| *** rfolco has quit IRC | 01:47 | |
| *** zz_dimtruck is now known as dimtruck | 03:53 | |
| *** dimtruck is now known as zz_dimtruck | 04:53 | |
| *** ilyashakhat has joined #openstack-performance | 05:27 | |
| *** ilyashakhat has quit IRC | 06:14 | |
| *** ilyashakhat has joined #openstack-performance | 06:21 | |
| *** pcaruana has joined #openstack-performance | 06:26 | |
| *** ilyashakhat has quit IRC | 06:38 | |
| *** ilyashakhat has joined #openstack-performance | 06:48 | |
| *** ilyashakhat has quit IRC | 06:51 | |
| *** ad_rien_ has quit IRC | 07:07 | |
| *** rmart04 has joined #openstack-performance | 07:20 | |
| *** ad_rien_ has joined #openstack-performance | 07:35 | |
| *** msimonin has joined #openstack-performance | 09:01 | |
| *** bvanhav has joined #openstack-performance | 11:27 | |
| *** rfolco has joined #openstack-performance | 11:57 | |
| *** markvoelker has joined #openstack-performance | 12:52 | |
| *** claudiub has joined #openstack-performance | 12:54 | |
| openstackgerrit | Sergey Galkin proposed openstack/performance-docs: Add info about 378 nodes testing https://review.openstack.org/362246 | 13:11 |
|---|---|---|
| *** markvoelker has quit IRC | 13:17 | |
| *** markvoelker has joined #openstack-performance | 13:40 | |
| *** markvoelker has quit IRC | 13:45 | |
| *** zz_dimtruck is now known as dimtruck | 13:48 | |
| *** hockeynut has joined #openstack-performance | 14:03 | |
| *** dimtruck is now known as zz_dimtruck | 14:04 | |
| *** zz_dimtruck is now known as dimtruck | 14:23 | |
| *** ilyashakhat has joined #openstack-performance | 14:53 | |
| *** AnarchyAo has joined #openstack-performance | 14:56 | |
| *** ilyashakhat has quit IRC | 15:02 | |
| *** rmart04 has quit IRC | 15:10 | |
| *** AugieMena has joined #openstack-performance | 15:26 | |
| *** rohanion has joined #openstack-performance | 15:27 | |
| *** rcherrueau has joined #openstack-performance | 15:28 | |
| DinaBelova | #startmeeting Performance Team | 15:30 |
| openstack | Meeting started Tue Aug 30 15:30:02 2016 UTC and is due to finish in 60 minutes. The chair is DinaBelova. Information about MeetBot at http://wiki.debian.org/MeetBot. | 15:30 |
| openstack | Useful Commands: #action #agreed #help #info #idea #link #topic #startvote. | 15:30 |
| openstack | The meeting name has been set to 'performance_team' | 15:30 |
| DinaBelova | hey folks :) | 15:30 |
| AugieMena | hey | 15:30 |
| ad_rien_ | hi | 15:30 |
| DinaBelova | hope new time will be more comfortable :) | 15:30 |
| DinaBelova | rohanion msimonin o/ | 15:30 |
| DinaBelova | let's wait for a few moments :) | 15:30 |
| msimonin | Hey, hello :) | 15:31 |
| DinaBelova | so let's get started with action items | 15:31 |
| DinaBelova | #topic Action Items | 15:31 |
| DinaBelova | last time we had only one in fact: find out what's slowing down OpenStack REST APIs in the Inria 1000 nodes experiment | 15:32 |
| msimonin | yes | 15:32 |
| DinaBelova | msimonin rcherrueau afaiu the issue was in DB settings? | 15:32 |
| msimonin | yes it was | 15:32 |
| msimonin | kolla deployment configure the mariadb with galera replication out of the box | 15:32 |
| msimonin | in our primary tests we only have 1 mariadb instance | 15:33 |
| rohanion | hiii | 15:33 |
| DinaBelova | msimonin yep, to have comparable stuff | 15:33 |
| DinaBelova | ok, so you found what was the difference even without any help :) | 15:33 |
| DinaBelova | rohanion o/ | 15:33 |
| DinaBelova | so we can jump to the nice part :) | 15:34 |
| DinaBelova | #topic Upcoming summit | 15:34 |
| rook | o/ | 15:34 |
| DinaBelova | so from what I know: 1000 nodes emulation testing sesison was approved | 15:34 |
| DinaBelova | lemme find a link | 15:34 |
| DinaBelova | #link https://www.openstack.org/summit/barcelona-2016/summit-schedule/events/15977/chasing-1000-nodes-scale | 15:35 |
| DinaBelova | so this means msimonin and Alex and I are going to have funny time preparing :) | 15:35 |
| msimonin | yes :) | 15:35 |
| ad_rien_ | rcherrueau should contribute too | 15:35 |
| DinaBelova | ad_rien_ ack | 15:36 |
| ad_rien_ | (even if his name does not appear ;) ) | 15:36 |
| DinaBelova | regarding the separated time slot for performance team discussions: WG sessions were not yet approved, although as technically we're part of LDT we may not capture separated slot as we were lucky to do last summit | 15:36 |
| msimonin | Is there any other talk accepted for the performance WG ? | 15:36 |
| DinaBelova | not that I know about | 15:37 |
| DinaBelova | :) | 15:37 |
| DinaBelova | so going back to the WG stuff: as we're part of LDT, we may not have separated slot | 15:38 |
| ad_rien_ | What do you mean ? | 15:38 |
| DinaBelova | so I wonder if LDT will give us some time to present the results and collect feedback | 15:38 |
| DinaBelova | klindgren ? ^^ | 15:38 |
| ad_rien_ | ok | 15:38 |
| klindgren | so | 15:38 |
| DinaBelova | klindgren do you think it's possible? | 15:39 |
| klindgren | I think our schedulue is fairly open right now. | 15:39 |
| ad_rien_ | What is your idea DinaBelova ? you would like to present twice ? | 15:39 |
| DinaBelova | klindgren ok, so I just want to have some backup variant if separated session/time slot won't be available | 15:39 |
| ad_rien_ | Or you plan to give a more synthetic presentation just for the LDT WG? | 15:40 |
| DinaBelova | ad_rien_ the thing is that official talk != design summit | 15:40 |
| DinaBelova | and usual discussions | 15:40 |
| ad_rien_ | yes | 15:40 |
| DinaBelova | + 1000 nodes is only one set of tests | 15:40 |
| DinaBelova | from what would be done | 15:40 |
| ad_rien_ | but we can expect that LDT key persons will attend the ''official'' presentation ? | 15:40 |
| DinaBelova | so sharing the whole status will be nice I think | 15:40 |
| klindgren | I think that should be fine. I haven't looked at the schedule to see the LDT sloted times. | 15:40 |
| DinaBelova | ad_rien_ this depends much on the schedule (that's not defined yet :)) | 15:41 |
| DinaBelova | klindgren I did not see these slots being added and defined yet | 15:41 |
| DinaBelova | klindgren that's the issue :) | 15:41 |
| DinaBelova | klindgren so I have 0 idea on if my slot separated request for performance team was accepted or not :) | 15:42 |
| DinaBelova | and that's also an issue :D | 15:42 |
| klindgren | Ah I - C | 15:43 |
| DinaBelova | #info right now schedule is not yet finalized, not clear if performance team will gather the separated time slot for discussions, or we can present our results using small part of LDT time slot: LDT agenda is fairly open right now | 15:43 |
| DinaBelova | ok, so that's pretty all I know about upcoming summit in terms of performance team :) | 15:44 |
| DinaBelova | does someone know something else? | 15:44 |
| DinaBelova | it looks like nope :) | 15:45 |
| AugieMena | fyi, someone from my team (Chris Kirkland) had a performance presentation accepted | 15:45 |
| DinaBelova | rook AugieMena ? | 15:45 |
| AugieMena | #link ttps://www.openstack.org/summit/barcelona-2016/summit-schedule/global-search?t=nova+scheduler | 15:45 |
| rook | We have a Performance talk accepted as well /me gets link | 15:45 |
| DinaBelova | rook ack | 15:45 |
| DinaBelova | #link https://www.openstack.org/summit/barcelona-2016/summit-schedule/events/15424/a-nova-scheduler-for-public-cloud-scale | 15:45 |
| rook | #link https://www.openstack.org/summit/barcelona-2016/summit-schedule/events/15279 | 15:46 |
| DinaBelova | rook ack, thanks :) | 15:46 |
| DinaBelova | so we have some summit agenda already defined :) | 15:46 |
| DinaBelova | btw, folks, who's going to attend the summit? | 15:47 |
| ad_rien_ | o/ | 15:47 |
| DinaBelova | msimonin I suppose you'll, and what's about rcherrueau ? | 15:47 |
| DinaBelova | ad_rien_ ;) | 15:47 |
| ad_rien_ | should be there too | 15:47 |
| DinaBelova | ok, cool, that's nice | 15:47 |
| DinaBelova | AugieMena, rook ? | 15:48 |
| rcherrueau | yep | 15:48 |
| AugieMena | I won't be there, but Chris will | 15:48 |
| rook | xnegative | 15:48 |
| DinaBelova | AugieMena ack, thanks for letting know | 15:48 |
| rook | I do have a bunch of people from my team attending | 15:48 |
| rook | Too close to the birth of my second son :) | 15:48 |
| DinaBelova | rook wow, congratulations on upcoming EVENT | 15:48 |
| rook | thanks! | 15:49 |
| AugieMena | congrats rook... also close to the birth of my first grandson :) | 15:49 |
| DinaBelova | ahaha, it's an epidemic :) | 15:49 |
| DinaBelova | ok, so it looks like we may proceed | 15:50 |
| DinaBelova | #topic Current progress on the planned tests | 15:50 |
| DinaBelova | msimonin rcherrueau may you please start? | 15:50 |
| msimonin | yes sure | 15:50 |
| msimonin | so with rcherrueau we deployed a 1000 compute nodes openstack | 15:51 |
| msimonin | to make some premilinary tests and validate our experiment workflow | 15:51 |
| msimonin | as we said before with the patch on the mariadb cofiguration, things were better | 15:51 |
| DinaBelova | ok, so it looks like you're having nice progress | 15:52 |
| DinaBelova | that's really cool | 15:52 |
| *** victorhe has joined #openstack-performance | 15:52 | |
| DinaBelova | msimonin thanks | 15:52 |
| msimonin | moreover :) | 15:52 |
| msimonin | Next week we will try different topologies | 15:52 |
| msimonin | with this 1000 computes (fake driver) | 15:53 |
| msimonin | like adding more controllers | 15:53 |
| msimonin | maybe we should discuss what could be relevant ? | 15:53 |
| DinaBelova | msimonin good idea | 15:53 |
| msimonin | because actually I discussed briefly with Steve Dake | 15:54 |
| msimonin | from Kolla | 15:54 |
| msimonin | and they are making some experimentation as well using a kolla deployed openstack and a set of rally benchmarks | 15:55 |
| DinaBelova | msimonin ok, any insights from them? | 15:55 |
| msimonin | let me share a link | 15:56 |
| msimonin | #link https://etherpad.openstack.org/p/kolla-N-midcycle-osic | 15:56 |
| * DinaBelova trying to find the deployment topology in the doc | 15:57 | |
| msimonin | line 35 | 15:57 |
| msimonin | for the first scenario | 15:57 |
| DinaBelova | a-ha, I see | 15:57 |
| DinaBelova | and what's meant by controller in this case btw? | 15:58 |
| msimonin | in the kolla terminology | 15:58 |
| msimonin | control = nova-[api|scheduler], horizon, rabbitmq, mariadb, keystone | 15:59 |
| DinaBelova | I'm asking as personally from what we've seen several control plane components need to be removed from controller nodes to separated ones if we're going up with scale (rabbitmq, mysql, conductor, neutron server, keystone) | 15:59 |
| DinaBelova | so for their case (130 nodes) just all-in-one controller should be ok | 15:59 |
| DinaBelova | but for 1000+ nodes scale I believe something needs to be separated | 16:00 |
| *** AugieMena has quit IRC | 16:00 | |
| msimonin | yes 1 control should be able to handle 100 compute node scale | 16:00 |
| msimonin | yes actually that's the purpose of the experiment I'd like to conduct next week | 16:00 |
| msimonin | having separated DB, rabbitmq, conductor, … | 16:01 |
| DinaBelova | and see how it'll go :) | 16:01 |
| DinaBelova | that's nice, thanks from doing this :) | 16:01 |
| msimonin | To your knowledge is their some similar evaluation in the Openstack community , | 16:02 |
| msimonin | ? | 16:02 |
| DinaBelova | msimonin I know operators were discussing the deployment topologies. LDT in particular | 16:02 |
| DinaBelova | and everyone is having it's own opinion on this :) | 16:03 |
| msimonin | I can imagine easily :) | 16:03 |
| DinaBelova | so we can just measure the numbers and present them and create some recommendations - but HOW to do it it's still up to operator | 16:03 |
| DinaBelova | and sometimes there are internal reasons not to follow these recommendations :) | 16:04 |
| ad_rien_ | Maybe we can add such a point in the agenda of the working session in Barcelona | 16:04 |
| DinaBelova | ad_rien_ good point | 16:04 |
| ad_rien_ | we have different scenarios in mind @Inria | 16:04 |
| ad_rien_ | the one msimonin explained and also somes that include regions/multi sites deployments | 16:04 |
| DinaBelova | #info let's go thorough 1000 nodes experiment result on Barcelona summit and present the deployment recommendations we'll come up with as a result of it | 16:05 |
| DinaBelova | ad_rien_ ack | 16:05 |
| DinaBelova | ok, so from Mirantis side: we have finished 400 nodes control plane / dataplane test runs, currently collecting the results | 16:06 |
| DinaBelova | the thing is that in fact due to several hw issues it were 378 nodes, not 400 :( | 16:06 |
| DinaBelova | but we decided not to wait till they will be fixed and run tests now | 16:06 |
| DinaBelova | if we'll be able, we'll rerun them on 500 nodes at the end of sept | 16:06 |
| DinaBelova | so what's upcoming: k8s + fuel-ccp (containerized control plane) evaluation, 1000 nodes emulation on 250 nodes | 16:07 |
| DinaBelova | as for the first item: it's something requested by Mirantis folks, who are working on fuel-ccp and and k8s, so we're interested on how k8s itself and openstack on top of it can scale | 16:08 |
| *** Odoylero0lz has joined #openstack-performance | 16:08 | |
| ad_rien_ | could you please clarify | 16:08 |
| ad_rien_ | I'm bit lost: | 16:08 |
| ad_rien_ | k8s + fuel ccp | 16:09 |
| ad_rien_ | are you deploying VMs or containers to emulate your 1000 nodes ? | 16:09 |
| DinaBelova | ad_rien_ there is much effort here in Mirantis is spent on containeraized OpenStack development | 16:09 |
| ad_rien_ | ok | 16:09 |
| DinaBelova | and we (as scale team inside Mirantis) got a request to try it | 16:09 |
| ad_rien_ | ok | 16:09 |
| ad_rien_ | I'm just trying to understand | 16:10 |
| ad_rien_ | how are you emulating your 1000 nodes on top of 250 physical servers | 16:10 |
| DinaBelova | ad_rien_ so that's something I was going to talk about now | 16:10 |
| ad_rien_ | cool | 16:10 |
| DinaBelova | last time on small lab we used containers for this purpose | 16:10 |
| DinaBelova | this time we really wanted to have non-fake driver | 16:11 |
| DinaBelova | so we have several options now: use kolla/ccp for this purpose (on top of 1000 vms run against 250 nodes) or just fuel (again, on top of 1000 vms) | 16:11 |
| DinaBelova | due to the fact we're pushed to use ccp, we're currently evaluating it on small scale | 16:12 |
| DinaBelova | and we'll see what will be chosen in next 2 weeks or so | 16:12 |
| DinaBelova | ad_rien_ this is much about politics and what's more useful for Mirantis as a company, but I really hope we'll grad these 1000 nodes cluster :D | 16:13 |
| DinaBelova | grab* | 16:14 |
| DinaBelova | so the main moment: we think there will be enough HW to run these 1000 nodes with usual libvirt Nova driver, not fake one | 16:14 |
| ad_rien_ | ok | 16:14 |
| ad_rien_ | it's clear thanks | 16:14 |
| DinaBelova | and see how the picture will change comparing with what we've done previously on small lab with fake river | 16:15 |
| DinaBelova | ok, cool | 16:15 |
| DinaBelova | so it looks like we can jump to the OSprofiler | 16:15 |
| DinaBelova | #topic OSProfiler weekly update | 16:15 |
| DinaBelova | rohanion the floor is yours :) | 16:15 |
| rohanion | ok cool | 16:15 |
| rohanion | I'm still working on a script that changes the config files and restarts the services | 16:16 |
| rohanion | will finish it by the end of today | 16:16 |
| rohanion | nothing besides that, unfortunately :( | 16:17 |
| DinaBelova | rohanion you are about automation of osprofiler usage on Fuel-installed clouds? | 16:17 |
| rohanion | yes | 16:17 |
| DinaBelova | rohanion ack, thanks | 16:17 |
| rohanion | but it will work with vanilla OS too | 16:18 |
| DinaBelova | rohanion ok, thanks for mentioning this :) | 16:18 |
| rohanion | I decided not to work with hiera and detect the role based on the services | 16:18 |
| DinaBelova | rohanion any updates from Alex? (I know he could not attend today meeting) | 16:19 |
| rohanion | No, he switched to another project | 16:19 |
| rohanion | afair | 16:19 |
| DinaBelova | rohanion ack | 16:20 |
| DinaBelova | #topic Open Discussion | 16:20 |
| DinaBelova | so do we have something else to cover? | 16:20 |
| DinaBelova | it looks like nope :) | 16:21 |
| DinaBelova | thanks everyone for participating :) | 16:21 |
| DinaBelova | bye! | 16:21 |
| ad_rien_ | bye | 16:21 |
| DinaBelova | #endmeeting | 16:21 |
| msimonin | Bye | 16:21 |
| openstack | Meeting ended Tue Aug 30 16:21:28 2016 UTC. Information about MeetBot at http://wiki.debian.org/MeetBot . (v 0.1.4) | 16:21 |
| openstack | Minutes: http://eavesdrop.openstack.org/meetings/performance_team/2016/performance_team.2016-08-30-15.30.html | 16:21 |
| openstack | Minutes (text): http://eavesdrop.openstack.org/meetings/performance_team/2016/performance_team.2016-08-30-15.30.txt | 16:21 |
| openstack | Log: http://eavesdrop.openstack.org/meetings/performance_team/2016/performance_team.2016-08-30-15.30.log.html | 16:21 |
| *** rohanion has quit IRC | 16:25 | |
| *** rcherrueau has quit IRC | 16:25 | |
| *** msimonin has quit IRC | 16:25 | |
| openstackgerrit | Sergey Galkin proposed openstack/performance-docs: Add results for 400 nodes control plane testing https://review.openstack.org/362246 | 16:28 |
| *** hockeynut has quit IRC | 16:33 | |
| *** hieulq_ has joined #openstack-performance | 17:02 | |
| *** ilyashakhat has joined #openstack-performance | 17:04 | |
| *** hieulq_ has quit IRC | 17:19 | |
| *** pcaruana has quit IRC | 17:25 | |
| *** victorhe has quit IRC | 17:27 | |
| *** hockeynut has joined #openstack-performance | 17:42 | |
| *** markvoelker has joined #openstack-performance | 17:54 | |
| *** ad_rien_ has quit IRC | 18:09 | |
| *** markvoelker has quit IRC | 18:22 | |
| *** ilyashakhat has quit IRC | 18:34 | |
| *** dmitryme has quit IRC | 18:52 | |
| *** dimtruck is now known as zz_dimtruck | 18:54 | |
| *** dmitryme has joined #openstack-performance | 18:57 | |
| *** zz_dimtruck is now known as dimtruck | 19:06 | |
| *** ilyashakhat has joined #openstack-performance | 19:08 | |
| *** ilyashakhat has quit IRC | 19:20 | |
| *** ilyashakhat has joined #openstack-performance | 19:36 | |
| *** bvanhav has quit IRC | 19:41 | |
| *** hockeynut has quit IRC | 19:49 | |
| *** harlowja has quit IRC | 19:58 | |
| *** msimonin has joined #openstack-performance | 19:58 | |
| *** ilyashakhat has quit IRC | 20:41 | |
| *** ilyashakhat has joined #openstack-performance | 20:53 | |
| *** ilyashakhat has quit IRC | 20:56 | |
| *** ad_rien_ has joined #openstack-performance | 20:57 | |
| *** harlowja has joined #openstack-performance | 21:17 | |
| *** hockeynut has joined #openstack-performance | 21:17 | |
| *** rfolco has quit IRC | 21:29 | |
| *** hockeynut has quit IRC | 21:31 | |
| *** claudiub has quit IRC | 21:35 | |
| *** ad_rien_ has quit IRC | 21:37 | |
| *** rfolco has joined #openstack-performance | 21:37 | |
| *** rfolco has quit IRC | 21:39 | |
| *** msimonin has quit IRC | 22:24 | |
Generated by irclog2html.py 2.14.0 by Marius Gedminas - find it at mg.pov.lt!