[mythtv-users] Anyone using the ASUS A7N8X-X motherboard?

[Tim Tait]

Rick Schultz wrote:

>On Mon, Jun 14, 2004 at 05:50:21PM -0400, Tim Tait wrote:
>  
>
>>On some systems it is caused by the "CPU Disconnect" feature being 
>>enabled.
>>    
>>
>
>Yeah, that's the one.
>"A hang is caused when the CPU generates a very fast CONNECT/HALT cycle
>sequence."
>
>  
>
>>The last kernel workaround I saw had a nasty performance hit, I don't
>>know if the latest fix is any better.
>>    
>>
>
>I'm talking about the patch discussed here:
>http://lkml.org/lkml/2004/5/3/157
>
>Nothing in the thread indicates that there should be a performance
>impact, and, after all, it is just delaying a HALT.  Are you talking
>about this patch, or something previous?  I can't make any performance
>comparisons myself, 'cause my machine locks up without the patch....
>
>-rick
>
The patch is newer than the last ones I saw. I was looking for fix 
somtime around October '03. The fix back then seemed to involve a ~1 ms 
wait after getting the interrupt before reading the APIC interrupt 
source. So you can imagine the performance hit. I preferred to just 
disable the "CPU Disconnect" feature.

This patch would seem to do what the Windows drivers do, much more 
elegant, and fast!

Tim