You make a good point. MS Windows became the kludge that it is by trying
to cover all bases and look what they have. Better to leave somethings
out of the mainstream to have a good system and let the ones who are
desperate learn and work a little more to patch their kernel than to
have a kludge that does not perform well. Any other position would just
take me away from linux in search of something else less kludgy.
Tom Berkley
Mark Garlanger wrote:
>
> Is this the type of kludges Linux should have in the kernel because a few people
> want to run
> configurations that Intel does not even support? In looking at the patch, every
> call to
> do_gettimeoffset() will now go through a procvar, instead of being called directly.
> It's not
> a significiant impact, but it is an impact none-the-less. ANY impact to support
> this type
> of configuration is too much (in my opinion). Some things belong off-stream. If
> someone
> is running this configuration, they should patch their own kernel to not impact the
> rest of us.
> Am I the only one to feel this way?
>
> Mark
>
> ....wait a sec, as I put on flame-resistant clothing ;-)
>
> Christopher Thompson wrote:
>
> > If you have an SMP machine and have CPUs with different multipliers (i.e.
> > different speeds), Linux does not work correctly, at least not if it uses TSC
> > which is currently the case for Celerons (?) and better.
> >
> > I am attaching a patch against 2.3.99-pre6 which attempts to fix this. It is a
> > PRELIMINARY patch which means I beg you to please send me some feedback. I
> > really am out of my league here with kernel hacking (so please be gentle).
> > However, the patch should detect the error condition and work around it, you
> > don't have to configure anything (but remember to do make dep).
> >
> > Once the bugs are fixed and/or no bugs are found :), I'll send it along to the
> > appropriate people.
> >
> > Please: I need this tested under the following environments:
> > ABIT BP6-style Celeron SMP motherboard with same speed CPUs
> > ABIT BP6-style Celeron SMP motherboard with different speed CPUs
> > PPro or better SMP machine with same speed CPUs
> > PPro or better SMP machine with different speed CPUs if such exists
> > Athlon (for the sake of consistency)
> > Cyrix CPU
> > And last but not least, a PPro-or-better and a worse-than-PPro SINGLE CPU
> > machine.
> >
> > If you have any of these, please try out the patch and let me know how you fair.
> >
> > The patch is my own work but with help from Alan Cox and this mailing list.
> >
> > --
> > Christopher Thompson http://hypocrite.org/
> > One Ring to rule them all, One Ring to find them,
> > One Ring to bring them all and in the darkness bind them
> > -- Fellowship of the Rings, movie, Christmas 2001
> >
> > ------------------------------------------------------------------------
> > Name: tsc.patch
> > tsc.patch Type: text/x-c
> > Encoding: base64
>
> -
> Linux SMP list: FIRST see FAQ at http://www.irisa.fr/prive/dmentre/smp-howto/
> To Unsubscribe: send "unsubscribe linux-smp" to [EMAIL PROTECTED]
-
Linux SMP list: FIRST see FAQ at http://www.irisa.fr/prive/dmentre/smp-howto/
To Unsubscribe: send "unsubscribe linux-smp" to [EMAIL PROTECTED]
