Joshua Burgin

Techniques are described for enabling users of a cloud provider network to request the conditional termination of computing resources based on a forecasted availability of replacement capacity at a specified time or range of time in the future. A cloud provider network provides an application programming interface that can be used to make such requests, where the computing resources are hosted by the cloud provider network as part of a capacity pool shared by tenants of the cloud provider… Show more

Techniques are described for enabling users of a cloud provider network to request the conditional termination of computing resources based on a forecasted availability of replacement capacity at a specified time or range of time in the future. A cloud provider network provides an application programming interface that can be used to make such requests, where the computing resources are hosted by the cloud provider network as part of a capacity pool shared by tenants of the cloud provider network. This type of request can be generated, for example, by a user desiring to terminate the use of some number of unproductive computing resources only if the user can be reasonably assured by the cloud provider network that capacity will be available at a future time when the user will likely need the capacity again. Show less

Techniques are described that enable a cloud provider network to provide specialized regions that can be used to achieve greater availability assurance for workloads highly sensitive to downtime or outages. Cloud provider network users may use specialized regions to complement the use of provider network services offered in other geographic regions defined by the cloud provider network, either to host redundant computing resources or for failover purposes, where the operation of a specialized… Show more

Techniques are described that enable a cloud provider network to provide specialized regions that can be used to achieve greater availability assurance for workloads highly sensitive to downtime or outages. Cloud provider network users may use specialized regions to complement the use of provider network services offered in other geographic regions defined by the cloud provider network, either to host redundant computing resources or for failover purposes, where the operation of a specialized region is designed to provide additional resiliency against various types of correlated failures among the geographic regions. As one example, a cloud provider network may stage deployments of software updates to the web services provided by the cloud provider network in a manner that ensures that specialized regions receive such updates last and over a relatively long period of time, thereby helping to ensure that any software defects are detected in an earlier deployment of the update Show less

Techniques are described for optimizing the allocation of computing resources provided by a service provider network—for example, compute resources such as virtual machine (VM) instances, containers, standalone servers, and possibly other types of computing resources—among computing workloads associated with a user or group of users of the service provider network

Techniques are described for optimizing the allocation of computing resources provided by a service provider network—for example, compute resources such as virtual machine (VM) instances, containers, standalone servers, and possibly other types of computing resources—among computing workloads associated with a user or group of users of the service provider network. A service provider network provides various tools and interfaces to help businesses and other organizations optimize the… Show more

Techniques are described for optimizing the allocation of computing resources provided by a service provider network—for example, compute resources such as virtual machine (VM) instances, containers, standalone servers, and possibly other types of computing resources—among computing workloads associated with a user or group of users of the service provider network. A service provider network provides various tools and interfaces to help businesses and other organizations optimize the utilization of computing resource pools obtained by the organizations from the service provider network, including the ability to efficiently schedule use of the resources among workloads having varying resource demands, usage patterns, relative priorities, execution deadlines, or combinations thereof. A service provider network further provides various graphical user interfaces (GUIs) to help users visualize and manage the historical and scheduled uses of computing resources by users' workloads according to user preferences. Show less

Techniques are described for optimizing the allocation of computing resources provided by a service provider network—for example, compute resources such as virtual machine (VM) instances, containers, standalone servers, and possibly other types of computing resources—among computing workloads associated with a user or group of users of the service provider network

This patent relates to system and user initiated hibernation for instances. An agent executing on the instance monitors for a signal to initiate hibernation. For example, during a capacity event the control plane updates instance metadata to signal to the instance that termination will occur and the instance should be hibernated. The agent periodically polls the instance metadata or receives a push notification, detects the signal, and sends an API call to the instance operating system to… Show more

This patent relates to system and user initiated hibernation for instances. An agent executing on the instance monitors for a signal to initiate hibernation. For example, during a capacity event the control plane updates instance metadata to signal to the instance that termination will occur and the instance should be hibernated. The agent periodically polls the instance metadata or receives a push notification, detects the signal, and sends an API call to the instance operating system to hibernate the instance. This hibernation information is stored to a disk which is then used to restart the instance reducing the impact on customer during capacity events and/or maintenance events. Show less

A fault injection service (FIS) which can be used to improve the resiliency of applications run using other AWS services, IoT devices, or other cloud provider services. A catalog of different types of faults which can be inserted into applications is built up, using the expertise developed at AWS on handling errors and sub-optimal behaviors over the years. Clients of the FIS specify target environments into which faults are to be injected by the FIS. Clients can provide guidance on the specific… Show more

A fault injection service (FIS) which can be used to improve the resiliency of applications run using other AWS services, IoT devices, or other cloud provider services. A catalog of different types of faults which can be inserted into applications is built up, using the expertise developed at AWS on handling errors and sub-optimal behaviors over the years. Clients of the FIS specify target environments into which faults are to be injected by the FIS. Clients can provide guidance on the specific mix of faults to be injected, or let the FIS decide the mix. Fault injection scheduling and selection can be randomized or deterministic, and clients can adjust fault injection rates. FIS agents can access internal resources of AWS services, allowing faults which require administrative privileges to be injected. The FIS provides results indicating the faults injected into an application, as well as a resiliency score computed for the application based on its responses to the injected faults. Show less

This patent relates to enabling customers of a compute instance provider to launch large amounts of instances at once, bypassing limits that otherwise would be in place, such as limits on the number of instances that can be launched and limits on the rate at which instances can be launched. A request for a large number of compute instances may be received, specifying both a minimum capacity and a target capacity. The provider may verify that there is sufficient capacity to launch at least the… Show more

This patent relates to enabling customers of a compute instance provider to launch large amounts of instances at once, bypassing limits that otherwise would be in place, such as limits on the number of instances that can be launched and limits on the rate at which instances can be launched. A request for a large number of compute instances may be received, specifying both a minimum capacity and a target capacity. The provider may verify that there is sufficient capacity to launch at least the minimum number of instances and that the number of instances being requested is authorized, before indicating that the request can be fulfilled. Checks on capacity may also include checks on downstream services, such as services that provide storage volumes for the instances.
Show less

An advisor service that allows customer to focus on developing their application rather than provisioning instances to execute their application. The customer provides the advisor service with application information such as a type of application and the advisor service determines the best configuration of computing resources to execute the customer’s application. The customer can modify or select different parameters that will affect the cost and performance of the instances executing the… Show more

An advisor service that allows customer to focus on developing their application rather than provisioning instances to execute their application. The customer provides the advisor service with application information such as a type of application and the advisor service determines the best configuration of computing resources to execute the customer’s application. The customer can modify or select different parameters that will affect the cost and performance of the instances executing the customer’s application.
Show less

This patent relates to dynamically provisioning and maintaining a fleet of Spot instances that meets a customer’s requirements. The system described in the patent uses historical and predictive analytics of capacity and price fluctuations to choose the appropriate instance capacity pools as well as the appropriate division of the fleet (how many instances to put into what pools) to maximize the probability the customer's requirements are met.

This patent relates to providing customers with the ability to mix and match instance types and purchasing models for implementing a workload. When there is insufficient capacity to provide the customer with a particular instance type that was selected by the customer, EC2 can suggest alternative instance types with the same or similar amount of computing capacity that can perform the customer’s workload. The customer can also provide constraints on executing the workload using the alternative… Show more

This patent relates to providing customers with the ability to mix and match instance types and purchasing models for implementing a workload. When there is insufficient capacity to provide the customer with a particular instance type that was selected by the customer, EC2 can suggest alternative instance types with the same or similar amount of computing capacity that can perform the customer’s workload. The customer can also provide constraints on executing the workload using the alternative instance types, such as cost and execution time. Show less

This patent relates to controlling the functionality of a browser when it displays sensitive content. This patent is based on split-browser configurations, in which the client-side browser, the network-side browser, or both can be programmatically configured to limit functionality. For example, the network-side browser can proxy content requests between a client and an authenticating content server to ensure that the network based limited functionality browser has been implemented prior to… Show more

This patent relates to controlling the functionality of a browser when it displays sensitive content. This patent is based on split-browser configurations, in which the client-side browser, the network-side browser, or both can be programmatically configured to limit functionality. For example, the network-side browser can proxy content requests between a client and an authenticating content server to ensure that the network based limited functionality browser has been implemented prior to transmitting content to the requesting client. The network side browser can respond to requests from the authenticating content server by verifying that network-side browser functionality has been limited. Show less

This patent is directed to “spot blocks” which are spot instances that are “guaranteed” to run for a specific period of time such as 1-6 hours. Normal spot instances survive as long as the spot price continues to be equal to or less than the bid price. Some customers like the cost savings that spot instances provide but need more predictability in terms of how of the lifespan of a spot instance. The customer can be specify the number of spot instances to include in the block and the length of… Show more

This patent is directed to “spot blocks” which are spot instances that are “guaranteed” to run for a specific period of time such as 1-6 hours. Normal spot instances survive as long as the spot price continues to be equal to or less than the bid price. Some customers like the cost savings that spot instances provide but need more predictability in terms of how of the lifespan of a spot instance. The customer can be specify the number of spot instances to include in the block and the length of time desired for the block, as well as other types of information such as the types of spot instances, the availability zones from which to select spot instances for the block, etc. Show less

This patent relates to spot fleet optimization. Workloads executed on a spot fleet differ in how well they tolerate interruption caused by lost instances. The spot fleet allocation system will apply one of three different optimization strategies to select spot instances that best accommodate a workload’s interruption tolerance. In a first optimization strategy, the lowest priced spot instances are assigned to workloads that are insensitive to instance loss. In a second optimization strategy… Show more

This patent relates to spot fleet optimization. Workloads executed on a spot fleet differ in how well they tolerate interruption caused by lost instances. The spot fleet allocation system will apply one of three different optimization strategies to select spot instances that best accommodate a workload’s interruption tolerance. In a first optimization strategy, the lowest priced spot instances are assigned to workloads that are insensitive to instance loss. In a second optimization strategy, spot instances are allocated from pools that historically experience the fewest interruptions to execute workloads that are intolerant to loss of any instances. In a third optimization strategy, spot instances are allocated from as many pools as possible to reduce the risk of losing all instances. Show less

Techniques for activating multiple interruptible resource instances on servers of a service provider environment. In an example embodiment, a system can activate multiple interruptible resource instances on behalf of a given customer based on a comparison of a bid cost value from the customer to the current, but variable cost value of the interruptible resource instances. The customer also can specify a value indicative of the number of interruptible resource instances to be activated on behalf… Show more

Techniques for activating multiple interruptible resource instances on servers of a service provider environment. In an example embodiment, a system can activate multiple interruptible resource instances on behalf of a given customer based on a comparison of a bid cost value from the customer to the current, but variable cost value of the interruptible resource instances. The customer also can specify a value indicative of the number of interruptible resource instances to be activated on behalf of the customer based on the bid cost value. Show less

An online advertising method comprises presenting sequenced or tiered interactive promotional content to a player of a computer-implemented online game. The interactive promotional content comprises a sequence of sponsored interactions with the content for performance by the player, with at least one of the sequence of sponsored activities being a gated activity which is available to the player only if the player has performed a corresponding preceding activity in the sequence.

Techniques are described for providing a multi-service storage layer in a cloud provider network for applications and workloads that are highly sensitive to outages affecting “mission critical” data or other resources. A multi-service storage layer is designed to provide additional resiliency against various types of correlated failures among existing geographic regions by enabling the storage of data using a plurality of separate storage services and storage resource types and across a… Show more

Techniques are described for providing a multi-service storage layer in a cloud provider network for applications and workloads that are highly sensitive to outages affecting “mission critical” data or other resources. A multi-service storage layer is designed to provide additional resiliency against various types of correlated failures among existing geographic regions by enabling the storage of data using a plurality of separate storage services and storage resource types and across a plurality of regions of the cloud-provider network. A multi-service storage layer provides an application programming interface (API) with actions for storing, retrieving, and querying data stored in a highly available storage resource across a selection of underlying storage services. The ability to store critical data and other resources using a multi-service storage layer provides additional resiliency while also providing a single interface that applications can use to interact with the data stored across any number of underlying storage services. Show less

Techniques are described for providing a multi-service storage layer in a cloud provider network for applications and workloads that are highly sensitive to outages affecting “mission critical” data or other resources. A multi-service storage layer is designed to provide additional resiliency against various types of correlated failures among existing geographic regions by enabling the storage of data using a plurality of separate storage services and storage resource types and across a… Show more

Techniques are described for providing a multi-service storage layer in a cloud provider network for applications and workloads that are highly sensitive to outages affecting “mission critical” data or other resources. A multi-service storage layer is designed to provide additional resiliency against various types of correlated failures among existing geographic regions by enabling the storage of data using a plurality of separate storage services and storage resource types and across a plurality of regions of the cloud-provider network. A multi-service storage layer provides an application programming interface (API) with actions for storing, retrieving, and querying data stored in a highly available storage resource across a selection of underlying storage services. The ability to store critical data and other resources using a multi-service storage layer provides additional resiliency while also providing a single interface that applications can use to interact with the data stored across any number of underlying storage services. Show less

Disclose methods and systems provide for management of game failure in distributed gaming by automated indication of a failure acknowledgment to a client device on which an associated player plays the game, for example by automatically presenting a failure apology message on the client device. An automated interactive acknowledgment process can include providing in-game compensation to the player, thereby to lessen player frustration resulting from game failures. The automated acknowledgment… Show more

Disclose methods and systems provide for management of game failure in distributed gaming by automated indication of a failure acknowledgment to a client device on which an associated player plays the game, for example by automatically presenting a failure apology message on the client device. An automated interactive acknowledgment process can include providing in-game compensation to the player, thereby to lessen player frustration resulting from game failures. The automated acknowledgment interaction can include gathering failure information from the client device.
Show less

A system and method for managing a computer-implemented online game provides an in-game advertising publication service to publish interactive advertising content within a computer-implemented game in accordance with a pricing structure that defines different prices for different types of player engagement, for example having a cost per acquisition (CPA) pricing mechanism and a cost per engagement (CPE) pricing mechanism. A linked sequence of prompts is presented on a user device, to prompt a… Show more

A system and method for managing a computer-implemented online game provides an in-game advertising publication service to publish interactive advertising content within a computer-implemented game in accordance with a pricing structure that defines different prices for different types of player engagement, for example having a cost per acquisition (CPA) pricing mechanism and a cost per engagement (CPE) pricing mechanism. A linked sequence of prompts is presented on a user device, to prompt a series of player engagements including at least two different engagement types. In some instances, a CPA prompt is presented earlier in the sequence, with an associated CPE prompt being presented subsequent to player engagement pursuant to the CPA prompt. Show less

An online advertising method comprises presenting sequenced or tiered interactive promotional content to a player of a computer-implemented online game. The interactive promotional content comprises a sequence of sponsored interactions with the content for performance by the player, with at least one of the sequence of sponsored activities being a gated activity which is available to the player only if the player has performed a corresponding preceding activity in the sequence.