| *** jkilpatr has quit IRC | 02:21 | |
| *** dims has quit IRC | 06:05 | |
| *** dims has joined #openstack-cyborg | 06:12 | |
| *** mpaolino has joined #openstack-cyborg | 08:26 | |
| *** zhipengh[m] has quit IRC | 09:43 | |
| *** ttk2[m] has quit IRC | 09:47 | |
| *** ttk2[m] has joined #openstack-cyborg | 09:57 | |
| *** zhipengh[m] has joined #openstack-cyborg | 10:04 | |
| *** crushil_ has joined #openstack-cyborg | 10:37 | |
| *** crushil has quit IRC | 10:40 | |
| *** crushil__ has joined #openstack-cyborg | 10:57 | |
| *** crushil_ has quit IRC | 11:00 | |
| *** crushil_ has joined #openstack-cyborg | 11:04 | |
| *** crushil__ has quit IRC | 11:07 | |
| *** crushil__ has joined #openstack-cyborg | 11:15 | |
| *** crushil_ has quit IRC | 11:18 | |
| *** crushil has joined #openstack-cyborg | 11:25 | |
| *** crushil__ has quit IRC | 11:27 | |
| *** crushil_ has joined #openstack-cyborg | 11:31 | |
| *** crushil has quit IRC | 11:34 | |
| *** crushil has joined #openstack-cyborg | 12:19 | |
| *** crushil_ has quit IRC | 12:22 | |
| *** mikeH has joined #openstack-cyborg | 12:29 | |
| *** jkilpatr has joined #openstack-cyborg | 12:32 | |
| *** crushil has quit IRC | 12:37 | |
| *** crushil has joined #openstack-cyborg | 14:07 | |
| *** zhipeng has joined #openstack-cyborg | 14:17 | |
| *** crushil has quit IRC | 14:25 | |
| *** zhipeng has quit IRC | 14:28 | |
| *** zhipeng has joined #openstack-cyborg | 14:33 | |
| *** crushil has joined #openstack-cyborg | 14:39 | |
| zhipeng | #startmeeting openstack-cyborg | 15:01 |
|---|---|---|
| openstack | Meeting started Wed Nov 8 15:01:50 2017 UTC and is due to finish in 60 minutes. The chair is zhipeng. Information about MeetBot at http://wiki.debian.org/MeetBot. | 15:01 |
| openstack | Useful Commands: #action #agreed #help #info #idea #link #topic #startvote. | 15:01 |
| *** openstack changes topic to " (Meeting topic: openstack-cyborg)" | 15:01 | |
| openstack | The meeting name has been set to 'openstack_cyborg' | 15:01 |
| zhipeng | #topic Roll Call | 15:02 |
| *** openstack changes topic to "Roll Call (Meeting topic: openstack-cyborg)" | 15:02 | |
| zhipeng | #info Howard | 15:02 |
| mpaolino | #info Michele | 15:02 |
| zhipeng | hey Michele | 15:04 |
| mpaolino | hi Howard! | 15:04 |
| zhipeng | let's wait to see if there are other folks coming | 15:06 |
| zhipeng | crushil ttk2[m] zhuli you guys there ? | 15:06 |
| crushil | yup | 15:06 |
| jkilpatr | yup | 15:06 |
| jkilpatr | daylight savings time tho | 15:07 |
| jkilpatr | we're an hour early by my calender | 15:07 |
| zhuli | hi folks, sorry for the late | 15:07 |
| crushil | Yup | 15:07 |
| jkilpatr | or is my calender screwed up | 15:07 |
| crushil | It's DST jkilpatr | 15:07 |
| jkilpatr | no biggie | 15:07 |
| jkilpatr | we can just do a 2 hour meeting and then anyone who wants to show up at the other time can :P | 15:07 |
| jkilpatr | #info Justin | 15:08 |
| zhipeng | :P | 15:08 |
| jkilpatr | after all we don't want to make Howard have to stay up any later than he is now. | 15:09 |
| zhipeng | we want the bot to rest as well | 15:09 |
| jkilpatr | lol bots rights | 15:10 |
| crushil | #info RUshil | 15:10 |
| jkilpatr | we've got another 5 years before we have to worry about the meeting bots unionizing zhipeng | 15:10 |
| zhipeng | jkilpatr if they do we just close business | 15:10 |
| zhipeng | #topic Sydney Summit Initial Feedback Gathering | 15:10 |
| *** openstack changes topic to "Sydney Summit Initial Feedback Gathering (Meeting topic: openstack-cyborg)" | 15:10 | |
| zhipeng | So I think I'm very thankful for Richard to step in for us to do the presentation | 15:11 |
| zhipeng | he even got the joke right (about our meeting time) | 15:11 |
| zhipeng | for those of you haven't seen the recording | 15:11 |
| jkilpatr | link? | 15:12 |
| jkilpatr | how was attendance? | 15:12 |
| zhipeng | #link https://www.youtube.com/watch?v=DXA0c62R4jI | 15:12 |
| zhuli | awesome guy, is there a video about the presentation, would love to see it | 15:12 |
| zhipeng | and for presentation slide itself | 15:12 |
| zhipeng | #link https://docs.google.com/presentation/d/1tERW4CVhyxNdX50AOPZRa44iPEhico8O_vQ0Ou75L80/edit?usp=sharing | 15:13 |
| zhipeng | crushil I was gonna to ask you, any feedback from Rich > | 15:13 |
| zhipeng | ? | 15:13 |
| crushil | It went really well | 15:13 |
| zhipeng | about the attendance, etc ? | 15:13 |
| zhuli | thanks for the link, will watch later | 15:14 |
| crushil | It was a lighting talk | 15:14 |
| crushil | So, there were like 15-20 folks there | 15:14 |
| zhipeng | anyone approached him after the talk ? | 15:14 |
| crushil | Obviously there was no time for questions | 15:14 |
| crushil | That we didn't get a chance to talk about | 15:14 |
| crushil | It was around midnight when he finished | 15:15 |
| zhipeng | ah ok | 15:15 |
| crushil | I'll catch up with him my evening (his morning) | 15:15 |
| zhipeng | sounds great :) | 15:15 |
| crushil | Sydney is 15 hours ahead of EST | 15:15 |
| crushil | It's like 3 hours ahead of you | 15:15 |
| zhipeng | ye we have 3 hour difference | 15:15 |
| zhipeng | let's try to get together in Dublin next year, for rocky ptg | 15:16 |
| zhipeng | late Feb | 15:16 |
| jkilpatr | I figure I'll get sent to the PTG, to be honest we get more work done there anyways | 15:17 |
| zhipeng | might freeze my balls off tho, considering the weather ... | 15:17 |
| zhipeng | jkilpatr for sure | 15:17 |
| zhipeng | any other comments re this topic ? | 15:17 |
| jkilpatr | speaking of getting work done, can we try and wrap up the interaction patch? Sorry I haven't gotten my nova hack ready been on PTO | 15:18 |
| zhipeng | so on that note, moving on to the next topic | 15:19 |
| zhipeng | #topic Placement-Cyborg Interaction Discussion | 15:19 |
| *** openstack changes topic to "Placement-Cyborg Interaction Discussion (Meeting topic: openstack-cyborg)" | 15:19 | |
| zhipeng | so last week crushil made a really good proposal | 15:19 |
| zhipeng | that before Xmas we should have like weekly video sprints | 15:19 |
| zhipeng | i asked Sean about the release sched | 15:19 |
| zhipeng | Feb 5th 2018 is the hard cutoff date for coding | 15:20 |
| crushil | cool | 15:20 |
| zhipeng | that will be when RC is released | 15:20 |
| jkilpatr | I can refocus on Cyborg last week of November and into December | 15:20 |
| jkilpatr | Wrapping up a lot of other projects in the next few weeks. | 15:20 |
| zhipeng | so I think let's just concentrate on Nov and Dec and try to hammer everything we need out in this period | 15:20 |
| zhipeng | jkilpatr no problem | 15:20 |
| zhipeng | then when would be the dates works for everyone about the sprint ? | 15:21 |
| zhipeng | crushil jkilpatr zhuli | 15:22 |
| jkilpatr | Nov 27 - Dec 4th short break for Ansible training then Dec 8 - EOY and probably beyond. | 15:23 |
| jkilpatr | I can attend meetings and maybe get some stuff done earlier in November but I' | 15:24 |
| jkilpatr | I'm getting a few racks of gear for release qualification so I need to focus on that when I have it. | 15:25 |
| zhipeng | how about you crushil ? | 15:25 |
| crushil | I should be ok to start sprint next week. Still wrapping up one project that has been pending for months | 15:26 |
| zhipeng | then I think zhuli and I could start with crushil first, starting next week | 15:28 |
| zhipeng | on driver side and traits | 15:28 |
| zhuli | since the summit is done, next week is ok for me too | 15:28 |
| zhuli | yep | 15:28 |
| zhipeng | and jkilpatr could jam in later on the agent and conductor parts | 15:28 |
| zhipeng | then maybe EOY we could have some E2E stuff, hopefully | 15:28 |
| jkilpatr | been looking at Nova don't see any reason why we can't add devices to the whitelist live | 15:28 |
| jkilpatr | there's actually not too much going on with the whitelist at all, just gets loaded and checked | 15:29 |
| zhipeng | jkilpatr I could also ping Matt if we encounter any problems at Nova side | 15:29 |
| jkilpatr | easier to write code and ask for a review than ask them to do it :P | 15:29 |
| jkilpatr | especially if it's short and easy to review | 15:29 |
| zhipeng | yep :P | 15:30 |
| zhipeng | then crushil which day of the week shall we pick ? | 15:30 |
| zhipeng | I think time wise the meeting time would be ideal | 15:30 |
| jkilpatr | I agree | 15:31 |
| zhipeng | we could do like the same time but on Tuesday, for example | 15:32 |
| jkilpatr | that's fine too but then what do we talk about during the Wednesday meetings? | 15:32 |
| crushil | ya, that works | 15:33 |
| zhipeng | jkilpatr to get you update :P | 15:34 |
| zhipeng | or shall we just use the weekly meeting time ? | 15:34 |
| jkilpatr | I think we should just use the weekly meeting time and be sure to note things in IRC don't want to turn away newcomers in the channel | 15:35 |
| zhipeng | crushil that ok for you ? | 15:35 |
| crushil | yup | 15:36 |
| zhipeng | okey great, then I will send out ZOOM links for the video conf | 15:37 |
| zhipeng | starting next week | 15:37 |
| zhipeng | jkilpatr regarding your current spec, I will have another set of comment, but I think we could wrap it up this week | 15:37 |
| jkilpatr | sounds good let me know | 15:38 |
| jkilpatr | zhuli, these times good for you? | 15:39 |
| zhuli | no problem | 15:39 |
| zhipeng | jkilpatr last week meeting, don't know if you have comb through the log yet, I have thought about adding another dimension of resource provider | 15:40 |
| jkilpatr | nope haven't read it, care to summarize? | 15:41 |
| zhipeng | we could implement it later, but I think I should submit a spec about it | 15:41 |
| zhipeng | so in a gist | 15:41 |
| jkilpatr | link me when you have it up | 15:41 |
| zhipeng | currently Placement uses Resource Provider to model resources | 15:41 |
| zhipeng | which consists of two dimensions: traits on the quantative side of things, and resource class for the qualitive side of things | 15:42 |
| zhipeng | e.g. you could use trait to define what you have and resource class for how much/many you have | 15:42 |
| zhipeng | however, i think for cyborg to deal with accelerator | 15:43 |
| zhipeng | purely enumeration would cause problems | 15:43 |
| zhipeng | since for example for FPGAs | 15:43 |
| zhipeng | you can't trait and resource class with every VF/PF combination/layout | 15:43 |
| jkilpatr | where you have possible traits that consume the same resource class? | 15:43 |
| jkilpatr | zhipeng, I would have a resource class fpga that was consumed by many traits which would be the VF/PF | 15:44 |
| zhipeng | jkilpatr my point is that many traits would be really hard to manage | 15:44 |
| zhipeng | we need a more fuzzy way to describe accelerator resource, besides traits and resource class | 15:45 |
| jkilpatr | what do you propose | 15:45 |
| zhipeng | so I think propably something like capability, that it could generally map to a set of resource that user would need | 15:45 |
| zhipeng | instead of specifically id the resource | 15:45 |
| zhipeng | for example for deep learning | 15:46 |
| zhipeng | there will be cases that operators just want to run their framworks on OpenStack Infra | 15:46 |
| zhipeng | doesn't really care about which GPU, FPGA, SoC solution it should use | 15:46 |
| zhipeng | and then if say, the infra got some GPU good for temporalachitecture | 15:47 |
| zhipeng | and some FPGA cards that good for spatial architecture | 15:47 |
| jkilpatr | but we need to get more specific at some point? | 15:48 |
| zhipeng | we should just label these like CAPABILITY: DL/TEM | 15:48 |
| zhipeng | we will still have traits ands resource class | 15:48 |
| jkilpatr | the way I see it we can just map a buncha traits to the same resource and it will be kinda ugly but work. | 15:48 |
| zhipeng | ye that is what I think | 15:48 |
| zhipeng | so my thought was that if we could add another dimension, to use with trait and resource class together | 15:48 |
| zhipeng | so that operators could do a specific request | 15:49 |
| zhipeng | or a fuzzy request | 15:49 |
| zhipeng | because unlike the general computing infras, which could almost be enumerated | 15:49 |
| zhipeng | accelerators just got so many types and combinations | 15:49 |
| jkilpatr | so we let operators aggregate things when their workload could run on either and schedule agains that? | 15:50 |
| jkilpatr | against* | 15:50 |
| zhipeng | not necessarily aggreagating, but just select a (super/sub) set of resource that satisfy the fuzzy request | 15:51 |
| zhipeng | if it deems to be a super set, then it is aggregation | 15:51 |
| zhipeng | if it just needs a subset, say just some of the FPGA card funcationalities | 15:51 |
| zhipeng | we could also do that mitigation | 15:51 |
| jkilpatr | still not sure I understand the usecase | 15:52 |
| zhipeng | I think I will just writeup a spec and we could review it :P | 15:52 |
| jkilpatr | sure, a better outline of the potential usecase would help a ton | 15:52 |
| zhipeng | I need to elaborate more | 15:52 |
| zhipeng | yep | 15:52 |
| zhipeng | okey | 15:52 |
| zhipeng | #agreed have weekly sprint video conf using team meeting timeslot starting Nov 15th | 15:53 |
| zhipeng | #topic AoB | 15:53 |
| *** openstack changes topic to "AoB (Meeting topic: openstack-cyborg)" | 15:53 | |
| zhipeng | I think we have covered the most important ones | 15:54 |
| zhipeng | any other business ? | 15:54 |
| zhipeng | okey let's conclude the meeting then, thanks everyone :) | 15:58 |
| zhipeng | #endmeeting | 15:58 |
| *** openstack changes topic to "#openstack-cyborg" | 15:58 | |
| openstack | Meeting ended Wed Nov 8 15:58:59 2017 UTC. Information about MeetBot at http://wiki.debian.org/MeetBot . (v 0.1.4) | 15:59 |
| openstack | Minutes: http://eavesdrop.openstack.org/meetings/openstack_cyborg/2017/openstack_cyborg.2017-11-08-15.01.html | 15:59 |
| openstack | Minutes (text): http://eavesdrop.openstack.org/meetings/openstack_cyborg/2017/openstack_cyborg.2017-11-08-15.01.txt | 15:59 |
| openstack | Log: http://eavesdrop.openstack.org/meetings/openstack_cyborg/2017/openstack_cyborg.2017-11-08-15.01.log.html | 15:59 |
| *** zhipeng has quit IRC | 16:00 | |
| *** crushil has quit IRC | 16:02 | |
| *** crushil has joined #openstack-cyborg | 16:06 | |
| *** mpaolino has quit IRC | 16:09 | |
| *** jkilpatr has quit IRC | 16:41 | |
| *** jkilpatr has joined #openstack-cyborg | 16:55 | |
| *** jkilpatr has quit IRC | 17:05 | |
| *** jkilpatr has joined #openstack-cyborg | 17:19 | |
| *** jkilpatr has quit IRC | 18:05 | |
| *** mikeH has quit IRC | 18:17 | |
| *** jkilpatr has joined #openstack-cyborg | 18:18 | |
| *** amol has joined #openstack-cyborg | 18:52 | |
| *** amol has quit IRC | 18:53 | |
| *** jkilpatr has quit IRC | 19:00 | |
| *** jkilpatr has joined #openstack-cyborg | 19:13 | |
| *** crushil has quit IRC | 19:20 | |
| *** mikeH has joined #openstack-cyborg | 19:27 | |
| *** crushil has joined #openstack-cyborg | 19:39 | |
| *** crushil_ has joined #openstack-cyborg | 20:15 | |
| *** crushil has quit IRC | 20:16 | |
| *** crushil_ has quit IRC | 20:17 | |
| *** crushil_ has joined #openstack-cyborg | 20:17 | |
| *** crushil_ has quit IRC | 20:18 | |
| *** crushil_ has joined #openstack-cyborg | 20:19 | |
| *** crushil has joined #openstack-cyborg | 20:23 | |
| *** crushil_ has quit IRC | 20:25 | |
| *** jkilpatr_ has joined #openstack-cyborg | 20:32 | |
| *** jkilpatr has quit IRC | 20:35 | |
| *** mikeH has quit IRC | 20:38 | |
| *** jkilpatr_ has quit IRC | 21:32 | |
| *** crushil has quit IRC | 21:47 | |
| *** jkilpatr has joined #openstack-cyborg | 21:57 | |
Generated by irclog2html.py 2.15.3 by Marius Gedminas - find it at mg.pov.lt!