Re: Rate monotonic scheduling

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



>>>>> "prasanna" == prasanna wakhare <prasannawakhare@yahoo.com> writes:

prasanna> I just want to design a rate monotonic scheduling

  SCHED_FIFO and SCHED_RR are both policies in a rate-monotonic
scheduling algorithm.

prasanna> algorithm(HARD real time) 

  Hard real-time is much more than the scheduling algorithm.  For
example, you'd have to replace every semaphore[1] in the kernel with a
mechanism supporting some kind of priority inversion avoidance scheme
(like priority inheritance or priority ceiling). Dunno if this sounds
feasible for you ... I'd rather think of it as next to impossible.

prasanna> I know it does'n't require for general purpose linux
prasanna> OS
prasanna> with a  O(1) Schedular (it's already give good
prasanna> perfomance for RT processes),But Still want to
prasanna> experiment,

  Note that O(1) of whatever is neither necessary nor sufficient for
real-time behaviour.

prasanna> Is this is possible? 
prasanna> Plz help me,or (the possible it is not practical at
prasanna> all)

prasanna> I just want to know Is it feasible??????

  Making the kernel a real-time one is not feasible IMHO ... Probably
a stripped down subsest can be made though.

~velco

[1] if there's the potential of unbounded wait, which is typical for
places where semaphores were considered the proper mechanism.
--
Kernelnewbies: Help each other learn about the Linux kernel.
Archive:       http://mail.nl.linux.org/kernelnewbies/
FAQ:           http://kernelnewbies.org/faq/


[Index of Archives]     [Newbies FAQ]     [Linux Kernel Mentors]     [Linux Kernel Development]     [IETF Annouce]     [Git]     [Networking]     [Security]     [Bugtraq]     [Yosemite]     [MIPS Linux]     [ARM Linux]     [Linux RAID]     [Linux SCSI]     [Linux ACPI]
  Powered by Linux