Given that we think the networking issue is likely due to using 4KB pages instead of hugepages, it would probably make sense to try specifying hugepages first. If that doesn't work, then we can start looking at the nova logs. Chris On 4/4/2019 8:16 AM, Xu, Chenjie wrote:
Hi Chris,
I have reinstalled StarlingX on the 4 bare metals but meet some problems. So I can’t execute your commands now. As soon as I deploy StarlingX successfully, I will execute those command and let you know the result.
Best Regards,
Xu, Chenjie
*From:*Chris Friesen [mailto:chris.friesen@windriver.com] *Sent:* Wednesday, April 3, 2019 11:54 PM *To:* starlingx-discuss@lists.starlingx.io *Subject:* Re: [Starlingx-discuss] OVS-DPDK Upgrade Testing
On 4/2/2019 9:50 AM, Khalil, Ghada wrote:
Thanks Chenjie.
Can you please run the following on your compute nodes and attach the output?
sudo lscpu sudo virsh capabilities
Richardo / Juan P,
Please provide the cpu models and the above output from your two hardware systems as well.
In addition to the above, can you please provide the logs from one of the nova-compute pods on an affected system?
You can get the logs by running :
POD=`kubectl -n openstack get pod -l application=nova,component=compute \
-o=jsonpath='{.items[0].metadata.name'}`
kubectl -n openstack logs -c nova-compute $POD
Thanks,
Chris