> Oops, forgot to explain the (*). > > On 6/13/07, André Braga <meianoite@xxxxxxxxx> wrote: > > On his lottery/stride scheduling thesis(*), Waldspurger suggests > > having a mechanism to transfer tickets among processes, for example > > when several processes are waiting on a semaphore while one is > > allowed > > "inside". The process "inside" the critical session gets boosted by > > receiving the tickets from all the other processes blocked on the > > semaphore. > > > (*) Waldspurger's thesis is *NOT* the Scheduler Design To Rule Them > ALL(TM), but he indeed happened to write about it. > This is just a variation on priority inheritance: the busy thread temporarily gets teh priority of the highest priority waiting thread. This is used in RT system to avoid some deadlocks, (they "fixed" a mars rover by enabling it and rebooting it remotely :p) but it's not the sangral. François.