| *** igordc has quit IRC | 01:24 | |
| *** bobh has quit IRC | 01:45 | |
| *** bobh has joined #openstack-meeting-4 | 02:13 | |
| *** yamamoto has joined #openstack-meeting-4 | 02:18 | |
| *** bobh has quit IRC | 02:38 | |
| *** bobh has joined #openstack-meeting-4 | 02:39 | |
| *** bobh has quit IRC | 02:39 | |
| *** bobh has joined #openstack-meeting-4 | 02:40 | |
| *** bobh has quit IRC | 02:45 | |
| *** bobh has joined #openstack-meeting-4 | 02:59 | |
| *** bobh has quit IRC | 03:00 | |
| *** bobh has joined #openstack-meeting-4 | 03:01 | |
| *** bobh has quit IRC | 03:01 | |
| *** bobh has joined #openstack-meeting-4 | 03:02 | |
| *** bobh has quit IRC | 03:03 | |
| *** gcheresh has joined #openstack-meeting-4 | 03:04 | |
| *** yamamoto has quit IRC | 03:19 | |
| *** gcheresh has quit IRC | 03:23 | |
| *** gcheresh has joined #openstack-meeting-4 | 03:28 | |
| *** yamamoto has joined #openstack-meeting-4 | 03:29 | |
| *** psachin has joined #openstack-meeting-4 | 03:31 | |
| *** psachin has quit IRC | 03:34 | |
| *** psachin has joined #openstack-meeting-4 | 03:37 | |
| *** cheng1 has quit IRC | 03:41 | |
| *** cheng1 has joined #openstack-meeting-4 | 03:42 | |
| *** psachin has quit IRC | 03:55 | |
| *** gcheresh has quit IRC | 04:15 | |
| *** LXM has joined #openstack-meeting-4 | 04:25 | |
| *** yamamoto has quit IRC | 04:29 | |
| *** yamamoto has joined #openstack-meeting-4 | 04:41 | |
| *** davee_ has quit IRC | 05:03 | |
| *** davee_ has joined #openstack-meeting-4 | 05:03 | |
| *** Luzi has joined #openstack-meeting-4 | 05:06 | |
| *** gcheresh has joined #openstack-meeting-4 | 05:14 | |
| *** radeks has joined #openstack-meeting-4 | 05:35 | |
| *** e0ne has joined #openstack-meeting-4 | 05:41 | |
| *** radeks has quit IRC | 05:49 | |
| *** radeks has joined #openstack-meeting-4 | 05:49 | |
| *** e0ne has quit IRC | 06:11 | |
| *** links has joined #openstack-meeting-4 | 06:32 | |
| *** slaweq has joined #openstack-meeting-4 | 06:58 | |
| *** janki has joined #openstack-meeting-4 | 07:02 | |
| *** cheng1 has quit IRC | 07:31 | |
| *** LXM has quit IRC | 07:31 | |
| *** pcaruana has joined #openstack-meeting-4 | 07:31 | |
| *** cheng1 has joined #openstack-meeting-4 | 07:33 | |
| *** jchhatbar has joined #openstack-meeting-4 | 07:34 | |
| *** janki has quit IRC | 07:38 | |
| *** iyamahat has joined #openstack-meeting-4 | 07:39 | |
| *** jchhatbar has quit IRC | 07:46 | |
| *** jchhatbar has joined #openstack-meeting-4 | 07:50 | |
| *** lpetrut has joined #openstack-meeting-4 | 07:51 | |
| *** ralonsoh has joined #openstack-meeting-4 | 08:08 | |
| *** ktibi has joined #openstack-meeting-4 | 08:18 | |
| *** lemko has joined #openstack-meeting-4 | 08:42 | |
| *** gkadam has joined #openstack-meeting-4 | 08:44 | |
| *** janki has joined #openstack-meeting-4 | 08:45 | |
| *** jchhatbar has quit IRC | 08:45 | |
| *** k_mouza has joined #openstack-meeting-4 | 08:55 | |
| *** lpetrut has quit IRC | 08:58 | |
| *** e0ne has joined #openstack-meeting-4 | 09:08 | |
| *** jchhatbar has joined #openstack-meeting-4 | 09:10 | |
| *** janki has quit IRC | 09:10 | |
| *** trident has quit IRC | 09:16 | |
| *** trident has joined #openstack-meeting-4 | 09:17 | |
| *** zhipeng[m] has quit IRC | 09:22 | |
| *** yamamoto has quit IRC | 09:23 | |
| *** altlogbot_0 has quit IRC | 09:24 | |
| *** yamamoto has joined #openstack-meeting-4 | 09:24 | |
| *** altlogbot_0 has joined #openstack-meeting-4 | 09:25 | |
| *** yamamoto has quit IRC | 09:27 | |
| *** yamamoto has joined #openstack-meeting-4 | 09:29 | |
| *** zhipeng[m] has joined #openstack-meeting-4 | 09:31 | |
| *** yamamoto has quit IRC | 09:41 | |
| *** yamamoto has joined #openstack-meeting-4 | 09:49 | |
| *** jraju__ has joined #openstack-meeting-4 | 10:37 | |
| *** links has quit IRC | 10:38 | |
| *** gkadam has quit IRC | 11:02 | |
| *** lpetrut has joined #openstack-meeting-4 | 11:07 | |
| *** gkadam has joined #openstack-meeting-4 | 11:17 | |
| *** links has joined #openstack-meeting-4 | 11:33 | |
| *** jraju__ has quit IRC | 11:34 | |
| *** gkadam has quit IRC | 11:42 | |
| *** gkadam has joined #openstack-meeting-4 | 11:44 | |
| *** abhishekk has joined #openstack-meeting-4 | 11:54 | |
| *** yamamoto has quit IRC | 12:44 | |
| *** yamamoto has joined #openstack-meeting-4 | 12:45 | |
| *** bh526r has joined #openstack-meeting-4 | 12:45 | |
| *** jroll has quit IRC | 13:07 | |
| *** jroll has joined #openstack-meeting-4 | 13:08 | |
| *** jchhatbar has quit IRC | 13:15 | |
| *** yamamoto has quit IRC | 13:57 | |
| *** cheng1 has quit IRC | 13:58 | |
| *** aperevalov has joined #openstack-meeting-4 | 13:58 | |
| *** dklyle has quit IRC | 14:00 | |
| *** dklyle has joined #openstack-meeting-4 | 14:00 | |
| dulek | #startmeeting Kuryr | 14:00 |
|---|---|---|
| openstack | Meeting started Mon Jul 29 14:00:33 2019 UTC and is due to finish in 60 minutes. The chair is dulek. Information about MeetBot at http://wiki.debian.org/MeetBot. | 14:00 |
| openstack | Useful Commands: #action #agreed #help #info #idea #link #topic #startvote. | 14:00 |
| *** openstack changes topic to " (Meeting topic: Kuryr)" | 14:00 | |
| openstack | The meeting name has been set to 'kuryr' | 14:00 |
| dulek | Well, it's been a few weeks since I run this. Sorry about that, crazy time with some deadlines for other projects. | 14:01 |
| *** cheng1 has joined #openstack-meeting-4 | 14:01 | |
| dulek | There are a few things that's going to change for Kuryr, so here they are. | 14:01 |
| dulek | First of all dmellado cannot be involved too much in the project, so me and ltomasbo are probably the go-to people here. I should probably figure out how to do a PTL change during the cycle to make sure all the formal things are ironed out. | 14:03 |
| ltomasbo | o/ | 14:04 |
| aperevalov | o/ | 14:04 |
| dulek | Second of all there's not a lot activity in those meetings, so I'd probably vote to switch to the office hours model, when this time during the week we'll simply welcome any questions on the #openstack-kuryr. | 14:04 |
| dulek | Any thoughts on that? | 14:05 |
| dulek | If there's none and we're here, I guess aperevalov can talk a bit about improve-pod-launch-time blueprint? | 14:05 |
| aperevalov | no problem, it's ok for us. | 14:05 |
| aperevalov | yes, it's a problem for us, I guess it's not problem for your, due to you are using ovn. | 14:06 |
| dulek | aperevalov: Well, not really, we're mostly running nested. | 14:07 |
| dulek | In that case ports are immediately ACTIVE, so the time is cut. | 14:07 |
| dulek | aperevalov: But I totally agree there's room for improvement. | 14:08 |
| aperevalov | nested - means you are plugging port to nova-instance? | 14:08 |
| dulek | aperevalov: Yup - trunk ports and subports. | 14:09 |
| dulek | Pods get the subports. | 14:09 |
| aperevalov | dulek, thanks | 14:09 |
| aperevalov | there are several parts in that blueprint. The first part about direct RPC (kuryr-controller - kuryr-daemon). Which probably should be faster than doing it through k8s. | 14:09 |
| aperevalov | and keep storing states into k8s, for fallback. | 14:10 |
| dulek | aperevalov: So we had some ideas about that in the past, I even crafted some code. | 14:10 |
| dulek | aperevalov: First of all… Are you using port pools? | 14:10 |
| aperevalov | yes, | 14:10 |
| aperevalov | we measured it, in bm case - 2x times faster | 14:11 |
| dulek | aperevalov: Direct? | 14:11 |
| aperevalov | yes, it was direct ports, but we still waiting for neutron's status Active. | 14:11 |
| *** cheng1 has quit IRC | 14:12 | |
| aperevalov | and than more ports we requested than more waiting time interval | 14:12 |
| dulek | aperevalov: Hm, okay, I don't think I'm immediately against direct communication. | 14:13 |
| dulek | We would just need to make sure we're not abusing some K8s paradigms. | 14:13 |
| aperevalov | it also depends on openstack controller performance | 14:13 |
| dulek | aperevalov: But here's an idea we had a long while ago. I think it addresses all the issues you list in the blueprint. | 14:14 |
| dulek | aperevalov: So basically we wanted to extend the port pools concept. | 14:14 |
| aperevalov | do you have a blueprint for it? | 14:14 |
| dulek | aperevalov: As we have host in the pool key, pools are already "attached" to a kuryr-daemon. | 14:14 |
| *** cheng1 has joined #openstack-meeting-4 | 14:14 | |
| dulek | aperevalov: Yes, just a sec… | 14:14 |
| dulek | aperevalov: https://blueprints.launchpad.net/kuryr-kubernetes/+spec/daemon-pool-port-choice | 14:15 |
| aperevalov | so, do you want to do "prebind" ports | 14:15 |
| aperevalov | wait a minute, I'm reading | 14:15 |
| dulek | Yup, that was part of the idea. | 14:15 |
| dulek | aperevalov: So the idea is that kuryr-controller would create ports for the pools and for each port create KuryrPort CRD. | 14:15 |
| dulek | aperevalov: kuryr-daemon would watch for those and choose the ports on their own. So if there are ports in the pool - daemon won't wait for kuryr-controller at all. | 14:16 |
| dulek | aperevalov: Then another improvement would be to "pre-bind" ports, so they become ACTIVE in Neutron even before pods get created. Then on the "real" binding only the interface gets moved to another netns. | 14:17 |
| aperevalov | if I truly understand you, all ports from such pool will be with ACTIVE status | 14:19 |
| dulek | aperevalov: Yup, so we won't wait for that. | 14:20 |
| dulek | aperevalov: Does this make any sense for you? I had some POC, it's listed on the blueprint. | 14:21 |
| dulek | While it was working okay, I haven't noticed much performance improvement back then. | 14:22 |
| dulek | But probably I made some mistakes somewhere in there. | 14:22 |
| *** michael-beaver has joined #openstack-meeting-4 | 14:23 | |
| aperevalov | but technically, e.g. neutron-openvswitch-agent - it's a controller for ports in ovs, it responsible for openflow rules and it set that rules when/after we attached tap into ovs. So you propose to create ovs port (osvif->plug) in batch, before real pod launch happend. | 14:23 |
| dulek | aperevalov: Yep, that was the idea. It was attaching those ports to a fake network namespace. | 14:24 |
| dulek | aperevalov: And on pod creation that port was moved to pod namespace. | 14:24 |
| aperevalov | looks like it will work with SR-IOV too, but in none pool mode we still have to wait for neutron updates. | 14:25 |
| dulek | aperevalov: Yes, that idea doesn't really have a lot of sense without pools. | 14:27 |
| aperevalov | we tried to improve wait mechanism, so please review https://review.opendev.org/#/c/669642/ ) | 14:27 |
| *** yamamoto has joined #openstack-meeting-4 | 14:27 | |
| dulek | aperevalov: This seems to be broken for containerized case? | 14:29 |
| dulek | Hm, maybe just a coincidence. | 14:30 |
| aperevalov | do you mean containerized kuryr? no, no, we checked it in containerized case. | 14:30 |
| aperevalov | this test kuryr-kubernetes-tempest-containerized passed | 14:31 |
| dulek | aperevalov: I see. Okay, I'll take a look, but I'm not totally convinced as it's pretty unusual case when you have access to RabbitMQ from Kuryr point. | 14:32 |
| dulek | aperevalov: That would only happen in clouds you manage. If you wanted to run Kubernetes + Kuryr on any OpenStack public cloud, that would not work. | 14:32 |
| aperevalov | ok, in this case kuryr will work as before, by request. | 14:33 |
| dulek | aperevalov: I see it's failing back to that, sure. | 14:34 |
| aperevalov | Fallback method should be invisible | 14:34 |
| dulek | aperevalov: Yes, yes, I see. | 14:35 |
| dulek | aperevalov: Okay, I'll take a look on that patch. Will you think about that daemon-pool-port-choice? It seems to be a bit more Kubernetes-style than to just allow direct communication. | 14:36 |
| aperevalov | it's a nice idea, who will finish implementation? We have resources for this... | 14:38 |
| *** yamamoto has quit IRC | 14:38 | |
| dulek | aperevalov: I'm pretty sure me, ltomasbo and Maysa are unable to work on that now. | 14:39 |
| dulek | So if you think it would help your use case - I'd be super happy if you can grab it. | 14:39 |
| *** yamamoto has joined #openstack-meeting-4 | 14:39 | |
| *** lpetrut has quit IRC | 14:39 | |
| aperevalov | ok, this review https://review.opendev.org/#/c/527243 was about it, wasn't it? | 14:41 |
| *** happyhemant has joined #openstack-meeting-4 | 14:42 | |
| dulek | aperevalov: Yes, but it's probably super outdated. | 14:42 |
| dulek | aperevalov: Back then we had some issue with CRD's support, but that's definitely fixed by now. | 14:43 |
| dulek | aperevalov: K8s API wasn't working as it should when using CRD's. | 14:43 |
| *** yamamoto has quit IRC | 14:44 | |
| dulek | Okay, I guess I'll just close the meeting. Thanks all! | 14:49 |
| aperevalov | Thanks!!! | 14:49 |
| dulek | #endmeeting | 14:50 |
| *** openstack changes topic to "OpenStack Meetings || https://wiki.openstack.org/wiki/Meetings/" | 14:50 | |
| openstack | Meeting ended Mon Jul 29 14:50:20 2019 UTC. Information about MeetBot at http://wiki.debian.org/MeetBot . (v 0.1.4) | 14:50 |
| openstack | Minutes: http://eavesdrop.openstack.org/meetings/kuryr/2019/kuryr.2019-07-29-14.00.html | 14:50 |
| openstack | Minutes (text): http://eavesdrop.openstack.org/meetings/kuryr/2019/kuryr.2019-07-29-14.00.txt | 14:50 |
| openstack | Log: http://eavesdrop.openstack.org/meetings/kuryr/2019/kuryr.2019-07-29-14.00.log.html | 14:50 |
| *** belmoreira has joined #openstack-meeting-4 | 14:51 | |
| *** gcheresh has quit IRC | 15:00 | |
| *** Luzi has quit IRC | 15:06 | |
| *** radeks_ has joined #openstack-meeting-4 | 15:11 | |
| *** radeks has quit IRC | 15:14 | |
| *** jamesgu has joined #openstack-meeting-4 | 15:16 | |
| *** e0ne has quit IRC | 15:30 | |
| *** links has quit IRC | 15:56 | |
| *** ktibi has quit IRC | 16:03 | |
| *** belmoreira has quit IRC | 16:05 | |
| *** diablo_rojo has joined #openstack-meeting-4 | 16:23 | |
| *** bh526r has quit IRC | 16:25 | |
| *** igordc has joined #openstack-meeting-4 | 16:59 | |
| *** happyhemant has quit IRC | 17:12 | |
| *** e0ne has joined #openstack-meeting-4 | 17:14 | |
| *** e0ne has quit IRC | 17:20 | |
| *** ralonsoh has quit IRC | 17:25 | |
| *** radeks_ has quit IRC | 17:31 | |
| *** trident has quit IRC | 17:47 | |
| *** trident has joined #openstack-meeting-4 | 17:51 | |
| *** lemko has quit IRC | 18:14 | |
| *** abhishekk has quit IRC | 18:44 | |
| *** e0ne has joined #openstack-meeting-4 | 19:22 | |
| *** yamamoto has joined #openstack-meeting-4 | 19:25 | |
| *** k_mouza has quit IRC | 19:26 | |
| *** yamamoto has quit IRC | 19:32 | |
| *** radeks_ has joined #openstack-meeting-4 | 19:41 | |
| *** iyamahat has quit IRC | 19:42 | |
| *** belmoreira has joined #openstack-meeting-4 | 20:09 | |
| *** k_mouza has joined #openstack-meeting-4 | 20:11 | |
| *** lemko has joined #openstack-meeting-4 | 20:30 | |
| *** slaweq has quit IRC | 20:35 | |
| *** radeks_ has quit IRC | 20:38 | |
| *** e0ne has quit IRC | 20:46 | |
| *** trident has quit IRC | 20:49 | |
| *** trident has joined #openstack-meeting-4 | 20:52 | |
| *** k_mouza has quit IRC | 21:04 | |
| *** belmoreira has quit IRC | 21:17 | |
| *** iyamahat has joined #openstack-meeting-4 | 21:57 | |
| *** k_mouza has joined #openstack-meeting-4 | 22:05 | |
| *** yamahata has joined #openstack-meeting-4 | 22:13 | |
| *** k_mouza has quit IRC | 22:20 | |
| *** davee_ has quit IRC | 22:25 | |
| *** davee_ has joined #openstack-meeting-4 | 22:26 | |
| *** michael-beaver has quit IRC | 22:32 | |
| *** diablo_rojo has quit IRC | 22:45 | |
| *** diablo_rojo has joined #openstack-meeting-4 | 22:52 | |
| *** yamahata has quit IRC | 23:12 | |
| *** lemko has quit IRC | 23:13 | |
| *** diablo_rojo has quit IRC | 23:48 | |
Generated by irclog2html.py 2.15.3 by Marius Gedminas - find it at mg.pov.lt!