[Openstack-operators] Neutron timeout issues

Kris G. Lindgren klindgren at godaddy.com
Wed Feb 25 01:44:42 UTC 2015


Nope, straight mysql.  We do have a replicated master but we only write to
a single master and it's not setup for master-master replication.
____________________________________________
 
Kris Lindgren
Senior Linux Systems Engineer
GoDaddy, LLC.



On 2/24/15, 6:41 PM, "Robert Collins" <robertc at robertcollins.net> wrote:

>On 25 February 2015 at 08:44, Kris G. Lindgren <klindgren at godaddy.com>
>wrote:
>> So an update on this.
>>
>> We dropped neutron API/RPC workers from 60 each on our 3 neutron api
>> servers to 10 workers each.  Since that change the neutron timeouts have
>> dropped to 0.  Under icehouse we were able to run with a 60 workers each
>> without any issues.
>
>Are you running Galera? Perhaps without an haproxy or some such to
>force all writes to one node?
>
>-Rob
>
>
>
>-- 
>Robert Collins <rbtcollins at hp.com>
>Distinguished Technologist
>HP Converged Cloud




More information about the OpenStack-operators mailing list