Re: Ideas for abstracting driver IO from bus implementation?
David Hinds (dhinds@hyper.stanford.edu)
Thu, 18 Mar 1999 12:40:35 -0800
Kind of an off topic question, I guess, but what is the point of I2O
supposed to be, anyway? Based on this discussion, it sounds like I2O is
not much more than asymmetric multiprocessing, where you've got special
I2O processors sitting in various places (maybe on your motherboard,
maybe on IO boards, maybe some combination) that just run driver code.
Hasn't this concept been tried and abandoned enough times before?
Looking at platforms with really high performance IO capabilities, they
don't seem to rely on particularly smart IO devices. Which seems to
tell me that current bus mastering IO designs are "smart enough", if
your system has adequate bandwidth and your OS doesn't suck??
The only benefit I see is that it might offer better performance than an
"equivalent" amount of SMP power if the host OS is particularly
inefficient at handling SMP or IO. And maybe reduce FSB contention in
Intel's primitive SMP architecture. And it lets Intel sell lots of I2O
processors. Am I missing something??
-- Dave Hinds
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/