At 08:51 PM 6/8/99 +0100, Alan Cox wrote:
>> Anyway i feel quite well that it basically isn't my problem but a
>> serious OS problem. They're smart, but not smart enuf
>> to understand that i'm running a parallel program where it's very
>> important that seemingly idle processes get a big deal of systemtime,
>> instead of waiting for a second before getting it.
>
>You can drop hints in a posix.4 compliant system using sched_yield() which
>basically says "I can't go forward, run someone else, but I want to get
running
>again too straight afterwards". Netscape uses buzz locks that spin briefly
>then yield. The code for that is in the Mozilla source.
thanks for the tip i'll checkout sched_yield
>To do it right on a multiprocessor machine you want a scheduler that is aware
>of such issues. They exist, but I dont know a lot about them
>
>
>
-
Linux SMP list: FIRST see FAQ at http://www.irisa.fr/prive/mentre/smp-faq/
To Unsubscribe: send "unsubscribe linux-smp" to [EMAIL PROTECTED]
