Big problems with 7.1 locking up :-(

[Garrett Cooper]

On Sun, Jan 11, 2009 at 4:45 AM, Pete French
<petefrench at ticketswitch.com> wrote:
>> I noticed a similar problem testing 7.1-RC1, It seemed to be a deep
>> deadlock, as it was triggered by lighttpd doing kern_sendfile, and
>> never returning. The side effects (being unable to create processes,
>> etc) is similar.
>
> Interesting - did you get any responses from anyone else regarding
> this ?  My last box which locked up was essentialy idle, so I am very
> surprised by all of this - also none of the heavilt loaded machines
> (i.e. the actual webservers) have locked up.
>
> I am also surprised that this isn't more widely reported, as
> the hardware is very common. The only oddity with ym compile
> is that I set the CPUTYPE to 'core2' - that shouldnt have an effect, but
> I will remove it anyway, just so I am actually building a completely
> vanilla amd64. That way I should have what everyone else has, and since
> I don't see anyone else saying they have isues then maybe mine will
> go away too (fingers crossed)
>
>> My kernconf is below, try building the kernel, and send an email
>> containing the backtrace from any process that has blocked (in my
>
> OK, will do. I can try this on the one non-essential box which
> locked up yesterday. I don't know how long it will before it
> locks up again, but will see if I can do some things to provoke it.
>
> -pete.

    Intel suggests nocona for x86_64 platforms and prescott for x86
(i386) based platforms on the 4.2 line, because they best matched the
cache size and featureset of the Core2 processors.

    I don't think that core2 support was fully completed in 4.2 (in
fact I believe it was just started), and I don't think that our
binutils supports it properly.

Some thoughts,
-Garrett