This paper describes the proposal of a priority flow oriented design of the Ksensor architecture. Ksensor is a multiprocessor traffic capture and analysis system for high speed networks developed at kernel space. While the current architecture permits the capture and analysis of data flows, there are several scenarios where it does not perform adequately to achieve this goal, for example, if a certain type of traffic is more valuable than others. Thus, this work pursues the design that allows Ksensor to provide data flow treatment to a larger extent. This improvement will allow the new architecture to provide more reliability in data flow capture and processing.

In NQaS, a kernel level network traffic sniffer under the name of Ksensor was created long ago. Ksensor has been using for long a kernel version which has become outdated with the pass of the years. In order to recover the relevance of the study of the sniffer and update with the latest trends in kernel efficiency, a project has been developed, in which Ksensor is adapted to get advantage of latest capture optimizations. Linux developers have created several ways to optimize the system throughput in high system load, and in the area of traffic capture, GRO and RPS mechanisms are the most important changes done.