| *** Duth has joined #openstack-cyborg | 03:19 | |
| *** Duth has quit IRC | 03:44 | |
| openstackgerrit | Li Liu proposed openstack/cyborg master: Added bitstream metadata standardization spec https://review.openstack.org/558265 | 04:20 |
|---|---|---|
| *** zhipeng has joined #openstack-cyborg | 06:20 | |
| *** goldenfri has quit IRC | 08:27 | |
| *** zhipeng has quit IRC | 08:50 | |
| *** circ-user-ojqFa has joined #openstack-cyborg | 13:55 | |
| *** Sundar has joined #openstack-cyborg | 13:58 | |
| *** Li_Liu has joined #openstack-cyborg | 14:02 | |
| *** zhipeng has joined #openstack-cyborg | 14:02 | |
| *** Melissa_S has joined #openstack-cyborg | 14:02 | |
| *** circ-user-ojqFa has left #openstack-cyborg | 14:03 | |
| zhipeng | #startmeeting openstack-cyborg | 14:03 |
| openstack | Meeting started Wed Apr 4 14:03:00 2018 UTC and is due to finish in 60 minutes. The chair is zhipeng. Information about MeetBot at http://wiki.debian.org/MeetBot. | 14:03 |
| openstack | Useful Commands: #action #agreed #help #info #idea #link #topic #startvote. | 14:03 |
| *** openstack changes topic to " (Meeting topic: openstack-cyborg)" | 14:03 | |
| openstack | The meeting name has been set to 'openstack_cyborg' | 14:03 |
| zhipeng | #topic Roll Call | 14:03 |
| *** openstack changes topic to "Roll Call (Meeting topic: openstack-cyborg)" | 14:03 | |
| zhipeng | #info Howard | 14:03 |
| Sundar | #info Sundar | 14:03 |
| Sundar | Hi Howard! | 14:03 |
| Li_Liu | #info Li_Liu | 14:03 |
| zhipeng | Hi Sundar :) | 14:04 |
| Melissa_S | #info Melissa | 14:04 |
| *** circ-user-ldzTg has joined #openstack-cyborg | 14:04 | |
| zhipeng | Hi Melissa_S | 14:05 |
| *** Helloway has joined #openstack-cyborg | 14:05 | |
| zhipeng | Can you introduce yourself a little bit ? | 14:05 |
| Melissa_S | Hi! I am new to this chat - my name is Melissa Sussmann. Sundar and I actually used to work together at Intel a while back. I am at Xilinx now and sitting in for Dutch :) | 14:06 |
| zhipeng | ah nice to meet you :) | 14:06 |
| Li_Liu | Welcome Melissa! | 14:06 |
| Melissa_S | Likewise :) | 14:06 |
| Sundar | Hi Melissa, welcome! Good to have you here. | 14:07 |
| Melissa_S | Thanks Sundar :) | 14:07 |
| *** Yumeng__ has joined #openstack-cyborg | 14:08 | |
| kosamara | #info kosamara | 14:08 |
| kosamara | hi! | 14:08 |
| *** chucksong has joined #openstack-cyborg | 14:09 | |
| zhipeng | Hey ! | 14:09 |
| Yumeng__ | #info Yumeng__ | 14:09 |
| Yumeng__ | Hi | 14:09 |
| zhipeng | Hi Yumeng :) | 14:09 |
| Yumeng__ | Hi zhipeng | 14:09 |
| chucksong | Hi everyone! | 14:10 |
| zhipeng | Hi chucksong | 14:10 |
| zhipeng | don't believe we met before | 14:10 |
| zhipeng | can you introduce yourself a little bit ? | 14:10 |
| chucksong | yes, I am Chuck Song of Xilinx | 14:11 |
| chucksong | Currently taking charge of the FaaS team | 14:11 |
| chucksong | I suppose we are going to talk about the Cyborg project. | 14:11 |
| zhipeng | FPGA as a service ? | 14:11 |
| chucksong | yes | 14:11 |
| Sundar | Hi Chuck, welcome! | 14:11 |
| Li_Liu | Hi Chuck | 14:11 |
| Li_Liu | We have a lot people joining :) | 14:12 |
| chucksong | hi Sundar and LiLiu | 14:12 |
| zhipeng | let's get into business :) | 14:12 |
| zhipeng | #topic sub-team report | 14:12 |
| *** openstack changes topic to "sub-team report (Meeting topic: openstack-cyborg)" | 14:12 | |
| zhipeng | I think we could start with release subteam | 14:13 |
| zhipeng | #link https://review.openstack.org/558223 | 14:13 |
| zhipeng | #info cyborg has been added for milestone based release | 14:14 |
| zhipeng | that was part of Rocky goal | 14:14 |
| Sundar | Is Apr 19 the spec freeze day for Cyborg too? | 14:15 |
| zhipeng | yes Sudnar the week of Apr 16 to Apr 20 | 14:16 |
| zhipeng | will be our very first deadline for spec freeze :) | 14:16 |
| Melissa_S | what do you need delivered on the Xilinx side before freeze? | 14:16 |
| Melissa_S | Pardon me - I am new to the project :) | 14:17 |
| zhipeng | Melissa_S altho currently all the drivers are in-tree which means Xilinx driver also needs a spec | 14:18 |
| Li_Liu | I think the major thing we need is Xilinx Device driver. But that doesn't have to be before spec freeze I think | 14:18 |
| zhipeng | but driver spec freeze should be expected for Rocky MS-2 | 14:18 |
| zhipeng | which will be week of Jun 04-Jun08 | 14:18 |
| Li_Liu | Does the vendor specific driver need a spec Howord? | 14:18 |
| zhipeng | Li_Liu at the moment yes | 14:18 |
| Li_Liu | ok | 14:18 |
| zhipeng | but yes as Li_Liu said, plz don't wait for the deadline :) | 14:19 |
| Sundar | Not to jump the gun :) but could I ask folks to review https://etherpad.openstack.org/p/Cyborg-Nova-Multifunction so that I can update https://review.openstack.org/#/c/554717/ ? | 14:19 |
| Sundar | This is based on the latest proposal from Nova community | 14:19 |
| zhipeng | Sundar will go into that very soon :) | 14:19 |
| Li_Liu | sure, I will take a look | 14:19 |
| zhipeng | Let's finish the subteam report first | 14:20 |
| zhipeng | Melissa_S chucksong plz refer to https://releases.openstack.org/rocky/schedule.html#r-release | 14:20 |
| zhipeng | for the general milestone sched | 14:20 |
| Sundar | Thanks, Li_Liu and Howard | 14:21 |
| Melissa_S | Yes - thank you. | 14:21 |
| zhipeng | Cyborg's specific sched could be found http://eavesdrop.openstack.org/meetings/openstack_cyborg/2018/openstack_cyborg.2018-03-14-14.07.html | 14:22 |
| zhipeng | okey moving on | 14:22 |
| zhipeng | Yumeng__ could you update the progress on your side ? | 14:22 |
| Yumeng__ | I sent out a update about the high time synchronisation card on the mail list | 14:23 |
| Yumeng__ | Pls check | 14:24 |
| Yumeng__ | And launchpad migration to storyboard will be done soon. | 14:24 |
| zhipeng | did you just send the clock driver proposal ? | 14:25 |
| zhipeng | or maybe I missed it ? | 14:25 |
| Yumeng__ | 1 second | 14:25 |
| zhipeng | BTW in case everyone not follow the storyboard migration, plz refer to | 14:26 |
| zhipeng | #link https://review.openstack.org/#/c/558327/ | 14:26 |
| Yumeng__ | https://docs.openstack.org/infra/manual/zuulv3.html | 14:26 |
| Yumeng__ | Pls go ahead, I will send out the right link | 14:27 |
| zhipeng | #link https://review.openstack.org/558821 | 14:27 |
| zhipeng | #info storyboard migration for cyborg | 14:28 |
| zhipeng | thx Yumeng__ :) doc subteam has been very responsive and active | 14:28 |
| zhipeng | Melissa_S chucksong Dutch signed on as co-lead for the driver sub-team | 14:29 |
| zhipeng | does one of you guys maybe interested in take the role ? | 14:29 |
| zhipeng | help update and coordinate the driver development for Rocky ? | 14:29 |
| Melissa_S | Chuck and I can work on this | 14:30 |
| zhipeng | great :) | 14:30 |
| Melissa_S | I think you could put Chuck's name down - he is on the apps side | 14:31 |
| zhipeng | duly noted :) | 14:31 |
| Melissa_S | we will find the correct internal team for this project | 14:31 |
| *** Yumeng has joined #openstack-cyborg | 14:31 | |
| zhipeng | #topic critical rocky spec review | 14:31 |
| *** openstack changes topic to "critical rocky spec review (Meeting topic: openstack-cyborg)" | 14:31 | |
| zhipeng | first up, Sundar's Nova-Cyborg interaction spec | 14:32 |
| chucksong | zhipeng, yes I will take the role | 14:32 |
| zhipeng | Sundar could you help get everyone up to speed ? | 14:32 |
| Sundar | Sure, Howard | 14:33 |
| zhipeng | #info Sundar cyborg-nova spec discussion | 14:33 |
| zhipeng | #link https://etherpad.openstack.org/p/Cyborg-Nova-Multifunction | 14:33 |
| zhipeng | #link https://review.openstack.org/#/c/554717/ | 14:33 |
| Sundar | We had arrived at a way of representing FPGA components in Nova, and worklfows for all use cases based on hat representation, back in the PTG | 14:34 |
| Sundar | The spec that Howard provided above codifies that | 14:34 |
| *** dolpher has joined #openstack-cyborg | 14:34 | |
| Sundar | However, there was a race condition for one use case, which has been debated in the community. An analogy was found with a vGPU issue, and a joint solution was proposed | 14:35 |
| Sundar | http://lists.openstack.org/pipermail/openstack-dev/2018-March/128888.html | 14:35 |
| zhipeng | #link http://lists.openstack.org/pipermail/openstack-dev/2018-March/128888.html | 14:35 |
| Sundar | Based on that, I worked out the details, in a way that should cover GPUs etc. but probably focuses more on FPGAs. | 14:36 |
| Sundar | #link https://etherpad.openstack.org/p/Cyborg-Nova-Multifunction | 14:36 |
| Sundar | I think this is a better solution than the PTG flow :) both for Nova and Cyborg | 14:36 |
| Sundar | For Cyborg, this means that we don't need to keep accelerator usage details in Cyborg DB -- just use placement info :) | 14:37 |
| Sundar | Eventually, if/when Nova supports preferred traits, maybe we don't need the weigher -- but we can evaluat that when it becomes real | 14:38 |
| *** Duth has joined #openstack-cyborg | 14:38 | |
| Sundar | For the new folks in Cyborg, this may sound cryptic :) I am open to walking folks through the proposal in a call if needed | 14:38 |
| Sundar | Howard, do you want me to explain the crux of the proposal here? | 14:39 |
| Li_Liu | Sundar, regardless, we still need to track individual assignment for each device in Cyborg, right? | 14:39 |
| zhipeng | Sundar it would be great to have a brief walk through and the central take aways :) | 14:40 |
| Sundar | Li_Liu: Yes, we will be handling acceleratr -PF/VF matching | 14:40 |
| Sundar | That is not involve din the scheduling, because Placement counts accelerator resources | 14:40 |
| Sundar | As instances are spawned and terminated, Cyborg agent can track PF/VF usage | 14:41 |
| Sundar | Howard, sure. | 14:41 |
| Sundar | The brief summary is this: | 14:41 |
| *** shaohe_feng_ has joined #openstack-cyborg | 14:42 | |
| Melissa_S | Sundar - I am open to scheduling a call and walkthrough of your proposal. | 14:42 |
| Sundar | We want to expose FPGAs in 2 ways: FPGA as a Service (FPGA aaS), and Accelerated Function as a Service (AFaaS) | 14:42 |
| Sundar | For FPGAaaS, user/flavor asks for a device type (or region type) and optionally a bitstream ID that needs to be applied by Cyborg before the instance comes up. | 14:43 |
| Sundar | This is similar to Amazon flow. | 14:43 |
| Sundar | For AFaaS, the user/flavor asks for a function/algorithm e.g. 'ipsec' + some indication of what device family the VM has the drivers for | 14:44 |
| Sundar | To cover both cases, we say that an accelerator can be a device/region or a function | 14:44 |
| Sundar | We represent a generic accelerator with the custom resource class (RC) CUSTOM_ACCELERATOR | 14:45 |
| Sundar | We also represent FPGAs and their inner regions as nested Resource Providers (RPs) | 14:45 |
| Sundar | So, a region RP can provide N instances of a CUSTOM_ACCELERATOR class. Most commonly, N=1 | 14:45 |
| Sundar | Also, each region RP has traits: region type (e.g. CUSTOM_FPGA_<vendor>_REGION_...) | 14:46 |
| Sundar | possibly function type (e.g. CUSTOM_FPGA_<ipsec_uuid>) | 14:47 |
| Sundar | and device family (e.g. CUSTOM_FPGA_XILINX_<product/part>...) | 14:47 |
| Li_Liu | Sundar, for AFaaS, on top of asking for a function/algorithm, I think users can also specify the minimum kpi/capability for the requested resources | 14:47 |
| Li_Liu | you keep going | 14:48 |
| Li_Liu | I just throw some of my thoughts here | 14:48 |
| Sundar | Li_Liu, NP, I'll get back to that | 14:48 |
| Sundar | With this background, here's how a flavor can ask for FPGA aaS: | 14:48 |
| Sundar | resource:CUSTOM_ACCELERATOR=1; trait:CUSTOM_FPGA_<vendor>_REGION_<uuid>=required | 14:49 |
| Sundar | optionally, one more extra spec: bitstream:3A56D4=required | 14:49 |
| Sundar | This gets Placement to choose all matching devices based on trait. Once a node is selected, the Cyborg agent in the node notes the extra spec and applies the bitstream | 14:50 |
| Sundar | Before I go to AFaaS, does this make sense for FPGA aaS/ | 14:50 |
| zhipeng | it does for me, this is awesome Sundar | 14:50 |
| Li_Liu | yup, it looks great | 14:51 |
| Sundar | Cool :) Now for AFaaS flavor | 14:51 |
| chucksong | It sounds good Sundar. I need to know more about this project though. I just joined this project and still have a lot to learn | 14:51 |
| Duth | Yes agreed. Sundar, can you share some more information on this proposal for FPGA aaS/ | 14:52 |
| zhipeng | Duth let's schedule another dedicated call for it | 14:52 |
| zhipeng | :) | 14:52 |
| Sundar | resource:CUSTOM_ACCELERATOR=1; trait:CUSTOM_FPGA_INTEL_<ipsec-uuid>=required; trait:CUSOTM_FPGA_INTEL_<product>=required | 14:52 |
| zhipeng | video conf would be better for a deep dive walk through | 14:52 |
| Sundar | Yes, we can do more in a video call | 14:53 |
| Melissa_S | Agreed. | 14:53 |
| zhipeng | Sundar plz carry on the AFaaS scenario | 14:53 |
| Sundar | Some folks don't like the UUIDs. I think UUIDs make it very concrete and we can make it more user-friendly later. Also, for AFaaS, we can avoid region UUIDs and use just product name | 14:54 |
| Sundar | OK, back to AFaaS :) | 14:54 |
| zhipeng | string name could do the trick ? | 14:54 |
| zhipeng | sorry go ahead | 14:54 |
| Sundar | Zhipeng: We can discuss strings in more deatail, may be in an email? | 14:56 |
| zhipeng | Sundar absolutely | 14:57 |
| *** Kevin_Zheng has joined #openstack-cyborg | 14:57 | |
| zhipeng | plz carry on, sorry for the interruption :) | 14:57 |
| Sundar | OK. AfFaaS flavor: resource:CUSTOM_ACCELERATOR=1; trait:CUSTOM_FPGA_INTEL_<ipsec-uuid>=required; trait:CUSOTM_FPGA_INTEL_<product>=required | 14:57 |
| Sundar | This picks all devices that have the required function. Makes sense, except that if no free instance of that function is available, the request will just fail, rather than have Cyborg pick an available region and reprogram it | 14:58 |
| Sundar | That is ok if that's what the operator wants: he may want to prevent reprogramming for whatever reason. | 14:59 |
| Sundar | But, in the general case, we want the ability to reprogram if needed. | 14:59 |
| Sundar | So, what we want is: trait:CUSTOM_FPGA_INTEL_<ipsec-uuid>=preferred (not required) | 15:00 |
| Sundar | But Nova does not support preferred traits today. I am told that it is not even close | 15:00 |
| Sundar | So, the next best thing: resource:CUSTOM_ACCELERATOR=1; trait:CUSOTM_FPGA_INTEL_<product>=required | 15:01 |
| Sundar | another extra spec: function:CUSTOM_FPGA_INTEL_<ipsec-uuid>=required | 15:01 |
| Sundar | Now, Placement chooses all devices that match the product, whether or not they have the function | 15:01 |
| Sundar | A Cyborg weigher can check the allocation candidates to see which ones have the function -- based on the function trait -- and rank them higher | 15:02 |
| Sundar | So, Nova is likely to pick a device that has the function. if not, Cyborg agent in the compute node will note the requested function is not present in the selected device/region RP | 15:03 |
| Sundar | It will contact Glance to get a matching bitstream and program it, before the instance comes up | 15:03 |
| zhipeng | where would the weigher be implemented ? | 15:03 |
| Sundar | This is the core of the proposal, and covers situations where each bitstream implements only one function | 15:04 |
| Sundar | Zhipeng: the weigher would initially be a Cyborg weigher in my understanding -- but it is not Cyborg-specific. It could possibly become Nova in-tree hopefully | 15:04 |
| Sundar | The weighe ris looking at a list of RPS and choosing those with a specific trait. It is generic | 15:05 |
| zhipeng | i mean the weigher will be part of the agent ? | 15:05 |
| Sundar | It is a weigher in the Nova controller -- like all other filters/weighers in Nova framework | 15:06 |
| Li_Liu | The weigher has to be in Cyborg Controller I think | 15:06 |
| shaohe_feng_ | yes, it should. And seems nova agree on the weigher | 15:07 |
| Sundar | Li_Liu: OK, what I meant is, it runs in the controlle ralong with Nova/Cyborg. The operator must update nova.conf to use this weigher | 15:07 |
| Li_Liu | Right :) | 15:07 |
| zhipeng | Okey | 15:07 |
| shaohe_feng_ | yes. just a config option in nova | 15:08 |
| zhipeng | Sundar I think it is definitely fine to update the spec patch based upon the current discussion conclusion | 15:08 |
| zhipeng | and let's schedule another video conf for a detailed discussion with Xilinx team | 15:09 |
| Sundar | The part of this proposal which needs further review from Nova is when one bitstream has multiple functions, say crypto and compression. I think that is for the future and may not be needed in rocky. Does that sound agreeable? | 15:09 |
| zhipeng | to see if there is any further improvements | 15:09 |
| shaohe_feng_ | but weigher may be not very high priority. It is help to speed up the creation of a VM. but no helpful for the VM performance after VM start | 15:09 |
| Sundar | Thanks, Howard! | 15:09 |
| zhipeng | Sundar yes that would be maybe next release :) | 15:09 |
| edleafe | Just an FYI - it's not likely that nested RPs will be complete in Rocky | 15:10 |
| zhipeng | shalhe_feng_ agree, let's implement the custom rc and traits first | 15:10 |
| zhipeng | edleafe it is possible that we try with the nrp first right ? | 15:10 |
| edleafe | zhipeng: sure, but it looks like the earliest nrp will be available will be in Stein | 15:11 |
| Sundar | edleafe: There is a release notes in Queens for nRPs, right? https://github.com/openstack/nova/blob/adc4d4a29d108c87f884c779af5696e4941b9549/releasenotes/notes/placement-rest-api-nested-resource-providers-552a923a96d7adca.yaml | 15:11 |
| edleafe | Sundar: that is the very beginnings of the structural changes needed for nrp | 15:12 |
| shaohe_feng_ | edleafe: so cyborg just can support a fpga resource class in node provider in this release? | 15:13 |
| edleafe | the full model we need is still far away | 15:13 |
| Sundar | edleafe: The backup optoion would be to apply the RCs and traits to the compute node RP. But, when there are multiple devices in the same node, that can result in issues. | 15:13 |
| edleafe | shaohe_feng_: I'm not sure how that would work if you have multiple devices per node | 15:13 |
| Sundar | edleafe: We crossed. :) | 15:14 |
| edleafe | I'm on a call right now - I just wanted to set your expectations | 15:14 |
| zhipeng | edleafe thx :) | 15:14 |
| shaohe_feng_ | edleafe: IMHO, we can support multiple devices later. | 15:14 |
| zhipeng | yes let's be flexible | 15:14 |
| zhipeng | #action Sundar update the spec according to the ml discussion conclusion | 15:15 |
| Sundar | We can support multiple devices with some restrictions, which may satisfy immediate needs and still give freedom to operaors | 15:15 |
| zhipeng | I would especially thanks Sundar for his initiative on the mailing list | 15:15 |
| *** dolpher has quit IRC | 15:16 | |
| shaohe_feng_ | Sundar: any code plan for the spec? | 15:16 |
| zhipeng | and also the spec discussion with Nova team | 15:16 |
| Li_Liu | Or can we put a simple version of multiple device support in Cyborg for now? | 15:16 |
| Sundar | shaohe, yes. | 15:16 |
| zhipeng | shaohe-feng_ your PoC code could be used right ? | 15:16 |
| Sundar | Thanks, Howard | 15:16 |
| shaohe_feng_ | zhipeng: yes. I think so. | 15:16 |
| Sundar | The POC code does not publish RCs and traits | 15:16 |
| Sundar | But we can build on that | 15:17 |
| zhipeng | yes that's what i meant | 15:17 |
| shaohe_feng_ | Sundar: it publish | 15:17 |
| Sundar | Also, the notion of using PFs and VFs as resources is something the Nova/PTG folks didn;t want ;) | 15:17 |
| Sundar | Shaohe: sorry, to clarify, it publishes PCI functions as RCs right? | 15:18 |
| zhipeng | let's take the details offline :) | 15:18 |
| Sundar | ok :) | 15:18 |
| shaohe_feng_ | Sundar: the poc is similar to nova teams conclusion. | 15:18 |
| zhipeng | next up, Li Liu's metadata spec | 15:18 |
| zhipeng | #info metadata standardization spec | 15:18 |
| zhipeng | #link https://review.openstack.org/558265 | 15:18 |
| shaohe_feng_ | and we know nrp is not ready, so simply it. | 15:19 |
| zhipeng | folks plz review it | 15:19 |
| zhipeng | anything you want to add, Li_Liu ? | 15:19 |
| chucksong | zhipeng, sorry for interrupt, what's the expected freeze date for the Xilinx driver spec? april 19 or Jun.4? | 15:19 |
| zhipeng | chucksong Jun 4 | 15:19 |
| Li_Liu | zhipeng, I made some modifications based on shaohe's comments couple days ago. Waiting for more suggestions | 15:19 |
| zhipeng | Li_Liu okey :) | 15:20 |
| chucksong | good, thanks! | 15:20 |
| zhipeng | okey moving on | 15:20 |
| Li_Liu | My next spec for programmability is on the way. within the week I think | 15:20 |
| zhipeng | Li_Liu you are the rock star man | 15:20 |
| Sundar | Li_Liu: I had some high level comments on the spec. We can discuss them in more detail when you want | 15:20 |
| zhipeng | I will cry myself to sleep tonight :P | 15:20 |
| zhipeng | #info cyborg-spec setup | 15:21 |
| Li_Liu | sure sundar, wehcat/skype/phone/email whatever you want man | 15:21 |
| zhipeng | #link https://review.openstack.org/554766 | 15:21 |
| zhipeng | Yumeng__ has been great to setup the cyborg-spec repo | 15:21 |
| zhipeng | I think the current patch look good, so if plz any core give a +2, I will land it this week | 15:22 |
| zhipeng | okey folks we still have planned specs missing for rocky | 15:23 |
| zhipeng | #info quota and os-acc spec still missing | 15:23 |
| zhipeng | I will talk to indicidual owners to see how to push forward | 15:23 |
| zhipeng | deadline is less than three weeks away :) | 15:23 |
| zhipeng | #action Howard to track the missing quota and os-acc spec | 15:24 |
| zhipeng | #topic open patches that need attention | 15:24 |
| *** openstack changes topic to "open patches that need attention (Meeting topic: openstack-cyborg)" | 15:24 | |
| zhipeng | #info shaohe_feng's devstack fix | 15:24 |
| zhipeng | #link https://review.openstack.org/557742 | 15:25 |
| Yumeng | sorry to interrup. Here is the more detailed clock-driver use case description link I sent in the mail list: https://etherpad.openstack.org/p/clock-driver | 15:25 |
| zhipeng | great work from shaohe, I will have zhuli help merge this by the end of the week | 15:25 |
| shaohe_feng_ | zhipeng: this should be land first. :) | 15:25 |
| zhipeng | Yumeng thx ! | 15:25 |
| Yumeng | Driver proposal would be provided next. | 15:25 |
| zhipeng | Yumeng I think you could directly put it up as a driver spec :P | 15:25 |
| shaohe_feng_ | shaohe_feng_: It can help to avoid other debugs coming. | 15:26 |
| Yumeng | zhipeng: okey.that would be great. | 15:26 |
| openstackgerrit | Li Liu proposed openstack/cyborg master: Implemented the Objects and APIs for vf/pf https://review.openstack.org/552734 | 15:26 |
| zhipeng | shaohe_feng_ I will nag zhuli :P | 15:26 |
| zhipeng | next, which Li_Liu just updated | 15:26 |
| zhipeng | #info object and apis for vf/pf | 15:27 |
| Li_Liu | lol.. I just addressed some comments from Shaohe yesterday | 15:27 |
| zhipeng | #link https://review.openstack.org/552734 | 15:27 |
| zhipeng | :) | 15:27 |
| zhipeng | Okey I think that is all the important stuff we need to discuss today | 15:28 |
| Li_Liu | Sundar, I hear you said Nova folks does not like vf/pf representations | 15:28 |
| *** Duth has quit IRC | 15:28 | |
| shaohe_feng_ | good | 15:29 |
| shaohe_feng_ | Li_Liu: it is internal implementation, Why do not like? | 15:29 |
| Li_Liu | but I think vf/pfs are more friendly to vendor drivers. And it can be used interchangeably with Deployables | 15:29 |
| shaohe_feng_ | Li_Liu: yes. | 15:29 |
| Sundar | Li_Liu: yes, this is PTG feedback: e.g. https://etherpad.openstack.org/p/cyborg-ptg-rocky-nova-cyborg-interaction Line 21 | 15:30 |
| shaohe_feng_ | Li_Liu: but your vf/pf representations is not expose | 15:30 |
| Li_Liu | shaohe_feng_, I know, just wanna point it out, in case nova folks have questions on them. :) | 15:30 |
| Sundar | Our implementation still uses PFs/VFs of course | 15:30 |
| Sundar | We can correlate regions/functions with PFs/VFs | 15:31 |
| Li_Liu | great | 15:31 |
| zhipeng | #topic Vancouver Forum | 15:31 |
| *** openstack changes topic to "Vancouver Forum (Meeting topic: openstack-cyborg)" | 15:31 | |
| zhipeng | almost forget this | 15:31 |
| zhipeng | plz feel free to propose forum topics for Vancouver Summit | 15:32 |
| zhipeng | I might not be able to attend that Summit due to several reasons | 15:32 |
| Melissa_S | what is the vancouver summit? | 15:32 |
| zhipeng | Li Liu will be my double there :P | 15:32 |
| zhipeng | OpenStack Vancouver Summit | 15:32 |
| Melissa_S | Chuck went to bed and I am here to keep track of actions :) | 15:33 |
| *** chucksong has quit IRC | 15:33 | |
| Melissa_S | he is in China right now | 15:33 |
| zhipeng | wow | 15:34 |
| zhipeng | would love to chat if he travel to shenzhen | 15:34 |
| zhipeng | or beijing next week | 15:35 |
| Melissa_S | oh ok - I will let him know | 15:35 |
| Melissa_S | what email do I use for you? | 15:36 |
| zhipeng | zhipengh512@gmail.com | 15:36 |
| zhipeng | my cell is +86-18576658966 | 15:37 |
| Melissa_S | okay - I sent you his cell phone number and our info via email | 15:40 |
| shaohe_feng_ | zhipeng: if https://review.openstack.org/#/c/555722/ not merged, I can not create the client repo? | 15:40 |
| Sundar | Zhipeng, shall we propose a talk on Cyborg architecture? | 15:41 |
| zhipeng | yes shaohe_feng_ | 15:42 |
| shaohe_feng_ | zhipeng: it is ready. wait for merge. | 15:42 |
| zhipeng | Sundar definitely a good idea :) | 15:42 |
| shaohe_feng_ | I have tried to push the repo, but failed | 15:43 |
| Sundar | Cool ;) | 15:43 |
| *** goldenfri has joined #openstack-cyborg | 15:45 | |
| zhipeng | okey if there is no other topics | 15:48 |
| zhipeng | let's conclude the meeting today :) | 15:48 |
| Melissa_S | sounds good - any additional actions for us? | 15:48 |
| zhipeng | nuh just keep in touch would be great :) | 15:50 |
| zhipeng | oh one more thing, kosamara will you have the bandiwidth to work on the GPU spec ? | 15:54 |
| zhipeng | let me just close the meeting first in case I sleep over it again :P | 15:57 |
| zhipeng | #endmeeting | 15:57 |
| *** openstack changes topic to "OpenStack Cyborg Project Discussion" | 15:57 | |
| openstack | Meeting ended Wed Apr 4 15:57:33 2018 UTC. Information about MeetBot at http://wiki.debian.org/MeetBot . (v 0.1.4) | 15:57 |
| openstack | Minutes: http://eavesdrop.openstack.org/meetings/openstack_cyborg/2018/openstack_cyborg.2018-04-04-14.03.html | 15:57 |
| openstack | Minutes (text): http://eavesdrop.openstack.org/meetings/openstack_cyborg/2018/openstack_cyborg.2018-04-04-14.03.txt | 15:57 |
| openstack | Log: http://eavesdrop.openstack.org/meetings/openstack_cyborg/2018/openstack_cyborg.2018-04-04-14.03.log.html | 15:57 |
| *** zhipeng has quit IRC | 15:59 | |
| *** Li_Liu has quit IRC | 16:01 | |
| *** circ-user-ldzTg has quit IRC | 16:19 | |
| *** Sundar has quit IRC | 16:43 | |
| *** Helloway has quit IRC | 16:55 | |
| *** Kevin_Zheng has quit IRC | 17:07 | |
| *** Yumeng__ has quit IRC | 17:57 | |
| *** shaohe_feng_ has quit IRC | 18:38 | |
| *** Melissa_S has quit IRC | 19:21 | |
| *** edleafe- has joined #openstack-cyborg | 23:31 | |
| *** edleafe has quit IRC | 23:33 | |
| *** edleafe- is now known as edleafe | 23:33 | |
Generated by irclog2html.py 2.15.3 by Marius Gedminas - find it at mg.pov.lt!