Abstract: Techniques for improving communications efficiency between pairs of communication nodes running within a computer system are described herein. Potential locations for placing a communication node are evaluated using one or more fitness values wherein the fitness value is based at least in part on one or more system metrics associated with placing a communication node in the potential location. If an improved location is found based on the fitness value, the communication node may be migrated to the new location, thus improving system efficiency.

Abstract: Techniques for improving communications efficiency between pairs of communication nodes running within a computer system are described herein. Potential locations for placing a communication node are evaluated using one or more fitness values wherein the fitness value is based at least in part on one or more system metrics associated with placing a communication node in the potential location. If an improved location is found based on the fitness value, the communication node may be migrated to the new location, thus improving system efficiency.

Abstract: A distributed execution environment can provide access to field-programmable device resources. The field-programmable device resources can be provided in association with one or more instances that are instantiated within the distributed execution environment upon request from a computing system. The computing system can be associated with a customer of the distributed execution environment. The customer can program the field-programmable device resources using designs created by or for the customer.

Abstract: Techniques for improving communications efficiency between pairs of communication nodes running within a computer system are described herein. Potential locations for placing a communication node are evaluated using one or more fitness values wherein the fitness value is based at least in part on one or more system metrics associated with placing a communication node in the potential location. If an improved location is found based on the fitness value, the communication node may be migrated to the new location, thus improving system efficiency.

Abstract: Described is an airborne fulfillment center (“AFC”) and the use of unmanned aerial vehicles (“UAV”) to deliver items from the AFC to users. For example, the AFC may be an airship that remains at a high altitude (e.g., 45,000 feet) and UAVs with ordered items may be deployed from the AFC to deliver ordered items to user designated delivery locations. As the UAVs descend, they can navigate horizontally toward a user specified delivery location using little to no power, other than to stabilize the UAV and/or guide the direction of descent. Shuttles (smaller airships) may be used to replenish the AFC with inventory, UAVs, supplies, fuel, etc. Likewise, the shuttles may be utilized to transport workers to and from the AFC.

Abstract: Technology for a distribution operating system is provided. In one example, a method may include executing a distribution operating system on a host operating system on a local computing device and executing an application within the distribution operating system using networked computing resources managed by the distribution operating system.

Abstract: Described is an airborne fulfillment center (“AFC”) and the use of unmanned aerial vehicles (“UAV”) to deliver items from the AFC to users. For example, the AFC may be an airship that remains at a high altitude (e.g., 45,000 feet) and UAVs with ordered items may be deployed from the AFC to deliver ordered items to user designated delivery locations. As the UAVs descend, they can navigate horizontally toward a user specified delivery location using little to no power, other than to stabilize the UAV and/or guide the direction of descent. Shuttles (smaller airships) may be used to replenish the AFC with inventory, UAVs, supplies, fuel, etc. Likewise, the shuttles may be utilized to transport workers to and from the AFC.

Abstract: The number of compute resource required by a user in a computing environment may change dynamically. For example, the virtual machine instances allocated to a particular user may host a web service. As queries to the web service increase, the current number of allocated virtual machine instances may be insufficient to provide timely responses. In response to the increased demand, the computing environment may increase the number of instances allocated to the user. To do so, the computing environment maintains one or more already executing virtual machine instances in a hotpool that have not been assigned to any user. When a user needs additional computing resources, one or more of the virtual machine instances in the hotpool may be allocated to the users. Because these instances are already executing, the computing environment avoids the relatively long delay corresponding to generating a new virtual machine instance.

Abstract: A first component of a network-accessible service is configured to participate in client-server interactions with other components of the service via a default communication channel. The first component has access to an alternate communication channel available only to a subset of components of the service. Using the alternate communication channel, the first component reaches a local workload agreement with a second component, in accordance with which at least some service requests of the first component or the second component are fulfilled using the alternate communication channel.

Abstract: A distributed execution environment can provide access to field-programmable device resources. The field-programmable device resources can be provided in association with one or more instances that are instantiated within the distributed execution environment upon request from a computing system. The computing system can be associated with a customer of the distributed execution environment. The customer can program the field-programmable device resources using designs created by or for the customer.

Abstract: A technology to isolate user software installations is described. A package database of software packages is maintained. A file system for a user account is isolated by setting a root directory of a file system hierarchy in the file system to be a user directory structure for the user account. A software package is installed from the package database into the user directory structure by linking files from the package database into the user directory structure.

Abstract: Technologies are described herein for delegating requests in a service-oriented architecture (SOA) environment. A calling service in the SOA environment can delegate the task of obtaining data used in a computation to a called service that performs the computation. In order to delegate, the calling service may provide a request specification that defines a mechanism by which the called service can obtain the data. For example, the request specification might define a request to another service in the SOA for obtaining the data. The calling service might also provide an authentication ticket that can be utilized to confirm that the calling service has delegated the task to the called service. The called service can utilize the request specification and the authorization ticket to obtain the data. The obtained data may then be used to perform a computation. The results of the computation may then be provided to the calling service.

Abstract: Methods and apparatus for operating system interface implementation using network-accessible services are described. A request to execute a particular program at a distributed computing platform implementing a set of operating system interfaces using resources of network-accessible services of a provider network is received. A compute instance of a computing service is selected for executing operations of a thread of the program. Corresponding to the invocation of a particular operating system interface within the program, at least one operation is performed at a particular service. An overall result of execution of the particular program is determined based at least in part of results of the at least one operation.

Abstract: Described is an airborne fulfillment center (“AFC”) and the use of unmanned aerial vehicles (“UAV”) to deliver items from the AFC to users. For example, the AFC may be an airship that remains at a high altitude (e.g., 45,000 feet) and UAVs with ordered items may be deployed from the AFC to deliver ordered items to user designated delivery locations. As the UAVs descend, they can navigate horizontally toward a user specified delivery location using little to no power, other than to stabilize the UAV and/or guide the direction of descent. Shuttles (smaller airships) may be used to replenish the AFC with inventory, UAVs, supplies, fuel, etc. Likewise, the shuttles may be utilized to transport workers to and from the AFC.