Algorithm for faster convergence through affinity override

摘要

A method is implemented by a network device having a symmetric multi-processing (SMP) architecture. The method improves response time for processes implementing routing algorithms in a network. The method manages core assignments for the processes during a network convergence process. The method includes determining a number of interrupts or system events processed by a subset of cores of a set of cores of a central processing unit and identifying a core within the subset of cores with a lowest number of interrupts or system events processed. The method further includes changing an affinity mask of at least one process implementing the routing algorithms during the network convergence to target the core within the subset of cores with a lowest number of interrupts or system events processed.