[PATCH v2 0/4] NUMA CPUs 'auto-fill' for incomplete topologies

Michal Privoznik mprivozn at redhat.com
Wed Jun 17 19:19:42 UTC 2020


On 6/10/20 8:35 PM, Daniel Henrique Barboza wrote:
> changes in v2:
> - removed patch 5/5
> 
> Gitlab link: https://gitlab.com/danielhb/libvirt/-/tree/vcpus_numa_v2
> 
> v1 link: https://www.redhat.com/archives/libvir-list/2020-June/msg00016.html
> 
> 
> Daniel Henrique Barboza (4):
>    numa_conf.c: add helper functions for cpumap operations
>    qemu_domain.c: NUMA CPUs auto-fill for incomplete topologies
>    qemuxml2xmltest.c: add NUMA vcpus auto fill tests
>    formatdomain.html.in: document the NUMA cpus auto fill feature
> 
>   docs/formatdomain.html.in                     | 11 ++++-
>   src/conf/numa_conf.c                          | 46 ++++++++++++++++++
>   src/conf/numa_conf.h                          |  3 ++
>   src/libvirt_private.syms                      |  1 +
>   src/qemu/qemu_domain.c                        | 47 +++++++++++++++++++
>   src/qemu/qemu_domain.h                        |  4 ++
>   src/qemu/qemu_driver.c                        |  9 ++++
>   .../numavcpus-topology-mismatch.xml           | 37 +++++++++++++++
>   ...avcpus-topology-mismatch.x86_64-latest.xml | 38 +++++++++++++++
>   tests/qemuxml2xmltest.c                       |  1 +
>   10 files changed, 196 insertions(+), 1 deletion(-)
>   create mode 100644 tests/qemuxml2argvdata/numavcpus-topology-mismatch.xml
>   create mode 100644 tests/qemuxml2xmloutdata/numavcpus-topology-mismatch.x86_64-latest.xml
> 

Patches look good to me.

My only concern is that I plan to introduce vCPU-less NUMA nodes [1] 
(because of HMAT [2]). But I guess if user assigns vCPUs to NUMA nodes 
fully, then we still can have vCPU-less nodes because your code would be 
NOP, right?

Michal

1: https://gitlab.com/MichalPrivoznik/libvirt/-/tree/hmat
2: https://www.redhat.com/archives/libvir-list/2020-January/msg00422.html




More information about the libvir-list mailing list