Patent application number | Description | Published |
20090064177 | METHOD FOR DATA DELIVERY IN A NETWORK - The present invention relates to a method of delivering data from a sender application to at least one receiver application that are arranged in a protocol stack comprising: underlying the sender application a sender messaging layer and a sender transport layer, and underlying the receiver application, a receiver messaging layer and a receiver transport layer, wherein the sender transport layer and the receiver transport layer are coupled by way of a network layer, the method comprising the steps of: incorporating a sender intermediate layer between the sender messaging layer and the sender transport layer and a receiver intermediate layer between the receiver messaging layer and the receiver transport layer; configuring the interface characteristics of the intermediate layers to be the same as for their corresponding transport layers; creating a sender queue in a non-volatile data storage component of the sender intermediate layer and a receiver queue in a non-volatile data storage component of the receiver intermediate layer, storing the data to be sent from the sender application to the receiver application in the sender queue, and transmitting the data stored in the sender queue to the receiver queue via the sender transport layer and the receiver transport layer. | 03-05-2009 |
20100135179 | COMMUNICATION DEVICE - A communication device, a computer program product, and a method for operating a communication device. The communication device has at least one protocol stack having at least two protocol modules, a number of threads for executing the protocol modules, the respective thread being blocked or active, the respective active thread being idle or busy, and a control unit having first means adapted to adjust the number of active threads by monitoring a ratio between a first time duration the active threads are busy and a second time duration the active threads are idle. | 06-03-2010 |
20100205484 | SYSTEM AND METHOD FOR DEMONSTRATING THE CORRECTNESS OF AN EXECUTION TRACE IN CONCURRENT PROCESSING ENVIRONMENTS - Since multi-core processors have become the standard architecture for general purpose machines, programmers are required to write software optimized for parallelism. Verification of correctness is an important issue for parallel code because of its complexity. There are still tools missing that provide verification for complex code, such as testing the execution of code provides. Consequently, described herein are systems and methods to evaluate the correctness of program traces. Furthermore, the systems and methods described herein do not demand excessive computational requirements and the size of the program trace being evaluated increases. | 08-12-2010 |
20100211671 | EFFICIENT MAINTENANCE OF A DISTRIBUTED SYSTEM MEMBERSHIP VIEW - A method, system and computer program product are disclosed for maintaining a membership view of a distributed computing system comprising a multitude of members, wherein each of said members sends out a message indicating that said each of the members is available in the system. In one embodiment, the method comprises maintaining a first list of at least some of the members in the distributed system; and over a period of time, when one of the members sends out the message indicating that said one of the members is available in the distributed system, adding said one of the members to a second list. At defined times, the first list is replaced with the second list. In an embodiment, the method further comprises at said defined times, starting a new, empty second list. | 08-19-2010 |
20100211696 | DISTRIBUTED SERVER ELECTION WITH IMPERFECT CLOCK SYNCHRONIZATION - Embodiments of the invention provide a method, system, and computer program product for selecting a server as a selected server for performing a specified function in a distributed computing system. In one embodiment, the method comprises identifying a group of servers in the system; and choosing as the selected server the server that has been in the system the longest. In one embodiment, each of the servers in the group has a respective contention period, during which the server sends a contention message, and the selected server is chosen using these contention messages. The servers in the group may have imperfect clock synchronization. In this case, the contention periods of the servers is kept greater than the maximum difference between the server clocks. The invention may be used to select a name server, or to select a server for another service. | 08-19-2010 |
20100211954 | PRACTICAL CONTENTION-FREE DISTRIBUTED WEIGHTED FAIR-SHARE SCHEDULER - Embodiments of the invention provide a method, system and computer program product for scheduling tasks in a computer system. In an embodiment, the method comprises receiving a multitude of sets of tasks, and placing the tasks in one or more task queues. The tasks are taken from the one or more task queues and placed in a priority queue according to a first rule. The tasks in the priority queue are assigned to a multitude of working threads according to a second rule based, in part, on share values given to the tasks. In an embodiment, the tasks of each of the sets are placed in a respective one task queue; and all of the tasks in the priority queue from each of the task queues, are assigned as a group to one of the working threads. | 08-19-2010 |
20110238795 | Semantic Matching of Federation Intents and Services Capabilities in a Planning System for Automatic Service Federation - A method, device, and computer program product are provided for automatically generating connectivity configuration between domains by a device. A rule is received by the device. The rule is read by the device to determine a first domain invoking a service, a second domain having the service, and connectivity requirements for the first and second domains. A first proxy and a second proxy are automatically determined to fulfill the rule by the device. The first proxy is automatically assigned to the first domain and the second proxy is automatically assigned to the second domain. | 09-29-2011 |
20120233295 | Declarative Service Domain Federation - A mechanism for declarative service domain federation uses a declarative approach to both the visibility aspect and the management aspect of service domain federation. Instead of manually exporting services, that is, selecting individual services from source domains to be visible in the target domain, using the present system, a federation architect uses a federation console to specify federation intent. The federation intent may include federation rule, query-based service group, and quality-of-service (QoS) policy. Based on the declared federation intent, a planning engine resolves the individual services based on the group query, generates the service visibility configuration, and creates the necessary service proxies and/or mediation objects to satisfy the goal. At runtime, a service monitor collects the performance metrics of federated services and dynamically adjusts the mediation/proxy configurations to maintain the QoS objectives specified by the federation architect. | 09-13-2012 |
20130031199 | TRANSMITTING DATA INCLUDING PIECES OF DATA - A method and system for transmitting data including pieces of data. The method includes the steps of: placing a piece of data on at least one cache memory; and sending a signal indicating a presence of the piece of data on the cache memory to at least one client, where at least one of the steps is carried out by a computer device. | 01-31-2013 |
20130060882 | TRANSMITTING DATA INCLUDING PIECES OF DATA - A method and system for transmitting data including pieces of data. The method includes the steps of: placing a piece of data on at least one cache memory; and sending a signal indicating a presence of the piece of data on the cache memory to at least one client, where at least one of the steps is carried out by a computer device. | 03-07-2013 |
20130262609 | EFFICIENT MAINTENANCE OF A DISTRIBUTED SYSTEM MEMBERSHIP VIEW - A method, system and computer program product are disclosed for maintaining a membership view of a distributed computing system comprising a multitude of members, wherein each of said members sends out a message indicating that said each of the members is available in the system. In one embodiment, the method comprises maintaining a first list of at least some of the members in the distributed system; and over a period of time, when one of the members sends out the message indicating that said one of the members is available in the distributed system, adding said one of the members to a second list. At defined times, the first list is replaced with the second list. In an embodiment, the method further comprises at said defined times, starting a new, empty second list. | 10-03-2013 |