Amazon Technologies, Inc.

Other

Malcolm Featonby

Umesh Chandani

John Merrill Phillips

Mihir Sadruddin Surani

Yuxuan Liu

Douglas Cotton Kurtz

Adithya Bhat

Letian Feng

Leslie Johann Lamprecht

Roberto Pentz De Faria

Ladan Mahabadi

Hou Liu

Nicholas Patrick Wilt

Jacob Adam Gabrielson

John David Dunagan

Mohit Gupta

Joshua Dawie Mentz

Ronen Dov Agranat

Willem Jacob Buys

Timothy Ralph Sjoberg

Manish Singh Rathaur

Gregory Jonathan Kempe

Siyu Wang

Omar Paul

Zachary Daniel Casper

Nathaniel Baird Jones

Shaokang Ni

Les Johann Lamprecht

John Michael Morkel

Nishant Kanaiyalal Mehta

Kai Fan Tang

Mats Lanner

Ethan John Faust

Munindra Nath Das

Neil Andrew Eriksson

Archana Srikanta

Paolo Maggi

Francois Norman Daniels

Gina Louise Morris

Carlos Eduardo Lopez Biagi

Fernando Paiva Zandona

Axel David Velazquez

Andrew Flower

Andrea Curtoni

Richard Lee Sanders

Sravan Rengarajan

Derek J Petersen

Li Chieh Young

Abhishek Nautiyal

Saloni Sonpal

Erik Quanstrom

James Rigby

Wenbo Bu

Jr John Merrill Phillips

Provided is a system for managing a pool of compute resources usable to execute user codes such as containerized software applications. The pool may include a plurality of sub-pools of compute instances that are each suited to handle a specific type of code execution requests and/or a specific set of capacity or resource configurations. For example, when a code execution request is received, the system may determine compute capacity from which sub-pool would be best suited to handle the request, and direct the request to that sub-pool (or execute the user code using compute capacity from that sub-pool). Each sub-pool may be assigned a generational indicator that indicates its level of use (e.g., rarely used, moderately use, frequently used, etc.) and/or its age (e.g., brand new, young, old, etc.). As a sub-pool experiences continued use, the sub-pool may be promoted and its retention/replenishment policy may be updated accordingly.

Generational management of compute resource pools

Systems and methods for implementing a right-sizing service that recommends and automatically implements resource sizing recommendations for compute clusters executing applications is disclosed. Performance metrics for compute nodes executing the application may be gathered and normalized, with anomalous nodes excluded. Then, respective time series data for the compute nodes may be temporally aligned to identify phases of execution of the application and resource sizes may be estimated for the various phases. A resource sizing recommendation may then be made based in part on this estimated resource sizes. The sizing recommendation may further integrate with other sizing recommendations and be used to manually or automatically size a compute cluster or selected among a number of pre-sized compute clusters, in various embodiments.

Resource right-sizing for compute clusters

Systems and methods for implementing a right-sizing service that recommends and automatically implements sizing recommendations for nodes and resources of compute clusters executing applications is disclosed. Performance metrics for compute nodes executing the application may be gathered and normalized with anomalous nodes excluded. Then, respective time series data for the compute nodes may be temporally aligned to identify phases of execution of the application and resource sizes may be estimated for the various phases. A sizing recommendation may then be made based in part on this estimated resource sizes. The sizing recommendation may further integrate with other sizing recommendations and be used to manually or automatically size a compute cluster or selected among a number of pre-sized compute clusters, in various embodiments.

Cluster right-sizing for cloud-based applications

Techniques for an optimization service of a service provider network to help optimize the selection, configuration, and utilization, of virtual machine (VM) instance types to support workloads on behalf of users. The optimization service may implement the techniques described herein at various stages in a life cycle of a workload to help optimize the performance of the workload, and reduce underutilization of computing resources. For example, the optimization service may perform techniques to help new users select an optimized VM instance type on which to initially launch their workload. Further, the optimization service may monitor a workload for the life of the workload, and determine new VM instance types, and/or configuration modifications, that optimize the performance of the workload. The optimization service may provide recommendations to users that help improve performance of their workloads, and that also increase the aggregate utilization of computing resources of the service provider network.

Compute platform recommendations for new workloads in a distributed computing environment

Generally described, one or more aspects of the present application relate to prefetching container image layers for use in a cluster of compute instances. For example, the dependencies among the individual layers within the container images stored and/or executed on a cloud provider network may be analyzed. Then, the layers that are likely to be used by a user of the cloud provider network may be identified and prefetched into the caches of the compute instances provided by the cloud provider network, before execution of the container images including such layers is requested by the user. By doing so, the latency between the time a request to execute a set of container images is received and the time the execution of the set of container images is actually initiated can be reduced, thereby providing an improved and more efficient application execution experience to the user.

Predelivering container image layers for future execution of container images

Compute platform optimization over the life of a workload in a distributed computing environment

Techniques implemented by a cloud computing system for providing fallback capacity providers to ensure that infrastructure capacity required to run containerized services is available despite primary capacity providers experiencing a failure. Cloud providers offer container-management services that automate the management and scaling of containerized services of users. The container-management services are supported by capacity providers that manage the computing infrastructure on which the containerized services run (e.g., servers, VMs, etc.). However, there are times when a capacity provider is unable to provision capacity for containerized services, such as due to a large scale failure. Rather than leaving capacity requests unserved, the container-management service designates a fallback capacity provider that acts as a failover for provisioning requested infrastructure capacity. The fallback capacity providers have different provisioning paths than the primary capacity providers, and thus different availability postures and failure modes, to ensure resiliency in provisioning capacity for containerized services.

Fallback capacity providers for capacity management of workload infrastructure

Provided is a system for inspecting and optimizing containerized software applications. A container image may include a plurality of files and layers, and some of such files and layers may not be used during the execution of the container image. A system described herein can identify and remove such unused files and/or layers from the container image by launching an inspector task configured to launch the container image, monitor access to the files in the container image, identify which files are unused, and remove the unused files from the container image (or generate a new container image not including the unused files). By doing so, the system can reduce the size of the container image, which can reduce the storage costs, startup latency, and security vulnerabilities associated with the container image.

Container image inspection and optimization

A graphic session coordinator is established to enable remote virtualized graphics operations on behalf of a set of graphics request generators. A request generator submits a graphics session request to the session coordinator. A configuration operation is performed at one or more routing devices to enable graphics operation request packets from the request generator to be delivered to a first remote virtualized graphics device and to enable graphics operation response packets to be transmitted to a destination.

Session coordination for auto-scaled virtualized graphics processing

Generally described, one or more aspects of the present application relate to prefetching container images for use in a cluster of virtual machines. For example, the cluster manifest may indicate an ordered list of image repositories and a set of container images that are likely to be executed on the cluster. Based on this indication, the set of container images can be prefetched onto the caches of the virtual machines in the cluster, such that when requests to execute those container images are eventually received, the container images can be accessed from the caches rather than from a remote repository.

Prefetching and managing container images using cluster manifest

Provided is a system for automatically generating a set of parameters that can be used to execute a user application on a cluster of compute instances on behalf of a user, where the set of parameters specifies the one or more container images that need to be executed as part of executing the user application. For example, the user may specify a set of container images that are part of the user application, and the system may automatically determine the parameters that define the computing environment in which the user application is to be executed, such as the resource allocation and networking configuration parameters, without the user having to provide such parameters to the system. These parameters can be packaged into the set of parameters (also referred to herein as a task definition), which can be used in future executions of the user application.

Automatically configuring execution of a containerized application

A database service that receives and manages time series data into a set of generational data tables. The database service generates a set of generational data tables configured to receive a subset of time series data. Each generational data table is created with an initial set of access parameters that facilitates the receipt of incoming time series data. Thereafter, the database service creates additional generational data tables to receive the continuous received time series data and then modifies the access parameters of the previously created data table, such as for read only rights.

Generational databases for managing time series data

Provided is a system for managing the resource limit associated with a user, where the resource limit indicates the amount of compute resources the user is allowed to use. As the user requests and obtains additional resources from a pool of resources, the user's resource usage is increased to reflect the additional resources being used by the user. As the resources used by the user are released, to ensure that the pool of resources has sufficient capacity to handle additional resource requests, the replenishment status of the pool is further checked, and if the replenishment status satisfies a condition for updating the user's resource usage, the user's resource usage is decreased to reflect the resources that are no longer in use by the user. The released resources are torn down and re-provisioned back into the pool of resources.

Replenishment-aware resource usage management

Growing community of inventors

Sammamish, WA, United States of America

Malcolm Featonby