Comparative Evaluation of Classical CPU Scheduling Algorithms in a Multicore Simulation Environment

Classical CPU scheduling algorithms remain useful
baselines for understanding the trade-offs among waiting time, turnaround time, responsiveness, processor utilization, and scheduling overhead. This study compares First-Come, FirstServed (FCFS), non-preemptive Shortest Job First (SJF), Shortest Remaining Time First (SRTF), and Round-Robin (RR) using a custom discrete-event simulator configured with a global ready queue and four CPU cores. Synthetic CPU-bound workloads are used to compare the policies under a common simulation framework. In the default workload reported here, SJF and SRTF
produce lower average waiting and turnaround times than FCFS
and RR, while RR incurs more dispatches as its time quantum
decreases. The results describe the behavior of this simulator and workload; they should not be interpreted as a direct benchmark of the Linux kernel scheduler. The study also discusses the limitations associated with CPU-only workloads, the global-queue model, and the absence of task migration and kernel-level scheduling overhead. Further validation is required for the interpretation of the utilization results and for metrics not numerically
reported in the present study.