svn commit: r199067 - in head/sys: amd64/amd64 i386/i386

[Ed Schouten]

Both systems run amd64. I'll try the tunable when I get back home.  
Thanks!

-- 
  Ed Schouten <ed at 80386.nl> (from iPod)
  WWW: http://80386.nl/

On 10 nov 2009, at 07:11, Jun Kuriyama <kuriyama at FreeBSD.org> wrote:

> At Tue, 10 Nov 2009 06:59:11 +0100,
> ed at 80386.nl wrote:
>>> (1) On MacBook, lock up occured on real hardware?  Not on  
>>> hypervisor?
>>
>> Nope. The MacBook does use Apple's Boot Camp, but I can't say whether
>> that can be considered to be a hypervisor. What happens, is that the
>> system just locks up after probing all the device. It doesn't mount  
>> the
>> root device anymore.
>
> Hmm, I think Boot Camp is not hypervisor, and should be treated as
> real hardware.  Which architecture (i386/amd64) you are using?
>
>>> (2) On both system, is there no problem before this commit?
>>
>> I bisected it and the revision before this one does boot. I'll
>> experiment with the tunables this afternoon. I really had to get some
>> sleep last night, so I couldn't investigate it any further.
>
> You can try with hw.clflush_disable="1" in loader.conf.  If you can
> boot with it, I must be mistaken something (anyway its my fault).
>
> Can you show me CPUID line at boot message (of course from the kernel
> you can boot) like this?
>
>> CPU: Dual-Core AMD Opteron(tm) Processor 2210 (1800.07-MHz K8-class  
>> CPU)
>>  Origin = "AuthenticAMD"  Id = 0x40f12  Stepping = 2
>>   
>> Features= 
>> 0x178bfbff< 
>> FPU, 
>> VME, 
>> DE, 
>> PSE, 
>> TSC, 
>> MSR, 
>> PAE, 
>> MCE, 
>> CX8, 
>> APIC,SEP,MTRR,PGE,MCA,CMOV,PAT,PSE36,CLFLUSH,MMX,FXSR,SSE,SSE2,HTT>
>>  Features2=0x2001<SSE3,CX16>
>>  AMD Features=0xea500800<SYSCALL,NX,MMX+,FFXSR,RDTSCP,LM,3DNow!+, 
>> 3DNow!>
>
>
> -- 
> Jun Kuriyama <kuriyama at FreeBSD.org> // FreeBSD Project
>         <kuriyama at s2factory.co.jp> // S2 Factory, Inc.
>