Duration of Blocked Interrupts

Mail Receiver rmail at ittc.ukans.edu
Mon Apr 27 22:24:59 PDT 1998


On Mon, 27 Apr 1998, Doug Ledford wrote:
> What version of the aic7xxx driver were you testing?  I wouldn't be suprised
> if the latest versions can do exactly this.  There are things that can be
> done to get around this problem in 2.0.x, but there won't be much we can do
> about it at all in 2.1.x and probably 2.2.x due to the spin lock semantics
> and requirements.  I would have to consider the consequences of changing
> things around in the 2.1.x driver before I would recommend the changes I'm
> thinking of.

Sorry about not mentioning that in the first message... These particular
tests were done using the driver that came with 2.1.75.  Would it be worth
instrumenting a 2.0.x (say 33, for instance) kernel and checking the
duration of blocking there?  We're not tied to any particular kernel
version (although somewhat recent kernels would be preferable...)  For our
particular purposes, we also need access to ATM drivers but those can be
found in both the recent 2.1.x as well as the 2.0.x kernels.

Part of our system gives us access to much finer resolution timers as
well, so were not bound to just doing things on jiffy boundaries (we can
schedule events with effectively microsecond accuracy). We'd be willing to
add a kernel thread using polling or something if that might help for our 
particular purposes. 

Thanks,
   Robert


To Unsubscribe: send mail to majordomo at FreeBSD.org
with "unsubscribe aic7xxx" in the body of the message



More information about the aic7xxx mailing list