-
公开(公告)号:US09575982B1
公开(公告)日:2017-02-21
申请号:US13872996
申请日:2013-04-29
Applicant: Amazon Technologies, Inc.
Inventor: Subramanian Sankara Subramanian , Stefano Stefani
IPC: G06F17/30
CPC classification number: G06F17/30339 , G06F17/30519
Abstract: Solid-state storage devices may be employed to store data maintained by a database management system, but may have characteristics that reduce the efficiency of interactions between the database management system and the device. A storage subsystem may receive information indicative of internal boundaries within database data. A segment of the database data may be selected for compression, wherein the size of the segment is based at least on one or more the internal boundaries, the memory page size of the solid-state drive, and a predicted rate of compression. The compressed segment may be stored if it has a size less than the memory page size of the device. If it does not, compression may be retried with a smaller segment of data or a portion of the data may be stored in uncompressed form. Additional segments of the data may be stored on the solid-state drive in a similar manner.
Abstract translation: 可以使用固态存储设备来存储由数据库管理系统维护的数据,但是可以具有降低数据库管理系统和设备之间的交互效率的特性。 存储子系统可以接收指示数据库数据内部边界的信息。 可以选择数据库数据的一部分用于压缩,其中段的大小至少基于一个或多个内部边界,固态驱动器的存储器页面大小和预测的压缩率。 如果压缩片段的尺寸小于设备的内存页面大小,则可以将其压缩。 如果没有,则可以用较小的数据段来重试压缩,或者可以以未压缩的形式存储一部分数据。 数据的附加段可以以类似的方式存储在固态驱动器上。
-
公开(公告)号:US11258725B2
公开(公告)日:2022-02-22
申请号:US16880740
申请日:2020-05-21
Applicant: Amazon Technologies, Inc.
Inventor: Parikshit Shivajirao Pol , Subramanian Sankara Subramanian , Rajaprabhu Thiruchi Loganathan , Rama Krishna Sandeep Pokkunuri , Gopinath Duddi , Akshat Vig , Safeer Mohiuddin , Sudarshan Narasimhan
IPC: G06F16/30 , H04L47/70 , G06F16/13 , G06F16/901 , G06F16/2455 , G06F9/50 , G06F11/34 , G06F16/23 , H04L43/065 , G06F11/30
Abstract: Information describing changes to a collection of items maintained by a database may be stored in a log file. The information in the log file may be converted into a stream of records describing the changes. The records may be directed to a computing node selected for performing a trigger function in response to the change, based on applying a hash function to a portion of the record, identifying a hash space associated with a value output by the hash function, and mapping from the hash space to the selected computing node.
-
公开(公告)号:US10423493B1
公开(公告)日:2019-09-24
申请号:US14977472
申请日:2015-12-21
Applicant: Amazon Technologies, Inc.
Inventor: Akshat Vig , Parikshit Shivajirao Pol , Subramanian Sankara Subramanian , Rama Krishna Sandeep Pokkunuri , Rajaprabhu Thiruchi Loganathan , Harini Chandrasekharan
Abstract: In response to determining that continuous data protection is to be enabled for a particular table of a database service, a service component verifies that automated transmission of change records of the table to a log-structured journal has been configured. A given change record comprises a before-image and an after-image associated with a committed database write, and is assigned a unique sequence number. In response to a determination to restore the table as of a specified point in time, a restore record set is identified from the journal with respect to a selected snapshot of the table. The restore record set includes change records which are not represented in the snapshot and are to be represented in the restored table. A restore result table is created using the selected snapshot and the restore record set.
-
公开(公告)号:US10310737B1
公开(公告)日:2019-06-04
申请号:US15404809
申请日:2017-01-12
Applicant: Amazon Technologies, Inc.
Inventor: Subramanian Sankara Subramanian , Stefano Stefani
IPC: G06F16/00 , G06F3/06 , G06F16/31 , G06F16/174 , G06F16/22
Abstract: Solid-state storage devices may be employed to store data maintained by a database management system, but may have characteristics that reduce the efficiency of interactions between the database management system and the device. A storage subsystem may receive information indicative of internal boundaries within database data. A segment of the database data may be selected for compression, wherein the size of the segment is based at least on one or more the internal boundaries, the memory page size of the solid-state drive, and a predicted rate of compression. The compressed segment may be stored if it has a size less than the memory page size of the device. If it does not, compression may be retried with a smaller segment of data or a portion of the data may be stored in uncompressed form. Additional segments of the data may be stored on the solid-state drive in a similar manner.
-
公开(公告)号:US20170093755A1
公开(公告)日:2017-03-30
申请号:US14868236
申请日:2015-09-28
Applicant: Amazon Technologies, Inc.
Inventor: Parikshit Shivajirao Pol , Subramanian Sankara Subramanian , Rajaprabhu Thiruchi Loganathan , Rama Krishna Sandeep Pokkunuri , Gopinath Duddi , Akshat Vig , Safeer Mohiuddin , Sudarshan Narasimhan
IPC: H04L12/911 , H04L12/26 , G06F17/30
Abstract: Information describing changes to a collection of items maintained by a database may be stored in a log file. The information in the log file may be converted into a stream of records describing the changes. The records may be directed to a computing node selected for performing a trigger function in response to the change, based on applying a hash function to a portion of the record, identifying a hash space associated with a value output by the hash function, and mapping from the hash space to the selected computing node.
-
公开(公告)号:US12229011B2
公开(公告)日:2025-02-18
申请号:US16575296
申请日:2019-09-18
Applicant: Amazon Technologies, Inc.
Inventor: Akshat Vig , Parikshit Shivajirao Pol , Subramanian Sankara Subramanian , Rama Krishna Sandeep Pokkunuri , Rajaprabhu Thiruchi Loganathan , Harini Chandrasekharan
Abstract: In response to determining that continuous data protection is to be enabled for a particular table of a database service, a service component verifies that automated transmission of change records of the table to a log-structured journal has been configured. A given change record comprises a before-image and an after-image associated with a committed database write, and is assigned a unique sequence number. In response to a determination to restore the table as of a specified point in time, a restore record set is identified from the journal with respect to a selected snapshot of the table. The restore record set includes change records which are not represented in the snapshot and are to be represented in the restored table. A restore result table is created using the selected snapshot and the restore record set.
-
公开(公告)号:US20200287841A1
公开(公告)日:2020-09-10
申请号:US16880740
申请日:2020-05-21
Applicant: Amazon Technologies, Inc.
Inventor: Parikshit Shivajirao Pol , Subramanian Sankara Subramanian , Rajaprabhu Thiruchi Loganathan , Rama Krishna Sandeep Pokkunuri , Gopinath Duddi , Akshat Vig , Safeer Mohiuddin , Sudarshan Narasimhan
IPC: H04L12/911 , G06F16/13 , G06F16/901 , G06F16/2455 , G06F9/50 , G06F11/34 , H04L12/26
Abstract: Information describing changes to a collection of items maintained by a database may be stored in a log file. The information in the log file may be converted into a stream of records describing the changes. The records may be directed to a computing node selected for performing a trigger function in response to the change, based on applying a hash function to a portion of the record, identifying a hash space associated with a value output by the hash function, and mapping from the hash space to the selected computing node.
-
公开(公告)号:US20200012568A1
公开(公告)日:2020-01-09
申请号:US16575296
申请日:2019-09-18
Applicant: Amazon Technologies, Inc.
Inventor: Akshat Vig , Parikshit Shivajirao Pol , Subramanian Sankara Subramanian , Rama Krishna Sandeep Pokkunuri , Rajaprabhu Thiruchi Loganathan , Harini Chandrasekharan
Abstract: In response to determining that continuous data protection is to be enabled for a particular table of a database service, a service component verifies that automated transmission of change records of the table to a log-structured journal has been configured. A given change record comprises a before-image and an after-image associated with a committed database write, and is assigned a unique sequence number. In response to a determination to restore the table as of a specified point in time, a restore record set is identified from the journal with respect to a selected snapshot of the table. The restore record set includes change records which are not represented in the snapshot and are to be represented in the restored table. A restore result table is created using the selected snapshot and the restore record set.
-
公开(公告)号:US11588755B2
公开(公告)日:2023-02-21
申请号:US17589643
申请日:2022-01-31
Applicant: Amazon Technologies, Inc.
Inventor: Parikshit Shivajirao Pol , Subramanian Sankara Subramanian , Rajaprabhu Thiruchi Loganathan , Rama Krishna Sandeep Pokkunuri , Gopinath Duddi , Akshat Vig , Safeer Mohiuddin , Sudarshan Narasimhan
IPC: G06F16/30 , H04L47/70 , G06F16/13 , G06F16/901 , G06F16/2455 , G06F9/50 , G06F11/34 , G06F16/23 , H04L43/065 , G06F11/30
Abstract: Information describing changes to a collection of items maintained by a database may be stored in a log file. The information in the log file may be converted into a stream of records describing the changes. The records may be directed to a computing node selected for performing a trigger function in response to the change, based on applying a hash function to a portion of the record, identifying a hash space associated with a value output by the hash function, and mapping from the hash space to the selected computing node.
-
公开(公告)号:US20220158953A1
公开(公告)日:2022-05-19
申请号:US17589643
申请日:2022-01-31
Applicant: Amazon Technologies, Inc.
Inventor: Parikshit Shivajirao Pol , Subramanian Sankara Subramanian , Rajaprabhu Thiruchi Loganathan , Rama Krishna Sandeep Pokkunuri , Gopinath Duddi , Akshat Vig , Safeer Mohiuddin , Sudarshan Narasimhan
IPC: H04L47/70 , G06F16/13 , G06F16/901 , G06F16/2455 , G06F9/50 , G06F11/34 , G06F16/23 , H04L43/065
Abstract: Information describing changes to a collection of items maintained by a database may be stored in a log file. The information in the log file may be converted into a stream of records describing the changes. The records may be directed to a computing node selected for performing a trigger function in response to the change, based on applying a hash function to a portion of the record, identifying a hash space associated with a value output by the hash function, and mapping from the hash space to the selected computing node.
-
-
-
-
-
-
-
-
-