Abstract: A service provider network includes host computers that have various computing devices connected thereto. In order to test the operation of a program, a developer creates a program and one or more test cases for use in testing the program. The developer also identifies devices in the service provider network for use in testing the program. Once this selection has been made, a test request is submitted to the service provider network. When the service provider network receives the test request, the program is installed on the devices upon which testing is to be performed. The supplied test case is then utilized to test various aspects of the operation of the program on the devices. Once the testing of the program has completed, the results of the testing may be transmitted to the developer. A similar process might be utilized to test a program on a variety of device emulators.

Abstract: A method for grouping and storing objects across different storage solutions in storage systems according to analysis of multiple dimensions of information may be implemented as or in a storage management module. The module collects information about objects (e.g., data objects) in a storage system (e.g., a data storage system). The objects may be objects already stored in the storage system or may be new objects to be stored in the storage system. The module analyzes the collected information across multiple dimensions to determine groupings of the objects, and determines a storage solution for each determined grouping. The module may then direct storage of the objects in the groupings according to the determined storage solutions. Upon obtaining new information about object(s) in the storage system, the module may direct movement of the object(s) from one storage solution to another storage solution according to an analysis including the new information.

Abstract: A distributed load balancer in which a router receives packets from at least one client and routes packet flows to multiple load balancer nodes. The router exposes a public IP address and the load balancer nodes all advertise the same public IP address to the router. The router may implement a per-flow hashed multipath routing technique, for example an equal-cost multipath (ECMP) routing technique, to distribute the flows across the load balancer nodes. Thus, the multiple load balancer nodes may service a single public endpoint. The load balancer nodes may advertise to the router according to the Border Gateway Protocol (BGP). Rather than advertising itself, however, a load balancer node may be advertised to the router by one or more neighbor load balancer nodes; the neighbor nodes may terminate the BGP sessions with the router in response to determining that the load balancer node has failed.

Abstract: A distributed load balancer in which a router receives packets from at least one client and routes packet flows to multiple load balancer (LB) nodes according to a per-flow hashed multipath routing technique. For a given packet flow, the LB nodes randomly select a server node as a target for the packet flow from among multiple server nodes and send a connection request to the server node. A load balancer module on the server node makes the decision on whether to accept or reject the connection based on one or more metrics indicating a respective server's current load. If the module accepts the connection request, a connection is established between the server and the client. Otherwise, the load balancer nodes may select another server node and try again. The connections established between clients and servers pass through the load balancer nodes, but are not terminated at the load balancer nodes.

Abstract: Methods and apparatus for token-based admission control for replicated writes are disclosed. Data objects are divided into partitions, and corresponding to each partition, at least a master replica and a slave replica are stored. A determination as to whether to accept a write request directed to the partition is made based at least in part on one or more of (a) available throughput capacity at the master replica, and (b) an indication, obtained using a token-based protocol, of available throughput capacity at the slave replica. If the write request is accepted, one or more data modification operations are initiated.

Abstract: This disclosure relates to systems and methods for projecting an image from a primary display onto a secondary display and enabling the user to interact with the user device by touching the secondary display. The secondary display may be positioned to intercept the light emitted from the primary display. The secondary display may be a transparent or semi-transparent component that reflects or refracts the image on the primary display.

Abstract: An overlay network analysis method obtains data including but not limited to client packet traffic data on an overlay network, and performs one or more analyses based on the obtained data to generate and output topological and/or performance information for the overlay network and/or the network substrate on which the overlay network is implemented. Client traffic data collected for specific client resource instances may be analyzed to generate performance metrics for the overlay network between the instances. Aggregated client traffic data for specific clients may also be analyzed to generate mappings of the clients' private network implementations on the overlay network, as well as performance metrics for the clients' private networks on the overlay network. In addition, client traffic data from multiple clients may be aggregated and analyzed to generate mappings and performance metrics for the overlay network as a whole.

Abstract: Disclosed are various embodiments for an inventory application. Machine instances execute a monitoring service to determine the process names of applications executed in the machine instance. An inventory application identifies the applications executed on the machine instances as a function of data obtained from the monitoring services. Analytics reports can be generated from data embodying the identified applications.

Abstract: Disclosed are various embodiments for reporting as well as tracking usage and/or installation of an application in a machine instance in a computing environment. A machine instance can execute an application and can be associated with a storage volume on which the application is installed. The application, or an installer utility associated with the application, can report installation and/or usage of the application to an application usage service.

Abstract: A system for managing air flow computing devices in a rack includes a stall and filler elements. The stall includes a stall top panel and two side panels spaced apart from one another. The stall accommodates a rack computing system. The filler elements fill gaps between the computing devices of the rack computing systems and the panels of the stalls. An air moving system moves air from the cold aisle through cold-aisle facing air inlets of the computing devices. The filler elements inhibit air moving toward the cold aisle-facing inlets from leaking through gaps between the computing devices of the rack computing systems and the stall panels such that the filler elements inhibit air moving toward inlets in the computing devices from leaking through the gaps between the computing devices in the rack and the stall panels.

Abstract: Systems and methods are presented for enabling a user to provide rules for the placement of computing resources at a data center for an entity that employs or is associated with the user. The data center can use the placement rules to select a data center computer system to host computing resources for a user. The rules can be used to establish diversity in computing resource placement at the data center thereby reducing the number of users who lose access to computing resources when a specific data center computer suffers a failure. Further, the placement rules can be used to facilitate configuration of the computer resources for the user based, for example, on the user's employment responsibilities.

Abstract: User input is accepted by a force sensing resistor (“FSR”) assembly, a force sensing capacitor (“FSC”) or both. The FSR or FSC assemblies may be located within an input device, such as behind a device exterior, display, and so forth. A force applied to the device exterior proximate to the assembly may result in activation of the assembly. The activation may be processed as input and used to determine and then perform a particular action. The particular action may be based at least in part on a particular portion of the assembly which has been activated, a magnitude of applied force, or both. A haptic output may be provided on activation to provide feedback to a user.

Abstract: A system for conveying air from one location to another includes a soft duct having a passage and an air flow control device. The air flow control device can be operated to vary a cross sectional area of a portion of the passage of the soft duct.

Abstract: Systems and methods are presented for accessing an application available from a data center of a program execution service. The metadata associated with a user computing device may be used to determine whether the user computing device is authorized to access the application through a virtual desktop instance. At least a portion of the application may be executed by the virtual desktop instance and provided to the user. Applications may be purchased, licensed, or rented by a user.

Abstract: A system includes a raised floor, a sub-floor space below the raised floor, electrical components in the sub-floor space, and a fire suppression device coupled to the raised floor. The fire suppression device dispenses fire suppression material the electrical components in the sub-floor space.

Abstract: A database service may provide multi-tenant and single-tenant environments in which tables may be maintained on behalf of clients. The service (or underlying system) may create database instances and tables in either or both types of environments (e.g., by default or according to various parameter values specified in requests to create the instances or tables). When receiving and servicing requests directed to a table hosted in a single-tenant environment, the system may elide at least some of the authentication or metering operations that would be performed when servicing requests directed to tables hosted in a multi-tenant environment. Tables may be moved from a single-tenant environment to a multi-tenant environment, or vice versa, automatically by the system (e.g., dependent on an observed, expected, or desired throughput) or in response to an explicit request from a client to do so (e.g., to increase throughput or reduce cost).

Abstract: A computing device can include a retail application and a virtual environment application. The retail application can display a product purchase interface and receive a request to purchase the product from a user. When the user orders the product, the retail application can provide the virtual environment application with an indication that the product has been purchased. In response to the user's purchase of the product, the virtual environment application can grant the user's virtual environment account with ownership of a virtual version of the product.

Abstract: Methods and systems for cost-minimizing job scheduling are disclosed. A definition of a task is received. The definition comprises a need-by time. The need-by time comprises a deadline for completion of execution of the task. An estimated duration to complete the execution of the task is determined for each of a plurality of computing resources. One or more of the computing resources are selected based on an estimated cost of completing the execution using the computing resources. The execution of the task is initiated at a scheduled time using the selected one or more computing resources. The scheduled time is earlier than the need-by time by at least the estimated duration.

Abstract: Disclosed are various embodiments for distributing application components among many devices across a network for optimal execution of the application. A distribution is determined based on performance metrics, distribution profiles, and/or other indications of how to distribute application components for execution on many devices. In various embodiments, an application component may be simultaneously executed on many devices or on one device. The application components execute as if on one device even though they are distributed among many devices. Performance metrics indicate how well an application component executes in a device. During execution, the application components may be redistributed if another distribution is indicated by performance tolerances. If application components are redistributed, the execution of the application continues as if no redistribution had occurred.

Abstract: Features are disclosed for enabling users to efficiently store and share browsing sessions or portions thereof with other users or the general public. Browsing session requests and other activities may be sent to an intermediary system, which can retrieve requested content and store a representation of the requested content or data regarding the requested content. The stored data may be organized as a saved browsing session such that users may access the shared browsing session at a subsequent time and view the browsing session substantially in its entirety. Users may search for shared browsing sessions and access data regarding the requests made during a browsing session. In addition, data regarding client devices used during shared browsing sessions may be tracked and associated with the shared browsing sessions such that subsequent users can search for shared browsing sessions based partly on such device characteristics.