In Multilevel Feedback Scheduling at the base level queue, the processes circulate in round robin fashion until they complete and leave the system. Processes in the base level queue can also be scheduled on a first come first served basis. Why can't they be scheduled on Shortest Job First (SJF) algorithm instead of First Come First Serve (FCFS) algorithm which seems to improve average performance of the algorithm.
2 Answers
The SJF algorithm gives more througput, only when processes differ a lot in their burst time. However its not always the case that it will perform better than FCFS. Take a loot at this answer.
Since in Multilevel Feedback Scheduling algorithm, all the processes that are unable to complete execution within defined time quantum of first 2 queues, are put to the last queue having FCFS, its very likely that they all have large CPU bursts and therefore wont differ much in their burst time. Hence, its preferred to have FCFS, scheduling for the last queue.
One simple reason:
The processes fall in the base level queue after they fail to finish in the time quantum alloted to them in the higher level queues. If you implement SJF algorithm in the base level queue, you may starve a process because shorter job may keep coming before a longer executing process ever gets the CPU.