Dynamic user-level CPU allocation for volunteer computing in CFS-based scheduler environment

In this paper, we propose a CPU allocation technique to solve the problem of running volunteer application on a system with Completely Fair Scheduler (CFS) using adaptive reservation. Our allocation technique works across user boundary without requiring administrative privilege. We implemented and evaluated our technique on Linux-based system with the CFS. Our technique could mitigate performance loss of foreground workload. In compute-heavy test and video playback test, performance loss is negligible. While in latency sensitive web server test, performance loss is only about 10 percent. Our technique also improves background workload performance up to 50 percent comparing to traditional static allocation method.