Methods, apparatus, and systems to aggregate partitioned computer database data

Patent metadata

Field	Value
Publication number	US-2022019601-A1
Application number	US-202117491146-A
Country	US
Kind code	A1
Filing date	Sep 30, 2021
Priority date	Mar 26, 2018
Publication date	Jan 20, 2022
Grant date	—

Abstract

Methods, apparatus, systems and articles of manufacture are disclosed. An example system to aggregate partitioned data includes a plurality of nodes, queriers associated with respective ones of the plurality of nodes, and a coordinator associated with a querier, the coordinator to identify a set of nodes, decompose the a to query the database data into a plurality of sub-queries, provide the plurality of sub-queries to the queriers of the identified set of nodes for execution, store, in response to a determination that a timeout has occurred, a hinted handoff notice for a node associated with the timeout, and combine results of execution of the respective ones of the plurality of sub-queries from the queriers of the identified set of nodes not associated with the timeout to generate a response to the request to query the database data.

First claim

What is claimed is:

1 . A system to aggregate partitioned data, the system comprising:
a plurality of nodes; queriers associated with respective ones of the plurality of nodes; and a coordinator associated with a querier, the coordinator to:
identify a set of nodes for use in preparing a response to a request to query database data, the database data distributed across the plurality of nodes irrespective of a data content, the request received from an application;
decompose the request to query the database data into a plurality of sub-queries;
provide the plurality of sub-queries to the queriers of the identified set of nodes for execution;
store, in response to a determination that a timeout has occurred, a hinted handoff notice for a node associated with the timeout; and
combine results of execution of the respective ones of the plurality of sub-queries from the queriers of the identified set of nodes not associated with the timeout to generate a response to the request to query the database data.

2 . The system of claim 1 , wherein the timeout is indicative of the node not providing a result of execution of the respective sub-queries to the coordinator.

3 . The system of claim 1 , further including a data director to distribute the database data across the plurality of nodes into database portions for storage of respective portions of the database data, the database portions associated with the respective ones of the plurality of nodes.

4 . The system of claim 3 , wherein the respective portions of the database data are stored in a horizontally-partitioned table, the sub-queries executed without a shuffle of the portions of the database data between ones of the nodes.

5 . The system of claim 1 , wherein the request to query database data includes a conditional statement, the conditional statement including a sharding key value indicative the set of nodes for response to the request.

6 . The system of claim 1 , wherein the request to query database data is a first request, a second request provided by the application to the coordinator to cause an update of a contents of a dashboard.

7 . The system of claim 1 , wherein the coordinator reduces the results of execution by removing redundant data.

8 . A non-transitory computer-readable storage medium comprising instructions that, when executed, cause a machine to at least:
identify a set of nodes from a plurality of nodes for use in preparing response to a request to query database data, the database data distributed across the plurality of nodes irrespective of a data content, the request received from an application; decompose the request to query the database data into a plurality of sub-queries; provide the plurality of sub-queries to queriers associated with respective ones of the identified set of nodes for execution; store, in response to a determination that a timeout has occurred, a hinted handoff notice for a node associated with the timeout; and combine results of execution of the respective ones of the plurality of sub-queries from the queriers of the identified set of nodes not associated with the timeout to generate a response to the request to query the database data.

9 . The non-transitory computer-readable storage medium of claim 8 , wherein the timeout is indicative of the node not providing a result of execution of the respective sub-queries.

10 . The non-transitory computer-readable storage medium of claim 8 , further including to distribute the database data across the plurality of nodes into database portions for storage of respective portions of the database data, the database portions associated with the respective ones of the plurality of nodes.

11 . The non-transitory computer-readable storage medium of claim 10 , wherein the respective portions of the database data are stored in a horizontally-partitioned table, the sub-queries executed without a shuffle of the portions of the database data between ones of the nodes.

12 . The non-transitory computer-readable storage medium of claim 8 , wherein the request to query database data includes a conditional statement, the conditional statement including a sharding key value indicative the set of nodes for response to the request.

13 . The non-transitory computer-readable storage medium of claim 8 , wherein the request to query database data is a first request, a second request provided by the application to cause an update of a contents of a dashboard.

14 . The non-transitory computer-readable storage medium of claim 8 , further including to reduce the results of execution by removing redundant data.

15 . A method for aggregation of partitioned data, the method comprising:
identifying a set of nodes from a plurality of nodes for use in preparing response to a request to query database data, the database data distributed across the plurality of nodes irrespective of a data content, the request received from an application; decomposing the request to query the database data into a plurality of sub-queries; providing the plurality of sub-queries to queriers associated with respective ones of the identified set of nodes for execution; storing, in response to a determination that a timeout has occurred, a hinted handoff notice for a node associated with the timeout; and combining results of execution of the respective ones of the plurality of sub-queries from the queriers of the identified set of nodes not associated with the timeout to generate a response to the request to query the database data.

16 . The method of claim 15 , wherein the timeout is indicative of the node not providing a result of execution of the respective sub-queries.

17 . The method of claim 15 , further including distributing the database data across the plurality of nodes into database portions for storage of respective portions of the database data, the database portions associated with the respective ones of the plurality of nodes.

18 . The method of claim 17 , wherein the respective portions of the database data are stored in a horizontally-partitioned table, the sub-queries executed without a shuffle of the portions of the database data between ones of the nodes.

19 . The method of claim 15 , wherein the request to query database data includes a conditional statement, the conditional statement including a sharding key value indicative the set of nodes for response to the request.

20 . The method of claim 15 , further including reducing the results of execution by removing redundant data.

Assignees

• Mcafee Llc

Inventors

• Michelis Pablo A
• Stewart Brian H

Classifications

• G06F16/2471 Primary

  Distributed queries · CPC title

• G06F16/278 Primary

  Data partitioning, e.g. horizontal or vertical partitioning · CPC title

• G06F16/24534

  Query rewriting; Transformation · CPC title

• G06F16/24554

  Unary operations; Data partitioning operations · CPC title

• G06F16/24542

  Plan optimisation · CPC title