Abstract: An example method of managing a plurality of hardware accelerators in a computing system includes executing workload management software in the computing system configured to allocate a plurality of jobs in a job queue among a pool of resources in the computer system; monitoring the job queue to determine required hardware functionalities for the plurality of jobs; provisioning at least one hardware accelerator of the plurality of hardware accelerators to provide the required hardware functionalities; configuring a programmable device of each provisioned hardware accelerator to implement at least one of the required hardware functionalities; and notifying the workload management software that each provisioned hardware accelerator is an available resource in the pool of resources.

Abstract: Methods and apparatus, including computer program products, implementing and using techniques for testing a data service on a computing cluster having several computing nodes. A test package is installed on a test administration machine and on one or more of the computing nodes in the computing cluster. Data service configuration information is collected for the data service to be tested. Computing cluster configuration information is collected. The data service configuration information and the computing cluster configuration information are distributed to one or more of the computing nodes in the computing cluster. The data service is tested on the computing cluster by applying one or more data service test suites in the test package to the data service. A report containing results of the application of one or more of the data service test suites to the data service is generated.

Abstract: Methods are provided for testing storage devices and related devices for use in a clustered system. Storage devices may be pre-qualified before cluster software is installed for controlling the clustered system. Some implementations allow one or more storage devices in a cluster to be automatically tested in a variety of fault and non-fault scenarios.

Abstract: Methods and apparatus, including computer program products, implementing and using techniques for testing a computing cluster having several computing nodes. Configuration information regarding a test system is received and used to generate a configuration file that profiles the test system. The configuration file may be passed to each computing machine in the test system whereupon an appropriate test suite is launched on each computing machine in the test system to perform the tests contemplated by the test suite.