On Wed, 2003-05-21 at 12:40, Duraid Madina wrote:
> Dear Arjan,
> 
> 
>        ///////
>        //    O
>       //      >                                    This is a graduate
>        / \__ ~                                     student, laboratory
>          ||                            /////       assistant, automotive
>        (\ \)   (~)                    //  o   <--- engineer or other
>        ( \ \  / /                    //    >       unfortunate soul
>        (  \ \/ /         ____________/ \__O        attempting to get
>        (   \__/         /  ___ ______\//           performance out of a
>        /   | /@        (  /  / ______)/            machine running Linux
>       (    |//          \ \ / /   (_)              by writing a simple
>        \   ()            \ \O/                     and correct
>         \  |              ) )                      multithreaded program.
>          ) )             / /
>         (  |_           / /_
>         (____>         (____>
> 
>            ^
>            |
>            |
>            |
>            |
> 
>       This is you.
> 
> 

if you had spent the time you spent on this colorful graphic on reading
SUS or Posix about what sched_yield() means, you would actually have
learned something. sched_yield() means "I'm the least important thing in
the system". It's the wrong thing for cross-cpu spinlocks; futexes are
optimal for that. For letting higher priority tasks run a sleep(0) is
also far more closer to the right behavior than a sched_yield().