Date: Fri, 25 Sep 1998 07:43:46 +0200 From: Tor.Egge@fast.no To: fn@radio-do.de Cc: freebsd-current@FreeBSD.ORG, freebsd-smp@FreeBSD.ORG Subject: Re: Weired top display at smp current kernel from today Message-ID: <199809250543.HAA26153@midten.fast.no> In-Reply-To: Your message of "Thu, 24 Sep 1998 18:20:25 %2B0200" References: <19980924182025.A9605@radio-do.de>
next in thread | previous in thread | raw e-mail | index | archive | help
> On Thu, Sep 24, 1998 at 10:58:37AM +0200, Frank Nobis wrote:
> >
> > I thought it was gone here, but...
>
> I can now reproduce the problem, but yet don't understand why it happens.
Replacing the aout /sbin/init with an elf /sbin/init seems to be sufficient
to trigger this problem.
Looking at mp_lock using
gdb -k /kernel.gdb /dev/mem
...
print/x mp_lock
gave 0x1 or 0x1000001 with the aout /sbin/init, but
0x2 or 0x1000002 with the elf /sbin/init.
This means that when a cpu returns to userland, mp_lock is still 0x1 or
0x1000001. Which blocks the other CPU until the CPU holding the giant
kernel lock enters _idle.
- Tor Egge
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-smp" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199809250543.HAA26153>