ah ha ... nmi_init.c/p4_int I printk'd the cpu_model ... it is 4...
there is a test "if (cpu_model >3) return 0;" .. not sure why this test ..
in any case this is why I am "dumbing" down to timer interrupt ... i.e. no
performance registers..
anybody have any idea the signficance of cpu_model > 3 is bad????
Regards, Vasili
"John Levon" <levon@xxxxxxxxxxxxxxxxx> wrote in message
news:20061003234957.GA29035@xxxxxxxxxxxxxxxxxxxxxxx
> On Tue, Oct 03, 2006 at 06:28:10PM -0500, Vasiili Galchin wrote:
>
>> I have been reading through the oprofile driver's oprof.c. In
>> oprofile_init, the call to oprofile_arch_init is failing so I am
>> "dumbing"
>> down to only timer interrupt, (I see in my system log /var/log/messages)
>> i.e. no performance registers for me. I am building for Intel x86_64. I
>> did
>> a find/grep for "oprofile_arch_init" under the arch directory. I noticed
>> that the x86_64 directory under arch has no definition for function
>> "oprofile_arch_init". So which definition of "oprofile_arch_init" am I
>> linking into the oprofile.ko (oprofile driver/fs)?? Help ...
>
> arch/i386/oprofile/ is re-used for 64-bit.
>
> john
>
> -------------------------------------------------------------------------
> Take Surveys. Earn Cash. Influence the Future of IT
> Join SourceForge.net's Techsay panel and you'll get the chance to share
> your
> opinions on IT & business topics through brief surveys -- and earn cash
> http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV
-------------------------------------------------------------------------
Take Surveys. Earn Cash. Influence the Future of IT
Join SourceForge.net's Techsay panel and you'll get the chance to share your
opinions on IT & business topics through brief surveys -- and earn cash
http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV
|
