Yup, IMHO this is where the rally[1] project, and others that attempt to push the boundaries are really helping openstack become much better around these types of issues. At yahoo! in a short-time it will not be that uncommon to boot 100+ VMs concurrently (traffic spikes, other random QA testing that requires more than 10 instances...). So the earlier these issues get solved then the better it will be for everyone (and they likely are not simple issues to solve, sadly).
[1] https://wiki.openstack.org/wiki/Rally On 12/10/13 10:17 AM, "Edgar Magana" <[email protected]> wrote: >FYI. Concurrent calls are a problem all around in OpenStack! > >Edgar > >On 12/10/13 8:47 AM, "Abhishek Chanda" <[email protected]> wrote: > >>** Changed in: nova >> Status: New => Triaged >> >>-- >>You received this bug notification because you are subscribed to >>neutron. >>https://bugs.launchpad.net/bugs/1257788 >> >>Title: >> nova-network doesn't handle large amount of concurrent booting >> instances well >> >>Status in OpenStack Neutron (virtual network service): >> Triaged >>Status in OpenStack Compute (Nova): >> Triaged >> >>Bug description: >> As seen by the large-ops test nova-network has trouble booting 150 VMs >> concurrently. Part of the problem is that setting up the network for >> each instance is relatively expensive with many locks and root-wrapped >> calls. Both of which significantly hurt performance. One possible fix >> would be to do more bulk network operations when possible, so instead >> of 100 separate calls to a root-wrapped tool call it once. >> >>To manage notifications about this bug go to: >>https://bugs.launchpad.net/neutron/+bug/1257788/+subscriptions > > > >_______________________________________________ >OpenStack-dev mailing list >[email protected] >http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-dev _______________________________________________ OpenStack-dev mailing list [email protected] http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-dev
