Control systems running on a computer are subject to timing disturbances coming from implementation constraints. Fortunately closed-loop systems behave robustly w.r.t. modelling errors and disturbances, and the controller design can be performed to explicitly enhance robustness against specific uncertainties. On one hand robustness in process controllers can be used to comply with weakly modelled timing uncertainties. On the other hand the principle of robust closed-loop control can also be applied to the real-time scheduler to provide on-line adaption of some scheduling parameters, with the objective of controlling the computing resource allocation. The control performance specification may be set according to both control and implementation constraints. The approach is illustrated through several examples using simulation and an experimental feedback scheduler is briefly described.