Abstract: Herein are acceleration techniques for resuming offloaded execution by replacing a failed computer with a hot spare computer. In an embodiment, a distributed system configures a DBMS, a set of participating computers, and a set of spare computers. The DBMS receives a query of a database. From the query, an offload query plan is generated for distributed execution. The DBMS sends the offload query plan and a respective portion of the database to each participating computer. The distributed system detects that a participating computer failed after the offload query plan was sent. Responsively, the DBMS sends the same offload query plan and same respective portion of the database of the failed computer to a replacement computer from the spare computers. Despite the computer failure, the DBMS receives results of successful distributed execution of the offload query plan that include a result from the replacement computer.

Abstract: Herein are computerized techniques for deploying JavaScript and TypeScript stored procedures and user-defined functions into a database management system (DBMS). In an embodiment, a computer generates a SQL call specification for each subroutine of one or more subroutines encoded in a scripting language. The generating is based on a signature declaration of the subroutine. Each subroutine comprises a definition of a stored procedure or a user-defined function. The computer packages the definition and the SQL call specification of each subroutine into a single bundle file. The definition and the SQL call specification of each subroutine are deployed into a DBMS from the single bundle file. Eventually, the SQL call specification of at least one subroutine is invoked to execute the definition of the subroutine in the DBMS.

Abstract: Herein are acceleration techniques for resuming offloaded execution by replacing a failed computer with a hot spare computer. In an embodiment, a distributed system configures a DBMS, a set of participating computers, and a set of spare computers. The DBMS receives a query of a database. From the query, an offload query plan is generated for distributed execution. The DBMS sends the offload query plan and a respective portion of the database to each participating computer. The distributed system detects that a participating computer failed after the offload query plan was sent. Responsively, the DBMS sends the same offload query plan and same respective portion of the database of the failed computer to a replacement computer from the spare computers. Despite the computer failure, the DBMS receives results of successful distributed execution of the offload query plan that include a result from the replacement computer.

Abstract: Techniques herein map between key spaces to generate a balanced adaptive resolution histogram for dataset partitioning. In embodiments, a computer (C) creates a mapping that associates sparse keys (SKs) with distinct dense keys. C constructs a trie by processing each item of a dataset as follows. Based on the item, C obtains an SK. C navigates from a root NT (node of the trie) to a particular NT based on a sequence of dense digits (SDD). Each dense digit of the SDD is based on the mapping. Each NT identifies a dense prefix comprising dense digits. C assigns the item to a target node based on a threshold and count of items assigned to a subtree rooted at the particular node. C determines a range of SKs for each partition of the dataset, based on: an item count for a node or subtree, dense prefixes of NTs, and the mapping.

Abstract: Database techniques are provided that use state machines to manage polyglot subroutine bindings for database commands. In an embodiment, a computer receives a database command that contains call sites (CSs). Each CS is associated with a user defined logic (UDL). The computer associates an initial operational state with each of the CSs. During a first invocation of a particular CS, the CS becomes initialized and transitions to an optimized state that is configured for streamlined invocation of the UDL. The UDL is invoked to contribute data to a partial result for the database command. Eventually, command execution stalls and causes the CS to transition to an unready state, which entails releasing shared resources. Later execution resumes and during another invocation of the CS, resources are reacquired, the CS is made ready and transitioned back to the optimized state. The CS may again be repeatedly invoked while revisiting the optimized state.

Abstract: Techniques related to distributed relational dictionaries are disclosed. In some embodiments, one or more non-transitory storage media store a sequence of instructions which, when executed by one or more computing devices, cause performance of a method. The method involves generating, by a query optimizer at a distributed database system (DDS), a query execution plan (QEP) for generating a code dictionary and a column of encoded database data. The QEP specifies a sequence of operations for generating the code dictionary. The code dictionary is a database table. The method further involves receiving, at the DDS, a column of unencoded database data from a data source that is external to the DDS. The DDS generates the code dictionary according to the QEP. Furthermore, based on joining the column of unencoded database data with the code dictionary, the DDS generates the column of encoded database data according to the QEP.

Abstract: Database techniques are provided that use state machines to manage polyglot subroutine bindings for database commands. In an embodiment, a computer receives a database command that contains call sites (CSs). Each CS is associated with a user defined logic (UDL). The computer associates an initial operational state with each of the CSs. During a first invocation of a particular CS, the CS becomes initialized and transitions to an optimized state that is configured for streamlined invocation of the UDL. The UDL is invoked to contribute data to a partial result for the database command. Eventually, command execution stalls and causes the CS to transition to an unready state, which entails releasing shared resources. Later execution resumes and during another invocation of the CS, resources are reacquired, the CS is made ready and transitioned back to the optimized state. The CS may again be repeatedly invoked while revisiting the optimized state.

Abstract: Techniques related to distributed relational dictionaries are disclosed. In some embodiments, one or more non-transitory storage media store a sequence of instructions which, when executed by one or more computing devices, cause performance of a method. The method involves generating, by a query optimizer at a distributed database system (DDS), a query execution plan (QEP) for generating a code dictionary and a column of encoded database data. The QEP specifies a sequence of operations for generating the code dictionary. The code dictionary is a database table. The method further involves receiving, at the DDS, a column of unencoded database data from a data source that is external to the DDS. The DDS generates the code dictionary according to the QEP. Furthermore, based on joining the column of unencoded database data with the code dictionary, the DDS generates the column of encoded database data according to the QEP.

Abstract: Techniques herein map between key spaces to generate a balanced adaptive resolution histogram for dataset partitioning. In embodiments, a computer (C) creates a mapping that associates sparse keys (SKs) with distinct dense keys. C constructs a trie by processing each item of a dataset as follows. Based on the item, C obtains an SK. C navigates from a root NT (node of the trie) to a particular NT based on a sequence of dense digits (SDD). Each dense digit of the SDD is based on the mapping. Each NT identifies a dense prefix comprising dense digits. C assigns the item to a target node based on a threshold and count of items assigned to a subtree rooted at the particular node. C determines a range of SKs for each partition of the dataset, based on: an item count for a node or subtree, dense prefixes of NTs, and the mapping.

Abstract: Herein are computerized techniques for deploying JavaScript and TypeScript stored procedures and user-defined functions into a database management system (DBMS). In an embodiment, a computer generates a SQL call specification for each subroutine of one or more subroutines encoded in a scripting language. The generating is based on a signature declaration of the subroutine. Each subroutine comprises a definition of a stored procedure or a user-defined function. The computer packages the definition and the SQL call specification of each subroutine into a single bundle file. The definition and the SQL call specification of each subroutine are deployed into a DBMS from the single bundle file. Eventually, the SQL call specification of at least one subroutine is invoked to execute the definition of the subroutine in the DBMS.

Abstract: Data recovery for a compute node in a heterogeneous database system is provided. A failure is detected of a particular compute node of a compute cluster comprising a plurality of compute nodes. The compute cluster is configured to store, in memory, data stored by a RDBMS. Particular data of the data stored by the RDBMS is identified that is assigned to the particular compute node. The particular compute node is restored. After restoring the particular compute node, the particular data assigned to the particular compute node is reloaded without taking the particular data offline. During reloading, the particular compute node receives pending modified data comprising data of the particular data that was modified during said reloading.

Abstract: Systems, methods, computer program product embodiments are provided for locking retained resources of database information in a distributed shared disk cluster environment. An embodiment includes providing a request on demand for physical access to a page by a task of a node among a cluster of nodes, managing selective bypassing of waiting access requests to the page at intranode and internode levels in response to the request on demand, and handling requests for page ownership to prioritize a request on demand. Further included are determining whether another node holds a lock on the page and identifying an access type for the waiting access requests in order to coordinate transfer of the lock to the node.

Abstract: A method and apparatus for data recovery for a RDBMS instance in a heterogeneous database system is provided. A failure of a first RDBMS instance is detected in a plurality of RDBMS instances of a shared-disk database system. A compute cluster is configured to store, in memory, one or more tables stored by the shared-disk database system. The first RDBMS instance is configured to modify the one or more tables stored by the shared-disk database system and transfer modified data to the compute cluster to update the one or more tables at the compute cluster. After detecting the failure of the first RDBMS instance, redo records generated by the first RDBMS instance are scanned, pending modified data that was not transferred to the compute cluster before the failure is identified, and the pending modified data is transferred to the compute cluster.

Abstract: A method and apparatus for data recovery for a RDBMS instance in a heterogeneous database system is provided. A failure of a first RDBMS instance is detected in a plurality of RDBMS instances of a shared-disk database system. A compute cluster is configured to store, in memory, one or more tables stored by the shared-disk database system. The first RDBMS instance is configured to modify the one or more tables stored by the shared-disk database system and transfer modified data to the compute cluster to update the one or more tables at the compute cluster. After detecting the failure of the first RDBMS instance, redo records generated by the first RDBMS instance are scanned, pending modified data that was not transferred to the compute cluster before the failure is identified, and the pending modified data is transferred to the compute cluster.

Abstract: Data recovery for a compute node in a heterogeneous database system is provided. A failure is detected of a particular compute node of a compute cluster comprising a plurality of compute nodes. The compute cluster is configured to store, in memory, data stored by a RDBMS. Particular data of the data stored by the RDBMS is identified that is assigned to the particular compute node. The particular compute node is restored. After restoring the particular compute node, the particular data assigned to the particular compute node is reloaded without taking the particular data offline. During reloading, the particular compute node receives pending modified data comprising data of the particular data that was modified during said reloading.