[libvirt] [PATCH v2 14/16] qemu: pass numa node binding preferences to qemu
Michal Privoznik
mprivozn at redhat.com
Fri Jul 11 15:10:49 UTC 2014
On 08.07.2014 13:50, Martin Kletzander wrote:
> Currently, we only bind the whole QEMU domain to memory nodes
> specified in nodemask altogether. That, however, doesn't make much
> sense when one wants to control from where the memory for particular
> guest nodes should be allocated. QEMU allows us to do that by
> specifying 'host-nodes' parameter for the 'memory-backend-ram' object,
> so let's use that.
>
> Signed-off-by: Martin Kletzander <mkletzan at redhat.com>
> ---
> src/qemu/qemu_command.c | 59 +++++++++++++++++++++-
> .../qemuxml2argv-numatune-memnode-no-memory.args | 8 +++
> .../qemuxml2argv-numatune-memnode.args | 11 ++++
> .../qemuxml2argv-numatune-memnode.xml | 14 ++---
> tests/qemuxml2argvtest.c | 7 +++
> 5 files changed, 92 insertions(+), 7 deletions(-)
> create mode 100644 tests/qemuxml2argvdata/qemuxml2argv-numatune-memnode-no-memory.args
> create mode 100644 tests/qemuxml2argvdata/qemuxml2argv-numatune-memnode.args
>
> diff --git a/tests/qemuxml2argvdata/qemuxml2argv-numatune-memnode.xml b/tests/qemuxml2argvdata/qemuxml2argv-numatune-memnode.xml
> index 18b00d8..49b328c 100644
> --- a/tests/qemuxml2argvdata/qemuxml2argv-numatune-memnode.xml
> +++ b/tests/qemuxml2argvdata/qemuxml2argv-numatune-memnode.xml
> @@ -1,12 +1,13 @@
> <domain type='qemu'>
> <name>QEMUGuest</name>
> <uuid>9f4b6512-e73a-4a25-93e8-5307802821ce</uuid>
> - <memory unit='KiB'>65536</memory>
> - <currentMemory unit='KiB'>65536</currentMemory>
> - <vcpu placement='static'>2</vcpu>
> + <memory unit='KiB'>24682468</memory>
> + <currentMemory unit='KiB'>24682468</currentMemory>
> + <vcpu placement='static'>32</vcpu>
> <numatune>
> - <memory mode='strict' nodeset='0-3'/>
> + <memory mode='strict' nodeset='0-7'/>
> <memnode cellid='0' mode='preferred' nodeset='3'/>
> + <memnode cellid='2' mode='strict' nodeset='1-2,5-7,^6'/>
> </numatune>
> <os>
> <type arch='x86_64' machine='pc'>hvm</type>
> @@ -14,8 +15,9 @@
> </os>
> <cpu>
> <numa>
> - <cell id='0' cpus='0' memory='32768'/>
> - <cell id='1' cpus='1' memory='32768'/>
> + <cell id='0' cpus='0' memory='20002'/>
> + <cell id='1' cpus='1-27,29' memory='660066'/>
> + <cell id='2' cpus='28-31,^29' memory='24002400'/>
AHA! This explain why I'm seeing the test error in 8/16. Something went
wrong during the rebase I think. Because now I have to revert the squash
in from 8/16 to make the test work again. Yes, it's failing now.
> </numa>
> </cpu>
> <clock offset='utc'/>
Unfortunately, I can't ACK neither this one (same as I couldn't 8/16).
Michal
More information about the libvir-list
mailing list