Re: priority inversion

Marc Lehmann (pcg@goof.com)
Sat, 31 Jul 1999 04:16:35 +0200


On Fri, Jul 30, 1999 at 09:42:30AM -0600, Jeff Merkey <jmerkey@timpanogas.com> wrote:
>
> Disagree. You can get into some pretty ugly starvation situations on a
> system with inversion. The "deadlocks" aren't really deadlocks at all, but

And what does this have to do with this discussion? you can produce deadlocks
(and other less severe starvation situations) with a myriad of ways.
sched_idle is special in the same way as other rt classes are.

(you can eassily kill your box and nothing will help you, even)

I admit I feel comfortable only when sched_idle is available to root only
(just like the other non-timesharing scheduling classe), however, the
reasoning "we could get a bad situation when misused so lets kill that
feature" could be applied to almost everything.

> these problems don't show up, but there's always someone out there putting
> out apps that uses locks excessively.

why not forbid mandatory locks, btw? could easily create a deadlock
situation ;)

> From: Marc Lehmann <pcg@goof.com>
> To: <linux-kernel@vger.rutgers.edu>
> Sent: Thursday, July 29, 1999 6:55 PM
> Subject: Re: priority inversion

Quoting a whole posting without referencing it in any way is a bad habit!

-- 
      -----==-                                             |
      ----==-- _                                           |
      ---==---(_)__  __ ____  __       Marc Lehmann      +--
      --==---/ / _ \/ // /\ \/ /       pcg@goof.com      |e|
      -=====/_/_//_/\_,_/ /_/\_\       XX11-RIPE         --+
    The choice of a GNU generation                       |
                                                         |

- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/