公开(公告)号：US20210406071A1

公开(公告)日：2021-12-30

申请号：US16915957

申请日：2020-06-29

Applicant: Amazon Technologies, Inc.

Inventor： Michael Groenewald ,  Diwakar Gupta ,  Izak van Van Der Merwe ,  Adam Scott King ,  Cindy-Lee Engelbrecht ,  Christopher Sam Goosen ,  Aletta Johanna Blanken ,  Ryan Walter Jason Waite

IPC: G06F9/50 ,  G06F9/48 ,  G06F9/445

Abstract: At a managed control plane service, constituent services and operational requirements of an application are identified. In response to an end-user request directed to the application, contents of an inter-service request are generated at a resource selected by the managed control plane service for a first constituent service, and a response to the message is generated at another resource selected for a second constituent service. Tasks to be performed for the operational requirements are initiated by the managed control plane service.

公开(公告)号：US20210240513A1

公开(公告)日：2021-08-05

申请号：US17214517

申请日：2021-03-26

Applicant: Amazon Technologies, Inc.

Inventor： Upendra Bhalchandra Shevade ,  Diwakar Gupta ,  Michael B. Furr ,  Kevin P. Smith ,  Nishant Mehta

IPC: G06F9/455 ,  G06F9/50

Abstract: A first virtualization control mode to be used for configuring one or more compute instances is determined. Based at least partly on the mode, preparatory configuration operations for launching a compute instance are initiated. The operations include transferring at least a portion of a machine image to a storage device accessible from a host, and initialization of a virtual network interface. A compute instance is instantiated using the machine image at the host. The compute instance is a thread of an intermediary process launched by an administrative agent at the host in response to a launch request.

公开(公告)号：US11036537B1

公开(公告)日：2021-06-15

申请号：US16365563

申请日：2019-03-26

Applicant: Amazon Technologies, Inc.

Inventor： Michael Phillip Quinn ,  Nishant Mehta ,  Diwakar Gupta ,  Bradley Joseph Gussin

IPC: G06F9/455 ,  G06F9/50

Abstract: Techniques for on demand capacity management in a provider network are described. The provider network includes electronic devices that provide computing-related resources to customers. The unused capacity of these electronic devices—such as processor cores, memory, network bandwidth, etc.—can be used to satisfy a variety of computing needs. Services of the provider network allocate portions of the unused capacity based on customer requests for computing-related resources.

公开(公告)号：US10963282B2

公开(公告)日：2021-03-30

申请号：US16216568

申请日：2018-12-11

Applicant: Amazon Technologies, Inc.

Inventor： Upendra Bhalchandra Shevade ,  Diwakar Gupta ,  Michael B. Furr ,  Kevin P. Smith ,  Nishant Mehta

IPC: G06F9/455 ,  G06F9/50

Abstract: A first virtualization control mode to be used for configuring one or more compute instances is determined. Based at least partly on the mode, preparatory configuration operations for launching a compute instance are initiated. The operations include transferring at least a portion of a machine image to a storage device accessible from a host, and initialization of a virtual network interface. A compute instance is instantiated using the machine image at the host. The compute instance is a thread of an intermediary process launched by an administrative agent at the host in response to a launch request.

公开(公告)号：US10951479B1

公开(公告)日：2021-03-16

申请号：US16201084

申请日：2018-11-27

Applicant: Amazon Technologies, Inc.

Inventor： Diwakar Gupta ,  Johannes Stephanus Jansen Van Rensburg ,  Aletta Johanna Blanken ,  Christopher Sam Goosen ,  Bret Kiraly

IPC: G06F15/177 ,  H04L12/24 ,  H04L12/751

Abstract: Techniques for managing fault domains using cells are described. An area of a provider network may be divided into multiple cells, with each cell representing a different fault domain of the area of the provider network. A customer can provide domain definitions for their service or application and a cell management service can use the domain definitions to place the infrastructure and compute resources underlying the customer's application or service in appropriate cells within an area of the provider network. In some embodiments, the domain definitions may be account-based, where the domain definition may be to place resources in different fault domains depending on the account they are associated with. Alternatively, the customer may tag resources with an identifier such that resources tagged with a first identifier may be placed in a first cell while resources tagged with a second identifier may be placed in a second cell.

公开(公告)号：US20210004262A1

公开(公告)日：2021-01-07

申请号：US17030245

申请日：2020-09-23

Applicant: Amazon Technologies, Inc.

Inventor： Diwakar Gupta ,  Alan Hadley Goodman ,  Georgios Elissaios ,  Arvind Suryakumar ,  Bret David Kiraly

IPC: G06F9/48 ,  G06F9/455

Abstract: Techniques for managing the migration of virtual machine instances are described herein. A migration of a virtual machine from a source host to a destination host is determined to be predicted to fail. The migration is cancelled by stopping the virtual machine at the destination host as a result of said determination.

公开(公告)号：US10684894B2

公开(公告)日：2020-06-16

申请号：US15809884

申请日：2017-11-10

Applicant: Amazon Technologies, Inc.

Inventor： Michael Phillip Quinn ,  Diwakar Gupta

IPC: G06F9/50 ,  G06F9/455 ,  H04L12/24 ,  H04L12/911

Abstract: Techniques for capacity management in provider networks using dynamic host device instance type reconfigurations are described. A fleet reconfiguration service performs runtime reconfiguration of slots of host electronic devices that are available to execute compute instances, while the electronic devices may execute other compute instances, to dynamically change the type and/or numbers of slots of the electronic devices available for compute instance execution.

公开(公告)号：US20190310881A1

公开(公告)日：2019-10-10

申请号：US16442331

申请日：2019-06-14

Applicant: Amazon Technologies, Inc.

Inventor： Diwakar Gupta ,  Alan Hadley Goodman ,  Georgios Elissaios ,  Arvind Suryakumar ,  Bret David Kiraly

IPC: G06F9/48 ,  G06F9/455

Abstract: A migration of a virtual machine running on a source host is determined to be performed for the virtual from the source host to a target host. The virtual machine is migrated from the source host to the target host at least by copying a state of the virtual machine from the source host to the target host while the virtual machine is running on the source host. Packets are caused to be forwarded to the virtual machine running on the target host.

公开(公告)号：US10382408B1

公开(公告)日：2019-08-13

申请号：US15652864

申请日：2017-07-18

Applicant: Amazon Technologies, Inc.

Inventor： Khaja Ehteshamuddin Ahmed ,  Diwakar Gupta ,  Matthew Shawn Wilson

IPC: H04L29/06 ,  G06F21/60 ,  G06F9/455

Abstract: Technology for migration of a computing instance is provided. In one example, a method may include receiving instructions to initiate migration of the computing instance from a first host to a second host. A first message for sending to the first host may be generated which includes instructions to send data representing the computing instance to the second host. The first message may further include encryption information for use in deriving at least one key for encrypting communications to the second host from the first host. A second message for sending to the second host may be generated which includes instructions to receive the data representing the computing instance from the first host. The second message may further include information for use in deriving at least one key for decrypting communications from the first host. The first and second messages may be sent to the respective first and second hosts.

公开(公告)号：US10228969B1

公开(公告)日：2019-03-12

申请号：US14750978

申请日：2015-06-25

Applicant: Amazon Technologies, Inc.

Inventor： Diwakar Gupta ,  Georgios Elissaios ,  Johannes Stephanus Jansen van Rensberg ,  Michael Groenewald

IPC: G06F9/44 ,  G06F9/48 ,  G06F9/455 ,  G06F9/54

Abstract: Techniques for optimistic locking of virtual machine instances during a migration are described herein. Application programming interface requests are classified by type. When a request such as an application programming interface request is received during the migration of a virtual machine instance from a source location to a target location, the request is classified according to the type and according to the state of the migration. Based on that classification, it is determined whether to block the request, allow the request, or cancel the migration.