On 03/06/2007 03:53 PM, Thomas Gleixner wrote:

quoted

2) Virtual interrupts have a relatively high overhead as compared with 
native interrupts.  So, in vmitime, we wanted to be able to lower the 
timer interrupt rate at runtime, even if HZ is a compile time constant 
(and set to something high, like 1000hz).  While we could hack this in 
by using evt->min_delta_ns, it wouldn't really work since process time 
accounting would be wrong.  Instead, we should allow the 
tick_sched_timer in cases (c) and (d) to have runtime configurable 
period, and then scale the time value accordingly before passing to 
account_system_time.  This is probably something the Xen folks will want 
also, since I think Xen itself only gets 100hz hard timer, and so it can 
implement at best a oneshot virtual timer with 100hz resolution.  Any 
objections to us doing something like this?

Yes. It's gross hackery. 

1) We want to have a cleanup of the tick assumptions _all_ over the
place and this is going to be real hard work.

2) As I said above. The time accounting for virtualization needs to be
fixed in a generic way.

I'm not going to accept some weird hackery for virtualization, which is
of exactly ZERO value for the kernel itself. Quite the contrary it will
make the cleanup harder and introduce another hard to remove thing,
which will in the worst case last for ever.

Okay, to confirm I'm on the same page as you, you want to move process 
time accounting from being periodic sampled based to being trace based? 
i.e. at the system-call/interrupt boundaries, read clocksource and 
compute directly the amount of system/user/process time?

Do you know if anyone has explored this?  I thought there was a 
discussion about this a while back but it was rejected due to the 
sample-based approach having much lower overheads on high system call 
rate workloads.