In hybrid systems on chip (SoC) the algorithms must share limited resources classified as hardware (FPGA logic, memory and DSP blocks) and software (CPU cycle budget). Embedded applications are implemented with concurrent processes, which have to coexist. Therefore, the algorithm performance or precision is often downgraded to fit on a FPGA or to meet timing constraints. One of the solutions to relax these constraints is to reconfigure the SoC according to application requirements observed at runtime. Hardware (HW) reconfiguration can be performed by means of dynamic partial reconfiguration (DPR). Beyond the intrinsic DPR complexity, the most critical aspect is the implementation of the reconfiguration decision. Academic adaptive architectures are usually based on power / performance rules. Nevertheless such solutions are usually application agnostic and so cannot fully exploit the possible adaptation to the environment. So real-life systems require solutions to capture the knowledge of algorithm experts that can be leveraged at runtime to drive the reconfiguration decision according to application scenarios. In this paper we propose a methodology to design a reconfiguration controller based on quality of service (QoS) indicators to be specified by experts. This controller monitors the reconfigurable partitions (RP) and can make DPR decisions to optimize the global QoS. We illustrate our methodology in the Radar domain with a tracking system based on Kalman filters implemented on a Zynq Ultrascale+. This study highlights expected gains and obstacles, it presents the different strategies to cope with the issues and draws perspectives.