Am Dienstag, 21. August 2007 schrieb Ingo Molnar:
> Wouldnt it be more consistent if a virtual box would not show any
> dependency on external load? (i.e. it would slow down all of its
> internal functionality transparently, without exposing it via /proc. The
> only way to observe that would be the TOD interfaces: gettimeofday and
> real-time clock driven POSIX timers. Even timer_list could be driven via
> virtual time - although that would probably break user expectations,
> right?) Or would accounting-in-virtual-time break user expectations too?
> (most of the other hypervisors let guests account in virtual time.)
Most hypervisors let guest account in virtual time because this requires no
code change. We had that in the past as well. But now we have lots of
customers that rely on a different accounting model. Before
CONFIG_VIRT_CPU_ACCOUNTING we got this model of top showing 99% of cpu used,
even if the hypervisor gives us 20% of the physical one. We actually want to
show that this process gets only 19.8% of a real cpu for several reasons:
- people do workload management based on used cycles
- people/departments pay money based on used cycles
- If your physical cpu has to much load, you want to identify processes by
physical cpu usage
There are even some vendors that claimed that Linux accouting was completely
broken and useless on s390 and people should use their vendor tool to get the
right numbers. While these tools still have important features
CONFIG_VIRT_CPU_ACCOUNTING fixed at least the "broken" parts.
Christian
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
[Index of Archives]
[Kernel Newbies]
[Netfilter]
[Bugtraq]
[Photo]
[Stuff]
[Gimp]
[Yosemite News]
[MIPS Linux]
[ARM Linux]
[Linux Security]
[Linux RAID]
[Video 4 Linux]
[Linux for the blind]
[Linux Resources]
