From: | Greg Stark <gsstark(at)mit(dot)edu> |
---|---|
To: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> |
Cc: | 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 15:37:24 |
Message-ID: | 8764t50yiz.fsf@stark.xeocode.com |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-hackers |
Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> writes:
> > On contented case you'll want task switch anyway, so the futex
> > managing should not matter.
>
> No, we DON'T want a task switch. That's the entire point: in a
> multiprocessor, it's a good bet that the spinlock is held by a task
> running on another processor, and doing a task switch will take orders
> of magnitude longer than just spinning until the lock is released.
> You should yield only after spinning long enough to make it a strong
> probability that the spinlock is held by a process that's lost the
> CPU and needs to be rescheduled.
Does the futex code make any attempt to record the CPU of the process grabbing
the lock? Clearly it wouldn't be a guarantee of anything but if it's only used
for short-lived spinlocks while acquiring longer lived locks then maybe?
> No; that page still says specifically "So a process calling
> sched_yield() now must wait until all other runnable processes in the
> system have used up their time slices before it will get the processor
> again." I can prove that that is NOT what happens, at least not on
> a multi-CPU Opteron with current FC4 kernel. However, if the newer
> kernels penalize a process calling sched_yield as heavily as this page
> claims, then it's not what we want anyway ...
Well it would be no worse than select or any other random i/o syscall.
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.
--
greg
From | Date | Subject | |
---|---|---|---|
Next Message | Josh Berkus | 2005-09-13 16:11:03 | Re: Spinlocks, yet again: analysis and proposed patches |
Previous Message | Tom Lane | 2005-09-13 15:27:31 | Re: Hard drive failure leads to corrupt db |