hujun260 commented on PR #16673: URL: https://github.com/apache/nuttx/pull/16673#issuecomment-3089129890
> I got this idea of changing the way how tasks are assigned to the CPUs. > > I don't believe there is any reason to try to force a specific tcb for another CPU; rather we could just keep all the pending tasks in ready-to-run list, and let each CPU pick one to run from the top themselves. > > Then we could change also all the priority adjustment, round robin etc. accross CPUs to just use the same smp_sched call. > > This change would be rather large though. I just made it; keeping it as draft for now as I have limited time to work on this. Initially it feels stable and is performant, but I'll need to do more testing on other targets still. Your modification seems too complicated and is likely to affect performance. Could you provide a comparison of the context switching performance data before and after the modification? Moreover, is it necessary to incorporate the Round Robin (RR) logic into addreadytorun as well? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: commits-unsubscr...@nuttx.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
