Wednesday, 2016-11-23

*** haleyb_ has quit IRC00:02
*** AlanClark has quit IRC00:10
*** emagana has quit IRC00:14
*** Sukhdev has quit IRC00:16
*** kaminohana has joined #openstack-meeting00:23
*** aeng has quit IRC00:25
*** spotz is now known as spotz_zzz00:28
*** enriquetaso has quit IRC00:39
*** Julien-zte has joined #openstack-meeting00:43
*** ijw has quit IRC00:45
*** Julien-zte has quit IRC00:50
*** Julien-z_ has joined #openstack-meeting00:50
*** guoshan has joined #openstack-meeting00:52
*** mriedem has joined #openstack-meeting00:57
*** guoshan has quit IRC00:57
*** haleyb_ has joined #openstack-meeting00:58
*** tovin07 has joined #openstack-meeting00:59
*** tovin07 has quit IRC00:59
*** tovin07 has joined #openstack-meeting01:00
*** ijw has joined #openstack-meeting01:00
*** tovin07 has quit IRC01:01
*** Julien-zte has joined #openstack-meeting01:01
*** tovin07 has joined #openstack-meeting01:01
*** tovin07 has quit IRC01:02
*** tovin07 has joined #openstack-meeting01:02
*** Julien-z_ has quit IRC01:02
*** haleyb_ has quit IRC01:04
*** JRobinson__ is now known as JRobinson__afk01:07
*** pvaneck has quit IRC01:09
*** vmadden has joined #openstack-meeting01:13
*** penick has joined #openstack-meeting01:14
*** tovin07_ has joined #openstack-meeting01:15
*** penick_ has joined #openstack-meeting01:15
*** xingchao has joined #openstack-meeting01:16
*** chrisplo has quit IRC01:17
vmaddenwell hey all01:17
*** penick has quit IRC01:19
*** penick_ is now known as penick01:19
*** zhurong has joined #openstack-meeting01:19
*** guoshan has joined #openstack-meeting01:28
*** chrisplo has joined #openstack-meeting01:30
*** Alagar has joined #openstack-meeting01:31
*** JRobinson__afk is now known as JRobinson__01:34
*** chrisplo has quit IRC01:35
*** bobh has quit IRC01:35
*** ljxiash_ has quit IRC01:37
*** huanxuan has joined #openstack-meeting01:37
*** mtanino has joined #openstack-meeting01:43
*** kaisers has quit IRC01:43
*** kaisers has joined #openstack-meeting01:44
*** vmadden has quit IRC01:47
*** gcb has joined #openstack-meeting01:51
*** ljxiash has joined #openstack-meeting01:56
*** ljxiash has quit IRC01:57
*** ljxiash has joined #openstack-meeting01:57
*** haleyb_ has joined #openstack-meeting01:59
*** haleyb_ has quit IRC02:04
*** xingchao has quit IRC02:05
*** bbzhao has joined #openstack-meeting02:05
*** bzhao has quit IRC02:08
*** lhx_ has joined #openstack-meeting02:11
*** bobh has joined #openstack-meeting02:13
*** chrisplo has joined #openstack-meeting02:14
*** haleyb_ has joined #openstack-meeting02:15
*** haleyb_ has quit IRC02:18
*** haleyb_ has joined #openstack-meeting02:19
*** xingchao has joined #openstack-meeting02:19
*** bbzhao has quit IRC02:20
*** diga has quit IRC02:21
*** bzhao has joined #openstack-meeting02:22
*** gongysh has joined #openstack-meeting02:24
*** bbzhao has joined #openstack-meeting02:31
*** thorst has joined #openstack-meeting02:32
*** thorst has quit IRC02:32
*** thorst has joined #openstack-meeting02:33
*** aeng has joined #openstack-meeting02:33
*** bzhao has quit IRC02:34
*** bbzhao has quit IRC02:37
*** thorst has quit IRC02:40
*** thorst has joined #openstack-meeting02:41
*** donghao has joined #openstack-meeting02:42
*** thorst has quit IRC02:45
*** kaisers__ has joined #openstack-meeting02:46
*** mriedem has quit IRC02:46
*** bzhao has joined #openstack-meeting02:47
*** kaisers_ has quit IRC02:49
*** bobh has quit IRC02:49
*** fzdarsky_ has joined #openstack-meeting02:50
*** yamamoto has joined #openstack-meeting02:51
*** Alagar has quit IRC02:52
*** yamamoto has quit IRC02:52
*** JRobinson__ has quit IRC02:53
*** Alagar has joined #openstack-meeting02:53
*** s3wong has quit IRC02:53
*** JRobinson__ has joined #openstack-meeting02:53
*** fzdarsky|afk has quit IRC02:54
*** noslzzp has quit IRC02:55
*** Alagar has quit IRC02:55
*** bobh has joined #openstack-meeting02:57
*** Alagar has joined #openstack-meeting02:58
*** brault has quit IRC03:04
*** zhurong has quit IRC03:04
*** bobh has quit IRC03:04
*** huanxuan has quit IRC03:07
*** zhurong has joined #openstack-meeting03:07
*** thorst has joined #openstack-meeting03:09
*** thorst has quit IRC03:10
*** dmacpher has joined #openstack-meeting03:14
*** martines_ has quit IRC03:15
*** bobh has joined #openstack-meeting03:16
*** martines_ has joined #openstack-meeting03:16
*** huanxuan has joined #openstack-meeting03:17
*** epico has joined #openstack-meeting03:20
*** cschwede has quit IRC03:23
*** myoung has quit IRC03:24
*** kylek3h_ has quit IRC03:24
*** RonghUI has quit IRC03:24
*** kylek3h has joined #openstack-meeting03:25
*** myoung has joined #openstack-meeting03:25
*** marios has quit IRC03:26
*** marios has joined #openstack-meeting03:26
*** iyamahat has quit IRC03:27
*** cschwede has joined #openstack-meeting03:28
*** kylek3h has quit IRC03:29
*** yamahata has quit IRC03:29
*** aeng has quit IRC03:31
*** aeng has joined #openstack-meeting03:32
*** liusheng has quit IRC03:33
*** unicell has quit IRC03:34
*** lhx_ has quit IRC03:35
*** zhurong has quit IRC03:35
*** zhurong has joined #openstack-meeting03:35
*** thorst has joined #openstack-meeting03:36
*** csomerville has quit IRC03:36
*** thorst has quit IRC03:37
*** sankarshan_away is now known as sankarshan03:40
*** zhangjl has joined #openstack-meeting03:41
*** links has joined #openstack-meeting03:42
*** armax has quit IRC03:46
*** zhangjl has left #openstack-meeting03:50
*** ljxiash has quit IRC03:50
*** kevinz has joined #openstack-meeting03:54
*** Guest83036 has joined #openstack-meeting03:56
*** sudipto_ has joined #openstack-meeting03:56
*** ijw has quit IRC03:56
*** dmorita has quit IRC03:59
*** JRobinson__ is now known as JRobinson__afk04:00
*** ricolin has joined #openstack-meeting04:00
*** markvoelker has quit IRC04:02
*** bobh has quit IRC04:02
*** kevinz has quit IRC04:04
*** julim has quit IRC04:04
*** julim has joined #openstack-meeting04:05
*** julim has quit IRC04:05
*** guoshan has quit IRC04:07
*** SridharP has joined #openstack-meeting04:08
*** jgriffith is now known as jgriffith_away04:10
*** Julien-zte has quit IRC04:11
*** lhx_ has joined #openstack-meeting04:11
*** ljxiash has joined #openstack-meeting04:11
*** Julien-zte has joined #openstack-meeting04:12
*** ljxiash has quit IRC04:15
*** GB21 has joined #openstack-meeting04:17
*** aeng is now known as aeng_mtg04:18
*** dmorita has joined #openstack-meeting04:20
*** yamamoto has joined #openstack-meeting04:21
*** haleyb_ has quit IRC04:22
*** GB21 has quit IRC04:22
*** guoshan has joined #openstack-meeting04:23
*** yamamoto has quit IRC04:23
*** Alagar has quit IRC04:24
*** ijw has joined #openstack-meeting04:24
*** dmorita has quit IRC04:24
*** kylek3h has joined #openstack-meeting04:25
*** ijw has quit IRC04:29
*** yamahata has joined #openstack-meeting04:29
*** kylek3h has quit IRC04:30
*** guoshan has quit IRC04:34
*** GB21 has joined #openstack-meeting04:34
*** sankarshan is now known as sankarshan_away04:35
*** ishafran has quit IRC04:37
*** Guest83036 has quit IRC04:41
*** sudipto_ has quit IRC04:41
*** yamahata has quit IRC04:43
*** Alagar has joined #openstack-meeting04:44
*** julim has joined #openstack-meeting04:45
*** julim has quit IRC04:50
*** yamamoto has joined #openstack-meeting04:54
*** yamamoto has quit IRC04:54
*** lpetrut has joined #openstack-meeting04:54
*** guoshan has joined #openstack-meeting05:02
*** jogo has joined #openstack-meeting05:02
*** jogo has quit IRC05:02
*** jogo has joined #openstack-meeting05:02
*** ayogi has joined #openstack-meeting05:02
*** ljxiash has joined #openstack-meeting05:03
*** JRobinson__afk is now known as JRobinson__05:03
*** sankarshan_away is now known as sankarshan05:05
*** yamahata has joined #openstack-meeting05:05
*** aeng_mtg has quit IRC05:08
*** klkumar has joined #openstack-meeting05:12
*** guoshan has quit IRC05:12
*** aeng_mtg has joined #openstack-meeting05:13
*** unicell has joined #openstack-meeting05:14
*** julim has joined #openstack-meeting05:16
*** Alagar has quit IRC05:16
*** prateek has joined #openstack-meeting05:18
*** Alagar has joined #openstack-meeting05:20
*** julim has quit IRC05:21
*** jogo has quit IRC05:22
*** unicell has quit IRC05:26
*** kylek3h has joined #openstack-meeting05:26
*** unicell has joined #openstack-meeting05:26
*** sandanar has joined #openstack-meeting05:30
*** kylek3h has quit IRC05:31
*** sandanar_ has joined #openstack-meeting05:34
*** trinaths has joined #openstack-meeting05:34
*** lhx_ has quit IRC05:38
*** sandanar has quit IRC05:38
*** lpetrut has quit IRC05:48
*** anilvenkata has joined #openstack-meeting05:49
*** gongysh has quit IRC05:49
*** sudipto_ has joined #openstack-meeting05:50
*** Guest83036 has joined #openstack-meeting05:50
*** Alagar has quit IRC05:52
*** yamamoto has joined #openstack-meeting06:02
*** markvoelker has joined #openstack-meeting06:02
*** dmacpher has quit IRC06:03
*** lhx_ has joined #openstack-meeting06:04
*** guoshan has joined #openstack-meeting06:06
*** liusheng has joined #openstack-meeting06:07
*** markvoelker has quit IRC06:08
*** Alagar has joined #openstack-meeting06:12
*** zhangshuai has joined #openstack-meeting06:12
*** rbartal has joined #openstack-meeting06:16
*** ricolin has quit IRC06:17
*** vishnoianil has quit IRC06:17
*** aeng_mtg is now known as aeng_afk06:18
*** jogo has joined #openstack-meeting06:20
*** jogo has quit IRC06:20
*** jogo has joined #openstack-meeting06:20
*** janki has joined #openstack-meeting06:26
*** kylek3h has joined #openstack-meeting06:27
*** epico has quit IRC06:29
*** vishnoianil has joined #openstack-meeting06:30
*** kylek3h has quit IRC06:31
*** ricolin has joined #openstack-meeting06:34
*** yamamoto has quit IRC06:34
*** sridharg has joined #openstack-meeting06:35
*** xiaofandh12 has joined #openstack-meeting06:37
*** nadya has joined #openstack-meeting06:37
*** nadya has quit IRC06:38
*** donghao has quit IRC06:38
*** yamamoto has joined #openstack-meeting06:43
*** yamamoto has quit IRC06:43
*** zengchen has quit IRC06:45
*** ricolin has quit IRC06:46
*** yamamoto has joined #openstack-meeting06:51
*** yamamoto has quit IRC06:57
*** jdurgin1 has joined #openstack-meeting06:57
*** bvandenh has joined #openstack-meeting06:59
*** huanxuan has quit IRC07:08
*** huanxuan has joined #openstack-meeting07:09
*** kaminohana has quit IRC07:10
*** nadya has joined #openstack-meeting07:12
*** nadya has quit IRC07:12
*** tesseract has joined #openstack-meeting07:12
*** Alagar has quit IRC07:12
*** Guest2_ has joined #openstack-meeting07:12
*** rasca has joined #openstack-meeting07:12
*** Alagar has joined #openstack-meeting07:12
*** tesseract is now known as Guest5952807:13
*** numans has joined #openstack-meeting07:17
*** nkrinner_afk is now known as nkrinner07:17
*** nkrinner has quit IRC07:19
*** GB21 has quit IRC07:21
*** astudenov has joined #openstack-meeting07:23
*** e0ne has joined #openstack-meeting07:24
*** nkrinner has joined #openstack-meeting07:24
*** nadya has joined #openstack-meeting07:27
*** kylek3h has joined #openstack-meeting07:28
*** nkrinner has quit IRC07:29
*** nkrinner has joined #openstack-meeting07:29
*** korzen has joined #openstack-meeting07:30
*** gouthamr has joined #openstack-meeting07:31
*** kylek3h has quit IRC07:32
*** shengping has joined #openstack-meeting07:34
*** brault has joined #openstack-meeting07:39
*** yamahata has quit IRC07:39
*** e0ne has quit IRC07:45
*** lpetrut has joined #openstack-meeting07:46
*** GB21 has joined #openstack-meeting07:53
*** matrohon has joined #openstack-meeting07:56
*** dvladar has joined #openstack-meeting08:01
*** frasantoro has joined #openstack-meeting08:03
*** yamamoto has joined #openstack-meeting08:08
*** huanxuan has quit IRC08:08
*** SridharP has quit IRC08:08
*** JRobinson__ has quit IRC08:11
*** dimtruck is now known as zz_dimtruck08:11
*** Guest2_ has quit IRC08:14
*** epico has joined #openstack-meeting08:14
*** Viet_Tran has joined #openstack-meeting08:18
*** yamamoto has quit IRC08:19
*** maishsk has joined #openstack-meeting08:19
*** maishsk has quit IRC08:19
*** nmagnezi has joined #openstack-meeting08:20
*** ralonsoh has joined #openstack-meeting08:20
*** iyamahat has joined #openstack-meeting08:20
*** derekjhyang has quit IRC08:21
*** yamamoto has joined #openstack-meeting08:23
*** SridharP has joined #openstack-meeting08:27
*** e0ne has joined #openstack-meeting08:28
*** kylek3h has joined #openstack-meeting08:28
*** yamamoto has quit IRC08:29
*** yamamoto has joined #openstack-meeting08:30
*** kylek3h has quit IRC08:33
*** e0ne has quit IRC08:34
*** yamamoto has quit IRC08:35
*** huanxuan has joined #openstack-meeting08:36
*** Alagar has quit IRC08:48
*** makowals has quit IRC08:49
*** makowals_ has joined #openstack-meeting08:49
*** shengping has quit IRC08:51
*** yuval has joined #openstack-meeting08:51
*** sofianes has joined #openstack-meeting08:56
*** priteau has joined #openstack-meeting08:56
*** GeraldK has joined #openstack-meeting08:56
*** rossella__ has joined #openstack-meeting08:57
*** oneswig has joined #openstack-meeting08:58
oneswigGood morning, time to get going09:00
oneswig#startmeeting scientific_wg09:00
openstackMeeting started Wed Nov 23 09:00:25 2016 UTC and is due to finish in 60 minutes.  The chair is oneswig. Information about MeetBot at
openstackUseful Commands: #action #agreed #help #info #idea #link #topic #startvote.09:00
*** openstack changes topic to " (Meeting topic: scientific_wg)"09:00
openstackThe meeting name has been set to 'scientific_wg'09:00
oneswig#link today's agenda
*** gongysh has joined #openstack-meeting09:01
oneswigBlair says he'll be in-and-out today - you hear yet Blair?09:01
*** arxcruz has joined #openstack-meeting09:01
oneswigLets give people a minute or two to gather09:02
*** b1airo has joined #openstack-meeting09:02
oneswig#topic Wrap up from Supercomputing 201609:03
*** openstack changes topic to "Wrap up from Supercomputing 2016 (Meeting topic: scientific_wg)"09:03
oneswig#chair b1airo09:03
openstackCurrent chairs: b1airo oneswig09:03
oneswigEvening b1airo09:03
oneswigJust getting started on SC wrap-up09:03
oneswigWell it was a good show, my first time.  The level of OpenStack interest was high but I have no prior experience to gauge the upward trend09:04
*** xiaofandh12 has quit IRC09:04
b1airoI only got home from SLC yesterday!09:04
oneswigGo by bike? :-)09:04
*** sofianes_ has joined #openstack-meeting09:04
b1airoHa! Just left via Bryce Canyon09:04
*** gouthamr has quit IRC09:04
b1airoIt was a good conference for OpenStack I think09:05
oneswigThe nice people at SuperUser invited us to write a trip report based on the roundup I wrote on the company blog09:05
oneswigNot massively detailed though...09:05
b1airoHeh - are they paying for our expenses? :-)09:06
priteauGreat job on getting science on the homepage!09:06
oneswigpriteau: Kate did a great job in the panel session, it was good to meet her again09:06
oneswigpriteau: I know - incredible isn't it!09:06
*** StefanPaetowJisc has joined #openstack-meeting09:06
StefanPaetowJiscGood morning all09:07
priteauWill you get statistics on number of book downloads?09:07
oneswigSo quite a few expectations to live up to there09:07
*** verdurin has joined #openstack-meeting09:07
oneswigmorning StefanPaetowJisc09:07
*** toscalix has joined #openstack-meeting09:07
*** sofianes has quit IRC09:07
oneswigpriteau: I expect I could ask, that would be good to know09:07
oneswigHi verdurin09:07
oneswigI don't think there was any more to add on SC - anyone else?09:08
oneswigOK lets go to the next item09:09
oneswig#item Scientific datasets - update from Sofiane09:09
oneswig#topic Scientific datasets - update from Sofiane09:09
*** openstack changes topic to "Scientific datasets - update from Sofiane (Meeting topic: scientific_wg)"09:09
sofianes_hi all09:09
sofianes_I just shared a document with you09:09
oneswigHi Sofiane, how are you doing09:09
sofianes_There's a summary of what we are doing09:09
*** iyamahat has quit IRC09:09
sofianes_We are building an academic cloud for Swiss Universities09:10
sofianes_and have numerous services on top of the infrastructure09:10
sofianes_which runs on OpenStack09:10
sofianes_SWITCH is hosting and operating the infrastructure09:11
sofianes_among the applications, we have big data and data science in general09:11
sofianes_and we need to host large datasets09:11
sofianes_compute has to be done close to the data09:11
oneswigWhat do you expect the interface to be for users seeking access to specific datasets?09:12
sofianes_direct access from any application susing S3 or SWIFT09:12
sofianes_or specific access with higher level APIs09:12
oneswigAre you thinking of creating a directory service?09:13
sofianes_We will definitely build a catalog09:13
sofianes_with appropriate search functionalities09:14
oneswigDo you expect it to be integrated with Horizon, or a separate freestanding catalog?09:14
sofianes_but there are many things that need improvment in the OpenStack ecosystem09:14
verdurinsofianes_: the higher level APIs are for applications that don't understand objects?09:14
sofianes_Sahara, bare emtal09:14
sofianes_bare metal09:14
sofianes_verdurin: yes09:15
sofianes_we are also thinking about the possibility to co-host datasets09:15
sofianes_with other interested insititutions09:16
*** StefanPaetowJisc has quit IRC09:16
sofianes_saverio has already initiated that with other NRENs09:16
*** StefanPaetowJisc has joined #openstack-meeting09:16
oneswigDo you also expect to provide access control to the datasets or can every user access every dataset all the time?09:16
b1airoIMHO this sort of hosting may be better served by something like CVFS09:16
sofianes_public data will be open09:16
oneswigb1airo: new to me, got a link?09:16
verdurinsofianes_: do you have details on what's missing for your use-case, that might be turned into blueprints?09:17
sofianes_private data will requires ACLs09:17
verdurinb1airo: do you mean CVMFS?09:17
oneswigAs in CERN VM FS?09:17
b1airoIt would offer a more familiar interface for legacy applications and is already designed to distribute data around the Internet09:17
b1airoYes, CVMFS sorry09:17
sofianes_I am not famililar with CVMFS09:17
sofianes_but will look at it09:17
sofianes_performance is very important09:18
b1airoAnd I should clarify - I don't mean instead of Swift, but as potential complim09:18
b1airo*compliment (sorry, on phone)09:18
sofianes_the direction in which we will go will be directed by the use cases09:18
oneswigsofianes_: my understanding is that it is an HTTP-delivered filesystem overlay.  The particle physics people use it with a minimal VM image to attach specific code/data - right?09:19
sofianes_we have aleady posted a bug report for sahara09:19
verdurinoneswig: yes, that's right09:19
*** tpsilva has joined #openstack-meeting09:19
verdurinoneswig: it has wider uses than that, i.e. not just for Micro-CernVM09:20
sofianes_our typical use cases come from machine learning, text analysis, genomics09:20
oneswigsofianes_: I notice billing in the SWITCH diagram - any plans to charge for access?09:20
sofianes_we have two directions09:20
sofianes_either have the datasets as an added value to attract users09:20
sofianes_or build a market place for data (not trivial)09:21
sofianes_oneswig: could you tell us more about the paricle physics use case?09:21
oneswigI don't know if there is a precedent for charging for datasets, might be problematic...09:21
sofianes_Microsoft is actually doing that on Azure09:22
oneswigI agree - good to have them as an attractor to your platform (which might then be charged for in usual ways)09:22
oneswigsofianes_: interesting!09:22
StefanPaetowJiscPossibly cross charging...09:22
sofianes_it makes sense for commercial applications where you consume data and sell services. You basicaly act as a broker in that case09:22
oneswigsofianes_: I'm not sure I have a link to CVMFS - anyone?09:22
verdurinsofianes_: they have a minimal VM image that pulls in experiment-specific software via CVMFS09:23
verdurinSo in WLCG it's primarily used for distributing software, but could be used for datasets too09:24
sofianes_there are also alternatives to expose S3 as a file system09:25
verdurinworldwide LHC computing group09:25
StefanPaetowJiscEspecially since it's read-only... :-)09:25
oneswig2 level acronym!09:25
sofianes_like this:
verdurinDe rigeur.09:25
StefanPaetowJiscDamn that HEP community... :-D09:25
verdurinsofianes_: I'm sure I came across a US group that was using it for data, but can't remember where right now09:26
verdurin(i.e. a non-HEP group)09:26
sofianes_if you find out, please let me know09:26
*** powerd has joined #openstack-meeting09:26
StefanPaetowJiscverdurin: possibly Jim Basney's group?09:26
sofianes_we are open to collaboration/sharing experience09:26
StefanPaetowJiscI can ask09:26
*** sshnaidm|away is now known as sshnaidm09:26
b1airoWe could ask Tim et al09:26
oneswigWhat do Globus do in this area?09:27
sofianes_our interest is not only about making data available for download09:27
sofianes_but mainly to bring computation to where data sits09:28
sofianes_that's at the heart of the hadoop principles09:28
oneswigThe holy grail...09:28
priteauoneswig: they have data publication and discovery capabilities
sofianes_for very large data, it's cheaper to move computation09:28
priteauit seems to be a commercial hosted service09:29
verdurinSome of the genomics data at Sanger is made available via Globus Connect09:29
sofianes_actually we have a mirror of that data09:29
sofianes_I want to add one thing09:29
sofianes_some datasets are so large09:29
sofianes_that you simply can't download them09:29
*** kylek3h has joined #openstack-meeting09:29
oneswigsofianes_: do you think there is value in a user story here?  I think there could be.09:29
sofianes_human genome which can be obtined through Globus is more than 100TB09:30
sofianes_common crawl, which is a crawl of the web is 500+ TB09:30
sofianes_this is said for static data09:30
sofianes_but we also have users interested in real time data09:31
*** rossella__ has quit IRC09:31
*** geguileo_out is now known as geguileo09:31
oneswigHence moving code to the data09:31
sofianes_they need to subscribe to streams09:31
sofianes_these can be weather or traffic data09:31
sofianes_or anything that comes from IOT09:31
*** rossella__ has joined #openstack-meeting09:31
sofianes_we are also working on such use cases09:31
sofianes_we receive data in real time, and users can selecte specific feeds09:32
*** markvoelker has joined #openstack-meeting09:32
sofianes_data can also be persisted and becomes historical data09:32
oneswigWhat are the gaps in OpenStack or does everything discussed build upon today's OpenStack?09:32
*** lin_yang has quit IRC09:33
sofianes_we have sahara and bare metal09:33
sofianes_but solutions don't seem to be mature enough09:33
oneswigI haven't heard of anyone using bare metal with swift - does it work?09:34
sofianes_ceph and swift have also issues with large objects09:34
*** kylek3h has quit IRC09:34
*** Julien-zte has quit IRC09:34
priteauoneswig: We use Swift from bare-metal instances. There's no reason for it not to work, it's all HTTP requests09:34
sofianes_support for hadoop is still not very established09:35
oneswigpriteau: I guess so - wasn't sure which network they'd be transported over09:35
oneswigsofianes_: there was a bug mentioned in Barcelona on Sahara with large objects - any news on that?09:35
*** egallen has joined #openstack-meeting09:36
sofianes_I have nothing new on that09:36
sofianes_I will ask saverio09:36
oneswigSaverio not here?  Saverio...?09:36
*** markvoelker has quit IRC09:37
b1airoWasn't that an issue with the related hdfs plugin rather than Swift?09:37
oneswigah, think you're right09:37
sofianes_if any of you is interested in our topic, your welcome to contact me09:37
oneswigsofianes_: would you be interested in transferring the google doc into a user story?09:37
b1airoWe are working on deploying Sahara in NeCTAR at the moment too09:38
sofianes_yes for the user story09:38
oneswigGreat, thanks sofianes_09:38
oneswig#action sofianes_ to transfer the google doc on data sharing into a user story09:38
*** adiantum has joined #openstack-meeting09:39
*** strigazi_AFK is now known as strigazi09:39
oneswigb1airo: any comment on how Sahara is working in Nectar?09:39
b1airoMain issue we've found is that current version defaults to putting Hadoop job binaries in rdbms09:40
b1airoShould be in object store for a large prod cloud, especially where users are not trusted/known09:41
oneswigHow responsive are the sahara crowd?09:41
sofianes_using object as back end for hadoop seems to be the current trned at least in public clouds (AWS, Azure, GCP)09:42
b1airoReasonably, problem is already being addressed09:42
*** dbecker has joined #openstack-meeting09:42
sofianes_when you deploy a cluster, storage is embeded in HDFS within the cluster09:42
sofianes_using objectr storage is a good compromise to share data09:43
oneswigI'd be interested to see performance comparisons, does seem to me to be breaking some assumptions about hadoop (unless I'm misunderstanding it)09:43
*** yuval has quit IRC09:43
sofianes_we have that on our roadmap09:44
oneswigAnyway, we have other topics, any more on big data & sahara?09:44
sofianes_performance  comparison09:44
sofianes_S3 vs HDFS09:44
oneswigsofianes_: would be interested to see that09:44
sofianes_and otjer dimensions as well09:44
sofianes_we will share our findings09:44
oneswigOK thanks sofianes_09:45
sofianes_typo: other dimensions as well09:45
*** astudenov has quit IRC09:45
oneswig#topic Federation user story up for review09:45
*** openstack changes topic to "Federation user story up for review (Meeting topic: scientific_wg)"09:45
oneswigSaverio's not here but there is a WG user story in review09:45
oneswigon identity federation09:45
oneswigPlease comment if it's an area of interest for you - I recall aloga had some questions about the original etherpad this user story came from09:46
StefanPaetowJiscI'll have to review that story again...09:46
b1airoCool - I will seek input locally09:46
oneswigGreat!  Want to make sure it's consistent with global experience09:47
oneswigDon't think there's any more to cover on this... anyone?09:48
oneswig#topic Cloud workload traces09:48
*** openstack changes topic to "Cloud workload traces (Meeting topic: scientific_wg)"09:48
oneswigLate addition to the agenda - b1airo want to cover this?09:49
alogasorry guys, I arrived late09:49
oneswigHi aloga09:49
b1airoSure - briefly09:50
oneswigaloga: Got backscroll?  Feedback here:
alogaoneswig: yes, I was catching up09:50
b1airoKate Keahey's BoF at SC raised the topic of getting cloud workload traces for ComSci work (e.g. scheduling simulation etc)09:51
oneswigIs this infrastructure or higher-level?09:51
alogaoneswig: I will go through the review and comment there, I still have concerns about the 2nd use case that is described there (i.e. L156-160)09:51
alogai.e. who will benefit from that use case09:52
aloga(same applies for user story 3)09:52
b1airoShe isn't sure what data they want yet, needs to do a review of existing archives from prior grid work, but we discussed the potential to have the work supported through this community so as to gain wider audience09:52
*** GeraldK has quit IRC09:53
oneswigWe have a project for OpenStack distributed profiling.  For user applications, how about
oneswig... which I would also love to see ...09:53
oneswigb1airo: I'd love to hear more, hopefully we can do a monitoring & telemetry session next week and she might attend?09:54
b1airoYes we need to invite her or a team member09:54
oneswig... know anyone ... ? :-)09:55
priteauoneswig: I am not sure we are on the same page, the traces we have in mind are the equivalent of job traces in hpc, ie instance creation / update / termination events09:55
b1airopriteau: yes that's what I thought, at least for initial data09:56
oneswigpriteau: possibly more on the same page than you think!  We've been looking at connecting SLURM with Monasca09:56
b1airoSo e.g. nova-scheduler logs09:56
oneswigSo this is infrastructure event tracing?09:56
b1airoBut the more data the better I assume09:56
oneswigNow I am even more interested.09:57
priteauoneswig: I was referring to your link to zipkin which seems to be more about inter-service call timings?09:57
oneswigOK, I previously took an action to define our use case - will do that for next week09:58
oneswigpriteau: wasn't sure if you were looking at infrastructure or application profiling09:58
oneswigwe are looking at profiling "infrastructure-plus", ie a bit of the stuff above09:59
oneswig#action oneswig to write up the profiling telemetry use case for next wee10:00
verdurinHave to go - bye.10:00
oneswigahem. week10:00
oneswigout of time!10:00
oneswigThanks all, we'd better clear the channel10:00
alogapriteau: we are interested on that10:00
*** openstack changes topic to "OpenStack Meetings ||"10:00
openstackMeeting ended Wed Nov 23 10:00:52 2016 UTC.  Information about MeetBot at . (v 0.1.4)10:00
openstackMinutes (text):
StefanPaetowJiscOk. Speak to you guys soon. Am at CERN next week...10:01
oneswigGreat session all, thank you10:01
*** zhurong has quit IRC10:01
*** StefanPaetowJisc has quit IRC10:01
priteaualoga: excellent! Are your contact details on the summit etherpad?10:02
b1airoBye all!10:02
alogapriteau: yes10:03
alogapriteau: or on lp10:03
dvladarthanks for the session - learned a lot today :).10:03
alogapriteau: and I am always online on IRC10:03
*** acoles_ is now known as acoles10:03
*** donghao has joined #openstack-meeting10:04
*** tovin07_ has quit IRC10:06
*** Viet_Tran has quit IRC10:06
*** hashar has joined #openstack-meeting10:07
*** donghao has quit IRC10:09
*** sofianes_ has quit IRC10:13
*** electrofelix has joined #openstack-meeting10:14
*** gongysh has quit IRC10:15
*** zhangshuai has quit IRC10:17
*** julim has joined #openstack-meeting10:21
*** guoshan has quit IRC10:22
*** zhangshuai has joined #openstack-meeting10:23
*** sambetts|afk is now known as sambetts10:24
*** ygbo has joined #openstack-meeting10:25
*** julim has quit IRC10:25
*** claudiub|2 has joined #openstack-meeting10:29
*** numans has quit IRC10:30
*** numans has joined #openstack-meeting10:33
*** korzen has quit IRC10:33
*** cebruns__ has joined #openstack-meeting10:35
*** pkoniszewski has quit IRC10:35
*** dvladar has quit IRC10:35
*** isq has quit IRC10:35
*** cebruns has quit IRC10:35
*** korzen has joined #openstack-meeting10:44
*** pkoniszewski has joined #openstack-meeting10:44
*** xingchao has quit IRC10:47
*** xingchao has joined #openstack-meeting10:49
*** dongfeng has joined #openstack-meeting10:51
*** nadya has quit IRC10:53
*** kevinz has joined #openstack-meeting10:55
*** xingchao has quit IRC10:55
*** lhx__ has joined #openstack-meeting10:55
*** huanxuan has quit IRC10:56
*** lhx_ has quit IRC10:58
*** longxiongqiu has joined #openstack-meeting11:00
*** dteselkin has quit IRC11:00
*** sankarshan is now known as sankarshan_away11:01
*** sankarshan_away is now known as sankarshan11:01
*** rakhmerov has quit IRC11:01
*** akuznetsova has quit IRC11:02
*** akuznetsova has joined #openstack-meeting11:02
*** priteau has quit IRC11:02
*** IgorYozhikov has quit IRC11:03
*** IgorYozhikov has joined #openstack-meeting11:03
*** nadya has joined #openstack-meeting11:04
*** rakhmerov has joined #openstack-meeting11:05
*** longxiongqiu has quit IRC11:05
*** yangyapeng has joined #openstack-meeting11:05
*** longxiongqiu has joined #openstack-meeting11:07
*** dteselkin has joined #openstack-meeting11:07
*** epico has quit IRC11:09
*** numans has quit IRC11:13
*** GB21 has quit IRC11:14
*** kevinz has quit IRC11:14
*** igordcard has quit IRC11:14
*** kevinz has joined #openstack-meeting11:15
*** yuval has joined #openstack-meeting11:15
*** yuval has quit IRC11:15
*** igordcard has joined #openstack-meeting11:15
*** adiantum has quit IRC11:17
*** sankarshan is now known as sankarshan_away11:17
*** dongfeng has quit IRC11:17
*** adiantum has joined #openstack-meeting11:20
*** donghao has joined #openstack-meeting11:21
*** priteau has joined #openstack-meeting11:21
*** guoshan has joined #openstack-meeting11:22
*** fzdarsky_ is now known as fzdarsky11:24
*** fzdarsky is now known as fzdarsky|lunch11:24
*** Guest83036 has quit IRC11:26
*** sudipto_ has quit IRC11:26
*** guoshan has quit IRC11:27
*** GB21 has joined #openstack-meeting11:30
*** kevinz has quit IRC11:33
*** kevinz has joined #openstack-meeting11:34
*** kylek3h has joined #openstack-meeting11:34
*** sridharg has quit IRC11:37
*** prateek has quit IRC11:37
*** kylek3h has quit IRC11:39
*** sridharg has joined #openstack-meeting11:40
*** lpetrut has quit IRC11:42
*** numans has joined #openstack-meeting11:42
*** lpetrut has joined #openstack-meeting11:42
*** alexpilotti has joined #openstack-meeting11:43
*** alexpilo_ has quit IRC11:43
*** liukun has joined #openstack-meeting11:46
*** priteau has quit IRC11:50
*** e0ne has joined #openstack-meeting11:50
*** priteau has joined #openstack-meeting11:50
*** claudiub has joined #openstack-meeting11:52
*** sridharg has quit IRC11:53
*** claudiub|2 has quit IRC11:54
*** priteau has quit IRC11:55
*** korzen_ has joined #openstack-meeting11:55
*** trinaths has quit IRC11:55
*** priteau has joined #openstack-meeting11:55
*** mkoderer has joined #openstack-meeting11:59
*** zhhuabj_ has quit IRC12:01
*** dongfeng has joined #openstack-meeting12:03
*** raildo has joined #openstack-meeting12:05
*** GB21 has quit IRC12:05
*** prateek has joined #openstack-meeting12:05
*** jaypipes has quit IRC12:06
*** prateek has quit IRC12:07
*** prateek has joined #openstack-meeting12:08
*** prateek has quit IRC12:10
*** GB21 has joined #openstack-meeting12:12
*** alexpilotti has quit IRC12:12
*** alexpilotti has joined #openstack-meeting12:12
*** sudipto_ has joined #openstack-meeting12:13
*** Guest83036 has joined #openstack-meeting12:13
*** zhhuabj_ has joined #openstack-meeting12:14
*** gongysh has joined #openstack-meeting12:15
*** prateek has joined #openstack-meeting12:17
*** gongysh has quit IRC12:17
*** GB21 has quit IRC12:17
*** prateek has quit IRC12:17
*** prateek has joined #openstack-meeting12:18
*** sridharg has joined #openstack-meeting12:19
*** guoshan has joined #openstack-meeting12:23
*** b1airo has quit IRC12:23
*** prateek has quit IRC12:24
*** prateek has joined #openstack-meeting12:25
*** huanxuan has joined #openstack-meeting12:26
*** rtheis has joined #openstack-meeting12:26
*** rtheis has quit IRC12:26
*** guoshan has quit IRC12:28
*** gouthamr has joined #openstack-meeting12:32
*** spligak has quit IRC12:35
*** kylek3h has joined #openstack-meeting12:36
*** spligak has joined #openstack-meeting12:36
*** nadya has quit IRC12:37
*** sankarshan_away is now known as sankarshan12:40
*** weshay_ has quit IRC12:40
*** SridharP has quit IRC12:40
*** kylek3h has quit IRC12:40
*** GB21 has joined #openstack-meeting12:43
*** nadya has joined #openstack-meeting12:45
*** nadya has quit IRC12:46
*** fzdarsky|lunch is now known as fzdarsky12:47
*** kylek3h has joined #openstack-meeting12:52
*** jaypipes has joined #openstack-meeting12:53
*** links has quit IRC12:54
*** joehuang has joined #openstack-meeting12:54
*** huanxuan_ has joined #openstack-meeting12:54
*** yinxiulin has joined #openstack-meeting12:56
*** dprince has joined #openstack-meeting12:56
*** sankarshan is now known as sankarshan_away12:57
*** huanxuan has quit IRC12:57
*** Rhett has joined #openstack-meeting12:59
*** hejiawei has joined #openstack-meeting12:59
*** RongHui11 has joined #openstack-meeting13:00
*** Yipei has joined #openstack-meeting13:00
openstackjoehuang: Error: A meeting name is required, e.g., '#startmeeting Marketing Committee'13:00
*** dmorita has joined #openstack-meeting13:00
joehuang#startmeeting tricircle13:00
openstackMeeting started Wed Nov 23 13:00:54 2016 UTC and is due to finish in 60 minutes.  The chair is joehuang. Information about MeetBot at
openstackUseful Commands: #action #agreed #help #info #idea #link #topic #startvote.13:00
*** openstack changes topic to " (Meeting topic: tricircle)"13:00
openstackThe meeting name has been set to 'tricircle'13:01
joehuang#topic rollcall13:01
*** openstack changes topic to "rollcall (Meeting topic: tricircle)"13:01
joehuang#info joehuang13:01
RongHui11#info ronghui13:01
zhiyuan#info zhiyuan13:01
longxiongqiu#info longxiongqiu13:01
yinxiulin#info xiulin13:01
Yipei#info Yipei13:01
*** liuzeyu has joined #openstack-meeting13:01
dongfeng#info dongfeng13:02
hejiawei#info jiawei13:02
joehuang#topic Ocata feature development review13:02
*** openstack changes topic to "Ocata feature development review (Meeting topic: tricircle)"13:02
*** ljxiash has quit IRC13:02
joehuanglet's have a short review for the feature development, the coming milestone is in the middle of Dec13:03
joehuangplease have a brief description of the feature you are working for13:03
*** liuzeyu has quit IRC13:03
dongfengthe patch for documentation for resource routing is in review, and the blueprint for resource routing is also in review.13:04
*** dmorita has quit IRC13:05
zhiyuan(1) the manual installation guide is under review. (2) the spec for combined bridge network is under review (3) the code for combined bridge network is under development, I will start to test the code with DevStack tomorrow13:05
joehuangto Dongfeng, yes, just receive the notification of the blueprint13:05
*** GB21 has quit IRC13:06
RongHui11for the configuraton i still try to use the document tools to get the configuraton guide13:06
*** priteau has quit IRC13:06
joehuangis there anyone install tricircle according to the manual13:06
RongHui11i install the tircircle according th the manual for singlenode13:07
RongHui11not the manual13:08
RongHui11is the devstack13:08
*** Junsik has joined #openstack-meeting13:09
*** mtanino has quit IRC13:09
joehuangyou can install the devstack without tricircle first, then try to configure the tricircle according to the manual guide13:09
joehuanghello Junsik, not see you some time13:09
*** korzen_ has quit IRC13:09
RongHui11i will try it13:10
joehuangto Zhiyuan, thank you for your great effort13:10
Yipeiimplement LBaaS for tricircle, still studying LBaaS. plan to run LBaaS in one OpenStack instance.13:10
joehuangthank you, ronghui13:10
joehuangto yipei, great13:11
joehuangLBaaS is applying openstack bigtent13:11
Yipeiwill try installing devstack tomorrow by following the manual13:11
joehuangthe project name is Ocataiva13:11
*** lhx__ has quit IRC13:12
Yipeiok, i will pay more attention to the project13:12
joehuangyou can refer to this guide:
*** noslzzp has joined #openstack-meeting13:13
joehuangthis is mitaka version, you'd better to read the newton release13:13
Yipeiok, got it. thx for sharing13:14
yinxiulin I am learning tricircle design documents. plan to start resource update function next week13:14
joehuangyou can discuss any questions in mail-list or irc13:15
*** noslzzp has quit IRC13:15
joehuangHello, there are several patches in review13:15
*** noslzzp has joined #openstack-meeting13:16
joehuangI hope that everyone can spend some time to review other's patch13:16
joehuangyou can have more broad knowledge on what's being developed, and improve the quality of each patch13:17
Yipeiok, got it13:18
joehuangthank you all, we are a team, team work can make everything better13:19
*** Guest59528 has quit IRC13:19
joehuang#topic Py35, Ubuntu Xenial gate and check jobs13:19
*** openstack changes topic to "Py35, Ubuntu Xenial gate and check jobs (Meeting topic: tricircle)"13:19
*** priteau has joined #openstack-meeting13:20
*** yinxiulin has quit IRC13:21
joehuangaccording to community requirement13:21
joehuangall project needs to adapt to pyhon313:21
joehuangand tested in ubuntu xenial release13:22
zhiyuanto support python 3, we need to use "six" library in the list and dict traverse13:23
joehuangafter the jobs enabled, two more jobs will be added in the gate and check test, but at first it's not voting job, that means it's ok if it failed13:24
joehuangto zhiyuan, yes, some update is needed13:24
*** yinxiulin has joined #openstack-meeting13:24
zhiyuanwhen will the two jobs become voting job?13:25
*** yamamoto has joined #openstack-meeting13:25
joehuangwe needs to fix the error in the failure job step by step, at last in this release, we should be able to migrate to python3 and xenial13:26
joehuangno, non-voting jobs13:26
*** prateek_ has joined #openstack-meeting13:26
joehuangafter all failure are fixed, I hope by the end of Ocata release13:27
joehuangthe earlier, the better13:27
joehuangthe sooner, the better13:27
joehuangit'll take one week or so to enable these jobs13:28
joehuangand one more job doc-publisher-site: is also added13:28
*** ljxiash has joined #openstack-meeting13:28
*** SridharP has joined #openstack-meeting13:28
*** markvoelker has joined #openstack-meeting13:28
zhiyuani think we just enable the jobs then we know what error needs to be fixed13:28
joehuangthat means all docs of tricircle will be published to website13:29
*** prateek has quit IRC13:30
joehuangthe jobs will report failure, but will not block any patch's merge13:30
*** priteau has quit IRC13:30
*** Menthos has joined #openstack-meeting13:30
*** ljxiash has quit IRC13:31
zhiyuanso if the doc job fails, the doc will not be updated in the website?13:32
*** ljxiash has joined #openstack-meeting13:32
joehuangit's better if someone of us can install tricircle under python35, and execute the pep8/unit/functest to see what error occured13:32
*** Guest83036 has quit IRC13:32
*** sudipto_ has quit IRC13:32
joehuanginfra team always suggest to enable a job as non-voting at first, after it's stable for the job, then make it as voting job13:34
*** Julien-zte has joined #openstack-meeting13:34
joehuangcurrently our doc test is successfully for each patch13:35
zhiyuanwe can use virtualenv to setup a python3 environment13:35
joehuangBut it's strange that all jobs are already ubuntu-xenial based13:36
joehuangfor example, I am not sure whether we need to enable special job for xenial13:36
*** xyang1 has joined #openstack-meeting13:36
*** Rhett has quit IRC13:37
joehuangyes, venv is a good way to try python313:37
joehuangor container13:37
zhiyuani think our test is already runnint on xenial, we just need to enable python3 test13:38
joehuangwill consult that in infra team13:38
*** lhx__ has joined #openstack-meeting13:39
*** lamt has joined #openstack-meeting13:39
joehuang#action consult infra team whether tricircle needs to enable special xenial jobs or alreay support that13:39
joehuang#topic open discussion13:40
*** openstack changes topic to "open discussion (Meeting topic: tricircle)"13:40
joehuangany topic to discuss?13:41
zhiyuanfor me, there may be risk to support shared vxlan network in this circle13:41
RongHui11no for me13:41
zhiyuanif we are going to follow the "vtep info in port" change in neutron13:42
*** baoli has joined #openstack-meeting13:43
*** baoli has quit IRC13:43
*** priteau has joined #openstack-meeting13:43
joehuangto zhiyuan, understand the risk13:43
*** baoli has joined #openstack-meeting13:43
joehuangwe need to work closely with anil for this feature13:44
*** jamesdenton has joined #openstack-meeting13:44
joehuangat the same time, enhance Tricircle basic capabilities13:44
joehuangfor example, qos, update operation, metering, etc13:44
joehuangdo you have other proposal to reduce the risk?13:45
joehuangor bypass the risk?13:45
*** nadya has joined #openstack-meeting13:46
*** prateek_ has quit IRC13:46
*** prateek has joined #openstack-meeting13:47
zhiyuanthere's other solution to support shared vxlan network, like the "remote port" way, but if we would like to use the "vtep info in port" feature, it will be a waste to implement "remote port" in this circle13:47
joehuangwe can discuss if it's possible, or how to reduce the waste, at least we need to know how Anil will implement the VTEP info in port bindings13:50
*** haleyb_ has joined #openstack-meeting13:51
zhiyuanok, so let's keep our eye on Anil's work13:51
*** nadya has quit IRC13:51
zhiyuanat least we can finish the bridge network combination change13:52
joehuangactively involve in Anil's improvement13:52
joehuangif necessary13:52
*** haleyb_ has quit IRC13:52
joehuangok, other topics?13:53
joehuangok, thank you for your attending13:53
*** openstack changes topic to "OpenStack Meetings ||"13:53
openstackMeeting ended Wed Nov 23 13:53:49 2016 UTC.  Information about MeetBot at . (v 0.1.4)13:53
openstackMinutes (text):
*** Junsik has quit IRC13:54
*** Yipei has quit IRC13:54
*** RongHui11 has quit IRC13:54
*** Menthos has quit IRC13:55
*** jamesdenton has quit IRC13:55
*** Menthos has joined #openstack-meeting13:55
*** longxiongqiu has quit IRC13:55
*** zhhuabj_ has quit IRC13:55
*** kevinz has quit IRC13:56
*** prateek_ has joined #openstack-meeting13:57
*** yinxiulin has quit IRC13:57
*** hejiawei has quit IRC13:59
*** prateek has quit IRC13:59
*** ayogi has quit IRC13:59
*** donghao has quit IRC13:59
*** kevinz has joined #openstack-meeting14:00
*** HeleneCoullon has joined #openstack-meeting14:00
*** jfpeltier has joined #openstack-meeting14:01
*** lpetrut has quit IRC14:01
*** lpetrut has joined #openstack-meeting14:02
*** huanxuan_ has quit IRC14:02
*** Zara has quit IRC14:04
*** SotK has quit IRC14:04
*** SotK has joined #openstack-meeting14:05
*** adiantum has quit IRC14:06
*** SridharP has quit IRC14:06
*** thorst has joined #openstack-meeting14:08
*** Zara has joined #openstack-meeting14:09
*** ijw has joined #openstack-meeting14:10
*** joehuang has quit IRC14:11
*** pcaruana has quit IRC14:14
*** ijw has quit IRC14:15
*** jamesdenton has joined #openstack-meeting14:15
*** parora has joined #openstack-meeting14:18
*** thorst has quit IRC14:19
*** lhx__ has quit IRC14:19
*** annegentle has joined #openstack-meeting14:19
*** prateek has joined #openstack-meeting14:21
*** prateek_ has quit IRC14:22
*** thorst has joined #openstack-meeting14:22
*** Cibo has joined #openstack-meeting14:23
*** mriedem has joined #openstack-meeting14:23
*** parora has quit IRC14:24
*** nadya has joined #openstack-meeting14:24
*** lhx__ has joined #openstack-meeting14:24
*** prateek_ has joined #openstack-meeting14:24
*** jamesdenton has quit IRC14:24
*** zhhuabj_ has joined #openstack-meeting14:27
*** imcsk8 has quit IRC14:27
*** prateek has quit IRC14:27
*** toscalix has quit IRC14:29
*** imcsk8 has joined #openstack-meeting14:30
*** thorst has quit IRC14:31
*** denaitre has joined #openstack-meeting14:31
*** nmagnezi has quit IRC14:31
*** marios_ has joined #openstack-meeting14:32
*** tesseract has joined #openstack-meeting14:32
*** marios_ has quit IRC14:33
*** tesseract is now known as Guest4865314:33
*** dongfeng has quit IRC14:36
*** dongfeng has joined #openstack-meeting14:38
*** Guest48653 has quit IRC14:39
*** tesseract- has joined #openstack-meeting14:39
*** ramineni_ has joined #openstack-meeting14:41
*** yamamoto has quit IRC14:42
*** yamamoto has joined #openstack-meeting14:44
*** yamamoto has quit IRC14:45
*** vishnoianil has quit IRC14:48
*** ansmith has joined #openstack-meeting14:49
*** bobh has joined #openstack-meeting14:49
*** bobh has quit IRC14:49
*** tesseract- has quit IRC14:49
*** bobh has joined #openstack-meeting14:50
*** kgiusti has joined #openstack-meeting14:51
*** andymaier has joined #openstack-meeting14:52
*** ricolin has joined #openstack-meeting14:53
*** haleyb_ has joined #openstack-meeting14:53
*** yamamoto has joined #openstack-meeting14:54
*** Jeffreyc42 has joined #openstack-meeting14:55
*** dongfeng has quit IRC14:57
*** haleyb_ has quit IRC14:57
*** rcherrueau has joined #openstack-meeting14:58
*** ad_rien_ has joined #openstack-meeting14:58
rcherrueauhello folks14:58
ad_rien_gonna start the meeting in two minutes14:58
*** mabderrahim has joined #openstack-meeting14:59
ad_rien_#startmeeting massively_distributed_clouds15:00
openstackMeeting started Wed Nov 23 15:00:12 2016 UTC and is due to finish in 60 minutes.  The chair is ad_rien_. Information about MeetBot at
ad_rien_#chair ad_rien_15:00
openstackUseful Commands: #action #agreed #help #info #idea #link #topic #startvote.15:00
*** openstack changes topic to " (Meeting topic: massively_distributed_clouds)"15:00
openstackThe meeting name has been set to 'massively_distributed_clouds'15:00
openstackCurrent chairs: ad_rien_15:00
*** rbak has joined #openstack-meeting15:00
ad_rien_Hi guys.15:00
ad_rien_May I ask you who is online ?(15:00
*** Julien-zte has quit IRC15:00
ad_rien_Hi kgiusti15:00
*** Menthos has quit IRC15:00
*** Julien-zte has joined #openstack-meeting15:01
*** Julien-zte has quit IRC15:01
ad_rien_so let's wait one or two minutes, meanwhile you can give a look to the agenda (line 21 of the pad)15:01
*** marina_ has joined #openstack-meeting15:01
*** Julien-zte has joined #openstack-meeting15:01
ad_rien_may I ask you to complete it (starting by who is attending the meeting today)15:02
*** Julien-zte has quit IRC15:02
*** Julien-zte has joined #openstack-meeting15:02
*** enriquetaso has joined #openstack-meeting15:02
*** Julien-zte has quit IRC15:03
ad_rien_ok so let's start15:03
*** yangyape_ has joined #openstack-meeting15:03
*** Julien-zte has joined #openstack-meeting15:03
ad_rien_#topic barcelona sumup15:03
*** Julien-zte has quit IRC15:03
*** openstack changes topic to "barcelona sumup (Meeting topic: massively_distributed_clouds)"15:03
ad_rien_as a reminder, the minutes we took during our face to face meeting in Barcelona are available at15:04
*** Julien-zte has joined #openstack-meeting15:04
*** Julien-zte has quit IRC15:04
*** claudiub|2 has joined #openstack-meeting15:04
ad_rien_we identify a few actions that can be addressed during this cycle15:04
*** Julien-zte has joined #openstack-meeting15:05
ad_rien_- Identify deployment scenarios for massively distributed/fog/edge clouds (multi regions / one region with cells / one region with compute nodes deployed at the edge, ....)15:05
ad_rien_- Identify technical challenges/limitations for each scenario (quotas, heat, network issues, live migration, ...)15:05
ad_rien_- Identify evaluation scenarios (from the performance and functionnal viewpoint). 15:05
*** thorst has joined #openstack-meeting15:05
*** Julien-zte has quit IRC15:05
ad_rien_do you think we should add other action candidates in this list?15:05
*** Julien-zte has joined #openstack-meeting15:05
*** yangyapeng has quit IRC15:06
*** Julien-zte has quit IRC15:06
*** korzen_ has joined #openstack-meeting15:06
ad_rien_ok it seems to be ok.15:06
*** Julien-zte has joined #openstack-meeting15:06
*** kevinz has quit IRC15:06
*** Julien-zte has quit IRC15:07
*** claudiub has quit IRC15:07
ad_rien_foliveira:  ?15:07
ad_rien_ok so the next question is then to put some priorities on each action15:08
ad_rien_we can follow the proposed order or change a bit15:08
*** mpaolino has joined #openstack-meeting15:08
ansmithTo go along with the scenarios, is there a general agreement on the definitions of terms?15:08
ad_rien_not yet15:09
ansmithe.g. what is the definition of region, site, edge, etc.15:09
ad_rien_maybe I should mention that we are discussing with the NFV working group15:09
*** reedip_ has joined #openstack-meeting15:09
ad_rien_about what can be a minimalist NVFi deployment15:09
ad_rien_some folks from AT&T are taking part to the discussion15:10
foliveiraETSI NFV IFA WG?15:10
ad_rien_The first approach would be to have a central control plane and the data plane on the edge. Concretely15:10
*** Menthos has joined #openstack-meeting15:10
MenthosHi everyone15:11
ad_rien_so the idea is to put keystone, glance, nova (main services), … in one ''central'' DC and put the nova-compute at the edge (i.e. on distinct location)15:11
*** jgregor has joined #openstack-meeting15:12
ad_rien_this is a first scenario where we can conduct functional and performance evaluations to see pros/cons15:12
*** rossella__ has quit IRC15:12
*** thorst has quit IRC15:12
ad_rien_we should try to identify two or three more deployment scenarios15:12
ad_rien_and for each identify pros/cons in terms of features and performances avantages/drawbacks15:13
*** egallen has quit IRC15:13
ad_rien_so maybe ansmith you are right we should define that in one document/pad15:13
ad_rien_just to avoid confusion.15:13
*** egallen has joined #openstack-meeting15:14
*** msimonin has joined #openstack-meeting15:14
ad_rien_#action make a proposal for defining the different terms (region, site, edge, fog…)15:14
ansmithattempt to unify definitision across openstack, etsi/nfv and edge/fog would be helpful15:14
ad_rien_yes exactly15:15
*** rossella_s has joined #openstack-meeting15:15
ad_rien_so let's try to identify what can be the key word:15:15
ansmithand what functionality is expected of the "edge"15:15
ad_rien_it depends the scenario but you are right we can define one.15:15
ad_rien_so what are the key terms we may use ?15:16
ad_rien_Region, edge, site, compute_node/hypervisor15:16
*** thorst has joined #openstack-meeting15:16
ad_rien_(ansmith BTW not sure how the cell V2 feature is going to progress as lasky left Mirantis)15:17
ansmithmaybe it is a term we should abstract away15:17
ad_rien_we got an information from DinaBelova from the performance WG that told us it will be now manage by two persons at redhat (if I'm right)15:18
*** spotz_zzz is now known as spotz15:19
*** sandanar_ has quit IRC15:19
ad_rien_There is another person at redhat that is also interested by this notion of fog/edge computing, maybe we should try to invite him15:19
* ad_rien_ is looking for his name15:19
*** zz_dimtruck is now known as dimtruck15:19
rcherrueauThere is someone from redhat that made a presentation on mobile edge computing. His name is Sanjay Aiyagari.15:20
*** thorst has quit IRC15:20
ad_rien_ansmith:  kgiusti do you know him ?15:21
*** dtrainor has quit IRC15:22
ansmithyes and we caught up with him in Barcelona15:22
ansmithwe have a follow up action to engage on nfv/iot topics with him15:22
ad_rien_ok maybe it can make sense to have him to make progress on these definitions15:22
ad_rien_getting back to the terms we should add in the list (see pad line 46)15:23
ad_rien_anything else?15:23
ad_rien_foliveira:  do you have a specific use-case in mind at Verizon ?15:24
*** unicell has quit IRC15:25
ad_rien_ansmith:  kgiusti do you have a deployment scenario in mind  to test QPID15:27
*** marina_ has quit IRC15:27
ad_rien_I mean in terms of how deploying the different openstack services15:27
ad_rien_(ie. considering only the core ones: keystone, glance, nova, neutron, horizon and cinder)15:27
kgiustiAt this point we're working with some of the downstream RDO folks in redhat to determine just that.15:29
*** jamesdenton has joined #openstack-meeting15:29
*** liukun has quit IRC15:29
ad_rien_as I said I think we should try to identify at least two other scenarios15:29
*** pnavarro has joined #openstack-meeting15:30
*** pnavarro has quit IRC15:30
ad_rien_RDO  ?15:30
kgiustiWe need to identify those deployments that represent a challenge for a single/cluster broker15:30
rbowen - a packaging of OpenStack for RPM.15:30
ad_rien_#link 15:31
kgiustiRDO is the downstream community openstack release sponsored by redhat15:31
*** slayer has joined #openstack-meeting15:31
kgiustithink fedora for openstack :)15:31
ansmiththinking about the first scenario (e.g. central DC) there may be scenarios 1A and 1B15:31
ad_rien_yes please go ahead ?15:31
ansmith1A which is hub and spoke, e.g. edge always goes back to central15:32
ansmith1B where edges have peer relations15:32
*** jmckind has joined #openstack-meeting15:32
*** unicell has joined #openstack-meeting15:32
ad_rien_to have peer relations, does it mean you have services deployed at the edge ?15:32
ansmith1B takes into account network communication topology as opposed to control path topology15:32
ad_rien_because AFAIK, compute nodes do not interact each other?15:33
ansmithno but there may be networking service chains that link them up15:33
*** korzen has left #openstack-meeting15:33
ad_rien_can you elaborate a bit please15:33
ad_rien_in 1A all control plane is within the DC15:33
*** korzen_ is now known as korzen15:34
ad_rien_and compute_nodes at the edge (in different locations)15:34
ansmithIf I have network functions deployed as VMs at the edge, I would want to create network paths15:34
ad_rien_in 1B?15:34
ansmiththat would not want to be constrained by "hub n spoke'15:34
foliveiraI would expect that compute nodes would communicate within a site but perhaps not between sites.   Is this 1B as well?15:34
*** numans has quit IRC15:34
ansmithI think it is a question for NFVi folks to see if this is implied by there scenario15:35
ad_rien_but in that case it looks to be communications between VMs (i.e. data plane)15:35
ad_rien_is it correct ?15:35
persiaConsider the case where a "site" consists of several buildings on a campus, with a few nodes per building.15:35
persia(or more widespread, but the campus model is fairly easy to map to a DC-focused model)15:36
foliveiraVxLAN tunnels between compute nodes?15:36
*** nkrinner has quit IRC15:36
ad_rien_persia:  ok ?15:36
ansmithI read scenario above to imply edge is at a distinct location15:37
ansmithpotentially large latencies from DC to edge, expected outages, etc.15:37
ad_rien_this is the scenario 1A (I'm trying to make an ascii figure in the pad)15:38
jaypipesy'all should just rename "massively distributed cloud working group" to "Telco/NFV workgroup"15:38
*** janki has quit IRC15:38
ad_rien_thanks jaypipes :-)15:38
ad_rien_but actually this is a bit different as massively distributed cloud is a bit larger than NFV (even if it is true that telcos operators are quite interested by the distribution of OpenStack)15:39
*** nkrinner has joined #openstack-meeting15:39
jaypipesand yes, dansmith and melwitt from nova are continuing alaski's work in cellsv215:39
*** jprovazn has joined #openstack-meeting15:39
ad_rien_ansmith:  scenario  1A is in the pad15:41
*** Cibo_ has joined #openstack-meeting15:41
ad_rien_what was your idea of 1B?15:41
ad_rien_what we would like to do by evaluating the performance of scenario 1A is to identify latency/bw limitations15:42
ad_rien_another scenario can be to evaluate the region deployment scenario (as described in the OpenStack documentation)15:42
msimoninscenario 1A seems similar to Nectar deployment where each location is a cell mapped to an availibilty zone ?15:43
ad_rien_in 1A you have only compute nodes in remote locations15:43
*** Xavier_JEANNIN has joined #openstack-meeting15:44
ad_rien_in the nectar approach, they follow the cell v1 approach so you have some controller services in each location15:44
ad_rien_let's move forward15:45
ad_rien_#action try to prepare figures to illustrate the different scenarios15:45
*** prateek_ has quit IRC15:46
ad_rien_so for the moment we have identified three scenarios15:46
*** prateek_ has joined #openstack-meeting15:46
*** nkrinner has quit IRC15:46
msimoninactually the scenario 1B proposed by ansmith is unclear to me15:47
ansmithif VNF1 instance is at B and VNF2 instances is at C15:48
ansmithscenario 1A implies they rely on A for network services15:48
msimoninwhat do you mean?15:48
ansmithscneario 1B would imply there are peer services at B and C15:49
msimoninin 1A instances can communicate between location using tunnels ? no ?15:49
ansmithto support optimal service chaining15:49
ad_rien_I get the feeling that it depends how you are managing the network15:49
ad_rien_(flat, ….)15:49
ad_rien_if you are in the same domain, once the VMs (NFV instance) get their IPs, they can discuss directly15:50
ad_rien_(this is a naive example just to check we are on the same wavelenght?)15:50
ad_rien_from my understanding this is a drawback/limitations of the scenario 1A.15:51
ansmithsame wavelength, need to think through some more in the scenario spec15:51
ad_rien_So just to be sure, with the vanilla code, is there other possible scenarios ?15:52
ad_rien_once again, the objective is to identify pros/cons of each approach, missing features, performance limitations...15:52
*** nadya has quit IRC15:53
*** adrianofr_ has joined #openstack-meeting15:53
ad_rien_based on that we can have stronger arguments to discuss with the openstack community and see what revisions/extensions can be proposed15:53
ad_rien_is it ok for everyone?15:53
*** nadya has joined #openstack-meeting15:54
ad_rien_of we have 5 min15:54
*** sukhdev has joined #openstack-meeting15:54
ad_rien_I propose to switch to the open discussion as the other points are still related to the deployment scenarios15:54
*** haleyb_ has joined #openstack-meeting15:54
ad_rien_#topic Open Discussion15:54
*** openstack changes topic to "Open Discussion (Meeting topic: massively_distributed_clouds)"15:54
ad_rien_so on our side as mentioned we would be happy to get in touch Sanjay Aiyagar15:55
ad_rien_would it be possible ansmith / kgiusti to introduce our WG?15:55
ansmithwe will reach out to Sanjay and invite him to participate as well15:56
*** andymaier has quit IRC15:56
*** nadya has quit IRC15:56
*** nadya_ has joined #openstack-meeting15:56
ad_rien_we should have a discussion with Deutch telekom next fridau on our side too15:56
ad_rien_will keep inform about the results15:56
ad_rien_that's all for the Inria side15:56
ad_rien_Others ?15:56
ad_rien_Ok it seems that we are done15:57
*** nadya_ has quit IRC15:57
ad_rien_I will clean the pad, please give it a look to see the actions we defined15:57
*** nadya has joined #openstack-meeting15:58
ad_rien_and feel free to complete/amend it15:58
ad_rien_For attending the meeting15:58
msimoninthanks :)15:58
*** openstack changes topic to "OpenStack Meetings ||"15:58
openstackMeeting ended Wed Nov 23 15:58:49 2016 UTC.  Information about MeetBot at . (v 0.1.4)15:58
openstackMinutes (text):
*** haleyb_ has quit IRC15:59
*** makowals has joined #openstack-meeting15:59
*** kgiusti has left #openstack-meeting15:59
*** nkrinner has joined #openstack-meeting16:00
*** jungleboyj has joined #openstack-meeting16:01
*** Sukhdev_ has joined #openstack-meeting16:01
*** HeleneCoullon has left #openstack-meeting16:01
*** nadya has quit IRC16:02
*** makowals_ has quit IRC16:02
*** ad_rien_ has quit IRC16:03
*** strigazi is now known as strigazi_AFK16:04
*** anilvenkata has quit IRC16:05
*** Menthos has quit IRC16:05
*** jgregor_ has joined #openstack-meeting16:07
*** Xavier_JEANNIN has left #openstack-meeting16:09
*** armax has joined #openstack-meeting16:09
*** mpaolino has quit IRC16:09
*** jgregor has quit IRC16:10
*** jgregor has joined #openstack-meeting16:10
*** mabderrahim has quit IRC16:11
*** whenry has quit IRC16:11
*** gouthamr has quit IRC16:12
*** jgregor_ has quit IRC16:13
*** gouthamr has joined #openstack-meeting16:13
*** whenry has joined #openstack-meeting16:15
*** sridharg has quit IRC16:16
*** rcherrueau has quit IRC16:19
*** Cibo_ has quit IRC16:19
*** Apoorva has joined #openstack-meeting16:19
*** rbak has quit IRC16:19
*** makowals has quit IRC16:23
*** Sukhdev_ has quit IRC16:24
*** jgriffith_away is now known as jgriffith16:25
*** unicell has quit IRC16:25
*** iyamahat has joined #openstack-meeting16:26
*** andymaier has joined #openstack-meeting16:27
*** yangyape_ has quit IRC16:27
*** dkehn__ has joined #openstack-meeting16:28
*** Apoorva has quit IRC16:32
*** fnaval has joined #openstack-meeting16:32
*** bogdando has quit IRC16:32
*** dprince has quit IRC16:33
*** lbeliveau has quit IRC16:36
*** weshay is now known as weshay_lunch16:37
*** thorst has joined #openstack-meeting16:38
*** thorst has quit IRC16:39
*** allanice001 has joined #openstack-meeting16:40
*** annegentle has quit IRC16:41
*** dankolbrs has joined #openstack-meeting16:42
*** slayer has quit IRC16:42
*** yamahata has joined #openstack-meeting16:42
*** nadya has joined #openstack-meeting16:43
*** yamamoto has quit IRC16:45
*** galstrom_zzz is now known as galstrom16:46
*** ad_rien_ has joined #openstack-meeting16:47
*** hashar has quit IRC16:50
*** toscalix has joined #openstack-meeting16:52
*** jungleboyj has quit IRC16:52
*** mtanino has joined #openstack-meeting16:52
*** egallen_ has joined #openstack-meeting16:53
*** dankolbrs has quit IRC16:54
*** Kiall has joined #openstack-meeting16:54
*** egallen has quit IRC16:54
*** dankolbrs has joined #openstack-meeting16:54
*** egallen_ is now known as egallen16:54
*** ayogi has joined #openstack-meeting16:54
*** haleyb_ has joined #openstack-meeting16:55
*** andymaier has quit IRC16:56
*** ad_rien_ has quit IRC16:56
*** galstrom is now known as galstrom_zzz16:56
*** Guest83036 has joined #openstack-meeting16:57
*** sudipto_ has joined #openstack-meeting16:57
*** dprince has joined #openstack-meeting16:58
*** korzen has quit IRC17:00
*** haleyb_ has quit IRC17:00
*** egallen_ has joined #openstack-meeting17:00
*** bobh has quit IRC17:01
*** egallen has quit IRC17:01
*** egallen_ is now known as egallen17:01
*** cody-somerville has joined #openstack-meeting17:02
*** artom has quit IRC17:03
*** artom_ has joined #openstack-meeting17:03
*** bobh has joined #openstack-meeting17:04
*** jmckind_ has joined #openstack-meeting17:05
*** rasca has quit IRC17:05
*** Leom has joined #openstack-meeting17:06
*** makowals has joined #openstack-meeting17:06
*** jmckind has quit IRC17:06
*** thorst has joined #openstack-meeting17:06
*** thorst_ has joined #openstack-meeting17:07
*** lpetrut has quit IRC17:10
*** lhx__ has quit IRC17:11
*** thorst has quit IRC17:11
*** lhx__ has joined #openstack-meeting17:11
*** thorst_ has quit IRC17:11
*** rbartal has quit IRC17:12
*** annegentle has joined #openstack-meeting17:12
*** jgregor has quit IRC17:13
*** ygbo has quit IRC17:13
*** jgregor has joined #openstack-meeting17:14
*** ricolin has quit IRC17:15
*** yamahata has quit IRC17:17
*** msimonin has quit IRC17:17
*** alraddarla has joined #openstack-meeting17:18
*** e0ne has quit IRC17:20
*** jgregor has quit IRC17:20
*** lhx__ has quit IRC17:21
*** Apoorva has joined #openstack-meeting17:25
*** jmckind has joined #openstack-meeting17:27
*** jmckind_ has quit IRC17:28
*** toscalix has quit IRC17:28
*** jamesde__ has joined #openstack-meeting17:28
*** hogepodge has joined #openstack-meeting17:28
*** ramineni_ has quit IRC17:29
*** allanice001 has quit IRC17:29
*** matrohon has quit IRC17:30
*** sambetts is now known as sambetts|afk17:30
*** jamesdenton has quit IRC17:30
*** jgregor has joined #openstack-meeting17:33
*** hogepodge has quit IRC17:33
*** jgregor_ has joined #openstack-meeting17:36
*** nkrinner is now known as nkrinner_afk17:37
*** dmorita has joined #openstack-meeting17:37
*** jgregor has quit IRC17:38
*** reedip_ has quit IRC17:39
*** jgregor_ has quit IRC17:40
*** msimonin has joined #openstack-meeting17:41
*** klkumar has quit IRC17:42
*** weshay_lunch is now known as weshay17:42
*** claudiub|2 has quit IRC17:42
*** mkoderer has quit IRC17:43
*** hogepodge has joined #openstack-meeting17:43
*** slaweq_ has quit IRC17:44
*** yamamoto has joined #openstack-meeting17:45
*** egallen_ has joined #openstack-meeting17:46
*** slaweq_ has joined #openstack-meeting17:46
*** matrohon has joined #openstack-meeting17:46
*** ayogi has quit IRC17:46
*** egallen has quit IRC17:47
*** egallen_ is now known as egallen17:47
*** yamamoto has quit IRC17:52
*** oneswig has quit IRC17:53
*** spligak has quit IRC17:53
*** powerd has quit IRC17:53
*** csomerville has joined #openstack-meeting17:54
*** jamesde__ has quit IRC17:54
*** Leom has quit IRC17:56
*** haleyb_ has joined #openstack-meeting17:56
*** cody-somerville has quit IRC17:57
*** priteau has quit IRC17:58
*** ralonsoh has quit IRC18:00
*** haleyb_ has quit IRC18:01
*** toscalix has joined #openstack-meeting18:02
*** jgregor has joined #openstack-meeting18:03
*** foliveira has left #openstack-meeting18:03
*** nadya has quit IRC18:04
*** qwebirc2383 has joined #openstack-meeting18:04
*** nadya has joined #openstack-meeting18:04
*** qwebirc2383 has quit IRC18:05
*** alraddarla has quit IRC18:05
*** jgregor has quit IRC18:07
*** nadya has quit IRC18:08
*** priteau has joined #openstack-meeting18:11
*** beagles has joined #openstack-meeting18:11
*** parora has joined #openstack-meeting18:13
*** slaweq_ has quit IRC18:13
*** iyamahat has quit IRC18:13
*** prateek_ has quit IRC18:16
*** noslzzp has quit IRC18:16
*** noslzzp has joined #openstack-meeting18:17
*** lpetrut has joined #openstack-meeting18:20
*** toscalix has quit IRC18:21
*** prateek_ has joined #openstack-meeting18:24
*** unicell has joined #openstack-meeting18:24
*** unicell has quit IRC18:25
*** unicell has joined #openstack-meeting18:27
*** parora has quit IRC18:27
*** egallen_ has joined #openstack-meeting18:29
*** egallen has quit IRC18:30
*** egallen_ is now known as egallen18:30
*** annegentle has quit IRC18:31
*** msimonin has quit IRC18:31
*** lpetrut has quit IRC18:32
*** electrofelix has quit IRC18:33
*** iyamahat has joined #openstack-meeting18:35
*** markvoelker has quit IRC18:35
*** egallen has quit IRC18:38
*** Guest83036 has quit IRC18:38
*** sudipto_ has quit IRC18:38
*** prateek_ has quit IRC18:38
*** lpetrut has joined #openstack-meeting18:41
*** jgriffith is now known as jgriffith_away18:42
*** acoles is now known as acoles_18:42
*** jfpeltier has quit IRC18:53
*** Jeffreyc42 has quit IRC18:55
*** yamahata has joined #openstack-meeting18:55
Zaraanybody about for the famed storyboard meeting?19:00
Zara*internationally famed19:00
Zarathen away we go!19:00
Zara#startmeeting storyboard19:01
openstackMeeting started Wed Nov 23 19:01:00 2016 UTC and is due to finish in 60 minutes.  The chair is Zara. Information about MeetBot at
openstackUseful Commands: #action #agreed #help #info #idea #link #topic #startvote.19:01
*** openstack changes topic to " (Meeting topic: storyboard)"19:01
openstackThe meeting name has been set to 'storyboard'19:01
*** sukhdev has quit IRC19:01
Zara#topic Announcements19:01
*** openstack changes topic to "Announcements (Meeting topic: storyboard)"19:01
ZaraI don't think we have any this week19:01
*** ad_rien_ has joined #openstack-meeting19:01
Zara#topic Urgent Items19:02
*** openstack changes topic to "Urgent Items (Meeting topic: storyboard)"19:02
Zara#topic In-Progress Work19:02
*** openstack changes topic to "In-Progress Work (Meeting topic: storyboard)"19:02
ZaraSo, this week I went to OpenStack Day France, and some stuff came out of that19:02
SotKdo tell!19:02
Zarahahaha, I was planning to come back to that in Discussion19:02
Zarasneak preview ^19:03
SotKthat works for me :)19:03
*** msimonin has joined #openstack-meeting19:03
SotKI'm afraid I've done very little this week19:03
Zarayeah, it's been a weird week19:04
Zarawe both spoke to the zuul team about some ui things, hoping for more feedback from there19:04
ZaraI sent a patch for SpamapS' suggestion19:04
Zarathat changes the 'stories' icon to a book19:05
Zarasince there was confusion over similarity with the 'tasks' icon19:05
Zaraso if people are interested in that, it's up there!19:06
SotKoh nice19:06
* SotK will review that later once I've decided how it makes me feel19:06
Zarahaha, yep, thought the best way for folk to discuss it was if they could see it19:07
ZaraI'm not attached to any particular icons for things19:07
Zaraso, other things...19:08
*** ad_rien_ has quit IRC19:08
Zarathis is waiting on +workflow:19:08
Zarawhich updates angular19:08
* SotK wonders if he trusts the SotK of Oct 2419:08
Zaraso a 'longterm health of the webclient' thing19:08
Zarawell, there's a draft build19:09
SotKtrusts enough to +1 right now that is19:09
ZaraI did test it on my end pretty thoroughly, but I agree you shouldn't take that as a guarantee19:09
Zaraother things...19:10
Zarathe 'about' page subheading annoyed me, so I sent a patch19:10
ZaraI'm fine leaving it if others feel strongly against that, it stuck out to me and I couldn't leave it.19:11
* SotK wonders what persia thinks of the new content19:11
Zarais the thought19:11
Zara(but I know not the specifics of the +1)19:12
SotKI don't really have any strong objection to either form19:12
SotKoh, I should have scrolled down19:12
*** msimonin1 has joined #openstack-meeting19:12
Zarajust noticed this19:13
Zarait got caught because it got the requisite +1 after +219:13
Zaraso it hasn't been +A'd19:13
* SotK merges19:13
Zara*this time*, we'll have working install instructions19:13
Zara(how many times will I repeat that with optimism...?)19:14
*** jgriffith_away is now known as jgriffith19:14
ZaraI think that's where I'm at with things; my changes have been pretty small and I've been travelling a bunch.19:14
*** msimonin has quit IRC19:14
* SotK wonders if such a thing has ever existed for anything19:15
Zaralmk if you see it!19:16
Zaraready to move on to discussion?19:16
SotKI am19:16
*** lin_yang has joined #openstack-meeting19:17
Zara#topic Discussion19:17
*** openstack changes topic to "Discussion (Meeting topic: storyboard)"19:17
ZaraThis Tuesday, I was at OpenStack Day, France!19:17
* SotK is excited19:17
ZaraIt was a nice event! Lots of informative talks, well organised, good wifi, tasty snacks19:18
SotKsounds great19:18
SotKI'm sad I couldn't make it19:18
Zaraso nice work, everyone involved in that! :D19:18
Zaraand yeah :( NEXT TIME19:18
Zaraanyway, while there, I spoke with diablo_rojo and ttx about migrating teams to StoryBoard and soforth19:20
Zaraone thing that's coming up a lot19:20
Zarais that there's a lot of tribal knowledge about the concepts and motivations behind storyboard19:21
*** beagles is now known as beagles_brb19:21
Zara(probably because the conversation is between a similar group of folk at each summit, same for our meetings, and so-on)19:22
Zaraso, for example, people are asking if there's an API, as they don't have the context that it was designed to be an API-driven task-tracker.19:22
Zaraand this information is readily available from our documentation, but people will not stumble across that19:23
SotKthat makes sense19:24
SotKI actually think the API point has even come up in the task tracking session both times I've been there too19:24
SotKs/session/summit session/19:24
*** jamesdenton has joined #openstack-meeting19:25
Zarayeah, I think it's a lot of folks' biggest concern, so it tends to be the first question for a newcomer, and I think in many projects it's something you only find out by looking at code. so yeah, in general, we need an easily-findable collection of materials that offer some context19:25
Zaraexplanations of the concepts (and how things map to lp), and so on19:26
Zaraat the moment, we have various scattered things19:26
*** LouisF has joined #openstack-meeting19:26
* Zara has wanted a nicer version of that as a base for the 'about' page for a while19:26
Zaraso one thing that came up19:27
Zarawas an idea to do a blog19:27
SotKI would like a blog19:27
*** ad_rien_ has joined #openstack-meeting19:27
SotKalso, this story is really nice and shiny19:27
*** makowals has quit IRC19:29
Zarahaha, it's something I periodically realise we need when people start asking questions, then it gets put down the list...19:29
ZaraI got things to line up by drawing them on paper and then tracing them with a tablet, because I don't quite understand how to use any technology, apparently19:29
Zara(paper = grid paper)19:29
Zaraanyway, yeah, blog!19:30
Zaraso, 'wordpress' came up; I think pelican is prrrrobably a better fit for us19:30
Zarasince I know you admin a pelican site already, and I have at least deployed a pelican thing for testing before19:31
*** jamesdenton has quit IRC19:31
*** jgregor has joined #openstack-meeting19:32
SotKwhere admin == have recently started utilising, yeah19:32
SotKoh actually, there is also a blog that uses it that is older than that that I look after19:32
Zarahi, expert19:32
SotKyes, I like pelican, +1 for pelican over wordpress19:32
*** msimonin1 has quit IRC19:33
Zara\o/ cool, I'm wondering about starting by putting things in a repo and then deciding where it can live later.19:33
SotKthat works for me19:33
ZaraI'd prefer more people around before we make anything formal, but I also don't want to get bogged down debating the best infrastructure19:33
Zaraso I'd rather just try to get something up, then replace if vetoed. (I really doubt anyone would veto, though)19:34
SotKyeah, that seems like a sensible approach to me19:34
*** LouisF has quit IRC19:35
SotKnow we get to debate where to put the repo!19:35
ZaraI like the idea of it being its own project, though that could take longer to set up, so we might want to make something first then import later19:36
SotKI feel like it definitely needs its own repository rather than being shoehorned elsewhere19:36
Zarayeah, when I say 'make something first', I was thinking of stuffing a repo into some free repo site hosting service thing someplace (I think I stumbled across some a while back, can't remember names offhand)19:37
SotKah, good19:38
SotKwe could use github pages perhaps?19:39
Zarayeah, I'd rather host it elsewhere for anything more serious than early 'hey does this look right?' purposes19:40
* SotK too19:40
SotKbut github feels acceptable for "throw something up quickly" to me19:41
* Zara currently uses it for her website but feels guilty19:41
Zaraso yeah, agreed on that19:41
* Zara won't use an actual '#agreed' since it's just us19:42
Zarabut I think we have enough to go on to put a skeleton up19:42
SotKshall we try to set somethign skeletal up by next meeting then?19:42
*** fnaval has quit IRC19:42
Zarasounds good to me19:42
Zarawe've got 18 minutes left19:42
SotKanything else you have that needs discussing here?19:43
Zarahm, well, would you rather start it or should I?19:44
* Zara is wondering if 'we' will mean we both procrastinate and rush on tues19:44
SotKI will try to throw something together this weekend, feel free to beat me to it :)19:45
Zaraokay, challenge accepted!19:45
*** jamesdenton has joined #openstack-meeting19:45
* Zara hasn't built one from scratch but should learn, and likes fussing with templates19:46
Zarathat's all I have to say on that; I'm hoping we can get a more detailed overview from other folk when they're no longer on planes and whatnot19:46
Zara(specific questions that keep coming up, etc)19:47
SotKI have nothing else to add either19:48
SotKI agree that more details from other folk would be best obtained when they are on solid ground19:48
*** fnaval has joined #openstack-meeting19:48
*** fnaval has quit IRC19:49
*** fnaval has joined #openstack-meeting19:49
*** betherly_ has joined #openstack-meeting19:50
*** lbeliveau has joined #openstack-meeting19:51
Zaraoh, I guess the other thing that's coming up is that the mobile interface is putting people off19:51
Zaracompared with other tools that offer boards19:51
SotKyeah, storyboard isn't great on mobile19:52
SotKI was reminded of that earlier in this meeting (my browser is half-width today and so I'm seeing the tablet version)19:52
Zarayeah, I think we have some form of 'fix mobile interface' story somewhere, and I hope/plan to divide that up19:53
Zarainto pieces I can look at one at a time19:53
*** spligak has joined #openstack-meeting19:53
Zarathough I think the big dependency for that was the less/sass change19:54
Zara(hi betherly_! :P)19:54
betherly_ nipped in for the end! Sorry to be so late19:54
betherly_will review logs :)19:54
SotKhi betherly_, no worries :)19:54
Zarano problem, it's great to see you! :D19:55
SotKoh yeah, what is holding that up these days?19:55
betherly_my time :p19:55
betherly_things have been super busy trying to get set up at red hat19:55
*** beagles_brb is now known as beagles19:55
*** ad_rien_ has quit IRC19:56
*** nadya has joined #openstack-meeting19:56
Zara:) how's it going? (yeah, headings were different sizes so I wanted to check fonts were rendering right, and needs a rebase)19:56
betherly_basically less compiles css in a different order to sass so I need to ensure nothing's being over written19:56
*** Cibo has quit IRC19:57
*** haleyb_ has joined #openstack-meeting19:58
Zaracool, I can fix mobile things in a hacky way, I'm just wary of it needing further rebases if I do that19:58
Zaraalso the emotional pain my hacks will cause19:58
Zaraoh, nearly out of time!19:59
ZaraI guess we can talk more in #storyboard if people want19:59
*** openstack changes topic to "OpenStack Meetings ||"20:00
openstackMeeting ended Wed Nov 23 20:00:13 2016 UTC.  Information about MeetBot at . (v 0.1.4)20:00
openstackMinutes (text):
Zarawell, that was abrupt, sorry! but thanks, all!20:00
SotKthanks Zara, good meeting :)20:00
betherly_thanks Zara !!20:03
*** haleyb_ has quit IRC20:03
*** rods has quit IRC20:05
*** rods has joined #openstack-meeting20:07
*** jamesdenton has quit IRC20:09
*** korzen has joined #openstack-meeting20:09
*** jmckind_ has joined #openstack-meeting20:09
*** jmckind has quit IRC20:11
*** ijw has joined #openstack-meeting20:11
*** dbecker has quit IRC20:11
*** msimonin has joined #openstack-meeting20:12
*** jamesdenton has joined #openstack-meeting20:13
*** allanice001 has joined #openstack-meeting20:21
*** e0ne has joined #openstack-meeting20:22
*** jmckind_ has quit IRC20:22
*** priteau has quit IRC20:24
*** msimonin has left #openstack-meeting20:25
*** mmotiani1 has joined #openstack-meeting20:26
*** egallen has joined #openstack-meeting20:26
*** slaweq_ has joined #openstack-meeting20:27
*** e0ne has quit IRC20:34
*** Sukhdev has joined #openstack-meeting20:36
*** betherly_ is now known as betherly20:41
*** m_kazuhiro has joined #openstack-meeting20:43
*** armax has quit IRC20:43
*** armax has joined #openstack-meeting20:45
*** armax has quit IRC20:45
*** csomerville has quit IRC20:45
*** dprince has quit IRC20:46
*** kaisers__ has quit IRC20:48
*** gouthamr has quit IRC20:50
*** nadya has quit IRC20:50
*** baoli has quit IRC20:51
*** baoli has joined #openstack-meeting20:51
*** flaper87 has quit IRC20:52
*** cody-somerville has joined #openstack-meeting20:53
*** cody-somerville has quit IRC20:53
*** cody-somerville has joined #openstack-meeting20:53
*** baoli has quit IRC20:56
*** hosanai has joined #openstack-meeting20:56
*** acoles_ is now known as acoles20:58
*** ansmith has quit IRC20:59
*** pdardeau has joined #openstack-meeting20:59
*** kota_ has joined #openstack-meeting20:59
notmynameswift meeting time21:00
notmyname#startmeeting swift21:00
openstackMeeting started Wed Nov 23 21:00:17 2016 UTC and is due to finish in 60 minutes.  The chair is notmyname. Information about MeetBot at
openstackUseful Commands: #action #agreed #help #info #idea #link #topic #startvote.21:00
*** openstack changes topic to " (Meeting topic: swift)"21:00
openstackThe meeting name has been set to 'swift'21:00
notmynamewho's here for the swift meeting?21:00
notmynameI know torgomatic is out today. as is clayg21:00
*** nadeem has joined #openstack-meeting21:00
notmynamehosanai: hello! I hope you weren't negatively affected by the quake this week21:01
mattoliverauThere are more americans in attendance then I expected :)21:01
notmynamemattoliverau: me too ;-)21:01
*** acoles is now known as acoles_21:02
*** joeljwright has joined #openstack-meeting21:02
notmyname#link the agenda21:02
notmynamejust a few things21:02
hosanainotmyname: thanks. my area doesn't close to the quake.21:02
notmynamehosanai: oh good21:03
notmynamea few FYIs that will affect us all21:03
notmynamefirst up21:03
notmyname#info swift 2.11.0 has been released21:03
notmynamethank you everyone who helped get that pushed over the line21:03
*** jprovazn has quit IRC21:03
*** vishnoianil has joined #openstack-meeting21:04
notmynameI've proposed both 2.10.1 and 2.7.1 for stable releases as well. the changelog patches are in gerrit, and they look mostly good. a few comments on one21:04
notmynameI'd expect those to land next week, just because tomorrow and friday are US holidays21:04
*** Guest2 has joined #openstack-meeting21:05
notmynamein other news, there was a significant change to the swift gate jobs this past weekend21:05
notmynameonovy did a great job finding, diagnosing, and fixing some issues that came up21:05
mattoliverauonovy: great work!21:05
notmynamethe summary is that linux has a 128 character limit on the shebang lines in scripts, and the job name + the tox environment name has busted through that21:06
*** acoles_ is now known as acoles21:06
mattoliveraulol, so long21:06
notmynamethe change to tox.ini is to drop the "-in-process" substring from the two jobs that had it21:06
notmynameI'm not super happy with having to do that, but I was less happy with dropping other parts of the job/env name21:06
notmynamebut, if we can figure out a better name, then we can change it21:07
notmynamehere is the patch that did it
notmynameso why this weekend instead of earlier? that part is my fault21:07
notmyname(but there's a silver lining too)21:07
notmynameso I added "-xfs-tmpdir" to the job name to distinguish it from the normal "tox" jobs in the gate21:08
notmynamethat's the change that made it longer21:08
notmynamehowever, the good news is that now we have xfs in the gate!21:08
notmynamewhich means that when lands, we'll have full testing21:09
notmynamespeaking of that patch, again I want to call it out this week -- it will potentially break your dev environment21:10
notmynamethe change is that we stop mocking out xattr, so you have to run tests in an environment where large xattrs are supported21:10
*** spotz is now known as spotz_zzz21:10
notmynamethe patch now indicates that in docs, and it's ready for a full review21:10
*** ad_rien_ has joined #openstack-meeting21:11
notmynamewith that patch, if there isnt' an xfs tmpdir used, many of the tests will be skipped. it will be obvious21:11
notmynameI'd suggest that even if you don't want to do a full review, at least download it and run it on your dev setup just to get ready21:12
mattoliverauahh skips over failure is good :)21:12
tdasilvajust over 1k tests will be skipped :)21:12
notmynameIIRC is's something like 1.3k skips of 4.3k unit tests. and something like 418 of 456 in-process functional tests21:12
notmynameso it's obvious :-)21:12
*** korzen has quit IRC21:13
notmynamealso, tdasilva keeps making merge conflicts for me with is refactoring of ;-)21:13
tdasilvaand i'm about to -1 that patch too ;)21:13
tdasilvahappy thanksgiving21:13
notmynamejoking aside, for everyone, it would be a good idea to prep now for the test environment change21:14
notmynameeither mount your /tmp as xfs or set up an XFS partition somewhere and set TMPDIR to it21:14
*** unicell has quit IRC21:14
mattoliveraueveryone update your saio build scripts ;)21:14
*** timburke has joined #openstack-meeting21:14
*** mmotiani1 has quit IRC21:15
*** mmotiani1 has joined #openstack-meeting21:15
notmynameso, also, there's a couple of things that have happened in openstack because of these changes21:15
notmynamefirst, fungi has proposed a TC resolution that explicitly says test prerequirements like this are perfectly ok. this is good, because previously it was a little bit of a gray area, and someone could have said "oh swift is being different".21:16
notmynameI'm happy to see that governance change21:16
*** Apoorva has quit IRC21:16
mattoliverau+1. fungi's awesome21:16
notmynamesecond, the -infra team is working on a longer term change that will make all the work I did in CI obsolete (which is good!)21:16
notmynamethey're proposing that projects can keep a script in a special place in the repo that will be called with root or sudo perms before tests are run21:17
notmynamein general that means that all the XFS setup I did in the CI system could be done in the future in a setup file in our repo21:18
notmynamewhich would have made the whole process a lot simpler21:18
*** kaisers_ has joined #openstack-meeting21:18
mattoliveraucool, that'll make life easier21:18
notmynameand from the infra side, it means that every different setup combination doesn't have to have a different job template now21:18
*** jamesdenton has quit IRC21:18
notmyname"now" == in the future when this is implemented21:18
notmynameso, all that's good to see21:18
notmynameany questions on any of that?21:19
notmynameit's a dump of info, but it's stuff that affects all of us21:19
acolesnotmyname: might the script be passed the name of the test job so it can behave differently for various jobs?21:20
mattoliverauthats a good idea21:20
acolesIDK why yet, just wondering21:20
notmynamethat is a good idea. I'm looking for the ML link21:21
*** unicell1 has joined #openstack-meeting21:21
notmynameacoles: probably best to raise that in the ML thread21:21
*** jgregor has quit IRC21:22
timburkealternatively, i wonder if they could pick out the env vars from the tox env, and set them before calling
acolesnotmyname: k21:22
notmynameyeah, I can imagine needing to do different swift test setup for the same reasons we have different tox environments now21:23
acolesso basically, "this is a neat idea, but you know swift, we'll probably want to use it differently" :P21:23
notmynameeven if the job name is the only thing passed in, that's probably a good enough starting place for us to do the right thing in our own repo21:23
*** mmotiani1 has quit IRC21:24
notmynamelol, no. form the ML thread, it seems there's several different setups that are needed already today. we're not at all special here :-)21:24
notmynamedifferent DB setups, from what I can tell21:24
*** csomerville has joined #openstack-meeting21:24
*** mmotiani1 has joined #openstack-meeting21:25
notmynameanything else on these test-related things?21:25
*** csomerville has quit IRC21:25
*** csomerville has joined #openstack-meeting21:25
notmynameok, last thing I had on the agenda was to get some info21:26
mattoliveraunot until I forget and wonder why an old SAIO is failing :P21:26
notmyname#topic current status of changing policies21:26
*** openstack changes topic to "current status of changing policies (Meeting topic: swift)"21:26
notmynameover the past couple of years, changing policies/tiering/migrations/etc has come up several times, and there's been quite a bit of work on it21:26
notmynameI was recently asked about it, and when we'll have it upstream (yay! predictions about "done"!)21:27
notmynameso I wanted to make sure I had my head around all the pieces21:27
*** armax has joined #openstack-meeting21:27
notmynameso here's what I remember:21:27
notmynamesymlinks needed first21:27
*** cody-somerville has quit IRC21:28
notmynamethen changing policies api21:28
notmynamethen (maybe) something that does the policy change automatically21:28
notmynameare those the same big parts you remember, or did I leave somethign out?21:28
tdasilvai'm not sure the changing policies is a dependency, at least to what m_kazuhiro is doing21:29
notmynamecurrent symlink work is at (led by tdasilva). then there's the change policies patch at from daisuke21:29
notmynamewhere's m_kazuhiro's work?21:30
tdasilvaone sec21:30
*** cody-somerville has joined #openstack-meeting21:30
*** cody-somerville has quit IRC21:30
*** cody-somerville has joined #openstack-meeting21:30
*** allanice001 has quit IRC21:30
m_kazuhironotmyname: automated-tiering is independent from changing policies.21:30
acolestdasilva: is the distinction between policy migration vs tiering the granularity? migration means entire policy contents, tiering is per object movement between policies?21:30
acolesm_kazuhiro: ^^21:31
*** rossella_s has quit IRC21:31
tdasilvaacoles: yeah, i think that sounds like a fair description (but my understanding of the changing policies work is limited)21:31
*** rossella_s has joined #openstack-meeting21:32
notmynamem_kazuhiro: is that how you understand it, too?21:32
kota_yeah, and AFAIK, only auto-tiering depends on symlink but changing-policies doesn't21:32
acoleskota_: +121:32
*** csomerville has quit IRC21:32
m_kazuhironotmyname: yes21:33
notmynameok, got it21:33
notmynamewell, wait :-)21:33
notmynamewe used a few different terms to talk about the same thing21:33
notmynameassert policy migration == changing policies21:34
notmynameassert tiering == auto tiering21:34
*** ijw has quit IRC21:34
notmynamegot it :-)21:34
tdasilvain my head21:34
notmynamethanks, tdasilva REPL21:34
tdasilvaacoles: ?21:34
acolesalso with policy-migration as I understand it the object urls remain unchanged, with tiering objects contents are moved to new (hidden) urls21:34
tdasilvahopefully hiddne21:35
acolesnot hiddnee21:35
notmynamewhich is why tiering needs symlinks. to keep the same URLs available21:35
acolesnotmyname: assertions correct IMO21:35
m_kazuhironotmyname: Yes21:36
acolesnotmyname: tiering needs symlinks because containers retain original policy, so new containers are need to move content to21:36
tdasilvanotmyname: just barcelona we also talked about some "infra" work that is somewhat generic that would be needed by auto-tiering and possibly used by other components21:37
notmynameso, hidden or not hidden URLs with tiering. I thought I remembered hidden URLs21:37
acolestdasilva: yes!21:37
tdasilvaI had a TODO to write those up, but haven't yet21:37
tdasilvasorry acoles21:37
notmynametdasilva: ah, ok. I wasn't in the barca conversation, so I'm definitely interested in that21:37
acolesnotmyname: I would hope for hidden urls for tiered objects21:37
*** ijw has joined #openstack-meeting21:37
tdasilvanotmyname: exactly, we all hope for hidden urls, but that's one of these "infra" discussions we had about how to tdo hidden urls21:38
notmynameright. new hidden urls in a differnet policy with a symlink in the original policy21:38
notmynameyeah, I could imagine myself arguing for not hidden urls ;-)21:38
notmyname(but now's not the time to hash that out)21:38
tdasilvawell, it was more like hidden containers, but you get the idea21:38
notmynameok, I got what I needed to know. thanks :-)21:39
notmyname#topic open discussion21:39
*** openstack changes topic to "open discussion (Meeting topic: swift)"21:39
notmynameanything else to bring up this week?21:39
acolestdasilva: notmyname: we discussed 1. how do we test these features? 2. is there a common "engine" for performing tasks required to implement internal object movement? 3. generic approach to hidden urls (e.g. alt reseller prefix??)21:39
tdasilvaacoles: perfect21:40
acolesmaybe timur's crawler is a step towards a common engine, IDK, I haven't reviewd it yet :/21:40
mattoliverauIn sharding I have hidden containers, but its a , (dot) prefixed account that is releted to the users account21:40
mattoliveraubut it's just for container metadata21:41
tdasilvamattoliverau: would love to hear more about that, because that's one of the ideas we had, but there are also downsides to it21:41
acolesmattoliverau: right - another example - and I guess I wonder if future us will find it easier to grok swift if there are some generic mechanisms/patterns21:41
*** priteau has joined #openstack-meeting21:41
*** rbowen has quit IRC21:42
mattoliverauin my case I don't have to worry about objects being hidden and therefore not tracked21:42
mattoliverauand I gather stats.. maybe a reseller prefix does make sense21:42
*** pradk has quit IRC21:43
tdasilvanotmyname: have you heard any status from the tape library guys? we had good conversations in barcelona but haven't heard anything since...21:43
notmynameI have not21:43
tdasilvathey were also interested in the auto-tiering work21:44
acolestdasilva: do you remember the downsides to . prefic accounts?21:44
mattoliverauthey have a weekly phone meeting, so there still working on it21:44
notmynamethey told me they had good conversations in barca with the optical storage people21:44
tdasilvaright, panasonic, right?21:44
* mattoliverau gets the invite but been to busy (work and baby to attend lately)21:44
hosanainotmyname, tdasilva: regarding tape discussion, we will have a meeting in next week21:44
notmynamemattoliverau: ah, cool21:44
notmynameI'm glad to hear that21:45
tdasilvaacoles: i think it's what mattoliverau alluded, tracking the objects21:45
kota_ping m_kazuhiro, he may know something on that21:45
*** lpetrut has quit IRC21:45
tdasilvahosanai: cool!21:45
notmynameanything else to bring up?21:45
dmoritaSorry I'm late21:45
dmoritaIt seems there was discussion about policy changingm, right?21:46
tdasilvaacoles: i'll write those items up on a etherpad and we can continue the discussions there21:46
notmynamedmorita: yeah, just an overview of what's going on21:46
acolestdasilva: thanks21:46
*** kaminohana has joined #openstack-meeting21:46
tdasilvaacoles: sorry for the delay21:46
dmoritaI think as kota_ said, policy changing does not have dependency with symlink.21:46
dmoritaI am working on how to work with fast-POST.21:46
dmoritaActually, it works well in my local, but need to add & fix some tests.21:47
acolestdasilva: NP :)21:47
dmoritanot fix tests.21:47
dmoritafix my code to work with unit tests.21:47
*** thorst_ has joined #openstack-meeting21:47
acolesdmorita: apologies, I owe you an email reply re fast-post21:47
dmoritaNP. Totally your first reply makes sense to me.21:48
dmoritaAnyway, after I fix something, I will update my patch in gerrit.21:49
notmynameare we all good for this meeting today? anything else to bring up?21:50
tdasilvasince we talked so much about it, here goes a shameless plug: symlinks is ready for review ;)21:50
notmynametdasilva: :-)21:50
tdasilvanotmyname: any other reviews to highlight this week?21:50
notmynameand look at all the work dependent on it!21:50
acolestdasilva: lol21:50
notmynameI've been heads-down on the infra changes and the xattr stuff. I don't have anything else to highlight this week. except maybe the libec/pyeclib stuff to fully close the ec issue21:51
timburkethanks everybody for looking at my slo patches lately!21:51
onovyam i late, right?21:51
mattoliverauonovy: yup, a little :P21:52
notmynameonovy: yeah, just ending21:52
acolestimburke: slo sysmeta merged right?21:52
onovydo we have time for one question?21:52
kota_hopefully, if someone would start my global ec cluster review :P21:52
timburkeacoles: yup. and the parallel verification21:52
notmynameonovy: yes21:52
notmynamekota_: yes! ( much to do...)21:53
onovyi think we found that strange 'rsync metrics bug'21:53
onovyand i need to know another one opinion about it21:53
tdasilvakota_: patch?21:53
onovyfix is really simple:
notmynameonovy: ah, cool21:54
onovyPavel is going to stress test it in lab tomorrow21:54
kota_tdasilva: here21:54
onovybut i don't want to test it in production before core review :)21:54
onovyi think it's relativly big regression. in some situation, replicator will not replicate changed partitions21:55
notmynameonovy: yeah, makes sense. this is a US holiday week, so reviews are a little light this week21:56
onovynotmyname: np21:56
onovyjust want to say: don't lost your data in 2.7.0+ swift plus, good luck :)21:56
cschwedeonovy: your patch is on my agenda for tomorrow morning21:57
onovycschwede: nice! thanks a lot21:57
cschwedesounds scary21:57
onovyshould Pavel go to IRC for talk?21:57
cschwedelet me review+test first21:57
onovycschwede: ok21:57
onovy1/10 replication phase will force-recount hashes21:58
*** aeng_afk has quit IRC21:58
onovyso this is fine21:58
onovyso every 10th phase will sync cluster correctly21:58
*** aeng has joined #openstack-meeting21:58
*** aeng has quit IRC21:58
notmynamewe're at time, so I'm going to close the meeting21:59
mattoliverauonovy: I've got a pretty busy day, but will also try and take a look today.21:59
acolesnotmyname: thanks for your work on infra stuff21:59
onovymattoliverau: thanks too21:59
notmynamenp. it's been a ...learning... experience :-)21:59
notmynamethanks everyone for coming. thanks for working on swift21:59
acolesgreat! :P21:59
onovyfor /me too :P21:59
*** openstack changes topic to "OpenStack Meetings ||"21:59
openstackMeeting ended Wed Nov 23 21:59:56 2016 UTC.  Information about MeetBot at . (v 0.1.4)21:59
openstackMinutes (text):
*** joeljwright has left #openstack-meeting22:00
*** pdardeau has left #openstack-meeting22:00
*** kota_ has left #openstack-meeting22:00
*** hosanai has quit IRC22:00
*** mmotiani1 has quit IRC22:00
*** timburke has left #openstack-meeting22:00
*** m_kazuhiro has quit IRC22:03
*** Guest2 has quit IRC22:03
*** Leom has joined #openstack-meeting22:05
*** tpsilva has quit IRC22:05
*** e0ne has joined #openstack-meeting22:09
*** acoles is now known as acoles_22:11
*** slagle has quit IRC22:18
*** thorst_ has quit IRC22:20
*** aeng has joined #openstack-meeting22:22
*** matrohon has quit IRC22:33
*** Julien-zte has joined #openstack-meeting22:34
*** vishnoianil has quit IRC22:34
*** JRobinson__ has joined #openstack-meeting22:39
*** e0ne has quit IRC22:39
*** dmorita has quit IRC22:40
*** cody-somerville has quit IRC22:40
*** dmorita has joined #openstack-meeting22:41
*** beagles is now known as beagles_brb22:43
*** vishnoianil has joined #openstack-meeting22:47
*** whenry has quit IRC22:52
*** ad_rien_ has quit IRC22:53
*** vishnoianil has quit IRC22:53
*** dimtruck is now known as zz_dimtruck22:59
*** xyang1 has quit IRC22:59
*** annegentle has joined #openstack-meeting23:03
*** vishnoianil has joined #openstack-meeting23:08
*** mtanino has quit IRC23:12
*** dmorita has quit IRC23:14
*** beagles_brb is now known as beagles23:14
*** bobh has quit IRC23:24
*** JRobinson__ is now known as JRobinson__afk23:26
*** priteau has quit IRC23:29
*** dkehn__ has quit IRC23:29
*** bobh has joined #openstack-meeting23:33
*** jgregor has joined #openstack-meeting23:34
*** bobh has quit IRC23:38
*** jgregor has quit IRC23:38
*** Julien-zte has quit IRC23:38
*** mriedem has quit IRC23:41
*** adiantum has joined #openstack-meeting23:42
*** lamt has quit IRC23:43
*** AlanClark has joined #openstack-meeting23:45
*** shashank_hegde has joined #openstack-meeting23:45
*** JRobinson__afk is now known as JRobinson__23:45
*** dmorita has joined #openstack-meeting23:49
*** jamesdenton has joined #openstack-meeting23:49
*** jamesdenton has quit IRC23:49
*** jamesdenton has joined #openstack-meeting23:50
*** jamesdenton has quit IRC23:52
*** ramineni_ has joined #openstack-meeting23:54
*** masahito has joined #openstack-meeting23:57
*** ekcs has joined #openstack-meeting23:58
*** dmorita has joined #openstack-meeting23:59

Generated by 2.14.0 by Marius Gedminas - find it at!