Inferring Temporal Behaviours Through Kernel Tracing

In order to provide reliable system support for real-time applications, it is often important to be able to collect statistics about the tasks temporal behaviours (in terms of execution times and inter-arrival times). Such statistics can, for example, be used to provide a-priori schedulability guarantees, or to perform some kind of on-line adaptation of the scheduling parameters (adaptive scheduling, or feedback scheduling). This work shows how the Linux kernel allows to collect such statistics by using an internal function tracer called Ftrace. Based on this feature, tools can be developed to evaluate the real-time performance of a system or an application, to debug real-time applications, and/or to infer the temporal properties (for example, periodicity) of tasks running in the system.