Amazon Technologies, Inc.

David Alexander Dunlap

Craig Wesley Howard

Bradley E Marshall

Tal Saraf

Nicholas J Maniscalco

Marc John Brooker

Benjamin W S Redman

Ajay Nair

Shubham Katiyar

Venkatesh Vijayaraghavan

Manigandan Radhakrishnan

Yilmaz Can Cecen

Martin Cornelis Frederik Slot

Katarzyna Anna Puchala

Vo Vuong

Meenakshi Vembusubramanian

Anton Stephen Radlein

Khawaja Salman Shams

Andrew Kent Warfield

Benjamin Aldouby Schwartz

Alex Xiaoye Zhang

Ryan Farris

An on-demand code execution environment present in points of presence (POPs) and in regions serviced by the POPs is provided herein. For example, a POP may receive a request to execute a task associated with user-defined code. If the POP determines that the computing resources necessary to execute a received task are not available or that the POP should not execute the received task for another reason (e.g., the task is not commonly received and the computing resources needed to execute the task are therefore best allocated for other requests), the POP can forward the task to a region that the POP services for execution by an on-demand code execution environment present in the region. The on-demand code execution environment present in the region can execute the task and forward the results of the execution to the POP for distribution back to a user device that requested the task execution.

Multi-region request-driven code execution system

A set of data units associated with a data object is obtained, such that respective instances of the data object can be reconstructed from respective subsets of the set. Corresponding to a request for the data object, a first subset of the set is identified. The first subset meets a uniqueness criterion with respect to other subsets of the set that are used to respond to other requests for the data object. An instance of the data object is reconstructed from the first subset.

Space-efficient techniques for generating unique instances of data objects

A system, method and computer-readable medium for data uploading based on points of presence (POPs) are provided. In response to a client's request for data uploading, the system provides routing information for POPs that may facilitate data communications between the client and a data storage service provider. The client may fragment the upload data and transmit the data fragments via data connections to POPs, which in turn may relay the received fragments to the data storage service provider. Upon receipt of necessary data fragments, the data storage service provider may merge the data fragments to reconstruct a copy of the upload data for storage.

Point of presence based data uploading

Aspects of the present disclosure relate to the generation and delivery of content including unique and shared components. A content delivery network service provider can obtain requests for content from client computing devices. Based on information provided in the request or otherwise managed by executable code on the client computing device, the CDN service provider obtains one or more pieces of content that may be shared by more than one user or client computing devices. Additionally, the CDN service provider obtains one or more pieces of content that will not be shared by more than one user or more than one client computing device. Responsive to the content request, the CDN service provider can combine the one or more pieces of shared content and the one or more pieces of unique content and deliver the combined content to the requested client computing device.

Context sensitive object management

An on-demand code execution environment present in points of presence (POPs) and in regions serviced by the POPs is provided herein. For example, a POP may receive a request to execute a task associated with user-defined code. If the POP determines that the computing resources necessary to execute a received task are not available or that the POP should not execute the received task for another reason (e.g., the task is not commonly received and the computing resources needed to execute the task are therefore best allocated for other requests), the POP can identify a region suitable for executing the task and forward the task to the identified region. An on-demand code execution environment present in the identified region can execute the task and forward the results of the execution to the POP for distribution back to a user device that requested the task execution.

Efficient region selection system for executing request-driven code

Systems and methods are described that enable high-data-rate network communications by use of a data transmission system, which can at least partially redirect data transmitted between two computing devices on a public network to a private network. The data transmission system may include a variety of endpoints at different locations, such that source and destination computing devices may pass information into and out of the data transmission system via the endpoints. To ensure that endpoints are able to communication with each computing device via a path of sufficient network quality, the data transmission system may dynamically generate additional endpoints within points of presence of the system. Where no endpoints or points of presence have a connection of sufficient quality to a source and destination computing device, the data transmission system may decline to transmit data, and instruct the source or destination computing devices to utilize traditional communication channels.

Use of virtual endpoints to improve data transmission rates

When a client requests content from a Content Delivery Network (or other system), a first portion of the content is transmitted to the client from a source capable of providing high performance to that client. When the client has a sufficient amount of the content to perform its function, then additional portions of the content can be transmitted to the client from a source that provides a lower performance to that client with a minimal or no performance penalty to the user of the client.

Opportunistic routing

When a client requests content from a Content Delivery Network (or other system), a first portion of the content is requested from a source capable of providing high performance to that client. When the client has a sufficient amount of the content to perform its function, then additional portions of the content can be requested from a source that provides a lower performance to that client with a minimal or no performance penalty to the user of the client.

Growing community of inventors

Seattle, WA, United States of America

David Alexander Dunlap