公开(公告)号：US20240330270A1

公开(公告)日：2024-10-03

申请号：US18740434

申请日：2024-06-11

Applicant: Amazon Technologies, Inc.

Inventor： Anurag Windlass Gupta ,  Neal Fachan ,  Samuel James McKelvie ,  Laurion Darrell Burchall ,  Christopher Richard Newcombe ,  Pradeep Jnana Madhavarapu ,  Benjamin Tobler ,  James McClellan Corey

IPC: G06F16/23 ,  G06F11/14 ,  G06F11/20

CPC classification number: G06F16/2365 ,  G06F11/1451 ,  G06F11/1471 ,  G06F16/23 ,  G06F11/2094 ,  G06F2201/80

Abstract: A database system may include a database service and a separate distributed storage service. The database service (or a database engine head node thereof) may be responsible for query parsing, optimization, and execution, transactionality, and consistency, while the storage service may be responsible for generating data pages from redo log records and for durability of those data pages. For example, in response to a write request directed to a particular data page, the database engine head node may generate a redo log record and send it, but not the data page, to a storage service node. The storage service node may store the redo log record and return a write acknowledgement to the database service prior to applying the redo log record. The server node may apply the redo log record and other redo log records to a previously stored version of the data page to create a current version.

公开(公告)号：US11030055B2

公开(公告)日：2021-06-08

申请号：US14201505

申请日：2014-03-07

Applicant: Amazon Technologies, Inc.

Inventor： Anurag Windlass Gupta ,  Laurion Darrell Burchall ,  Pradeep Jnana Madhavarapu ,  Neal Fachan

IPC: G06F11/14 ,  G06F11/20

Abstract: A distributed database system may implement fast crash recovery. Upon recovery from a database head node failure, a connection with one or more storage nodes of a distributed storage system storing data for a database implemented by the database head node may be established. Upon establishment of the connection with the storage nodes, that database may be made available for access, such as for various access requests. In various embodiments, redo log records may not be replayed in order to provide access to the database. In at least some embodiments, the storage nodes may provide a current state of data stored for the database in response to requests.

公开(公告)号：US20200327114A1

公开(公告)日：2020-10-15

申请号：US16914075

申请日：2020-06-26

Applicant: Amazon Technologies, Inc.

Inventor： Anurag Windlass Gupta ,  Neal Fachan ,  Samuel James McKelvie ,  Laurion Darrell Burchall ,  Christopher Richard Newcombe ,  Pradeep Jnana Madhavarapu ,  Benjamin Tobler ,  James McClellan Corey

IPC: G06F16/23 ,  G06F11/14

Abstract: A database system may include a database service and a separate distributed storage service. The database service (or a database engine head node thereof) may be responsible for query parsing, optimization, and execution, transactionality, and consistency, while the storage service may be responsible for generating data pages from redo log records and for durability of those data pages. For example, in response to a write request directed to a particular data page, the database engine head node may generate a redo log record and send it, but not the data page, to a storage service node. The storage service node may store the redo log record and return a write acknowledgement to the database service prior to applying the redo log record. The server node may apply the redo log record and other redo log records to a previously stored version of the data page to create a current version.

公开(公告)号：US10331655B2

公开(公告)日：2019-06-25

申请号：US15613637

申请日：2017-06-05

Applicant: Amazon Technologies, Inc.

Inventor： Anurag Windlass Gupta ,  Pradeep Jnana Madhavarapu ,  Laurion Darrell Burchall ,  Neal Fachan

IPC: G06F16/00 ,  G06F16/23 ,  G06F16/27 ,  G06F11/14

Abstract: A database system may maintain a plurality of log records at a distributed storage system. Each of the plurality of log records may be associated with a respective change to a data page. Upon detection of a coalesce event for a particular data page, log records linked to the particular data page may be applied to generate the particular data page in its current state. Detecting the coalesce event may be a determination that the number of log records linked to the particular data page exceeds a threshold.

公开(公告)号：US09501501B2

公开(公告)日：2016-11-22

申请号：US14201509

申请日：2014-03-07

Applicant: Amazon Technologies, Inc.

Inventor： Pradeep Jnana Madhavarapu ,  Neal Fachan ,  Anurag Windlass Gupta ,  Samuel James McKelvie

IPC: G06F17/00 ,  G06F17/30

CPC classification number: G06F11/1458 ,  G06F17/30283 ,  G06F17/30289 ,  G06F17/30368 ,  G06F2201/84

Abstract: A database system may maintain a plurality of log records at a distributed storage system. Each of the plurality of log records may be associated with a respective change to a data page. The plurality of log records may be transformed (e.g., cropped, prune, reduce, fused, deleted, merged, added, etc.).

Abstract translation: 数据库系统可以在分布式存储系统上维护多个日志记录。 多个日志记录中的每一个可以与对数据页的相应改变相关联。 多个日志记录可以被转换（例如，裁剪，修剪，减少，融合，删除，合并，添加等）。

公开(公告)号：US20230092908A1

公开(公告)日：2023-03-23

申请号：US18054870

申请日：2022-11-11

Applicant: Amazon Technologies, Inc.

Inventor： Anurag Windlass Gupta ,  Neal Fachan ,  Samuel James McKelvie ,  Laurion Darrell Burchall ,  Christopher Richard Newcombe ,  Pradeep Jnana Madhavarapu ,  Benjamin Tobler ,  James McClellan Corey

IPC: G06F16/23 ,  G06F11/14

Abstract: A database system may include a database service and a separate distributed storage service. The database service (or a database engine head node thereof) may be responsible for query parsing, optimization, and execution, transactionality, and consistency, while the storage service may be responsible for generating data pages from redo log records and for durability of those data pages. For example, in response to a write request directed to a particular data page, the database engine head node may generate a redo log record and send it, but not the data page, to a storage service node. The storage service node may store the redo log record and return a write acknowledgement to the database service prior to applying the redo log record. The server node may apply the redo log record and other redo log records to a previously stored version of the data page to create a current version.

公开(公告)号：US11500852B2

公开(公告)日：2022-11-15

申请号：US16914075

申请日：2020-06-26

Applicant: Amazon Technologies, Inc.

Inventor： Anurag Windlass Gupta ,  Neal Fachan ,  Samuel James McKelvie ,  Laurion Darrell Burchall ,  Christopher Richard Newcombe ,  Pradeep Jnana Madhavarapu ,  Benjamin Tobler ,  James McClellan Corey

IPC: G06F16/23 ,  G06F11/14 ,  G06F11/20

Abstract: A database system may include a database service and a separate distributed storage service. The database service (or a database engine head node thereof) may be responsible for query parsing, optimization, and execution, transactionality, and consistency, while the storage service may be responsible for generating data pages from redo log records and for durability of those data pages. For example, in response to a write request directed to a particular data page, the database engine head node may generate a redo log record and send it, but not the data page, to a storage service node. The storage service node may store the redo log record and return a write acknowledgement to the database service prior to applying the redo log record. The server node may apply the redo log record and other redo log records to a previously stored version of the data page to create a current version.

公开(公告)号：US10698881B2

公开(公告)日：2020-06-30

申请号：US15369681

申请日：2016-12-05

Applicant: Amazon Technologies, Inc.

Inventor： Anurag Windlass Gupta ,  Neal Fachan ,  Samuel James McKelvie ,  Laurion Darrell Burchall ,  Christopher Richard Newcombe ,  Pradeep Jnana Madhavarapu ,  Benjamin Tobler ,  James McClellan Corey

IPC: G06F16/23 ,  G06F11/14 ,  G06F11/20

Abstract: A database system may include a database service and a separate distributed storage service. The database service (or a database engine head node thereof) may be responsible for query parsing, optimization, and execution, transactionality, and consistency, while the storage service may be responsible for generating data pages from redo log records and for durability of those data pages. For example, in response to a write request directed to a particular data page, the database engine head node may generate a redo log record and send it, but not the data page, to a storage service node. The storage service node may store the redo log record and return a write acknowledgement to the database service prior to applying the redo log record. The server node may apply the redo log record and other redo log records to a previously stored version of the data page to create a current version.

公开(公告)号：US20170270152A1

公开(公告)日：2017-09-21

申请号：US15613637

申请日：2017-06-05

Applicant: Amazon Technologies, Inc.

Inventor： Anurag Windlass Gupta ,  Pradeep Jnana Madhavarapu ,  Laurion Darrell Burchall ,  Neal Fachan

IPC: G06F17/30 ,  G06F11/14

CPC classification number: G06F16/2358 ,  G06F11/1474 ,  G06F16/27 ,  G06F2201/80 ,  G06F2201/82

Abstract: A database system may maintain a plurality of log records at a distributed storage system. Each of the plurality of log records may be associated with a respective change to a data page. Upon detection of a coalesce event for a particular data page, log records linked to the particular data page may be applied to generate the particular data page in its current state. Detecting the coalesce event may be a determination that the number of log records linked to the particular data page exceeds a threshold.

公开(公告)号：US09514007B2

公开(公告)日：2016-12-06

申请号：US14201493

申请日：2014-03-07

Applicant: Amazon Technologies, Inc.

Inventor： Anurag Windlass Gupta ,  Neal Fachan ,  Samuel James McKelvie ,  Laurion Darrell Burchall ,  Christopher Richard Newcombe ,  Pradeep Jnana Madhavarapu ,  Benjamin Tobler ,  James McClellan Corey

IPC: G06F17/30 ,  G06F11/14 ,  G06F11/20

CPC classification number: G06F17/30371 ,  G06F11/1451 ,  G06F11/1471 ,  G06F11/2094 ,  G06F17/30345 ,  G06F2201/80

Abstract: A database system may include a database service and a separate distributed storage service. The database service (or a database engine head node thereof) may be responsible for query parsing, optimization, and execution, transactionality, and consistency, while the storage service may be responsible for generating data pages from redo log records and for durability of those data pages. For example, in response to a write request directed to a particular data page, the database engine head node may generate a redo log record and send it, but not the data page, to a storage service node. The storage service node may store the redo log record and return a write acknowledgement to the database service prior to applying the redo log record. The server node may apply the redo log record and other redo log records to a previously stored version of the data page to create a current version.

Abstract translation: 数据库系统可以包括数据库服务和单独的分布式存储服务。 数据库服务（或其数据库引擎头节点）可以负责查询解析，优化和执行，事务性和一致性，而存储服务可能负责从重做日志记录生成数据页面以及对这些数据的耐久性 页面。 例如，响应于针对特定数据页的写请求，数据库引擎头节点可以生成重做日志记录，并将其发送到存储服务节点，而不是数据页。 存储服务节点可以存储重做日志记录，并在应用重做日志记录之前向数据库服务返回写入确认。 服务器节点可以将重做日志记录和其他重做日志记录应用于先前存储的数据页面版本，以创建当前版本。