Abstract: Systems and methods are described for implementation by a computing system having a non-uniform memory access (NUMA) architecture comprising a plurality of NUMA nodes. A query of a document store storing a collection of slices each comprising one or more documents is received from a client. Thereafter, it is determined which of the slices within the document store are required for execution of the query. An execution plan is then generated, using the query, that comprises a plurality of nodes each specifying at least one database operation to execute a portion of the query. The execution plan assigns one of the plurality of NUMA nodes to each slice determined to be required for execution of the query. The database operations specified by the nodes of the execution plan are then executed using the corresponding assigned NUMA nodes for the associated slice. Data responsive to the query is then provided to the client.

Abstract: A query is received from a client that specifies at least one database operation implicating data within a first database and within a second database. The first database has a first transaction manager and the second database has a second transaction manager. Thereafter, a plurality of transactions responsive to the query are initiated to access the data within the first database and the second database. Execution of the plurality of transactions are coordinated using the first transaction manager such that commits for both of the first database and the second database are handled by the first transaction manager. Data responsive to the query can then be provided to the client. Related apparatus, systems, techniques and articles are also described.

Abstract: A query is received by a document store from a client. The query specifies at least one database operation implicating documents within the document store. At least one of the implicated documents has partially compressed objects in which only a portion of the document is compressed. Thereafter, the documents are scanned to identify the compressed objects and to identify decompression keys. The scanned compressed objects are then decompressed using the corresponding decompression keys. Data responsive to the query can then be provided to the client. lated apparatus, systems, techniques and articles are also described.

Abstract: A database system can receive, from a client, a query specifying at least one database operation implicating data within a first database and within a second database. The first database can have a first transaction manager and the second database can have a second transaction manager. Thereafter, a plurality of transactions are initiated that are responsive to the query to access the data within the first database and the second database. The first transaction manager and the second transaction manager together coordinate execution of the plurality of transactions. All changes specified by the at least one database operation are persisted in persistence of the first database including changes implicating data stored within the second database. Data responsive to the query can then optionally be provided to the client. Related apparatus, systems, techniques and articles are also described.

Abstract: First page data from one or more pages stored on a persistent storage can be loaded into a page buffer in a main system memory of one or more computing systems, and second page data that includes first dictionary values of a first dictionary for a first database column can be loaded and pinned into the page buffer in the main system memory. First contents of a first dictionary block containing first re-direction references to the first dictionary can be copied from the loaded first page data into a first in-memory array, and the first page data can be deallocated from the page buffer. The first re-direction references can direct to the first dictionary values of the first dictionary in the pinned second page data.

Abstract: A data storage and retrieval system for a computer memory configured according to a document store adapted to contain documents. The document store includes a document data structure containing a header and a document having one or more members. The document store further includes a chain of one or more differential data structures, each having a header and at least one updated member. The updated member has a value which is updated relative to a value in a corresponding member having a same identifier in the document data structure or in a preceding differential data structure in the chain. A header of each of the differential data structures includes a pointer to the document data structure or the preceding differential data structure in the chain, and a flag indicating that each of the differential data structures contains less than all of the members of the document data structure.

Abstract: A query is received from a client that specifies at least one database operation implicating data within a first database and within a second database. The second database includes a document store storing a collection of documents. Thereafter, a plurality of transactions responsive to the query are initiated to access the data within the first database and the second database. Execution of the plurality of transactions are coordinated between the first database and the second database. All changes specified by the at least one database operation are persisted in the first database including changes implicating data stored within the second database. Data responsive to the query can then be provided to the client.

Abstract: A query is received from a client that specifies at least one database operation implicating data within a first database and within a second database. The first database can have a first transaction manager and the second database can have a second transaction manager. Thereafter, a plurality of transactions responsive to the query are initiated to access the data within the first database and the second database. Execution of the plurality of transactions is then coordinated using the first transaction manager and the second transaction manager. All changes specified by the at least one database operation are logged in a distributed log in the first database including changes implicating data stored within the second database. The distributed log is configured such that it is accessible by both of the first transaction manager and the second transaction manager.

Abstract: Provided are systems and methods to acquire a manifest data file and a binary copy of a document store slice log having a first filename and comprising a plurality of entries, each of the plurality of entries associated with a respective database transaction and a commit identifier, and the manifest data file indicating one or more data partitions and one or more slices of each of the one or more data partitions, acquire a partition log for one of the indicated one or more data partitions, the generated partition log comprising a log entry associated with a transaction to create a slice and including a second filename associated with the slice, sort the plurality of entries of the document store slice log based on their associated commit identifiers, change the commit identifiers of each of the plurality of entries to a same commit identifier, and store the sorted and changed entries in a second document store slice log having the second filename.

Abstract: A data storage and retrieval system for a computer memory including a memory slice formed of segments and adapted to contain one or more documents and a checkpoint adapted to persist the memory slice. The checkpoint includes a document vector containing a document pointer corresponding to a document. The document pointer including a segment identifier identifying a logical segment of the memory slice and an offset value defining a relative memory location of the first document within the identified segment. There are checkpoint memory blocks, each storing a copy of a corresponding segment of the memory slice. The segment identifier of the document pointer identifies a checkpoint memory block and the offset value of the document pointer defines a relative location of the document within the checkpoint memory block.

Abstract: A data storage and retrieval system for a computer memory configured according to a columnar document store adapted to contain one or more documents. The columnar document store includes a dictionary containing one or more identifiers, each of the identifiers being associated in the dictionary with a value ID. The document store further includes a data structure having fields and containing at least a first column. The first column is associated with a first identifier of the one or more identifiers, and the first identifier is associated with a first set of values in a first set of documents which contain the first identifier. The first column includes a value ID of the first identifier, one or more document IDs, each identifying a document in the first set of documents, and the first set of values.

Abstract: Provided are systems and methods for paging data into main memory from checkpoint data stored on disk. In one example, the method may include one or more of receiving a request for a database record in main memory, determining whether the database record has been previously stored in the main memory, in response to determining that the database record has been previously stored in the main memory, identifying a slice where the database record was stored from among a plurality of slices included in the main memory, and paging content of the identified slice including a copy of the requested database record into the main memory from a snapshot captured of content included in the identified slice and previously stored on disk. Accordingly, documents can be paged into main memory on-demand from snapshots of slice content rather than paging an entire partition of content.

Abstract: Provided are systems and methods for implementing a database notification and statistics framework. In one example, the method may include receiving a message published by a database, the message including information about a database event performed by the database, determining a publication type of the message from among a plurality of publication types based on attributes included in the message, identifying one or more database components that have subscribed to the identified publication type of the message, and transferring the information about the database event included in the message to the one or more identified database components that have subscribed to the publication type of the message.

Abstract: Provided are systems and methods for storing checkpoints of an in-memory storage device. In one example, the method may include detecting database transactions performed on a slice of an in-memory storage and storing a record of the database transactions in a log file, receiving a request to persist the slice of in-memory storage, the request comprising a timing indicator corresponding to a timing of database transactions, trimming the log file based on the timing indicator to remove a record of one or more database transactions from the log file that occurred prior to the timing indicator and to preserve a record of one or more database transactions that occurred after the timing indicator, and persisting, to disk, data from the slice of in-memory storage and the trimmed log file preserving the record of the one or more database transactions that occurred after the timing indicator.

Abstract: Provided are a device and method of managing data stored in memory. The device may include a buffer for storing data blocks including a head data block, a tail data block, and intermediate data blocks. Non-used blocks may be further included in the buffer between the head data block and the tail data block. The device may further include a controller for managing the data blocks within the buffer. The managing may include determining a shift direction for the data blocks based on a distribution of the data blocks within the buffer, shifting at least one data block from among the data blocks in the determined direction, and shifting the one or more non-used blocks in an opposite direction from which the at least one data block is shifted. As a result of the shifting, the data blocks may be aggregated within the buffer.

Abstract: The present disclosure describes methods, systems, and computer program products for optimizing single-value database read operations. One computer-implemented method includes initializing, by a computer, a single value cache associated with a created database table where a column of the database table contains a single or unique data value, verifying that the created database table is in a useable state, performing an operation on the database table, and retrieving the data value from the single value cache without locking the column containing the single or unique data value.

Abstract: A first block in a page chain can be assigned to a first dictionary for a first column of a database. The page chain can include a plurality of dictionary blocks allocated to a plurality of dictionaries of a plurality of columns including the first column such that the plurality of dictionary blocks is interleaved in the page chain. A new unique value to be added to the first column can be appended to an end of the first dictionary. The plurality of dictionaries can be loaded from the page chain into memory of one or more computers performing operations of a database management system. The loading can include scanning the page chain a single time and assigning the plurality of dictionary blocks to the respective dictionaries of the plurality of dictionaries.

Abstract: An encoded data object notation persistence format can be used in a variety of scenarios to advantage. The encoded format accommodates key name-value pairs and can employ dictionary compression to reduce the amount of storage needed to represent a data object. Searching and querying a collection of encoded data objects can be done more efficiently by taking advantage of the format.

Abstract: Provided are a device and method of managing data stored in memory. The device may include a buffer for storing data blocks including a head data block, a tail data block, and intermediate data blocks. Non-used blocks may be further included in the buffer between the head data block and the tail data block. The device may further include a controller for managing the data blocks within the buffer. The managing may include determining a shift direction for the data blocks based on a distribution of the data blocks within the buffer, shifting at least one data block from among the data blocks in the determined direction, and shifting the one or more non-used blocks in an opposite direction from which the at least one data block is shifted. As a result of the shifting, the data blocks may be aggregated within the buffer.

Abstract: Flexible text searching for data objects can be implemented. For example, inexact matching of key name terms can be supported. An inverted index can be used to find data objects having key names with terms that are a superset of the key name term being searched. A similar index can be used for values, and the search results can be determined via an intersection. Pattern searching and other features can be supported. Text searching for schema-less collections of data objects can be supported for use in enterprise computing scenarios.