Tuesday, 2016-01-19

« Monday, 2016-01-18 Index Wednesday, 2016-01-20 »
*** zz_dimtruck is now known as dimtruck00:02
*** dslevin_ has joined #openstack-performance00:17
*** dslevin_ has quit IRC00:17
*** dslevin has quit IRC00:18
*** dslevin has joined #openstack-performance00:18
*** dimtruck is now known as zz_dimtruck00:29
*** dslevin has quit IRC00:35
*** dslevin has joined #openstack-performance00:38
*** dslevin has quit IRC00:48
*** dslevin has joined #openstack-performance00:51
*** dims has quit IRC01:01
*** markvoelker has quit IRC01:14
*** dims has joined #openstack-performance01:23
*** dslevin has quit IRC01:31
*** rfolco has joined #openstack-performance01:36
*** dslevin has joined #openstack-performance01:36
openstackgerritJeff Buell proposed openstack/performance-docs: Database testing plan  https://review.openstack.org/26352301:40
*** paco20151113 has joined #openstack-performance01:42
*** rfolco has quit IRC01:46
*** sc68cal has quit IRC01:49
*** harshs has joined #openstack-performance01:50
*** sc68cal has joined #openstack-performance01:54
*** dslevin has quit IRC01:56
*** dslevin has joined #openstack-performance02:07
*** sc68cal has quit IRC02:09
*** sc68cal has joined #openstack-performance02:12
*** markvoelker has joined #openstack-performance02:52
*** markvoelker_ has joined #openstack-performance02:56
*** markvoelker has quit IRC03:00
*** markvoelker_ has quit IRC03:01
*** lezbar has quit IRC03:04
*** markvoelker has joined #openstack-performance03:06
*** dims has quit IRC03:20
*** zz_dimtruck is now known as dimtruck03:52
*** dimtruck is now known as zz_dimtruck04:03
*** ngoracke has joined #openstack-performance04:13
*** zz_dimtruck is now known as dimtruck04:32
*** markvoelker has quit IRC04:39
*** ngoracke has quit IRC04:40
*** markvoelker has joined #openstack-performance04:40
*** dimtruck is now known as zz_dimtruck04:41
*** harshs_ has joined #openstack-performance05:17
*** harshs has quit IRC05:17
*** harshs_ is now known as harshs05:17
*** harshs has quit IRC05:39
*** nihilifer has quit IRC06:49
*** nihilifer has joined #openstack-performance06:50
*** markvoelker_ has joined #openstack-performance07:11
*** ngoracke has joined #openstack-performance07:13
*** markvoelker has quit IRC07:15
*** ngoracke has quit IRC07:19
*** markvoelker_ has quit IRC07:57
*** amaretskiy has joined #openstack-performance08:10
*** markvoelker has joined #openstack-performance08:38
*** markvoelker has quit IRC08:43
*** markvoelker has joined #openstack-performance08:46
*** lezbar has joined #openstack-performance08:56
*** markvoelker has quit IRC09:02
*** markvoelker has joined #openstack-performance09:19
*** markvoelker has quit IRC09:24
*** markvoelker has joined #openstack-performance09:40
*** boris-42 has quit IRC09:43
*** markvoelker has quit IRC09:45
*** rmart04 has joined #openstack-performance09:47
openstackgerritMerged openstack/performance-docs: Add job to test plans against the template  https://review.openstack.org/26823609:58
*** paco20151113 has quit IRC10:15
*** markvoelker has joined #openstack-performance10:16
*** markvoelker has quit IRC10:21
openstackgerritDina Belova proposed openstack/performance-docs: Database testing plan  https://review.openstack.org/26352310:29
openstackgerritDina Belova proposed openstack/performance-docs: Make tests simple-tables tolerant  https://review.openstack.org/26953910:29
*** markvoelker has joined #openstack-performance10:44
*** dims has joined #openstack-performance10:48
*** rfolco has joined #openstack-performance10:48
*** markvoelker has quit IRC10:49
*** markvoelker has joined #openstack-performance11:14
*** markvoelker has quit IRC11:20
*** markvoelker has joined #openstack-performance11:32
*** markvoelker has quit IRC11:36
*** markvoelker has joined #openstack-performance12:11
*** markvoelker has quit IRC12:16
*** markvoelker has joined #openstack-performance12:49
*** markvoelker has quit IRC12:54
*** markvoelker has joined #openstack-performance13:10
*** markvoelker has quit IRC13:15
*** rvasilets has joined #openstack-performance13:47
*** markvoelker has joined #openstack-performance13:52
*** markvoelker has quit IRC13:57
*** markvoelker has joined #openstack-performance14:00
*** markvoelker_ has joined #openstack-performance14:01
*** markvoelker has quit IRC14:05
*** harshs has joined #openstack-performance14:23
*** harshs_ has joined #openstack-performance14:28
*** v12aml has quit IRC14:30
*** mriedem_away is now known as mriedem14:31
*** harshs has quit IRC14:31
*** harshs_ is now known as harshs14:31
*** harshs has quit IRC14:49
*** v12aml has joined #openstack-performance14:55
*** v12aml has quit IRC14:55
*** regXboi has joined #openstack-performance14:55
*** v12aml has joined #openstack-performance14:56
*** ngoracke has joined #openstack-performance15:05
*** nicholas_ has joined #openstack-performance15:06
*** ngoracke has quit IRC15:09
*** zz_dimtruck is now known as dimtruck15:14
*** v12aml has quit IRC15:17
*** dslevin has quit IRC15:18
*** v12aml has joined #openstack-performance15:19
*** AugieMena has joined #openstack-performance15:22
*** pglass has joined #openstack-performance15:41
*** mdorman has joined #openstack-performance15:44
* regXboi gets a chair in the back of the room and starts quietly snoring15:45
*** markvoelker_ has quit IRC15:51
*** listomin has joined #openstack-performance15:52
DinaBelova:)15:56
DinaBelovaregXboi ack :)15:56
regXboimorning :) [or afternoon for folks on the other side of "the pond"]15:57
DinaBelovaregXboi lol :D15:57
DinaBelovakun_huang - are you around, sir?15:57
* DinaBelova hopes that YES15:57
*** Patryk-Intel has joined #openstack-performance15:57
*** nicholas_ has quit IRC15:59
DinaBelova#startmeeting Performance Team16:00
openstackMeeting started Tue Jan 19 16:00:00 2016 UTC and is due to finish in 60 minutes.  The chair is DinaBelova. Information about MeetBot at http://wiki.debian.org/MeetBot.16:00
openstackUseful Commands: #action #agreed #help #info #idea #link #topic #startvote.16:00
openstackThe meeting name has been set to 'performance_team'16:00
DinaBelovao/16:00
regXboio/16:00
*** ngoracke has joined #openstack-performance16:00
DinaBelovaI wish so much that kun_huang will be here today :) wanted to place him and listomin in one room, and forget the place where the room key is :)16:00
DinaBelovatodays agenda: https://wiki.openstack.org/wiki/Meetings/Performance#Agenda_for_next_meeting16:01
DinaBelovalet's wait for a few more moments :) probably harlowja, kun_huang and boris-42 will appear :)16:01
DinaBelova#topic Action Items16:02
DinaBelovaok, so let's go through the action items first16:03
DinaBelovaboth on me in fact16:03
DinaBelovathe first one is about pinging kun_huang and the huawei lab doc status16:03
*** boris-42 has joined #openstack-performance16:03
DinaBelovain fact he has updated the google doc, but did not publish the info to the performance-docs yet16:03
DinaBelovaI'll go quickly through what I can see about huawei lab status during the needed section16:04
DinaBelovaand the second one is about publishing info about mirantis-intel lab16:04
boris-42hi DinaBelova16:04
DinaBelovaboris-42 o/16:04
*** ikhudoshyn has joined #openstack-performance16:04
DinaBelovasadly the lab was not prepared ok during the previous week16:04
DinaBelovaso I'm going to do it this week16:05
rvasiletso/16:05
DinaBelovaAugieMena - probably you'll be interested16:05
DinaBelovarvasilets o/16:05
DinaBelovaAugieMena - Intel-Mirantis lab is now 250 nodes16:05
DinaBelovastill some networking issues, but I believe we'll be able to start running test plans agains it very soon16:05
DinaBelovaat least it's more or less available now, etc.16:05
DinaBelova#action DinaBelova share details about Mirantis-Intel lab (mailing list + performance-docs)16:06
DinaBelovaso I'll keep action item on me for this16:06
DinaBelova#topic Test plans statuses16:06
DinaBelovatest plans template was merged to the performance-docs16:06
DinaBelova#link https://review.openstack.org/#/c/268236/16:07
DinaBelovaand the already merged stuff was modified to fit it16:07
DinaBelovaalso we have DB test plan almost merged16:07
DinaBelova#link https://review.openstack.org/#/c/263523/16:07
DinaBelovaI love how it looks now, so I believe we're close :)16:07
DinaBelovathanks Jeff :)16:08
DinaBelovaso I believe that's everything new about the test plans for now16:08
DinaBelova#topic Huawei lab status16:08
* regXboi catches up on scrollback16:08
DinaBelovaregXboi :)16:08
DinaBelovaabout the Huawei lab I can share something very high level without kun_huang who has all info16:09
AugieMenaDina - sorry for the late response.  Yes, interested!16:09
DinaBelovaAugieMena no problem :)16:09
DinaBelovaAugieMena I'll try to publish info asap16:09
DinaBelovareally planned to do it before this meeting, but lab was not ok...16:10
DinaBelova:)16:10
kun_huangDuan and dragonflow team are starting perf testing recently16:10
DinaBelovakun_huang yay!16:10
DinaBelovanice to see you sir!16:10
kun_huangnice to see you ;)16:10
DinaBelovakun_huang - hm... I did not see the test plan from them in fact :)16:10
DinaBelovakun_huang are they planning to publish it to the performance docs?16:10
AugieMenaDina - thx, from our side we need to review the plans and figure out how we can help16:10
kun_huangbecause dragonflow team just fly back16:11
DinaBelovaAugieMena ack!16:11
kun_huangDinaBelova: I could ask them share something16:11
DinaBelovakun_huang ok16:11
kun_huangit is not diffcult16:11
DinaBelovakun_huang I believe that's a good idea16:11
DinaBelovabecause it'll be good to have all stuff like that in on place16:11
DinaBelova#action kun_huang ask DragonFly team to share the test plan16:11
DinaBelovaok, cool16:11
kun_huangyep, we all need make dragonflow more public16:12
DinaBelovakun_huang ;)16:12
DinaBelovaalso I can see that the lab has grown during the holidays16:12
DinaBelova46 nodes now16:12
DinaBelovavery cool!16:12
kun_huangthere are 40 on the way to Hangzhou16:12
DinaBelovakun_huang - ok, and they will be available after Feb 15th?16:12
DinaBelovakun_huang - can you please publish the lab doc to the perofrmance docs?16:13
DinaBelovakun_huang - I'll do the same for Intel-Mirantis lab16:13
kun_huangokay, no problem16:13
kun_huanggood idea16:13
DinaBelovacool16:13
DinaBelova#action kun_huang publish info about Huawei lab to performance-docs16:14
DinaBelovavery nice16:14
DinaBelovakun_huang - I wanted to present you listomin16:14
listominkun_huang Hello! :)16:14
DinaBelovalistomin is one of Mirantis performance team engineers16:14
kun_huanglistomin: nice to meet you16:14
DinaBelovaand he is very interested in running the provisioning test plan against your lab16:14
DinaBelovawhen it'll be possible :)16:15
kun_huangit will be a nice cooperation16:15
DinaBelovaso 6 nodes are under the dragonflow testing, and 40 are coming16:15
DinaBelovaI dunnot when this will be available to be done in fact16:15
DinaBelovabut I want you guys to coordinate on this topic :)16:16
kun_huangone or two is ready I think16:16
DinaBelovaso just keep in touch16:16
kun_huangyep16:16
DinaBelovakun_huang - may you please ensure something is available and ping listomin if yes?16:16
listominkun_huang I'll look at Huawei lab docs and probably ask you to configure something. Also I'll try to prepare automations or qcow image to deploy it on your env16:16
DinaBelovalistomin ok :) so we're waiting public Huawei lab doc16:17
DinaBelovaok, cool16:18
DinaBelovaso let's move forward16:18
DinaBelova#topic OSProfiler weekly update16:18
DinaBelovathe most interesting news are about Nova change :)16:19
DinaBelova#link https://review.openstack.org/#/c/254703/16:19
DinaBelovaduring the last week it passed several stages16:19
DinaBelova1 - tests began to work ok16:19
DinaBelova2 - change was modified to gather more info16:19
DinaBelova3 - something else was merged to nova and shown that osprofiler has a bug16:20
DinaBelova:)16:20
DinaBelovaso tests right now will be failing due to the following issue: trace_cls decorator in osprofiler modifies (somehow) the static methods of the class (faving "function type") to not static - having "inctancemethod" type16:21
DinaBelovathat leads to wrong number of args coming to the methods like that16:21
DinaBelovaI'm writing the fix at the moment16:21
* DinaBelova hopes to publish it today16:21
DinaBelovaboris-42 - I'll ping you once the change will be ready16:22
DinaBelovaplease take a look on it when this will happen16:22
DinaBelovasurprising moment is that special tracing meta class does not have this behaviour, that's really surprising for me16:23
DinaBelovaalso I'm going to grab neutron flag from regXboi :)16:23
DinaBelovaand start working on osprofiler to neutron change16:23
DinaBelova#link https://bugs.launchpad.net/neutron/+bug/133564016:24
openstackLaunchpad bug 1335640 in neutron "[RFE] Neutron support for OSprofiler" [Wishlist,Triaged] - Assigned to Dina Belova (dbelova)16:24
regXboiyes - I'll pitch in and help, but I'm running around like a one-armed paper hanger16:24
DinaBelovaregXboi - no worries16:24
DinaBelovaregXboi, I completely understand your situation16:24
DinaBelovaI really hope you'll be able to deal with all your current tasks, I don't like the "one-armed paper hanger" metaphor :)16:25
*** Patryk-Intel has quit IRC16:25
regXboineither do I16:25
DinaBelovaack, cool16:25
DinaBelovaone more interesting change is from dims16:25
DinaBelova#link https://review.openstack.org/#/c/269059/16:26
DinaBelovathat will allow not to copy paste all the stuff to various projects and just use the osprofiler here16:26
DinaBelovaI'll update it to meet recent comments I got in nova change and I believe we can merged it16:26
DinaBelovaI guess that's everything interesting about the osprofiler16:27
DinaBelovaboris-42 - anything to add?16:27
boris-42DinaBelova: so16:27
boris-42DinaBelova: I am working on devstack-osprofiler integration16:27
boris-42DinaBelova: so we should get soon functional job16:27
DinaBelovayay!16:27
boris-42DinaBelova: and it should be very easy to set up specific version in devstack16:28
boris-42#link https://review.openstack.org/#/c/267888/16:28
boris-42#link https://review.openstack.org/#/c/267889/16:28
boris-42I'll create today branch16:28
boris-42patch*16:28
boris-42to infra16:28
DinaBelovaboris-42, very cool16:28
boris-42DinaBelova: plus I was debugging yestarday a lot osprofiler16:29
boris-42seems like Nova started using greenthreads a lot16:29
DinaBelovaboris-42 - yes, and I want to say you big THANK YOU16:29
boris-42and that is why we are losing our messages16:29
boris-42DinaBelova: it works for you as well?16:29
DinaBelovathe latest nova change looks much better16:29
DinaBelovaafter some fixing in trace_cls yes16:29
boris-42DinaBelova: so the only one thing that we need to fix now  is keystone?16:29
DinaBelovaboris-42 http://dinabelova.github.io/fixed_nova_and_profiler_trace.html16:30
DinaBelovaboris-42 I believe yes16:30
boris-42DinaBelova: so this is bad trace16:30
*** ilyashakhat has joined #openstack-performance16:30
boris-42DinaBelova: are you sure that you put there proper trace?16:30
boris-42DinaBelova: there is only one compute point and there should be more16:31
DinaBelovaboris-42 one?16:31
DinaBelovait looks like I see more16:31
boris-42DinaBelova: yep only one from nova-compute16:31
DinaBelovaa-ha, you mean rpc call?16:32
boris-42DinaBelova: that's the bug that patching spawn method is addressing16:32
boris-42DinaBelova: not rpc call16:32
DinaBelovayep, I used your fix16:32
DinaBelovaone moment16:32
DinaBelovalemme check16:32
boris-42DinaBelova: I mean call from nova-compute16:32
boris-42DinaBelova: there should be zillion calls from nova-compute16:32
boris-42DinaBelova: otherwise fix doesn't work16:32
boris-42DinaBelova: I believe that this is missing in your patch as ewll https://github.com/boris-42/nova/commit/a3c002e9cb32e98952e18ea7ec447b0e3ae46d6316:32
DinaBelovanope, I added it16:32
DinaBelovatherefore you can see compute_api points16:33
boris-42DinaBelova: in any case working profiler means a lot of points from nova-compute16:34
DinaBelovahttps://review.openstack.org/#/c/254703/21/nova/compute/api.py here is nova_compute16:34
boris-42DinaBelova: I will test your patch today16:34
DinaBelovaboris-42 it looks like I really removed for mistake the https://github.com/boris-42/nova/commit/a3c002e9cb32e98952e18ea7ec447b0e3ae46d6316:34
DinaBelovainteresting16:34
DinaBelovawas sure I applyed it16:34
boris-42DinaBelova: actually that code is executed on osapi-compute16:34
boris-42DinaBelova: and node-compute and that name should be fixed16:34
DinaBelovaI'll retest it16:35
boris-42DinaBelova: I am going to renaming of points16:35
boris-42DinaBelova: otherwise it becomes a bit unclear16:35
DinaBelovaboris-42 ack16:35
DinaBelovathank you sir16:35
DinaBelova#action DinaBelova add https://github.com/boris-42/nova/commit/a3c002e9cb32e98952e18ea7ec447b0e3ae46d63 and retest the nova racing with it16:35
boris-42DinaBelova: that's all from my sie16:35
boris-42side16:35
*** markvoelker has joined #openstack-performance16:36
DinaBelovaboris-42 thank you sir16:36
DinaBelovaok, it looks like the complete version of osprofiler news16:36
DinaBelovagood16:36
DinaBelova#topic Open Discussion16:36
DinaBelovaI don't have much to add here16:36
DinaBelovathe only moment16:36
DinaBelova#link https://wiki.openstack.org/wiki/Performance_Team#Mitaka_Roadmap16:36
DinaBelovaI've added just for the clarification Mitaka roadmap16:37
DinaBelovaI probably missed something, like one more osprofielr release16:37
DinaBelovabut more or less it's full now16:37
DinaBelovaboris-42, kun_huang - please take a look and update in case of any comments16:37
DinaBelovaand that's all from my side16:38
DinaBelovado you guys have something to add?16:38
rvasiletsno16:39
DinaBelovaboris-42 ooops https://review.openstack.org/#/c/254703/21/nova/utils.py16:39
DinaBelovaI've added your fix already16:40
DinaBelovaI'll recheck it on the env16:40
DinaBelovaand if it's already added, that means something went wrong16:40
DinaBelovaso I'll recheck anyway16:40
DinaBelovaok, so it looks like no more comments today16:41
DinaBelovathanks everyone for attending and have a nice day/evening16:41
DinaBelova#endmeeting16:41
openstackMeeting ended Tue Jan 19 16:41:26 2016 UTC.  Information about MeetBot at http://wiki.debian.org/MeetBot . (v 0.1.4)16:41
openstackMinutes:        http://eavesdrop.openstack.org/meetings/performance_team/2016/performance_team.2016-01-19-16.00.html16:41
openstackMinutes (text): http://eavesdrop.openstack.org/meetings/performance_team/2016/performance_team.2016-01-19-16.00.txt16:41
openstackLog:            http://eavesdrop.openstack.org/meetings/performance_team/2016/performance_team.2016-01-19-16.00.log.html16:41
*** listomin has quit IRC16:41
*** linuxaddicts has quit IRC16:59
*** linuxaddicts has joined #openstack-performance17:02
*** amaretskiy has quit IRC17:04
*** rmart04_ has joined #openstack-performance17:59
*** rmart04_ has quit IRC17:59
*** rmart04 has quit IRC18:00
*** ngoracke has quit IRC18:06
*** nicholas_ has joined #openstack-performance18:09
*** nicholas_ has quit IRC18:10
*** nicholas_ has joined #openstack-performance18:15
*** tpeoples has quit IRC18:34
*** kun_huang has quit IRC18:35
*** hockeynut has quit IRC18:36
*** tpeoples has joined #openstack-performance18:36
*** hockeynut has joined #openstack-performance18:36
*** kun_huang has joined #openstack-performance18:38
harlowjadamn there was another meeting, lol18:46
harlowjaand i missed it :(18:46
*** boris-42 has quit IRC18:53
*** rmart04 has joined #openstack-performance19:13
*** rmart04_ has joined #openstack-performance19:15
*** rmart04 has quit IRC19:18
*** rmart04_ is now known as rmart0419:18
*** rmart04 has quit IRC19:26
*** harshs has joined #openstack-performance19:36
*** nicholas_ has quit IRC19:43
*** rfolco has quit IRC19:56
*** ngoracke has joined #openstack-performance20:31
*** nicholas_ has joined #openstack-performance20:36
*** ngoracke has quit IRC20:39
*** boris-42 has joined #openstack-performance20:42
*** harshs has quit IRC20:51
*** harshs has joined #openstack-performance20:55
*** pglass has quit IRC21:05
*** pglass has joined #openstack-performance21:08
*** pglass has quit IRC21:10
*** pglass has joined #openstack-performance21:20
*** mriedem has quit IRC21:29
*** harshs has quit IRC21:49
*** Guest51217 is now known as med_22:00
*** med_ has quit IRC22:00
*** med_ has joined #openstack-performance22:00
*** ngoracke has joined #openstack-performance22:10
*** nicholas_ has quit IRC22:14
*** harshs has joined #openstack-performance22:14
*** harshs has quit IRC22:31
*** ngoracke has quit IRC22:35
*** harshs has joined #openstack-performance22:36
*** harshs has quit IRC22:36
*** nicholas_ has joined #openstack-performance22:36
*** harshs has joined #openstack-performance22:38
*** nicholas_ has quit IRC23:06
*** dimtruck is now known as zz_dimtruck23:12
*** pglass has quit IRC23:15
*** regXboi has quit IRC23:16
*** harshs has quit IRC23:43
*** ngoracke has joined #openstack-performance23:44
« Monday, 2016-01-18 Index Wednesday, 2016-01-20 »

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