Re: calcru: negative time ... followed by freeze

From: Julian Elischer <julian_at_elischer.org>
Date: Mon, 21 Jun 2004 00:44:09 -0700 (PDT)
On Mon, 21 Jun 2004, Bruce Evans wrote:

> Ah, here is a likely cause of the bug in -current:
> 
> % 	if (p == curthread->td_proc) {
> % 		/*
> % 		 * Adjust for the current time slice.  This is actually fairly
> % 		 * important since the error here is on the order of a time
> % 		 * quantum, which is much greater than the sampling error.
> % 		 * XXXKSE use a different test due to threads on other
> % 		 * processors also being 'current'.
> % 		 */
> % 		binuptime(&bt);
> % 		bintime_sub(&bt, PCPU_PTR(switchtime));
> % 		bintime_add(&bt, &p->p_runtime);
> % 	} else
> % 		bt = p->p_runtime;
> 
> The XXXKSE comment is correct that this might be broken.  If the (p
> != curthread->td_proc) case happens at all for a running process, then
> it gives a wrong (out of date) timestamp in bt.  This wrongness will
> be detected if calcru() is was called called earlier in the current
> timeslice and took the other path here.

It should be fairly easy as there is now a thread state that indicates
that it is actually running now..

> 
> The recent change to fill_kinfo() is quite likely to trigger detection
> of this bug.  fill_kinfo() is often used to iterate over all processes
> for ps, so it will call calcru() with (p != curthread->td_proc) for
> all processes other than the one running it, and give a bt that is out
> of date for all such processes that are actually running.  Since there
> can be at most one running process per CPU, this bug only affects SMP.
> 
> The call to calcru() from ttyinfo() may be the only other trigger.
> ttyinfo() picks a process and should rarely or never pick the ithread
> running it, so it will almost always take the (p != curthread->td_proc)
> path.  Again, this is only a problem for the SMP case since in the !SMP
> case the picked process must have been switched away from to run the
> ithread, so it cannot be running.
> 
> Bruce
> _______________________________________________
> freebsd-current_at_freebsd.org mailing list
> http://lists.freebsd.org/mailman/listinfo/freebsd-current
> To unsubscribe, send any mail to "freebsd-current-unsubscribe_at_freebsd.org"
> 
Received on Mon Jun 21 2004 - 05:44:37 UTC

This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:37:58 UTC