Microsoft Technology Licensing, LLC

Hewlett-packard Development Company, L.p.

Hewlett Packard Enterprise Development LP

Google Inc.

Micro Focus Lcc

Tandem Computers Incorporated

Microsoft Corporation

Goetz Graefe

Harumi Kuno

David L Detlefs

John Joseph Duffy

Michael M Magruder

Vinod Grover

Janet Lynn Wiener

Cesar Alejandro Galindo-Legaria

Florian Michael Waas

Milind Madhukar Joshi

Ross Thomas Bunker

David W Birdsall

Oliver Nicholas Seeliger

Yung-Li L Jow

Istvan Cseri

Mehul A Shah

Mark David Lillibridge

Craig Steven Freedman

Lingli Zhang

Stavros Harizopoulos

Michael Rys

Christian Kleinerman

Gideon Schaller

Frank Mantek

Michael Mee

Umeshwar Dayal

Timothy Lawrence Harris

Torsten Walther Grabs

Per-Ake Larson

Craig C Peeper

Robert E Tarjan

William Kevin Wilkinson

Nigel Robin Ellis

Ajay Kalhan

Sameet Harishanker Agarwal

Hideaki Kimura

Hansjorg Zeller

Charles Stuart Johnson

Terence Patrick Kelly

Rodger N Kline

Peter Alan Carlin

Joseph Andrew Tucek

Gang He

Haris Volos

Steven John Lindell

Pedro Celis

Wojciech Golab

Jay Vaishnav

Jeffrey A East

Samuel H Smith

Murali Mallela Krishna

James Hyungsun Park

Yevgeniy L Kogan

Dimitrios Tsirogiannis

Amrish Kumar

Cesar A Galinda-Legaria

Wey Guy

Harold R Berenson

Jeff Alger

Albert L Lingelbach

Craig G Zastera

Vinod K Grover

At least one aspect of the present disclosure is directed to a systems and methods of maintaining key-value stores. The method can include establishing a first run of data records indexed by a key value. The method can include tracking, using an index, a merging of the data records of the first run onto a merge level on a database. The method can include establishing, concurrent to the merging of the first run, a second run of data records indexed by a key value. The method can include determining that the index tracking the merge of the data records of the first run onto the merge level satisfies a quantile condition. The method can include adding the subset of the second plurality of records of the second run to the merging of the first plurality of records of the first run onto the merge level maintained on the database.

Staggered merging in log-structured merge forests

Computer-implemented systems and associated operating methods take measurements and landmarks associated with robustness maps and perform tests evaluating the robustness of a database engine's operator implementations and/or query components. The illustrative computer-implemented system comprises logic that receives one or more robustness maps of measured database system performance acquired during database execution in a predetermined range of runtime conditions and uses information from the robustness map or maps to perform regression testing wherein landmarks in the robustness maps are operated upon as a robustness bugs describing conditions under which a predetermined implementation of a database operator or query component degrades in a manner different from a predetermined expected manner.

Database system testing using robustness maps

Systems and methods for providing deferred lock enforcement for transactions are described. The method includes receiving a first request for access to a data resource for a transaction, assigning a first lock to the transaction, and receiving, from a candidate reader, a second request for access to the data resource. The method further includes determining an interpretation of the first lock as i) a first lock type responsive to determining that the transaction is in a read phase or ii) a second lock type responsive to determining that the transaction is in a commit processing phase, and assigning a second lock to the candidate reader responsive to interpreting the first lock as the first lock type, or declining to assign the second lock to the candidate reader responsive to interpreting the first lock as the second lock type.

Systems and methods for deferred lock enforcement

This disclosure provides systems, methods, and apparatus for managing locks for non-existing keys in an index of a database. The system can receive a first transaction for accessing a first requested key that does not match any of a plurality of keys in the index. The system partitions the first requested key using a partitioning function to a first partition. The system can also receive a second transaction for accessing a second requested key that does not match any of the plurality of keys in the index. The system also partitions the second requested key using the partitioning function to a second partition. The system assigns locks to the second transaction only if the second partition is distinct from the first partition.

Managing transactions requesting non-existing index keys in database systems

Systems and methods associated with page modification are disclosed. One example method may be embodied on a non-transitory computer-readable medium storing computer-executable instructions. The instructions, when executed by a computer, may cause the computer to fetch a page to a buffer pool in a memory. The page may be fetched from at least one of a log and a backup using single page recovery. The instructions may also cause the computer to store a modification of the page to the log. The modification may be stored to the log as a log entry. The instructions may also cause the computer to evict the page from memory when the page is replaced in the buffer pool. Page writes associated with the eviction may be elided.

Eliding memory page writes upon eviction after page modification

Systems and methods associated with latch-free searching are disclosed. One example method includes receiving a key identifying data to be retrieved from a tree-based data structure. The method also includes performing a concurrent, latch-free search of the tree-based data structure until a leaf node is reached. The method also includes validating the leaf node. The method also includes retreading a portion of the search if the leaf node fails validation.

Latch-free concurrent searching

Disclosed herein are a system, non transitory computer-readable medium, and method for estimating database performance. A request for an estimate of data is read. The estimate is calculated based at least partially on a node located in a data structure.

Estimating data

A data processing system performs query progress estimation based on processed value packets. In the illustrative data processing system, a database query processor comprises a query optimizer that creates a query plan, and a database plan executor that executes the query plan and observes intermediate result streams processed as the query plan is executed. A value packet manager anticipates value packets during query optimization, creates value packets as the intermediate result streams are processed, and compares anticipated value packets with created value packets to determine accuracy of the anticipated value packets and estimate query progress.

Query progress estimation based on processed value packets

A method of implementing a tree data structure comprises creating a parent and child relationship between a first node and a second node, in which the first node and second node are at the same hierarchical level of the tree data structure, and maintaining only one incoming pointer for each of the nodes in the tree data structure at all times. A tree data structure in which each node in the tree data structure has a single incoming pointer, and in which the tree data structure comprises a pointer directed to a local overflow node from a node at the same hierarchical level as the local overflow node.

Tree data structure

A shiftable memory supporting in-memory data structures employs built-in data shifting capability. The shiftable memory includes a memory having built-in shifting capability to shift a contiguous subset of data from a first location to a second location within the memory. The shiftable memory further includes a data structure defined on the memory to contain data comprising the contiguous subset. The built-in shifting capability of the memory to facilitate one or more of movement of the data, insertion of the data and deletion of the data within the data structure.

Shiftable memory supporting in-memory data structures

There is provided a computer-implemented method of dynamically reordering operations in a query plan. An exemplary method comprises processing a first set of tuples according to a first operation. The query plan is pipelined and specifies that the first operation generates input for a second operation. The query plan further specifies that the second operation is executed after the first operation. The computer-implemented method further includes determining that the second operation is to precede the first operation based on a specified policy. The computer-implemented method further includes executing the second operation for a second set of tuples before executing the first operation for the second set of tuples. The second operation generates an input for the first operation. The first operation is executed after the second operation.

Dynamic reordering of operations in a query plan

A system is disclosed for managing address reflectors. In one example, the system discloses a reflector storage, with a set of reflector membersassociated with a set of reflector names. The system also includes a computerprogrammed with executable instructionswhich operate a set of modules. The modules includes reflector management modulewhich, receives a character-string from user input, and identifies the reflector nameswhose reflector membersare partially defined by the character-string.

System for managing address reflectors

There is provided a computer-implemented method of executing a query plan against a database. An exemplary method comprises accessing a first subset of rows of a database table using a direct access method for an index. The query plan may comprise the direct access method. The exemplary method also comprises determining a processing cost of accessing the first subset of rows. The exemplary method further comprises modifying the direct access method for the index in response to determining that the processing cost exceeds a specified threshold. Additionally, the exemplary method comprises accessing a second subset of rows of the database table using the modified direct access method.

System and method for executing queries

A data portion is evicted from a buffer, where the evicted data portion is modified from a corresponding data portion in a persistent storage. Write elision is applied to suppress writing the evicted data portion to the persistent storage. Subsequent to applying the write elision and in response to reading a version of the data portion, a redo of a modification of the read data portion is applied.

Applying write elision

Various technologies and techniques are disclosed for supporting parallel nested transactions in a transactional memory system. Multiple closed nested transactions are created for a single parent transaction, and the closed nested transactions are executed concurrently as parallel nested transactions. Various techniques are used to ensure effects of the parallel nested transactions are hidden from other transactions outside the parent transaction until the parent transaction commits. For example, retry is allowed to work correctly with parallel nested transactions. When a transaction that is a parallel nested transaction or a child transaction of the parallel nested transaction executes a retry, a read set of the transaction is registered for the retry. When a decision is made to propagate the retry past a parallel nested transaction parent of the transaction, keeping the read set registered and making the read set part of a parent read set.

Parallel nested transactions in transactional memory

Growing community of inventors

Madison, WI, United States of America

Goetz Graefe