Hi Evgeniy et al,
On 11/2/17 6:52 am, Evgeniy L wrote:
What version of Fuel do you use?
We started with Mirantis' Fuel, then switched over to the community
version 10, downloaded from https://www.fuel-infra.org/ and currently
using the UCA repositories in our OpenStack deployment.
I'm not
Hi Evgeniy,
I built a repository and added my DKMS deb package into the repository,
then added repository URL and package name into:
1. /etc/fuel-bootstrap-cli/fuel_bootstrap_cli.yaml
2. Fuel UI > Settings > General
3. /usr/lib/python2.7/site-packages/nailgun/fixtures/openstack.yaml
4. /usr/share/
Hi Jonathan,
On your compute host, can you check the configuration in
/etc/ceilometer/pipeline.yaml ?
The default configuration contains :
- name: cpu_source
interval: 600
meters:
- "cpu"
sinks:
- cpu_sink
And
- name: cpu_sink
transformers:
Thanks for the info.For these hosts specifically, NUMA shows a total of 32 cores. Given the way you explained it, I would map something like 2 cpus to dpdk (for a 3gb interface, although I could probably use 1 cpu) and allocate all the remaining 30 cpus for nova usage, correct?Basically, it seems
Hi,
> When a vm is mapped to a flavor using dpdk, do all the vcpus the VM uses
> have to 'pinned' to use dpdk, thus this value means the total number of vcpus
> available to VMs needing dpdk?
>
I don’t think that Nova CPU pinning should be mandated once you choose to use
DPDK on that Compute
