Abstract: A global index with a repartitioning operator is provided. A method for executing a query includes receiving a query including a request to search a first table based on a first value in a first column. The method may include generating a second table by partitioning the second table based on the first column and including, in the second table, a partition identifier and a reference row identifier. The method may include pruning the second table such that a row corresponding to the first value remains in the second table. The method may include repartitioning the row to a stream based on the partition identifier. The method may include executing the query by at least searching the partition of the first table based on the stream and the row identifier of the row. Related systems and articles of manufacture are provided.

Abstract: Methods and apparatus are disclosed for staged query compilation. One or more intermediate plans between a query and its execution plan are stored according to a common specification for plan data structures. Data sources, a plan flow, and annotations can be stored in respective fields of the plan data structure, which can be extended with a field for a serialized execution plan. Plan data structures provide a stable interface for integration of local and external software modules, and decouple plan representation from plan optimization. Use cases are disclosed for integrating offline optimization with inline software modules, for integrating local query handling with external services, for caching intermediate plans, and for archiving plans across version changes of optimizers. A hub architecture flexibly supports numerous compilation workflows. Disclosed technologies are suitable for cloud deployments and for migration of databases into the cloud.

Abstract: A global index with a repartitioning operator is provided. A method for executing a query includes receiving a query including a request to search a first table based on a first value in a first column. The method may include generating a second table by partitioning the second table based on the first column and including, in the second table, a partition identifier and a reference row identifier. The method may include pruning the second table such that a row corresponding to the first value remains in the second table. The method may include repartitioning the row to a stream based on the partition identifier. The method may include executing the query by at least searching the partition of the first table based on the stream and the row identifier of the row. Related systems and articles of manufacture are provided.

Abstract: Methods and apparatus are disclosed for staged query compilation. One or more intermediate plans between a query and its execution plan are stored according to a common specification for plan data structures. Data sources, a plan flow, and annotations can be stored in respective fields of the plan data structure, which can be extended with a field for a serialized execution plan. Plan data structures provide a stable interface for integration of local and external software modules, and decouple plan representation from plan optimization. Use cases are disclosed for integrating offline optimization with inline software modules, for integrating local query handling with external services, for caching intermediate plans, and for archiving plans across version changes of optimizers. A hub architecture flexibly supports numerous compilation workflows. Disclosed technologies are suitable for cloud deployments and for migration of databases into the cloud.

Abstract: Provided is a system and method for reconstructing and visualizing transformation steps that are performed to an optimized database query. In one example, the method may include receiving a database query including an initial set of execution steps, generating a plurality of alternative sets of execution steps for the database query based on transformations to the initial set of execution steps, selecting an alternative set of execution steps from among the plurality of alternative sets of execution steps based on a performance of the alternative set of execution steps, identifying transformations that are used to transform the initial set of execution steps into the selected alternative set of execution steps, and displaying information about the identified transformations via a user interface.

Abstract: Provided is a system and method for reconstructing and visualizing transformation steps that are performed to an optimized database query. In one example, the method may include receiving a database query including an initial set of execution steps, generating a plurality of alternative sets of execution steps for the database query based on transformations to the initial set of execution steps, selecting an alternative set of execution steps from among the plurality of alternative sets of execution steps based on a performance of the alternative set of execution steps, identifying transformations that are used to transform the initial set of execution steps into the selected alternative set of execution steps, and displaying information about the identified transformations via a user interface.