Re: How to query the number of processes queueing for the CPU inside the VM

[João Vilaça]

That's exactly it. How can we proceed to get it into guest-get-cpustat?

On Fri, Nov 29, 2024 at 3:17 PM Daniel P. Berrangé <berrange@redhat.com> wrote:

On Fri, Nov 29, 2024 at 02:38:52PM +0000, João Vilaça wrote:
> In KubeVirt, through libvirt, we need to know the number of processes
> queued for the CPU inside the VM.
>
> Can we get this information through the qemu-guest-agent?

The only CPU stats related command in QGA is 'guest-get-cpustat's
returning:

# @user: Time spent in user mode
#
# @nice: Time spent in user mode with low priority (nice)
#
# @system: Time spent in system mode
#
# @idle: Time spent in the idle task
#
# @iowait: Time waiting for I/O to complete (since Linux 2.5.41)
#
# @irq: Time servicing interrupts (since Linux 2.6.0-test4)
#
# @softirq: Time servicing softirqs (since Linux 2.6.0-test4)
#
# @steal: Stolen time by host (since Linux 2.6.11)
#
# @guest: ime spent running a virtual CPU for guest operating systems
#     under the  control of the Linux kernel (since Linux 2.6.24)
#
# @guestnice: Time spent running a niced guest (since Linux 2.6.33)

none of which match your rquest

Essentially what you're asking for seems to be the "load average" which
is a measure of waiting runnable tasks, over some period (1, 5, 15 minutes
typically).

I imagine guest-get-cpustat could be enhanced to include load info without
too much work.

With regards,
Daniel
--
|: https://berrange.com      -o-    https://www.flickr.com/photos/dberrange :|
|: https://libvirt.org         -o-            https://fstop138.berrange.com :|
|: https://entangle-photo.org    -o-    https://www.instagram.com/dberrange :|

--

kind regards,

João Vilaça