Abstract: Systems and methods for multilayered resource scheduling are provided. A system may include a user interface, an upper level scheduler, at least one lower level scheduler, and a reporting module. The user interface may receive a plurality of tasks. The upper level scheduler may sort the plurality of tasks into tasks with identical resource requirements. The lower level scheduler may be operable to receive resource requirements associated with a task. The lower level scheduler may ascertain compute resources sufficient to execute the task on a machine in a compute farm and advertise the compute resources as matching the resource requirements. The lower level scheduler may further receive a request to execute the task on the machine. The compute resources may be controlled to execute the tasks with the identical resource requirements without further scheduling operations. The lower level scheduler may control the compute resources to execute the task.
Abstract: Systems and methods for multilayered resource scheduling are provided. A system may include a user interface, an upper level scheduler, at least one lower level scheduler, and a reporting module. The user interface may receive a plurality of tasks. The upper level scheduler may sort the plurality of tasks into tasks with identical resource requirements. The lower level scheduler may be operable to receive resource requirements associated with a task. The lower level scheduler may ascertain compute resources sufficient to execute the task on a machine in a compute farm and advertise the compute resources as matching the resource requirements. The lower level scheduler may further receive a request to execute the task on the machine. The compute resources may be controlled to execute the tasks with the identical resource requirements without further scheduling operations. The lower level scheduler may control the compute resources to execute the task.
Abstract: A method and apparatus for performing fair-share preemption in a distributed computing environment is disclosed. The invention allows the suspension of jobs in a preempt-able set and the transfer of their respective resources, e.g. either hardware or software resources, to jobs in a preempting set. These activities are performed, all while assuring fairness among jobs scheduled to be executed and optimizing the use of available resources. In a preferred embodiment, the preempt-able and the preempting sets may include jobs characterized by, for example, job priorities, job ownership, or combinations thereof.
Abstract: A method and apparatus for controlling the propagation of changes made to a data file in a system of interrelated data files is described. In one embodiment of the method of the invention, a run-time dependency management facility is provided on the computer system which is effective to generate under computer control a graph indicating relationships among the data files and software tools present on the system. A change is made to at least one of the data files and a determination is made as to whether that change is significant. If a significant change is made, then at least one propagation barrier is provided which is effective to prevent computer-implemented propagation of the change in said data file through at least one data file which is interdependent with the changed data file.