公开(公告)号：US11947516B1

公开(公告)日：2024-04-02

申请号：US15902222

申请日：2018-02-22

Applicant: Amazon Technologies, Inc.

Inventor： Ankit Kumar ,  Alazel Acheson ,  Jasmeet Chhabra ,  Luke Edward Kennedy ,  Daniel Stephen Popick ,  Weixun Wang

IPC: G06F16/23 ,  G06F16/185 ,  G06F16/21 ,  G06F16/22 ,  G06F16/27

CPC classification number: G06F16/23 ,  G06F16/185 ,  G06F16/211 ,  G06F16/22 ,  G06F16/27

Abstract: The updating of a definition layer or schema for a large distributed database can be accomplished using a plurality of data store tiers. A distributed database can be made up of many individual data stores, and these data stores can be allocated across a set of tiers based on business logic or other allocation criteria. The update can be applied sequentially to the individual tiers, such that only data stores for a single tier are being updated at any given time. This can help to minimize downtime for the database as a whole, and can help to minimize problems that may result from an unsuccessful update. Such an approach can also allow for simplified error detection and rollback, as well as providing control over a rate at which the update is applied to the various data stores of the distributed database.

公开(公告)号：US11126520B2

公开(公告)日：2021-09-21

申请号：US16530650

申请日：2019-08-02

Applicant: Amazon Technologies, Inc.

Inventor： Alazel Acheson ,  Meng Hu ,  Nauman Zubaid Khan ,  Mai-Lan Tomsen Bukovec

IPC: G06F16/00 ,  G06F11/267 ,  G06F3/00 ,  G06F16/23

Abstract: A computing resource service provider may store user data in a distributed data storage system. The distributed data storage system may contain one or more storage partitions configured to store based at least in part on prefixes of keys contained in a key-value store, where the size of the keys may vary. The one or more storage partitions may track requests to access data where the requests include a key such that the data may be located by the service provider based at least in part on the key. When a request is received a skew value associated with the key included in the request may be determined. The skew value may be determined based at least in part on the ratio of rate estimators, where the rate estimators represent a weighted average of the movement of the keys in a key space. If the skew value exceeds a threshold the service provider may take mitigating action.

公开(公告)号：US11086531B2

公开(公告)日：2021-08-10

申请号：US16575258

申请日：2019-09-18

Applicant: Amazon Technologies, Inc.

Inventor： Mahendra Manshi Chheda ,  Srikanth Mandadi ,  Alazel Acheson ,  Christopher Ryan Baker ,  Matthew William Berry, Jr.

IPC: G06F3/06

Abstract: Scaling events may be detected for hosting hierarchical data structures. Scaling events may be detected to modify the capacity of a data store for hierarchical data structures to handle changing write workloads, read workloads, or storage capacity. Hierarchical data structures may be moved from one group of storage hosts to another group of storage hosts according to a filtered snapshot that includes the hierarchical data structures to be moved that is provided to the destination storage hosts. Changes made to the hierarchical data structures made at the source storage hosts during the move can be applied to the filtered snapshot so that the hierarchical data structures may be made available at the destination storage hosts inclusive of the changes.

公开(公告)号：US11010361B1

公开(公告)日：2021-05-18

申请号：US15475007

申请日：2017-03-30

Applicant: Amazon Technologies, Inc.

Inventor： Mahendra Manshi Chheda ,  James Robert Englert ,  Christopher Ryan Baker ,  Alazel Acheson ,  Srikanth Mandadi

IPC: G06F16/22 ,  G06F9/448 ,  G06F16/21 ,  G06F16/28

Abstract: Code may be associated with one or more objects in a hierarchical data structure for execution. An access request for an object in the hierarchical data structure may be received. A schema applicable to the hierarchical data structure may be accessed and evaluated to identify code associated with the object. The code may be executed and servicing of the access request may be performed based, at least in part, on a result of executing the code. Code may be received and stored for inclusion in the schema, in some embodiments. Code may be executed by requesting execution of code that is stored and executed at a remote execution platform, in some embodiments.

公开(公告)号：US10678528B1

公开(公告)日：2020-06-09

申请号：US15819170

申请日：2017-11-21

Applicant: Amazon Technologies, Inc.

Inventor： Alazel Acheson ,  Mahendra Manshi Chheda ,  Srikanth Mandadi

IPC: G06F8/65 ,  G06F11/36 ,  G06F16/21

Abstract: A system such as a service of a computing resource service provider, a directory service, a directory server, or any suitable system includes executable code that, if executed by one or more processors, causes the system to perform a first stage of a multi-stage deployment of a first directory schema by at least providing a second directory schema to a first computer system, wherein the first computer system is associated with a directory configured according to the first directory schema and causing the first computer system to reconfigure the directory according to the second directory schema The system may also determine, based on a result of reconfiguring the directory, whether to proceed to a second stage of the multi-stage deployment of the first directory schema. The system may be utilized as part of a directory schema update process wherein a multi-stage deployment pipeline is utilized.

公开(公告)号：US10657119B1

公开(公告)日：2020-05-19

申请号：US14975353

申请日：2015-12-18

Applicant: Amazon Technologies, Inc.

Inventor： Alazel Acheson ,  David Carroll ,  Christopher Andrew Stephens ,  Seth William Markle ,  Jonathan Herman ,  Mihir Dharamshi ,  Rajesh Sampath ,  Shreeranga Puttur Ramakrishna ,  Rameez Sajwani

IPC: G06F40/197 ,  G06F16/23

Abstract: A fleet node management system may include a metadata store, a plurality of fleet nodes, and one or more metadata mutation devices. The metadata store may be configured to store dynamic metadata. The plurality of fleet nodes may be configured to determine, based on a gossip protocol, whether to continue performance of a function that uses a local version of the metadata. The one or more metadata mutation devices may be configured to determine, based on a global state of the fleet nodes, whether to modify the dynamic metadata for the fleet nodes.

公开(公告)号：US11080332B1

公开(公告)日：2021-08-03

申请号：US15820227

申请日：2017-11-21

Applicant: Amazon Technologies, Inc.

Inventor： Alazel Acheson ,  Mahendra Manshi Chheda ,  Srikanth Mandadi ,  Hyun Sik Kim

IPC: G06F16/901 ,  G06F16/23 ,  G06F16/903

Abstract: A processing device generates an index node for an attribute in a graph database, wherein the index node is linked to a second node by a first edge having a first edge type. The processing device determines a first plurality of additional nodes that have the attribute. For each node of the first plurality of additional nodes, the processing device generates an edge linking the node to the index node, wherein the edge comprises a second edge type.

公开(公告)号：US20200334374A1

公开(公告)日：2020-10-22

申请号：US16919305

申请日：2020-07-02

Applicant: Amazon Technologies, Inc.

Inventor： Srikanth Mandadi ,  Mahendra Manshi Chheda ,  Alazel Acheson ,  Daniel Stephen Popick ,  James Robert Englert

IPC: G06F21/62 ,  G06F16/22 ,  G06F16/23

Abstract: A schema for a hierarchical data structure may include application specific extensions to the schema applied to a hierarchical data structure. Class may be added to the schema by individual applications granted access to a hierarchical data structure. When an access request for an object of the hierarchical data structure is received, the class may be identified in the schema and applied to process the access request to the object. Different classes may be added by different applications without disrupting the utilization of the schema for accessing the hierarchical data structure of other applications.

公开(公告)号：US10671639B1

公开(公告)日：2020-06-02

申请号：US15475031

申请日：2017-03-30

Applicant: Amazon Technologies, Inc.

Inventor： Alazel Acheson ,  Christopher Ryan Baker ,  Mahendra Manshi Chheda ,  James Robert Englert ,  Meng Li ,  Srikanth Mandadi ,  Slavka Praus ,  Colin Watson

IPC: G06F16/18 ,  G06F16/27 ,  G06F16/22 ,  G06F16/23

Abstract: Updates to a hierarchical data structure may be selectively replicated to other replicas of the hierarchical data structure. An update for a hierarchical data structure may be received and committed to the hierarchical data structure. A determination as to whether any other replicas of the hierarchical data structure have permission to receive the update may be made. For those replicas of the hierarchical data structure with permission to receive the update, the update may be provided to the replicas and committed to the replicas. Different types of replication techniques may be implemented, such as pull-based replication techniques or push-based replication techniques. Replication permissions for objects of the hierarchical data structure may be individually defined, in some embodiments.

公开(公告)号：US10423342B1

公开(公告)日：2019-09-24

申请号：US15475034

申请日：2017-03-30

Applicant: Amazon Technologies, Inc.

Inventor： Mahendra Manshi Chheda ,  Srikanth Mandadi ,  Alazel Acheson ,  Christopher Ryan Baker ,  Matthew William Berry, Jr.

IPC: G06F3/06

Abstract: Scaling events may be detected for hosting hierarchical data structures. Scaling events may be detected to modify the capacity of a data store for hierarchical data structures to handle changing write workloads, read workloads, or storage capacity. Hierarchical data structures may be moved from one group of storage hosts to another group of storage hosts according to a filtered snapshot that includes the hierarchical data structures to be moved that is provided to the destination storage hosts. Changes made to the hierarchical data structures made at the source storage hosts during the move can be applied to the filtered snapshot so that the hierarchical data structures may be made available at the destination storage hosts inclusive of the changes.