Selectively rebooting components of a computer system. One or more tables which list respective costs to reboot the components and respective likelihoods that reboots of the respective components will correct respective problems with the computer system are generated. Each of the costs is based on a time to reboot or delays caused by the reboot of the respective component. In response to a subsequent problem with the computer system, an order to reboot components of the computer system is determined from the table based on the costs and likelihoods that the reboot will correct the problem, such that a component of the computer system characterized by a relatively low cost and high likelihood to correct the problem will be rebooted before another component characterized by a relatively high cost and low likelihood to correct the problem. The tables are updated through actual experience.