Abstract: Techniques for replication rule evaluation are provided. A replication rule is received at a first node of a plurality of nodes where the replication rule defines object replication among the plurality of nodes. The replication rule is labeled as pending, where a second replication rule on the first node is labeled as active. Upon receiving a request to predict an effect of the replication rule, a first object of a plurality of objects is identified based on the first replication rule. Upon determining that the first object is present on the first node but is not present on a second node of the plurality of nodes, an indication of the first object is outputted.

Abstract: Techniques for dynamically detecting objects that are out of sync in an active mirrored environment are provided. A request is received at a local node of an active mirroring environment from a system function to perform a change operation on an object. Upon determining that the object is OOS, it is determined whether the local node or a remote node of the active mirroring environment has the most recent changes for the object. In one embodiment, the determination includes analyzing corresponding time stamps of changes listed in a repository of changes for objects in the mirrored environment. Upon determining that a remote node has the most recent changes for the object, a blocking attribute is set and the requested operation on the object blocked. However, upon determining that the local node has the most recent changes for the object, a tracking attribute is set and the requested operation allowed.

Abstract: Techniques for replication rule evaluation are provided. A replication rule is received at a first node of a plurality of nodes where the replication rule defines object replication among the plurality of nodes. The replication rule is labeled as pending, where a second replication rule on the first node is labeled as active. Upon receiving a request to predict an effect of the replication rule, a first object of a plurality of objects is identified based on the first replication rule. Upon determining that the first object is present on the first node but is not present on a second node of the plurality of nodes, an indication of the first object is outputted.

Abstract: Techniques for dynamically detecting objects that are out of sync in an active mirrored environment are provided. A request is received at a local node of an active mirroring environment from a system function to perform a change operation on an object. Upon determining that the object is OOS, it is determined whether the local node or a remote node of the active mirroring environment has the most recent changes for the object. In one embodiment, the determination includes analyzing corresponding time stamps of changes listed in a repository of changes for objects in the mirrored environment. Upon determining that a remote node has the most recent changes for the object, a blocking attribute is set and the requested operation on the object blocked. However, upon determining that the local node has the most recent changes for the object, a tracking attribute is set and the requested operation allowed.

Abstract: In an embodiment, a first driver source specified by a first execution plan that implements a query is designated, and a second driver source specified by a second execution plan that implements the query is designated. A portion of the first execution plan and a portion of the second execution plan are executed. If a unique identifier of a first row returned by the executing the portion of the first execution plan does not match all unique identifiers of all rows from the second driver source that were saved to a result set by the executing the portion of the second execution plan, then the first row returned by the executing the portion of the first execution plan is added to the result set and the unique identifier of the first row that was returned by the executing the portion of the first execution plan is added to a unique identifier log.

Abstract: In an embodiment an execution plan for a query is created. A wakeup threshold is set proportional to an amount of time taken by the creation of the execution plan. In various embodiments, the wakeup threshold is increased by a percentage equal to one minus a percentage of free resources at a computer system, is increased inversely proportional to an amount of execution time of a previous execution of the execution plan, or is decreased proportional to a number of times the execution plan was executed. A portion of the execution plan is executed to produce a portion of rows in a result set until the wakeup threshold expires. After the wakeup threshold expires, changes to the execution plan are evaluated.

Abstract: In an embodiment, a portion of the execution plan is executed to produce a portion of records in a partial result set. If a first join of a table is performed that eliminates more than a first threshold number of records from the partial result set, a determination is made whether an estimated cost of a forced primary join is less than an estimated cost of a star join. If the estimated cost of the forced primary join is less than the estimated cost of the star join, then the table is moved first in a join order in the execution plan, the portion of the records in the partial result set is discarded, and the execution is re-started with a different portion of the execution plan to produce a different portion of the records.

Abstract: In an embodiment, a first driver source specified by a first execution plan that implements a query is designated, and a second driver source specified by a second execution plan that implements the query is designated. A portion of the first execution plan and a portion of the second execution plan are executed. If a unique identifier of a first row returned by the executing the portion of the first execution plan does not match all unique identifiers of all rows from the second driver source that were saved to a result set by the executing the portion of the second execution plan, then the first row returned by the executing the portion of the first execution plan is added to the result set and the unique identifier of the first row that was returned by the executing the portion of the first execution plan is added to a unique identifier log.

Abstract: In an embodiment an execution plan for a query is created. A wakeup threshold is set proportional to an amount of time taken by the creation of the execution plan. In various embodiments, the wakeup threshold is increased by a percentage equal to one minus a percentage of free resources at a computer system, is increased inversely proportional to an amount of execution time of a previous execution of the execution plan, or is decreased proportional to a number of times the execution plan was executed. A portion of the execution plan is executed to produce a portion of rows in a result set until the wakeup threshold expires. After the wakeup threshold expires, changes to the execution plan are evaluated.

Abstract: A process combines multiple grouping sets into single rollup sets with depth lists defining the levels of grouping that must be performed. Grouping sets are identified that are contained within other sets and combined into single rollups with depth lists. Cube aggregation conversion to rollup aggregation is provided for optimizing database query processing. Natural sets of rollup hierarchies within a cube are recognized and the cube is converted into those rollup hierarchies. Once converted, the rollup aggregation is performed to significantly reduce required processing.

Abstract: In an embodiment, a portion of the execution plan is executed to produce a portion of records in a partial result set. If a first join of a table is performed that eliminates more than a first threshold number of records from the partial result set, a determination is made whether an estimated cost of a forced primary join is less than an estimated cost of a star join. If the estimated cost of the forced primary join is less than the estimated cost of the star join, then the table is moved first in a join order in the execution plan, the portion of the records in the partial result set is discarded, and the execution is re-started with a different portion of the execution plan to produce a different portion of the records.

Abstract: A process combines multiple grouping sets into single rollup sets with depth lists defining the levels of grouping that must be performed. Grouping sets are identified that are contained within other sets and combined into single rollups with depth lists. Cube aggregation conversion to rollup aggregation is provided for optimizing database query processing. Natural sets of rollup hierarchies within a cube are recognized and the cube is converted into those rollup hierarchies. Once converted, the rollup aggregation is performed to significantly reduce required processing.