| From: | Greg Stark <gsstark(at)mit(dot)edu> |
|---|---|
| To: | Douglas McNaught <doug(at)mcnaught(dot)org> |
| Cc: | Greg Stark <gsstark(at)mit(dot)edu>, Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>, Marko Kreen <marko(at)l-t(dot)ee>, pgsql-hackers(at)postgresql(dot)org |
| Subject: | Re: Spinlocks, yet again: analysis and proposed patches |
| Date: | 2005-09-13 17:11:12 |
| Message-ID: | 87zmqgzydr.fsf@stark.xeocode.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
Douglas McNaught <doug(at)mcnaught(dot)org> writes:
> > It seems to me what you've found is an outright bug in the linux scheduler.
> > Perhaps posting it to linux-kernel would be worthwhile.
>
> People have complained on l-k several times about the 2.6
> sched_yield() behavior; the response has basically been "if you rely
> on any particular sched_yield() behavior for synchronization, your app
> is broken--it's not a synchronization primitive."
They're not talking about this. They're talking about applications that spin
on sched_yield() and expect it to reduce cpu load as if the process were
calling sleep().
What Tom found was that some processes are never scheduled when sched_yield is
called. There's no reason that should be happening.
--
greg
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Mark Wong | 2005-09-13 17:11:49 | postgresql CVS callgraph data from dbt2 |
| Previous Message | Douglas McNaught | 2005-09-13 16:24:04 | Re: Spinlocks, yet again: analysis and proposed patches |