In a guest with only one vcpu, when pinning the emulator in say CPU184
and the vcpu0 in CPU0 of the host, the user might expect that only
CPU0 and CPU184 of the host will be used by the guest.
The reality is that Libvirt takes some time to honor the emulator
and vcpu pinning, taking care of NUMA constraints first. This will
result in other CPUs of the host being potentially used by the
QEMU thread until the emulator/vcpu pinning is done. The user
then might be confused by the output of 'virsh cpu-stats' in this
scenario, showing around 200 microseconds of cycles being spent
in other CPUs.
Let's document this behavior, which is explained in detail in
Libvirt commit v5.0.0-199-gf136b83139, in the cputune section
of formatdomain.html.in.
Signed-off-by: Daniel Henrique Barboza <danielhb413@xxxxxxxxx>
---
docs/formatdomain.html.in | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/docs/formatdomain.html.in b/docs/formatdomain.html.in
index 47e10a836c..932bf8841f 100644
--- a/docs/formatdomain.html.in
+++ b/docs/formatdomain.html.in
@@ -808,6 +808,13 @@
<dd>
The optional <code>cputune</code> element provides details
regarding the CPU tunable parameters for the domain.
+
+ Note: for the qemu driver, the optional <code>vcpupin</code>
+ and <code>emulatorpin</code> pinning settings are honored after
+ the emulator is launched and NUMA constraints considered. This
+ means that it is expected that other physical CPUs of the host
+ will be used during this time by the domain, which will be
+ reflected by the output of <code>virsh cpu-stats</code>.
<span class="since">Since 0.9.0</span>
</dd>
<dt><code>vcpupin</code></dt>
--
2.25.1
