[TUHS] OT: critical Intel design flaw
lm at mcvoy.com
Thu Jan 4 10:51:03 AEST 2018
On Wed, Jan 03, 2018 at 06:40:25PM -0500, Theodore Ts'o wrote:
> On Wed, Jan 03, 2018 at 01:27:19PM -0500, Clem Cole wrote:
> > > This slowdown (which is not much -- L4 shows it is about 5% or so)
> > >
> > ???I agree. We came to the same conclusion in the early/mid 1990's with
> > Mach and Chorus. In fact, the UI 'requirements for modern OS' document
> > (which is part of why AT&T got behind Chorus for the never completed
> > SVR5/R6 stuff - I'll see if I can find a copy) was based on that work.
> > The OS weenies at the time felt that the cost was low enough and hardware
> > cheap enough that of course kernels would be the way to go.
> It's possible to keep the slowdown at 5%, but how much extra
> engineering work does it take to get the performance gap down to that
> level? And during that time while the micro kernel team is playing
> catchup, if the OS with the monolithic kernel adds new features to the
> OS, how much additional time does it take to add those features to the
> OS? (Regardless of whether the features are implemented in userspace,
> or in the kernel, or some combination of the two.)
To add to Ted's points. I was good friends with one of the core guys
on the QNX team a long time ago (he died early in 1998 of brain cancer.
Yuck). The QNX micro kernel really was micro, the kernel fit entirely in
a 4K instruction cache on x86 (thanks CISC). It did very, very little.
It took a lot of thinking and discipline to figure out what the kernel
should do and what should be delegated. There was constant pressure to
put more stuff in the kernel.
My buddy told me that there were only 4 people who were allowed to touch
the actual kernel code. And they all both backed each other up and
second guessed each other in code reviews. They counted instructions
and cache misses each time they changed stuff.
As a result, the QNX kernel of the late 1980's and 1990's was super
super fast. I ran as much as 10 users logged in to a 80286 running
QNX doing text editing and compiles and it actually worked. I'd
argue that it worked better than Unix would have worked on that
QNX made it work. I think they slowed down when they put full posix in
but they made it work.
The problem is that most people / companies are not that disciplined.
Oh, we need this for $CUSTOMER and this for $BENCHMARK and this for
$STANDARD and the easiest way to get it is to shove it into the kernel.
I'd argue that microkernels are indeed the best answer but only if you
have the best programmers. Which nobody does even though everyone claims
Monolithic kernels are far more amenable to less than awesome people
messing with them. Sad but true, I'd love a microkernel world but I
fear we are too stupid to get it. Something, something, something,
this is why we can't have nice things.
More information about the TUHS