公开(公告)号：US20230359627A1

公开(公告)日：2023-11-09

申请号：US18351453

申请日：2023-07-12

Applicant: Amazon Technologies, Inc.

Inventor： Ippokratis Pandis ,  Naresh Chainani ,  Kiran Kumar Chinta ,  Venkatraman Govindaraju ,  Andrew Edward Caldwell ,  Naveen Muralimanohar ,  Martin Grund ,  Fabian Oliver Nagel ,  Nikolaos Armenatzoglou

IPC: G06F16/2455 ,  G06F16/242 ,  G06F16/22 ,  G06F16/2453 ,  G06F16/2458

CPC classification number: G06F16/24552 ,  G06F16/2445 ,  G06F16/2255 ,  G06F16/2443 ,  G06F16/24539 ,  G06F16/2458

Abstract: Compiled portions of code generated to perform a query plan at a query engine may be shared with other query engines. A data store, separate from the query engines, may store compiled portions of query code generated for different queries. If a query engine does not have a locally stored compiled portion of query code, then the separate data store may be accessed in order to obtain a compiled portion of query code, allowing reuse of compiled query code across different queries engines for queries directed to different databases.

公开(公告)号：US20200050694A1

公开(公告)日：2020-02-13

申请号：US16102545

申请日：2018-08-13

Applicant: Amazon Technologies, Inc.

Inventor： Bhaven Avalani ,  Andrew Edward Caldwell ,  Naresh Chainani ,  Martin Grund ,  Anurag Windlass Gupta ,  Frederick Ryan Johnson ,  Ippokratis Pandis ,  Michail Petropoulos ,  Srividhya Srinivasan

IPC: G06F17/30

Abstract: Burst performance of a database query may be determined according to a size of the database query. A query to a database may be received. A size may be determined for the query. If the size is less than a size threshold assigned to a first query engine, then the query may be performed at the first query engine. If the size is greater than or equal to the size threshold assigned to the first query engine, then the query may be performed at a second query engine.

公开(公告)号：US11074261B1

公开(公告)日：2021-07-27

申请号：US15382334

申请日：2016-12-16

Applicant: Amazon Technologies, Inc.

Inventor： Ippokratis Pandis ,  Mengchu Cai ,  Martin Grund ,  Anurag Windlass Gupta

IPC: G06F16/2455 ,  G06F16/25 ,  G06F16/9535

Abstract: Data processing engines implement format independent data processing for distributed data in local and remote data stores. Requests execute at least a portion of an access request are received from a data processing engine that does not support a data format for data stored in a data store. The data format for the data is identified and the data accessed according to the identified data format. The portion of the access request is applied to the accessed data in order to generate results. The generated results for the portion of the access request are then sent to the data processing engine.

公开(公告)号：US10922316B2

公开(公告)日：2021-02-16

申请号：US16007697

申请日：2018-06-13

Applicant: Amazon Technologies, Inc.

Inventor： Gaurav Saxena ,  George Constantin Caragea ,  Naresh Kishin Chainani ,  Martin Grund

IPC: G06F16/00 ,  G06F16/2453 ,  G06F16/28

Abstract: Database queries may be performed using resources based on a determined size of the database query. Database query size may be dynamically determined for a database query when the query is received. The database query may be assigned to resources used for database queries of the determined size. In some embodiments, timeouts may be applied to reassign database queries to different resources if the performance of the database query exceeds a timeout threshold.

公开(公告)号：US11133933B1

公开(公告)日：2021-09-28

申请号：US16199000

申请日：2018-11-23

Applicant: Amazon Technologies, Inc.

Inventor： Martin Grund ,  Mikhail Krestyaninov ,  Luxiang Yin ,  Davide Pagano ,  William Michael McCreedy ,  Ippokratis Pandis

IPC: H04L29/06 ,  H04L9/32 ,  G06F16/2458 ,  G06F16/27 ,  G06F9/455

Abstract: Techniques for rapid secure authentication and communications through multitenant components in a provider network are described. A main database cluster can request a burst cluster from a burst service, which can provide the main cluster with a shared secret associated with only a selected burst cluster. The main cluster can use the shared secret to encrypt a value that can be passed, via a proxy, to the selected burst cluster in a connection request. The selected burst cluster can validate that the connection request was truly originated by the main cluster by validating the encrypted value using the shared secret.

公开(公告)号：US10769148B1

公开(公告)日：2020-09-08

申请号：US15714834

申请日：2017-09-25

Applicant: Amazon Technologies, Inc.

Inventor： Nathan Binkert ,  Mengchu Cai ,  Martin Grund ,  Maor Kleider ,  Michail Petropoulos ,  Ippokratis Pandis

IPC: G06F16/00 ,  G06F16/2453 ,  G06F16/2455

Abstract: Relocating data sharing operations for query processing may be implemented when generating plans to perform a query. A query operation that causes a node to share data obtained from a different set of nodes with other nodes in a same set of nodes may be identified. The identified query operation may be replaced with another operation that causes the different set of nodes to share the data directly with the other nodes in the same set of nodes.

公开(公告)号：US12013856B2

公开(公告)日：2024-06-18

申请号：US16102545

申请日：2018-08-13

Applicant: Amazon Technologies, Inc.

Inventor： Bhaven Avalani ,  Andrew Edward Caldwell ,  Naresh Chainani ,  Martin Grund ,  Anurag Windlass Gupta ,  Frederick Ryan Johnson ,  Ippokratis Pandis ,  Michail Petropoulos ,  Srividhya Srinivasan

IPC: G06F16/24 ,  G06F16/2453 ,  G06F16/2455 ,  G06F16/28

CPC classification number: G06F16/2455 ,  G06F16/2453 ,  G06F16/283 ,  G06F16/285

Abstract: Burst performance of a database query may be determined according to a size of the database query. A query to a database may be received. A size may be determined for the query. If the size is less than a size threshold assigned to a first query engine, then the query may be performed at the first query engine. If the size is greater than or equal to the size threshold assigned to the first query engine, then the query may be performed at a second query engine.

公开(公告)号：US11853301B1

公开(公告)日：2023-12-26

申请号：US16370614

申请日：2019-03-29

Applicant: Amazon Technologies, Inc.

Inventor： Ippokratis Pandis ,  Naresh Chainani ,  Kiran Kumar Chinta ,  Venkatraman Govindaraju ,  Andrew Edward Caldwell ,  Naveen Muralimanohar ,  Martin Grund ,  Fabian Oliver Nagel ,  Nikolaos Armenatzoglou

IPC: G06F16/00 ,  G06F16/2455 ,  G06F16/2458 ,  G06F16/22 ,  G06F16/2453 ,  G06F16/242

CPC classification number: G06F16/24552 ,  G06F16/2255 ,  G06F16/2443 ,  G06F16/2445 ,  G06F16/2458 ,  G06F16/24539

Abstract: Compiled portions of code generated to perform a query plan at a query engine may be shared with other query engines. A data store, separate from the query engines, may store compiled portions of query code generated for different queries. If a query engine does not have a locally stored compiled portion of query code, then the separate data store may be accessed in order to obtain a compiled portion of query code, allowing reuse of compiled query code across different queries engines for queries directed to different databases.

公开(公告)号：US20190384845A1

公开(公告)日：2019-12-19

申请号：US16007697

申请日：2018-06-13

Applicant: Amazon Technologies, Inc.

Inventor： Gaurav Saxena ,  George Constantin Caragea ,  Naresh Kishin Chainani ,  Martin Grund

IPC: G06F17/30

Abstract: Database queries may be performed using resources based on a determined size of the database query. Database query size may be dynamically determined for a database query when the query is received. The database query may be assigned to resources used for database queries of the determined size. In some embodiments, timeouts may be applied to reassign database queries to different resources if the performance of the database query exceeds a timeout threshold.

公开(公告)号：US11308106B1

公开(公告)日：2022-04-19

申请号：US15985270

申请日：2018-05-21

Applicant: Amazon Technologies, Inc.

Inventor： Naveen Muralimanohar ,  Bhaven Avalani ,  Martin Grund ,  William Michael McCreedy ,  Ippokratis Pandis ,  Michalis Petropoulos

IPC: G06F16/2458 ,  G06F16/27 ,  G06F16/2453 ,  G06F16/2455

Abstract: Caching results of sub-queries to different locations in a data store may be performed. A database query may be received that causes different storage engines to perform sub-queries to different locations in a data store that stores data for a database. The results of the sub-queries may be stored in a cache. When another database query is received, sub-queries generated to perform the other database query that are the same as one or more of the previously performed sub-queries may obtain the results of the sub-queries from the cache instead of performing the sub-queries again.