Increasing the amount of work completed by volunteer computing projects with task distribution policies

Improving the Productivity of Volunteer Computing by Using the Most Effective Task Retrieval Policies

“…As we study the various policies, we consider the effects the green movement and the trend of building computers with multi-core CPUs have on the policies. The research on how task retrieval policies affect the number of tasks volunteer computing clients complete for computers with single-core and multicore CPUs was previously published in [7] and [8]. We summarize those results here, present new research on how the environmental movement may influence the productivity of clients using the various task retrieval policies, and indicate directions for future research.…”

“…4 Buffer multiple tasks "Buffers some number of days of tasks. The amount of tasks is limited to a number that can possibly be completed before the tasks' deadlines" [7]. 5 Super-optimal "Does not buffer any tasks.…”

“…Downloads a task after returning the result of the previous task, but assumes tasks are downloaded instantaneously. Does not attempt to execute a task that will not be completed on time" [7].…”

“…If the client is able to complete the task on time, it downloads the task and begins working on it. Otherwise, the client sleeps for 1 s and then checks to see whether it could complete a task if it downloaded and started it then" [7]. This policy "ensures that the most tasks will be completed by a client using the Super-Optimal policy by ensuring that a task that will not be completed does not use CPU time that could otherwise be used to complete a task.…”

“…However, the Super-Optimal policy provides an upper bound on the number of tasks a client can complete in a given amount of time. The upper bound serves as a benchmark, allowing us to determine how effective other policies are and whether there is sufficient motivation to try to develop better policies" [7].…”