Tuesday, 2016-11-22

*** yujunz has joined #openstack-performance00:25
*** luzC has quit IRC00:33
*** luzC has joined #openstack-performance00:38
*** dimtruck is now known as zz_dimtruck00:39
*** victorhe has joined #openstack-performance00:43
*** victorhe has quit IRC00:47
*** yujunz is now known as yujunz[away]00:59
*** yujunz[away] is now known as yujunz01:02
*** yujunz is now known as yujunz[away]01:02
*** yujunz[away] is now known as yujunz01:05
*** yujunz is now known as yujunz[away]01:05
*** rfolco has joined #openstack-performance01:21
*** yujunz[away] is now known as yujunz01:40
*** zz_dimtruck is now known as dimtruck01:41
*** victorhe has joined #openstack-performance01:45
*** victorhe_ has joined #openstack-performance01:48
*** victorhe has quit IRC01:52
*** victorh__ has joined #openstack-performance01:52
*** victorhe_ has quit IRC01:55
*** victorh__ has quit IRC02:01
*** victorhe_ has joined #openstack-performance02:02
*** victorhe_ has quit IRC02:07
*** victorhe has joined #openstack-performance02:07
*** victorhe has quit IRC02:09
*** victorhe has joined #openstack-performance02:09
*** victorhe has quit IRC02:11
*** victorhe has joined #openstack-performance02:11
*** yujunz is now known as yujunz[away]02:41
*** yujunz[away] is now known as yujunz02:52
*** yujunz is now known as yujunz[away]02:52
*** yujunz[away] is now known as yujunz02:57
*** rfolco has quit IRC03:08
*** yujunz is now known as yujunz[away]03:43
*** victorhe has quit IRC04:10
*** victorhe has joined #openstack-performance04:10
*** yujunz[away] is now known as yujunz04:13
*** yujunz is now known as yujunz[away]04:14
*** victorhe has quit IRC04:15
*** yujunz[away] is now known as yujunz04:19
*** yujunz is now known as yujunz[away]04:19
*** victorhe has joined #openstack-performance04:19
*** yujunz[away] is now known as yujunz04:33
*** yujunz is now known as yujunz[away]04:33
*** victorhe has quit IRC04:35
*** victorhe has joined #openstack-performance04:35
*** victorhe has quit IRC04:40
*** yujunz[away] is now known as yujunz04:49
*** yujunz is now known as yujunz[away]04:49
*** yujunz[away] is now known as yujunz05:27
*** ad_rien_ has joined #openstack-performance05:52
*** ad_rien_ has quit IRC05:52
*** ad_rien_ has joined #openstack-performance05:52
*** ad_rien_ has quit IRC05:52
*** yujunz-zte has joined #openstack-performance06:01
*** yujunz has quit IRC06:01
*** ad_rien_ has joined #openstack-performance06:02
*** ad_rien_ has quit IRC06:06
*** yujunz_ has joined #openstack-performance06:11
*** yujunz-zte has quit IRC06:11
*** yujunz_ is now known as yujunz[away]06:18
*** yujunz[away] is now known as yujunz_06:18
*** rfolco has joined #openstack-performance07:04
*** rfolco has quit IRC07:04
*** ad_rien_ has joined #openstack-performance07:35
*** ad_rien_ has quit IRC07:35
*** pcaruana has joined #openstack-performance07:56
*** yujunz_ is now known as yujunz[away]08:04
*** yujunz[away] is now known as yujunz_08:14
*** victorhe has joined #openstack-performance08:27
*** ad_rien_ has joined #openstack-performance08:29
*** victorhe has quit IRC08:32
*** ad_rien_ has quit IRC08:55
*** ad_rien_ has joined #openstack-performance08:56
*** yujunz_ has quit IRC09:26
*** victorhe has joined #openstack-performance09:27
*** victorhe has quit IRC09:31
*** ad_rien_ has quit IRC09:43
*** ad_rien_ has joined #openstack-performance09:46
*** brault has joined #openstack-performance10:13
*** victorhe has joined #openstack-performance10:24
*** victorhe has quit IRC10:28
*** ad_rien_ has quit IRC10:42
*** ad_rien_ has joined #openstack-performance10:44
*** brault has quit IRC10:46
*** ad_rien_ has quit IRC10:50
*** ad_rien_ has joined #openstack-performance10:51
*** brault has joined #openstack-performance10:53
*** brault has quit IRC10:58
*** ad_rien_ has quit IRC10:59
*** brault has joined #openstack-performance11:00
*** ad_rien_ has joined #openstack-performance11:02
*** msimonin has joined #openstack-performance11:08
*** victorhe has joined #openstack-performance11:15
*** victorhe has quit IRC11:20
*** brault has quit IRC11:24
*** rfolco has joined #openstack-performance11:35
*** jkilpatr has quit IRC12:03
*** jkilpatr has joined #openstack-performance12:03
*** victorhe has joined #openstack-performance12:15
*** bvanhav_ has joined #openstack-performance12:15
*** victorhe has quit IRC12:20
*** ad_rien_ has quit IRC12:29
*** ad_rien_ has joined #openstack-performance12:32
*** rmart04 has joined #openstack-performance12:33
*** victorhe has joined #openstack-performance13:00
*** msimonin has quit IRC13:03
*** victorhe has quit IRC13:04
*** msimonin has joined #openstack-performance13:15
*** yujunz has joined #openstack-performance13:55
*** ad_rien_1 has joined #openstack-performance13:55
*** ad_rien_ has quit IRC13:56
*** brault has joined #openstack-performance13:59
*** ad_rien_1 has quit IRC13:59
*** ad_rien_ has joined #openstack-performance14:00
*** brault has quit IRC14:07
*** bvanhav__ has joined #openstack-performance14:10
*** bvanhav__ is now known as bvanhav14:10
*** bvanhav_ has quit IRC14:10
*** dalvarezs is now known as dalvarez14:12
*** dalvarez is now known as dalvarezs14:12
*** ad_rien_ has quit IRC14:23
*** ad_rien_ has joined #openstack-performance14:28
*** brault has joined #openstack-performance14:29
*** ad_rien_ has quit IRC14:32
*** ad_rien_ has joined #openstack-performance14:33
*** msimonin has quit IRC14:33
*** brault has quit IRC14:33
*** ad_rien_1 has joined #openstack-performance14:35
*** ad_rien_ has quit IRC14:37
*** msimonin has joined #openstack-performance14:45
*** msimonin has left #openstack-performance14:46
*** victorhe has joined #openstack-performance14:52
*** brault has joined #openstack-performance14:52
*** msimonin has joined #openstack-performance14:56
*** victorhe_ has joined #openstack-performance14:56
*** victorhe_ has quit IRC14:56
*** victorhe_ has joined #openstack-performance14:56
*** victorhe has quit IRC14:56
*** victorhe_ has quit IRC14:56
*** victorhe has joined #openstack-performance14:57
*** msimonin has quit IRC14:58
*** brault has quit IRC15:01
*** msimonin has joined #openstack-performance15:12
msimoninre15:19
*** ad_rien_1 has quit IRC15:19
*** ad_rien_ has joined #openstack-performance15:23
*** yujunz has quit IRC15:24
*** rcherrueau has joined #openstack-performance15:25
DinaBelova#startmeeting Performance Team15:30
openstackMeeting started Tue Nov 22 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
openstackUseful Commands: #action #agreed #help #info #idea #link #topic #startvote.15:30
openstackThe meeting name has been set to 'performance_team'15:30
DinaBelovaok, let's see who's around :)15:30
DinaBelovamsimonin ad_rien_ rcherrueau o/15:30
msimonino/15:30
DinaBelovasai are you around?15:30
rcherrueauo/15:31
ad_rien_o/ (but in no so proactive mode sorry,  few pendings todos on my side)15:31
DinaBelovaack, got it15:31
DinaBelovaso let's get started I guess15:32
DinaBelovalet's got through action items first15:32
DinaBelovaand I think people may join in progress15:32
DinaBelova#topic Action Items15:32
DinaBelovaone of the items was on me regarding the nova cells V2 status15:33
DinaBelovamsimonin rcherrueau ad_rien_ I've posted that info recently, but only msimonin was online :)15:33
DinaBelovaso lemme repaste it :)15:33
rooko/15:34
DinaBelova#info Andrew Laski is not working anymore at Mirantis -> most probably he won't take part in OpenStack dev -> Dan Smith and Melanie Witt at Red Hat are picking up the remaining cellsv2 tasks15:34
DinaBelovarook o/15:34
DinaBelovamsimonin ad_rien_ rcherrueau so you guys need to ping those two ^^ about what's going on right now in the Nova Cells V215:35
msimoninthanks DinaBelova15:35
ad_rien_thanks15:35
DinaBelovaokay, so let's proceed with action items15:35
DinaBelovaone more was on ad_rien_ - regarding adding info about the nfv group info to the summit recaps section of performance docs15:36
ad_rien_Sorry I missed it15:36
ad_rien_(too many todos)15:36
DinaBelovaI guess it was a big load on you15:36
DinaBelovayeah15:37
ad_rien_I will do it by tomorrow evening15:37
DinaBelovalemme keep this action item15:37
ad_rien_you can count on me15:37
DinaBelovathanks15:37
DinaBelova#action ad_rien_ add info about the nfv group info to the summit recaps section of performance docs15:37
DinaBelovathanks again :)15:37
DinaBelovaand the last action item was on sai15:37
DinaBelovaas he did not answer yet and he seems to be in silent mode right now, lemme keep his action item as well15:38
DinaBelovasai find out when information about telemetry researched Red Hat has done can be published to performance docs15:38
DinaBelova#action sai find out when information about telemetry researched Red Hat has done can be published to performance docs15:38
DinaBelovaso we are done with action items!15:38
DinaBelovaand may jump to the next section15:38
rookDinaBelova: he is in a way different timezone15:38
DinaBelova#topic Current progress on the planned tests15:38
rookDinaBelova: akrzos can speak to that15:38
DinaBelovarook yay15:38
DinaBelovathanks for letting me know15:39
rookakrzos re: Telemetry work you have done15:39
DinaBelovaakrzos the thing is that OpenStack operators were really excited to hear that you folks have done telemetry researches on the summit15:39
DinaBelovaand LDT kindly asked to publish this info to the performance-docs15:40
DinaBelovawhen I checked that with sai he told he need to check if and when this can be done15:40
akrzosDinaBelova: gotcha, yeah I need to revisit it with a ceph backend15:40
DinaBelovaakrzos ok, so any understanding of when you're going to finish those experiments? and to publish the results of course! folks were really excited - telemetry is on of the pain points for a while :)15:41
akrzosi have looked at it with file and swift backends but with not great disks so i'd say the results are less than exciting wrt to Gnocchi vs database15:41
DinaBelovaakrzos ack, got that15:42
DinaBelova#info akrzos looked at Gnocchi with file and swift backends but with not great disks so i'd say the results are less than exciting wrt to Gnocchi vs database, need to revist with Ceph backend15:42
akrzosalso here is a link to my initial strobe of it https://browbeatproject.org/2016/09/12/performance-testing-openstack-telemetry-ceilometer-and-gnocchi/15:42
DinaBelova#link https://browbeatproject.org/2016/09/12/performance-testing-openstack-telemetry-ceilometer-and-gnocchi/15:43
DinaBelovaok, so the next steps are: good HW, Ceph backend, retest15:43
DinaBelovaakrzos so again - any plans to publish that to performance-docs?15:43
akrzosDinaBelova: I can start with the test plan15:44
DinaBelovaakrzos sure15:44
DinaBelovathis will be a good start15:44
DinaBelovaok, so lemme create an action item15:44
akrzosand then post what results we currently have and build on it when more hardware better disks are available for me again15:45
DinaBelovaif you won't be able to finish it till next week, it's ok, let's just have that pinned15:45
akrzosso let me take that action on the test plan for now15:45
DinaBelova#action akrzos publish OpenStack telemetry teat plan to performance-docs15:45
*** jkilpatr has quit IRC15:45
DinaBelovaok, cool15:45
DinaBelovathanks akrzos15:45
*** jkilpatr has joined #openstack-performance15:46
DinaBelovamsimonin any news about most recent experiments at Inria?15:46
DinaBelovaor ad_rien_ or rcherrueau  :)15:46
msimoninActually we are writing a paper about our evaluation framework15:47
msimonin#link https://github.com/BeyondTheClouds/enos15:47
DinaBelovagood thing to be done! and to be shared once finished :)15:47
DinaBelovaack15:47
msimoninwe are also performing energy evaluation of openstack services15:47
msimonin(no link to that yet I think)15:48
DinaBelova#info energy evaluation of openstack services by Inria in progress15:48
msimoninWe are adapting the tool to support multi site deployment15:48
msimoninDinaBelova: sure we'll share it15:48
msimonindeadline is next week for the paper :s15:48
DinaBelovamsimonin yeah, any plans on what Grid'5000 locations will be first tested in multi-site deployment?15:48
DinaBelovajust curious15:49
DinaBelovamsimonin ahaha, good luck with paper work :)15:49
ad_rien_What do you mean DinaBelova?15:49
ad_rien_Can you elaborate ?15:49
msimonin:)15:49
ad_rien_Thanls15:49
ad_rien_Our idea is to define with the help of the NFV working group15:49
ad_rien_a minimalist openstack deployment15:49
ad_rien_that can federate resources spread across different locations15:50
ad_rien_and then performs the same experiments we made in order to understand15:50
ad_rien_major bottlenecks/performance limitations15:50
DinaBelovawell, Grid'5000 contains lots of servers in multiple cities - so I was just curious - last time for 1000 nodes experiment you used only one location of servers, this time you want to have multi-site deployment - so I was just curious what servers locations are affected15:50
ad_rien_G5K is already a distributed infrastructure. So we have two possibilities: either deploy the control plane on one site and the other (i.e. compute nodes) on other sites.15:51
ad_rien_yes15:51
ad_rien_but since we want to ensure reproducibility15:51
DinaBelovaanyway, forgot what I was asking about :) I seem to confuse you15:51
DinaBelovadon't worry :)15:51
ad_rien_we usually prefer to have the experiment in one site (and emulate the locations)15:51
DinaBelovaok, so you're extending your experience15:52
ad_rien_This way enables to control everything and collect relevant results (i.e. that do not have noise coming from another experiment)15:52
DinaBelovaindeed15:52
ad_rien_the issue right now is that none knows what can be the minimalist deployment15:53
ad_rien_we are exchanging with the NFV folks and colleagues from Orange Labs, BT,...15:53
ad_rien_it is unclear what can be the right deployment scenario.15:53
ad_rien_so the idea is probably to identify two or three and make comparisons between them15:54
ad_rien_by using performance and functional metrics15:54
ad_rien_(I hope I've been clear enough)15:54
DinaBelovayeah, thank you!15:54
DinaBelovaand sorry again for confusion15:55
ad_rien_the only thing that looks quite sure is that more and more operators would like to supervise several DCs in an unified manner (i.e. with a single openstack system)15:55
ad_rien_no problem15:55
DinaBelovaok, so let's proceed15:55
DinaBelovaon Mirantis side we're almost done with our advanced monitoring :) hope to publish this info to our perf docs soon :) we have crazy combination of Prometheus, Telefraf and CollectD to collect all info about system, k8s and OpenStack on top of it15:56
DinaBelovawe're going to use that approach during our k8s and OpenStack testing soon15:57
DinaBelovawe'll start with k8s most probably15:57
DinaBelovawith k8s density and kubelet capacity testing15:57
DinaBelovatest plans should appear on review soon15:58
DinaBelovaand that's all for now from our side15:58
DinaBelovaanything else to cover in this topic?15:58
msimoninone question15:58
DinaBelovasure15:58
msimoninYour deployment method here : will it be part of fuel ?15:59
DinaBelovadeployment of OpenStack == fuel-ccp15:59
DinaBelovaand we have to install k8s separately - right now using Kargo tool15:59
DinaBelovaall steps are automated in our Scale team Jenkins16:00
msimoninok I see, thanks16:00
DinaBelovathat manages all the steps - e.g. "provision nodes (usually via cobbler)", "install k8s", "run fuel-ccp", "run tests"16:00
DinaBelovawe found that approach convenient for us16:01
DinaBelovabut for OpenStack yes - we're using fuel-ccp16:01
msimoninIs the monitoring stack included in the tool (sorry for my ignorance)16:01
msimonin?16:01
DinaBelovaright now in progress of integration16:01
DinaBelovawe were playing with different methodologies mostly manually16:01
DinaBelovaright now - when even all Grafana boards are almost finished - we'll proceed with automation16:02
DinaBelovaof the monitoring installation and usage16:02
DinaBelovaI hope that answers your question :)16:02
msimonindo you intend to publish the grafana dashboards ?16:02
msimonin:)16:02
DinaBelovawe have that wish, we'll check if Intel folks (who're on other side of our co-dev activity) will agree16:03
DinaBelovabut they are usually very happy with upstreaming things16:03
msimonincool :)16:03
DinaBelova#action DinaBelova find out if and when we're going to publish our Grafana dashboards16:03
DinaBelovayeah ;)16:04
DinaBelovaokay, anything else in "test plans and results" section?16:04
DinaBelovait looks like nope :)16:05
DinaBelova#topic PTG in Atlanta16:05
DinaBelovaokay :D summit has just passed16:05
DinaBelovaand we need to think already about next one :D16:05
DinaBelovaas all you know starting after Barcelona summit design summit (PGT, project team gathering) ir separated from main summit event16:05
ad_rien_DinaBelova:  can you please explain what our WG can achieve in this PTG meeting.16:05
ad_rien_Still not clear from my side.16:06
DinaBelovaad_rien_ the idea is to discuss if we need that :)16:06
DinaBelovaRally team is going to have separated room on the summit16:06
ad_rien_ok but I mean. From my understanding the meeting is mainly for core-devs ?16:06
ad_rien_But our meeting, what non developers can do ?16:07
DinaBelovaad_rien_ the thing is that if something needs to be improved in the projects - e.g. their performance and scalability - it's a good idea to have this planned for the next cycle..16:07
ad_rien_We can come but it should be relevant (i.e. not  only for our meeting…. a bit expensive to bring 4/5 persons in one place if it is for one day working session).16:07
DinaBelovaso right now andreykurilin asked ttx to name the room "performance team and tools"16:08
ad_rien_ok16:08
DinaBelovaso basically what I was thinking about is tools development16:08
ad_rien_this has sense16:08
DinaBelovawe have rally, osprofiler, browbeat16:08
DinaBelovaand we're in fact developing them ourselves :)16:08
msimonin:)16:09
DinaBelovaso something I was thinking about is to have some discussions about how things might be improved16:09
DinaBelovawe all are Rally users and there is plenty of things that need to be done there16:09
DinaBelovacan we help rally team somehow here? can we leave feedback?16:10
DinaBelovado we have any wishes on what needs to be done there?16:10
DinaBelovaand so on16:10
ad_rien_ok16:10
ad_rien_thanks for the clarification16:10
msimoninThe same for shaker ? We are actually using it aswell16:10
DinaBelovayes and shaker!16:10
DinaBelovaI forget about all of them :)16:10
DinaBelovaos-faults for destructive testing as well.16:11
msimoninsure they are plenty of them16:11
DinaBelovaso bunch of tools16:11
DinaBelovaand it looks like this PGT is a good place to work on their progress16:11
DinaBelovaor even have kinda workshops16:11
DinaBelovawith ideas -> development -> reviews being done in plane16:11
DinaBelovaso what am I suggesting here16:11
DinaBelovalet's have 1 week for ideas gathering16:12
DinaBelovaand share them next time16:12
DinaBelovaon what can be discussed and how16:12
DinaBelovaakrzos ^^ fiy16:12
ad_rien_DinaBelova:  can you please remind the dates ?16:13
DinaBelova#info let's think if PGT will be useful for our group and if we can use this time for tools roadmaps discussions16:13
DinaBelovasure16:13
DinaBelova#info The first Project Teams Gathering (PTG) will be held in Atlanta, Feb 20-24, 2017.16:13
ad_rien_thanks16:13
DinaBelovaso... I'm not insisting that we really need to have that... but let's think about if we will benefit from that16:14
ad_rien_ok16:14
ad_rien_the idea is also to attend the summit16:14
ad_rien_(i.e. one face-to-face meeting in Atlanta and one in Boston)?16:14
DinaBelovayeah, main summit is still an EVENT :) my company likes PGT more than summit mostly because PGT locations should be usually cheaper16:15
*** msimonin has quit IRC16:15
DinaBelovabut ideally - yes16:15
DinaBelovatwo face-to-face meetings should be a good idea16:16
DinaBelovaas usually it's all question of money to be spent16:16
DinaBelovaso that's floating and vague - and that's ok16:17
*** msimonin has joined #openstack-performance16:17
DinaBelovaso again - please think if and how we can benefit from PGT16:17
ad_rien_ok16:17
msimoninack DinaBelova16:18
DinaBelovathat's all from my side for this topic16:18
DinaBelovaso I think we can jump to open discussions16:18
DinaBelova#topic Open Discussion16:18
DinaBelovaanything else to cover folks?16:18
DinaBelovaquestions / ideas / notes?16:18
msimoninnot from our side I guess16:19
DinaBelovaack, cool16:19
DinaBelovait looks like we're done for today16:19
DinaBelovathanks everyone!16:19
msimoninthanks16:19
DinaBelova#endmeeting16:19
openstackMeeting ended Tue Nov 22 16:19:38 2016 UTC.  Information about MeetBot at http://wiki.debian.org/MeetBot . (v 0.1.4)16:19
openstackMinutes:        http://eavesdrop.openstack.org/meetings/performance_team/2016/performance_team.2016-11-22-15.30.html16:19
openstackMinutes (text): http://eavesdrop.openstack.org/meetings/performance_team/2016/performance_team.2016-11-22-15.30.txt16:19
openstackLog:            http://eavesdrop.openstack.org/meetings/performance_team/2016/performance_team.2016-11-22-15.30.log.html16:19
*** brault has joined #openstack-performance16:38
*** brault has quit IRC16:42
*** rmart04_ has joined #openstack-performance16:46
*** rmart04 has quit IRC16:49
*** rmart04_ is now known as rmart0416:49
*** bvanhav has quit IRC16:57
*** rcherrueau has quit IRC17:02
*** ad_rien_ has quit IRC17:08
*** ad_rien_ has joined #openstack-performance17:08
*** bvanhav has joined #openstack-performance17:14
*** msimonin has quit IRC17:21
*** rmart04 has quit IRC17:30
*** msimonin has joined #openstack-performance18:08
*** rmart04 has joined #openstack-performance18:19
*** ad_rien_ has quit IRC18:22
*** rmart04_ has joined #openstack-performance18:34
*** rmart04 has quit IRC18:36
*** rmart04_ is now known as rmart0418:36
*** brault has joined #openstack-performance18:48
*** brault has quit IRC18:52
*** bvanhav has quit IRC19:20
*** brault has joined #openstack-performance19:23
*** bvanhav has joined #openstack-performance19:29
*** msimonin1 has joined #openstack-performance19:48
*** msimonin has quit IRC19:50
*** odyssey4me has quit IRC19:56
*** odyssey4me has joined #openstack-performance20:02
*** rfolco has quit IRC20:04
*** catinthe_ has joined #openstack-performance20:11
*** catintheroof has quit IRC20:13
*** catintheroof has joined #openstack-performance20:16
*** dalvarezs has quit IRC20:18
*** catinthe_ has quit IRC20:20
*** akrzos has quit IRC20:20
*** dalvarez has joined #openstack-performance20:30
*** bvanhav has quit IRC20:34
*** rmart04 has quit IRC21:16
*** msimonin1 has quit IRC21:24
*** sai has quit IRC21:29
*** sai has joined #openstack-performance21:30
*** jkilpatr has quit IRC21:40
*** msimonin has joined #openstack-performance21:50
*** jkilpatr has joined #openstack-performance21:52
*** msimonin has quit IRC22:07
*** victorhe_ has joined #openstack-performance22:54
*** victorhe has quit IRC22:58
*** victorhe has joined #openstack-performance22:59
*** victorhe_ has quit IRC23:01
*** victorhe has quit IRC23:03
*** akrzos has joined #openstack-performance23:16
*** victorhe has joined #openstack-performance23:29
*** victorhe has quit IRC23:34
*** catintheroof has quit IRC23:46
*** catintheroof has joined #openstack-performance23:47
*** catintheroof has quit IRC23:51
*** victorhe has joined #openstack-performance23:55

Generated by irclog2html.py 2.14.0 by Marius Gedminas - find it at mg.pov.lt!