公开(公告)号：US20210168092A1

公开(公告)日：2021-06-03

申请号：US17162799

申请日：2021-01-29

Applicant: Amazon Technologies, Inc.

Inventor： Diwakar GUPTA ,  Georgios ELISSAIOS ,  Ishwardutt PARULKAR ,  Upendra Bhalchandra SHEVADE

IPC: H04L12/911

Abstract: Techniques are described for enabling users of a service provider network to create and configure “application profiles” that include parameters related to execution of user workloads at provider substrate extensions. Once an application profile is created, users can request the deployment of user workloads to provider substrate extensions by requesting instance launches based on a defined application profile. The service provider network can then automate the launch and placement of the user's workload at one or more provider substrate extensions using edge-optimized compute instances (e.g., compute instances tailored for execution within provider substrate extension environments). In some embodiments, once such edge-optimized instances are deployed, the service provider network can manage the auto-resizing of the instances in terms of various types of computing resources devoted to the instances, manage the lifecycle of instances to ensure maximum capacity availability at provider substrate extension locations, and perform other instance management processes.

公开(公告)号：US20230084799A1

公开(公告)日：2023-03-16

申请号：US17953073

申请日：2022-09-26

Applicant: Amazon Technologies, Inc.

Inventor： Diwakar GUPTA ,  Georgios ELISSAIOS ,  Ishwardutt PARULKAR ,  Upendra Bhalchandra SHEVADE

IPC: H04L47/70 ,  H04L47/74 ,  H04L47/78 ,  H04L47/783

Abstract: Techniques are described for enabling users of a service provider network to create and configure “application profiles” that include parameters related to execution of user workloads at provider substrate extensions. Once an application profile is created, users can request the deployment of user workloads to provider substrate extensions by requesting instance launches based on a defined application profile. The service provider network can then automate the launch and placement of the user's workload at one or more provider substrate extensions using edge-optimized compute instances (e.g., compute instances tailored for execution within provider substrate extension environments). In some embodiments, once such edge-optimized instances are deployed, the service provider network can manage the auto-resizing of the instances in terms of various types of computing resources devoted to the instances, manage the lifecycle of instances to ensure maximum capacity availability at provider substrate extension locations, and perform other instance management processes.