Grid-enabled, service-oriented architecture for enabling high-speed computing applications

摘要

According to one aspect of the present disclosure, a method and technique for data processing in a distributed computing system having a service-oriented architecture is disclosed. The method includes: receiving, by a workload input interface, workloads associated with an application from one or more clients for execution on the distributed computing system; identifying, by a resource management interface, available service hosts or service instances for computing the workloads received from the one or more clients; responsive to receiving an allocation request for the one or more hosts or service instances by the workload input interface, providing, by the resource management interface, address information of one or more workload output interfaces; and sending, by the one or more workload output interfaces, workloads received from the workload input interface to the one or more service instances.

主权项

1. A service manager installed on one or more computing devices for operation in a distributed computing system, the distributed computing system for receiving workloads from one or more client applications and executing the workloads on one or more service instances running on one or more service hosts within the distributed computing system, the service manager comprising:
a workload input interface operable to receive workloads associated with an application from one or more clients for execution on the distributed computing system; a resource management interface operable to identify available service hosts or service instances for computing the workloads received from the one or more clients; and a workload output interface operable to send the workloads received from the workload input interface to the one or more service instances; wherein the workload input interface receives address information of the workload output interface from the resource management interface in response to an allocation request for the one or more hosts or service instances by the workload input interface; wherein the workload input interface sends the received workloads to a persistent store device substantially at the same time that the workload input interface sends the received workloads to the one or more workload output interfaces; and wherein the service manager is further operable to monitor operation of the service instances for failures in execution and re-queue the failed workloads to the failed service instances or to queue the workloads to other service instances that are available to the service manager.