摘要:
Techniques are described for managing distributed execution of programs. In some situations, the techniques include dynamically modifying the distributed program execution in various manners, such as based on monitored status information. The dynamic modifying of the distributed program execution may include adding and/or removing computing nodes from a cluster that is executing the program, modifying the amount of computing resources that are available for the distributed program execution, terminating or temporarily suspending execution of the program (e.g., if an insufficient quantity of computing nodes of the cluster are available to perform execution), etc.
摘要:
The environmental impact of various transactions can be reduced or offset by determining the impact of various shipping and packaging options, and providing these options to customers. Customers then have the ability to select options that reduce the environmental impact of each transaction. A customer also can purchase environmental offsets to offset the determined impact. Customers can be provided with environmental impact information determined or tracked for each item viewed by the customer, such that each customer can be informed of the additional impact of each individual when making a selection. The selections and/or actions of a customer can be tracked such that environmentally friendly options and suggestions can be provided for subsequent transactions.
摘要:
The environmental impact of various transactions can be reduced or offset by determining the impact of various shipping and packaging options, and providing these options to customers. Customers then have the ability to select options that reduce the environmental impact of each transaction. A customer also can purchase environmental offsets to offset the determined impact. Customers can be provided with environmental impact information determined or tracked for each item viewed by the customer, such that each customer can be informed of the additional impact of each individual when making a selection. The selections and/or actions of a customer can be tracked such that environmentally friendly options and suggestions can be provided for subsequent transactions.
摘要:
Techniques are described for managing execution of programs on multiple computing systems, such as based at least in part of user-specified constraints. For example, constraints related to execution of a program may be based on a desired relative location of a host computing system to execute a copy of the program with respect to an indicated target (e.g., computing systems executing other copies of the program or copies of another indicated program), on particular geographic locations, and/or on factors not based on location (e.g., cost of use of a particular computing system, capabilities available from a particular computing system, etc.). Some or all of the multiple computing systems may be part of a program execution service for executing multiple programs on behalf of multiple users, and each may provide multiple virtual machines that are each capable of executing one or more programs for one or more users.
摘要:
A scalable event notification system is provided. The event notification system manages the set of topics available for notification via a topic manager network. The event notification system transmits event notifications to event consumers via a subscription manager network. The configuration and operation of the subscription manager network may to reconfigured in response to changing load and fault conditions to facilitate the timely delivery of event notifications. The notification to subscribers also includes mechanisms to provide individual privacy and non-tampering of notifications. Notification may dynamically be delivered to alternative locations and localized to accommodate different natural languages.
摘要:
Mechanisms for operating in recovery mode while ensuring reliable message processing for messages received during the recovery operation mode. Upon receiving a message corresponding to a particular message transaction, the instance responsible for that message transaction determines from state information corresponding to the transaction, whether or not that instance is operating in normal mode, or recovery mode. If the state information reflects normal operation mode, then the instance processes the message. If recover mode, then the instance evaluates whether or not the message is a normal message suitable for normal operation mode, or a recovery message suitable for recovery operation mode. If the message is a normal message, then the message is placed in a persistent queue for later processing. If the message is a recovery message, the message is processed. Upon completion of recovery, the normal message in the queue may be processed.
摘要:
Mechanisms for providing requested data items in a request-driven enumeration session while retaining control over how much inter-message context information is retained by the data provider. Upon receiving a request for the data items, the data provider identifies a portion of the data items to be provided in the first response along with context information that reflects that the first portion of information has been provided. The data provider then makes a determination of how much of the context is to be provided to the data receiver system, and then provides that appropriate context information to the data receiver. Furthermore, the data provider provides a response that includes the first portion of the data items. The data receiver includes this first provided context information in the second request for the next portion of the data items, allowing continuity in the data transfer session.
摘要:
Example embodiments provide for keeping an HTTP reply flow for a communication open such that portions of an overall response corresponding to a single request may be sent across the HTTP reply flow. As the various portions of the overall response become available at a corresponding service endpoint, the service appropriately encapsulates the messages and sends them to the requesting endpoint. The recipient or requesting endpoint of the response is then capable of reading the available portions of the response and appropriately decodes the embedded portions and is free to process these as appropriate. Accordingly, because only one request is made for several portions of a response valuable system resource are reserved for only requiring one authentication and/or validation of a requesting endpoint.
摘要:
Methods and systems for providing a virtual network are disclosed. At least one layer of abstraction is created between network service applications and conventional network protocols by inserting an adaptive dispatcher between applications and network transport services on each machine in a network. The message protocol in the virtual network is extensible, allowing application programs to create new headers within any message as needed. The adaptive dispatcher contains handlers that route and dispatch messages within the virtual network based on arbitrary content within each message, including any combination of headers and/or data content. Each device on the virtual network has a virtual address to which messages are directed, allowing devices to move within the network without reconfiguring routing tables. Handlers may be automatically created when an event meeting predefined criteria occurs, including the non-occurrence of a condition, making the virtual network self-healing and adaptive to reconfiguration.
摘要:
Systems and methods for performing an on-demand determination of a correct set of volumes to be exported are described. A disk platter is defined to be the unit of volume migration. Volumes are added to the platter based on whether or not the volume coexists on a disk containing a volume to be exported.