Microsoft Technology Licensing, LLC

Amazon Technologies, Inc.

Sudipto Das

Vivek Ravindranath Narasayya

Feng Li

Manoj A Syamala

Surajit J Chaudhuri

Badrish Chandramouli

Arnd Christian König

Kanishka Chaturvedi

Bailu Ding

Hyunjung Park

Gaoxiang Xu

Timothy Andrew Rath

Lin Ma

Wentao Wu

Bolin Ding

Sanuj Basu

Lokendra Singh Panwar

Lonnie J Princehouse

Mohammad Foyzur Rahman

Jayanta Mondal

Dhruv Goel

Andrija Jovanovic

Rajesh Iyer

Jingjing Wang

Adith Swaminathan

Ryan Marcus

Harish Tummalacherla

Miodrag Radulovic

Avinash Goutham Reddy Aluguvelly

Tiratat Patana-anake

Fabian Oliver Nagel

Ewout Willem Prangsma

Arnd Christian KÖNIG

A consumer database of a service provider network may perform writes to a producer database. To do so, the consumer database obtains metadata and a transaction context from the producer database and uses that information to perform a write from the consumer database to the producer database. A consumer database may access (read and/or write) a producer database that uses a different topology to manage data. To do so, the consumer database obtains topology metadata from the producer database and uses the topology metadata to perform a query (read or write) from the consumer database to the producer database. A consumer database may access a producer database based on a mapping of local user IDs to consumer databases at the producer database. The access may be granted to the consumer database based on permissions assigned to the local user IDs.

Performing writes from a consumer database to a producer database

A system to manage database queries including storage devices to implement a data store to store database data and computing devices to implement a query engine. The query engine is configured to receive, from a client, a database query and initiate performance of the query at the data store. The query engine is configured to compare a performance time of the query with a performance time threshold. Based on the performance time exceeding the performance time threshold: send a query identifier for the query and a token indicating that the query has not been completed; and receive, from the client, an additional query comprising the token and the query identifier. Based on a determination that the performance time does not exceed the performance time threshold, send a response to the query to the client, the response comprising data requested by the query.

Paginated synchronous database querying

Methods, systems, and computer-readable media for versioned metadata management for a time-series database are disclosed. A metadata service of a distributed time-series database stores, to one or more metadata storage resources, first metadata descriptive of a table. The first metadata is associated with a version number in a logical sequence for the table. The metadata service stores, in a log, data indicative of one or more metadata updates for the table. The metadata update(s) are associated with an additional version number higher than the version number in the logical sequence. Responsive to a read request, the metadata service determines a most recent version number that has been applied from the log to the metadata storage resource(s). Responsive to the read request and based (at least in part) on the most recent version number, the metadata service returns either the first metadata or second metadata comprising the update(s).

Versioned metadata management for a time-series database

Methods, systems, and computer-readable media for adaptive querying of time-series data over tiered storage are disclosed. A distributed time-series database receives a query indicating spatial and temporal boundaries of requested time-series data in a table. The time-series database stores time-series data using a plurality of storage resources, wherein a first storage tier is accessible using a first access interface and a second storage tier is accessible using a second access interface. The time-series database determines, in the plurality of storage resources, one or more storage locations corresponding to the spatial and temporal boundaries of the query. Using the first access interface, the time-series database reads one or more elements of the requested time-series data from storage locations in the first storage tier. Using the second access interface, the time-series database reads one or more additional elements of the requested time-series data from storage locations in the second storage tier.

Adaptive querying of time-series data over tiered storage

Described herein are technologies relating to computing resource allocation among multiple tenants. Each tenant may have a respective absolute reservation for rate-based computing resources, which is independent of computing resource reservations of other tenants. The multiple tenants vie for the rate-based computing resources, and tasks are scheduled based upon which tenants submit the tasks and the resource reservations of such tenants.

Dynamic allocation of resources while considering resource reservations

Systems, methods, and computer-executable instructions for reorganizing a physical layout of data of a database a database. A workload is selected from previously executed database operations. A total resource consumption of the previously executed database operations and of the workload is determined. The total resource consumption of the workload is more than a predetermined threshold of the total resource consumption of the previously executed database operations. Optimization operations for the database are determined using the workload. A cloned database of the database is created. The optimization operations are executed on the cloned database. A database operation is received for the database. The database operation is executed on the database and the cloned database. The performance of the cloned database is verified as being improved compared to the performance of the database based on the executing of the database operation on the database and the cloned database.

Database tuning and performance verification using cloned database

Systems and techniques for leveraging query executions to improve index recommendations are described herein. In an example, a machine learning model is adapted to receive a first query plan and a second query plan for performing a query with a database, where the first query plan is different from the second query plan. The machine learning model may be further adapted to determine execution cost efficiency between the first query plan and the second query plan. The machine learning model is trained using relative execution cost comparisons between a set of pairs of query plans for the database. The machine learning model is further adapted to output a ranking of the first query plan and second query plan, where the first query plan and second query plan are ranked based on execution cost efficiency.

Leveraging query executions to improve index recommendations

Architecture that enables a Database-as-a-Service (DaaS) to auto-scale container sizes on behalf of tenants. An abstraction is provided that enables tenants to reason about monetary budget and query latency, rather than resource provisioning. An auto-scaling module automatically determines a container size for a subsequent billing interval based on telemetry that comprises latencies (e.g., waits), resource utilizations, and available budget, for example. A set of robust signals are derived from database engine telemetry and combined to significantly improve accuracy of resource demand estimation for database workloads. In a more specific implementation, resource demands can be estimated for arbitrary SQL (structured query language) workloads in a relational database management system (RDBMS).

Automatic demand-driven resource scaling for relational database-as-a-service

Systems, methods, and computer-executable instructions for creating a query execution plan for a query of a database includes receiving, from the database, a set of previously executed query execution plans for the query. Each previously-executed query execution plans includes subplans. Each subplan indicates a tree of physical operators. Physical operators that executed in the set of previously-executed query execution plans are determined. For each physical operator, an execution cost based is determined. Invalid physical operators from the previously-executed query execution plans that are invalid for the database are removed. Equivalent subplans from the previously-executed query execution plans are identified based on physical properties and logical expressions of the subplans. A constrained search space is created based on the equivalent subplans. A query execution plan for the query is constructed from the constrained search space based on the execution cost. The constructed query execution plan is not within the previously-executed query execution plans.

Execution plan stitching

Provided are methods and systems for generating physical database design tuning recommendations. Given a workload, the system analyzes the workload to identify and recommend a set of rowstore and columnstore indexes optimal for the performance of the workload. The system is designed to estimate the size of the columnstore index (at the granularity of each column) without actually building the index, estimate the improvement in query performance that each columnstore index would result in when built, and automatically derive the workload used for the physical design tuning task by analyzing stored query execution history data. This automatic workload derivation is orthogonal to columnstores and can be used even when columnstore indexes are not being used.

Workload-driven recommendations for Columnstore and Rowstore indexes in relational databases

Techniques for tenant performance isolation in a multiple-tenant database management system are described. These techniques may include providing a reservation of server resources. The server resources reservation may include a reservation of a central processing unit (CPU), a reservation of Input/Ouput throughput, and/or a reservation of buffer pool memory or working memory. The techniques may also include a metering mechanism that determines whether the resource reservation is satisfied. The metering mechanism may be independent of an actual resource allocation mechanism associated with the server resource reservation.

Isolating resources and performance in a database management system

A server system may include a cluster of multiple computers that are networked for high-speed data communications. Each of the computers has a remote direct memory access (RDMA) network interface to allow high-speed memory sharing between computers. A relational database engine of each computer is configured to utilize a hierarchy of memory for temporary storage of working data, including in order of decreasing access speed (a) local main memory, (b) remote memory accessed via RDMS, and (c) mass storage. The database engine uses the local main memory for working data, and additionally uses the RDMA accessible memory for working data when the local main memory becomes depleted. The server system may include a memory broker to which individual computers report their available or unused memory, and which leases shared memory to requesting computers.

Memory sharing for working data using RDMA

A partitioning advisor for online transaction processing (OLTP) workloads generates a workload dependency graph based on a schema defining a structure of a relational database and a workload associated with an OLTP application that accesses the relational database. Based on the workload dependency graph, the partitioning advisor generates one or more partitioning strategy recommendations for sharding the relational database. The partitioning advisor may also render a visualization based on the workload dependency graph, enabling a user to see the impact each recommended partitioning strategy is predicted to have.

Growing community of inventors

Redmond, WA, United States of America

Sudipto Das