Amazon Technologies, Inc.

Robin Alan Golden

Marc Andrew Bowes

James Alfred Gordon Greenfield

Christopher Richard Jacques De Kadt

Izak Van Der Merwe

Gregory Branchek Roth

Arjun Radhakrishnan

Randall Avery Shealey

Jacob Adam Gabrielson

Stephen Andrew Brodsky

John Michael Morkel

Andrew James Lusk

Rahul Sharma Pathak

Anthony A Virtuoso

Michael Groenewald

Joseph Rozenfeld

Dallas Lamont Willett

Aaron-Kenneth Karl Rehaag

Shuki Binyamin

Jacobus Johannes Van Der Merwe

Jeff Thomas Carter

Techniques for adaptive sleep virtual machine management are described. A service of a provider network receives a parameter indicating that a first virtual machine can be slept and determines to sleep the first virtual machine based at least in part on the parameter. A state of the first virtual machine is captured, and the first virtual machine is terminated. The service determines to resume the captured state of the first virtual machine based at least in part on an indication. A second virtual machine is launched using the captured state of the first virtual machine and resumes execution of the captured state of the first virtual machine. A proxy server sends traffic to the first virtual machine before the termination of the first virtual machine and to the second virtual machine after the resumption of execution of the captured state of the first virtual machine by the second virtual machine.

Adaptive sleep virtual machines in a cloud provider network

A unique identifier of an expression which refers to a cell of a data sheet is stored in a repository. In an application comprising an operation based on evaluating the expression, the expression is indicated by the unique identifier. In response to detecting a write directed to the cell, a modified version of contents of the cell is stored without re-evaluating the expression. The expression is re-evaluated in response to determining that the operation of the application is to be implemented.

Expressions management service for data sheet-based applications

Methods, systems, and computer-readable media for request authorization using service coordination are disclosed. An authorization data structure and an operation data structure are selected based at least in part on a request for an operation. The authorization data structure comprises a directed acyclic graph representing a flow of data between service operations associated with authorization of the operation, and the operation data structure comprises a directed acyclic graph representing a flow of data between a service operations associated with execution of the operation. Authorization of the operation is attempted using the authorization data structure, comprising invoking one or more of the service operations associated with authorization. If the authorization is successful, then the execution of the operation is initiated using the operation data structure, comprising invoking one or more of the service operations associated with execution.

Request authorization using recipe-based service coordination

Methods, systems, and computer-readable media for a customer-facing service for service coordination are disclosed. Via a request gateway, a request to perform an operation is received. A data structure associated with the operation is retrieved. The data structure is generated based at least in part on one or more models and an indication of service operations. The one or more models are formatted using a modeling language associated with the request gateway. The data structure comprises a directed acyclic graph representing a flow of data between the service operations, and the flow of data is determined based at least in part on analysis of typed fields of the service operations. The request is processed to perform the operation based at least in part on the data structure, including invoking a plurality of the service operations using traversal of the directed acyclic graph.

Customer-facing service for service coordination

A service workflow agent associated with a particular service of a provider network identifies a repository in which workflow descriptors indicative of tasks to be performed by the service are stored. In response to determining that a modification has been applied at one such repository, the agent examines a particular workflow descriptor stored in the repository. The agent initiates an attempt to implement a first task indicated in the descriptor. Subsequently, the agent updates the descriptor in accordance with an optimistic concurrency control technique to indicate a status of the first task.

Decentralized management of multi-service workflows

A system includes a plurality of computing devices configurable to implement a compute instance of a provider network. A computing device is configured to implement a load balancer that allocates the computing devices to service requests received by the load balancer. The load balancer configured to receive service requests from a plurality of sources, to extract a parameter from each received service request, to select, based on the parameter, a first subset of the plurality of computing devices to be used to service the request, and to forward the request to a selected computing device of the first subset of the computing devices for service.

Shuffle sharded load balancing

Systems with multiple components managing storage may implement efficient storage reclamation. A storage reclamation event may be detected for a system component. An indication to a request dispatching mechanism may be made which indicates that the system component is unable to perform further tasks in order to perform storage reclamation. A storage reclamation operation, such as a stop-the-world garbage collection technique, or a service process restart may be performed to reclaim at least some storage. Upon completion of the storage reclamation operation, an indication may be made to the request distribution mechanism that the service process has resumed performing tasks for the system. In some embodiments, a gossip protocol communicating availability information to different nodes of a distributed system may provide information to schedule storage reclamation operations at different compute nodes of the distributed system.

Efficient storage reclamation for system components managing storage

A distributed execution environment provides instances of computing resources for customer use, such as instances of data processing resources, data storage resources, database resources, and networking resources. Data is collected from systems internal to and external to the distributed execution environment. Some or all of the data is utilized to compute instance availability information for instances of computing resources provided by the distributed execution environment. The instance availability information might then be provided to customers and other users of the distributed execution environment. Various types of actions might be taken in a manual or automated way based upon the computed instance availability information.

Growing community of inventors

Los Gatos, CA, United States of America

Robin Alan Golden