses let you control how the shrink operation proceeds:

• The COMPACT clause lets you divide the shrink segment operation into two phases. When you specify COMPACT, Oracle Database defragments the segment space and compacts the table rows but postpones the resetting of the high water mark and the deallocation of the space until a future time. This option is useful if you have long-running queries that might span the operation and attempt to read from blocks that have been reclaimed. The defragmentation and compaction results are saved to disk, so the data movement does not have to be redone during the second phase. You can reissue the SHRINK SPACE clause without the COMPACT clause during off-peak hours to complete the second phase.

• The CASCADE clause extends the segment shrink operation to all dependent segments of the object. For example, if you specify CASCADE when shrinking a table segment, all indexes of the table will also be shrunk. (You need not specify CASCADE to shrink the partitions of a partitioned table.) To see a list of dependent segments of a given object, you can run the OBJECT_DEPENDENT_SEGMENTS procedure of the DBMS_SPACE package.

As with other DDL operations, segment shrink causes subsequent SQL statements to be reparsed because of invalidation of cursors unless you specify the COMPACT clause.

Examples

Shrink a table and all of its dependent segments (including BASICFILE LOB segments):

ALTER TABLE employees SHRINK SPACE CASCADE;

Shrink a BASICFILE LOB segment only:

ALTER TABLE employees MODIFY LOB (perf_review) (SHRINK SPACE);

Shrink a single partition of a partitioned table:

ALTER TABLE customers MODIFY PARTITION cust_P1 SHRINK SPACE;

Shrink an IOT index segment and the overflow segment:

ALTER TABLE cities SHRINK SPACE CASCADE;

Shrink an IOT overflow segment only:

ALTER TABLE cities OVERFLOW SHRINK SPACE;

Before deallocation, you can run the UNUSED_SPACE procedure of the DBMS_SPACE package, which returns information about the position of the high water mark and the amount of unused space in a segment. For segments in locally managed tablespaces with automatic segment space management, use the SPACE_USAGE procedure for more accurate information on unused space.

The following statements deallocate unused space in a segment (table, index or cluster):

ALTER TABLE table DEALLOCATE UNUSED KEEP integer;
ALTER INDEX index DEALLOCATE UNUSED KEEP integer;
ALTER CLUSTER cluster DEALLOCATE UNUSED KEEP integer;

The KEEP clause is optional and lets you specify the amount of space retained in the segment. You can verify that the deallocated space is freed by examining the DBA_FREE_SPACE view.

Example: Using DBMS_SPACE.UNUSED_SPACE

The following SQL*Plus example uses the DBMS_SPACE package to obtain unused space information.

SQL> VARIABLE total_blocks NUMBER
SQL> VARIABLE total_bytes NUMBER
SQL> VARIABLE unused_blocks NUMBER
SQL> VARIABLE unused_bytes NUMBER
SQL> VARIABLE lastextf NUMBER
SQL> VARIABLE last_extb NUMBER
SQL> VARIABLE lastusedblock NUMBER
SQL> exec DBMS_SPACE.UNUSED_SPACE('SCOTT', 'EMP', 'TABLE', :total_blocks, -
>    :total_bytes,:unused_blocks, :unused_bytes, :lastextf, -
>    :last_extb, :lastusedblock);

PL/SQL procedure successfully completed.

SQL> PRINT

TOTAL_BLOCKS
------------
           5

TOTAL_BYTES
-----------
      10240

...

LASTUSEDBLOCK
-------------
            3

These views display information about space usage in schema objects:

See Oracle Database PL/SQL Packages and Types Reference for details on the parameters of this procedure.

The procedure has two variants. The first variant uses average row size to estimate size. The second variant uses column information to estimate table size. Both variants require as input the following values:

• TABLESPACE_NAME: The tablespace in which the object will be created. The default is the SYSTEM tablespace.

• ROW_COUNT: The anticipated number of rows in the table.

• PCT_FREE: The percentage of free space you want to reserve in each block for future expansion of existing rows due to updates.

In addition, the first variant also requires as input a value for AVG_ROW_SIZE, which is the anticipated average row size in bytes.

The second variant also requires for each anticipated column values for COLINFOS, which is an object type comprising the attributes COL_TYPE (the data type of the column) and COL_SIZE (the number of characters or bytes in the column).

The procedure returns two values:

• USED_BYTES: The actual bytes used by the data, including overhead for block metadata, PCT_FREE space, and so forth.

• ALLOC_BYTES: The amount of space anticipated to be allocated for the object taking into account the tablespace extent characteristics.

The procedure requires as input the following values:

• DDL: The CREATE INDEX statement that would create the index. The table specified in this DDL statement must be an existing table.

• [Optional] PLAN_TABLE: The name of the plan table to use. The default is NULL.

The results returned by this procedure depend on statistics gathered on the segment. Therefore, be sure to obtain statistics shortly before executing this procedure. In the absence of recent statistics, the procedure does not issue an error, but it may return inappropriate results. The procedure returns the following values:

• USED_BYTES: The number of bytes representing the actual index data.

• ALLOC_BYTES: The amount of space allocated for the index in the tablespace.

The function retrieves the space use totals from the Automatic Workload Repository or computes current space use and combines it with historic space use changes retrieved from Automatic Workload Repository. See Oracle Database PL/SQL Packages and Types Reference for detailed information on the parameters of this function.

The function requires as input the following values:

• OBJECT_OWNER: The owner of the object.

• OBJECT_NAME: The name of the object.

• PARTITION_NAME: The name of the table or index partition, is relevant. Specify NULL otherwise.

• OBJECT_TYPE: The type of the object.

• START_TIME: A TIMESTAMP value indicating the beginning of the growth trend analysis.

• END_TIME: A TIMESTAMP value indicating the end of the growth trend analysis. The default is "NOW".

• INTERVAL: The length in minutes of the reporting interval during which the function should retrieve space use information.

• SKIP_INTERPOLATED: Determines whether the function should omit values based on recorded statistics before and after the INTERVAL ('YES') or not ('NO'). This setting is useful when the result table will be displayed as a table rather than a chart, because you can see more clearly how the actual recording interval relates to the requested reporting interval.

The function returns a table, each of row of which provides space use information on the object for one interval. If the return table is very large, the results are pipelined so that another application can consume the information as it is being produced. The output table has the following columns:

• TIMEPOINT: A TIMESTAMP value indicating the time of the reporting interval.

  Records are not produced for values of TIME that precede the oldest recorded statistics for the object.

• SPACE_USAGE: The number of bytes actually being used by the object data.

• SPACE_ALLOC: The number of bytes allocated to the object in the tablespace at that time.

• QUALITY: A value indicating how well the requested reporting interval matches the actual recording of statistics. This information is useful because there is no guaranteed reporting interval for object size use statistics, and the actual reporting interval varies over time and from object to object.

  The values of the QUALITY column are:

• • GOOD: The value whenever the value of TIME is based on recorded statistics with a recorded timestamp within 10% of the INTERVAL specified in the input parameters.

  • INTERPOLATED: The value did not meet the criteria for GOOD, but was based on recorded statistics before and after the value of TIME. Current in-memory statistics can be collected across all instances in a cluster and treated as the "recorded" value for the present time.

  • PROJECTION: The value of TIME is in the future as of the time the table was produced. In an Oracle Real Application Clusters environment, the rules for recording statistics allow each instance to choose independently which objects will be selected.

  The output returned by this function is an aggregation of values recorded across all instances in an Oracle RAC environment. Each value can be computed from a combination of GOOD and INTERPOLATED values. The aggregate value returned is marked GOOD if at least 80% of that value was derived from GOOD instance values.