On Mar 6, 2007, at 5:16 PM, Jason Thorpe wrote:

>
> On Mar 6, 2007, at 5:08 PM, Matt Thomas wrote:
>
>> which is why I wanted kernel realtime.  Note that the recently  
>> committed OSK5912 support in evbarm supports 160 interrupt  
>> sources, so having lots of interrupt priorities gives a lot of  
>> flexibility on those interrupts.
>
> So, basically every kernel thread that we have now would map into  
> "kernel real-time"?

No.  I don't see nfsiod or even the server lwps needs to be real- 
time.  For instance,
threads that service "soft interrupts" would be realtime.  However, a  
kernel thread that handles USB attach/disconnect events would not be.

It's a "it depends".