03:01:19 #startmeeting openstack-cyborg 03:01:20 Meeting started Thu Oct 17 03:01:19 2019 UTC and is due to finish in 60 minutes. The chair is Sundar. Information about MeetBot at http://wiki.debian.org/MeetBot. 03:01:21 Useful Commands: #action #agreed #help #info #idea #link #topic #startvote. 03:01:23 The meeting name has been set to 'openstack_cyborg' 03:01:28 #topic Who's here 03:01:36 #info chenke 03:01:42 #info s_shogo 03:01:58 Hi chenke, s_shogo, Yumeng 03:02:14 Hi all. 03:02:26 May be we can wait a couple of minutes for others to join 03:02:31 Hi Sundar, hi all 03:02:35 Hi all 03:02:52 Ok. 03:03:12 Today's agenda: https://wiki.openstack.org/wiki/Meetings/CyborgTeamMeeting#Agenda 03:03:54 PTG etherpad: https://etherpad.openstack.org/p/cyborg-ptg-ussuri 03:04:51 emmm... what's the meaning of "Poject updates: Not at Summit, but in etherpad" ? 03:05:50 Is it canceled ? 03:06:56 Xinran WANG proposed openstack/cyborg master: bug fix: ensure resource class instead of getting it. https://review.opendev.org/688231 03:07:25 #topic PTG, Summit 03:07:35 Yumeng: here's the email I got: 03:07:43 " Due to various constraints, we are unable to record Project Updates this Summit. ... 03:07:59 We suggest that as an alternative, you record your main updates in an etherpad and use that as a resource to share afterwards. ... 03:08:09 Hi, all. Sorry for being late. 03:08:16 After the event, we’ll send out an email requesting slides and an etherpad link for each project. ... 03:08:36 hi all 03:08:39 sorry for late 03:08:43 Those materials will be placed on the Summit Schedule and we will notify the community once they are live. If you would like to record a version of your presentation and send us a link, we can also add that to the Schedule. " 03:08:46 hi xinran ,shaohe. 03:08:52 That's the message 03:09:23 Alright Thanks! make sense. 03:09:58 Please add your suggested topics to the PTG etherpad, linked above 03:10:24 Also, it would be good to have dinner as a team, as we have done before. 03:10:44 Does Thursday night (Nov 7) work for all of you? 03:11:46 It's ok for me. 03:11:54 +1 03:11:58 +1 03:12:57 Cool. Let's go with that. If you want to bring anybody else, please go ahead. 03:13:47 Cool. 03:13:52 I will let you all choose the restaurant! Please make sure it has vegetarian food. :) 03:15:50 #topic Doc patches 03:16:16 https://review.opendev.org/#/q/status:open+project:openstack/cyborg+branch:stable/train 03:16:29 Thanks to Xinran for backporting the doc patches to stable/train 03:16:50 These were in cyborg master but the release team cut the stable branch after RC1 03:17:59 Release team has said we can backport doc patches any time, and they will take effect wothout version number changes 03:18:03 *without 03:18:27 So, Yumeng and all, please review it. 03:18:49 can we get bug fix patch in now, as the doc patch ;) 03:19:09 ok, will do. 03:19:24 Done. 03:19:48 Nope :( There was lots of resistance to backporting other patches. We can potentially do a point-release early in U if we really want, IMO, all that is beside the point till we get nova integ. 03:20:18 Once we get nova integ done, we have the option of doing an early point release instead of waiting for April/May 03:20:52 Basically, non-doc patches require version change. 03:21:09 ok, got it. 03:21:43 now the doc patch review has high priority. 03:22:01 Yes. 03:22:15 when is the ddl for doc patches? 03:23:02 No deadline. Train is more or less done. So, we can backport any time 03:24:36 BTW, Cyborg got some free press in OpenStack press releases: https://www.zdnet.com/article/the-openstack-train-keeps-chugging-on/, https://www.theregister.co.uk/2019/10/15/openstack_train/ 03:24:44 Kudos to all of you :) 03:25:30 In other news, Nova-Cyborg interaction spec (https://review.opendev.org/#/c/684151/) got +2 from Nova PTL. Need to follow up more. 03:26:11 good news! 03:26:17 Great 03:26:29 will follow up. 03:27:52 The press articles sound a bit weak because they mentioned only the Nova spec merge. We haven't really claimed that Cyborg supports VM creation etc. in this release. The next release is going to dleiver the goods, and we should be able to make stringer statements. 03:28:03 *stronger 03:28:20 Ye. 03:28:44 #topic AoB 03:28:50 Cyborg is a popular project for openstack. 03:29:00 Yes 03:29:03 Anything else for today? 03:29:25 I want to confirm that the version has been sent out. Does it make sense to change the documentation? 03:30:02 Are you asking if it is ok to change the docs after Train has shipped? 03:30:04 If users take the version, they won't get the latest documents 03:30:33 Hmm, if they clone stable/train in the future, after we merge the doc patches, they will get them all. 03:30:33 Has the train been sent out? 03:31:09 Yes. If they clone the stable/train , they will get them. 03:31:15 More or less: https://review.opendev.org/#/c/687991/ has bene merged 03:31:53 I think they have some backend work. It should be done by this week, I think 03:32:31 Will this release add more ACC support? 03:32:49 Do you mean if we get more drivers in U? 03:32:49 another questions. 03:32:54 yes. 03:33:02 more drivers? 03:33:10 any plane for it? 03:34:16 Do we support apply FPGA pf to a VM? 03:34:36 We could. We need to talk about it. Right now, we got some drivers for GPU and Ascend. However, the maintainers are not regularly participating in Cyborg activities. That makes me concerned about maintenance. Also, we don;t have 3rd party CI for any driver yet. We are planning that for FPGAs, but what about other drivers? 03:35:01 I was replying about drivers, not PF 03:35:27 so the questions is that. 03:35:43 If a end user apply a FPGA 03:35:43 As a team, we may have to decide on a higher bar for drivers. That is something we can discuss here on at the PTG. 03:35:45 *or 03:35:56 I will not attend PTG. 03:36:29 Ah yes, too bad. You can give your ideas here or in the PTG etherpad. 03:36:30 if he found there's bug on his bitstream? 03:36:50 what should he do? 03:37:06 delete the VM, rebuild a new VM with a FPGA? 03:37:14 Passing a FPGA PF to a VM is potential security hole, because we don;t know what bitstreams get programmed 03:37:14 Wow, it's so good > CI for FPGA driver's. 03:37:22 or just re-program it? 03:38:21 We have a usage model called Runtime Programming, which we don't support today. It involves VM issuing requests for new bitstreams, Cyborg or something receives that request and does the reprogramming. We don;t see many customers asking for that 03:38:42 maybe, the end user after doing his AI, then he want to change the AI model, which means he maybe need a new bitstream for his AI net model. 03:38:48 what should he do? 03:39:16 I think we can provider a program interface for this kind of users. 03:39:25 in vf use case. 03:39:44 He could get the VM to issue a request somehow to underlying infra. That is not there today. Today, he only needs to stop that VM and start a new one 03:40:13 xinranwang: User cannot reprogram a FPGA via VF. 03:40:59 yes, but he take a great effort to setup his AI env, such as install the openvino and the dependency, set connection with the camera maybe. 03:41:07 if boot with bit-stream failed, vm should become failed. if user boot a vm successfully, and want reprogram the FPGA, what will we do. 03:41:27 so should should delete vm, rebuild one, and take effort to setup the env again? 03:42:58 Seams now, the user just can use FPGA as fix function PCI devices once he create the VM 03:43:29 If there is a strong customer demand for that, have that customer(s) call Intel. This use case will require changes in the product level, software stack and in Cyborg. It will also require discussion among ourselves in Cyborg community. 03:44:21 I did not seen the flexible advantage of FPGA. 03:44:44 hat is a problem. 03:44:52 * That 03:45:09 There are different usage models of FPGA. Many customers are adopting it with the current software stack. 03:45:21 Perhaps we can take this offline, rather than hold everybody up. 03:45:22 the question is that, cyborg is not adopt in a product at present. So we miss so many customer demand for end user. 03:45:23 IMHO, Cyborg should support reprogram right? 03:45:53 xinranwang: It should and it does today (at least will after Nova integ). 03:46:59 Sundar: Yes, so I think it is doable for user who want update their bitstream. 03:47:28 so I should tell the user who wants to try cyborg, that we will not support reprogram, right? 03:48:29 In my case,the current PAC seems to have some constraints (ex necessary for disabling SR-IOV when programming) and that is problem for reprogram in our usecase. 03:48:32 shaohe_feng: Why do you say that? We can reprogram when a VM is being launched. We cannot reprogram after a VM is launched. Most users today need only the former, from what we have seen. 03:48:36 I would like to discuss these constraints are temporary or not, and cyborg( and user ) should think them as premise or not,in PTG and so on. 03:49:25 s_shogo: Sure, I;ll add usage models as a topic at the PTG, and come with some slides explaining our thoughts/plans. 03:49:48 Great, thanks > Sundar 03:49:55 Sundar, just think you want to do a AI with FPGA. you want to try you different model to find the best solution, what you should do? 03:50:30 You can can add the reprogram in the etherpad list. 03:50:58 and involve more end users to discuss it during PTG. 03:51:05 General question to all: s_shogo, chenke, Yumeng, shaohe_feng, xinranwang: Are you interested in FPGAs with networking? Adding that will require further discussion. We started that at the beginning of Train, but didn't follow u. 03:51:26 s/u./up./ 03:52:03 It will require Cyborg-Neutron interaction. I have some ideas for that, but they haven't been discussed deeply with neutron community yet. 03:52:30 s_shogo: Could you list the constraints you met in etherpad? 03:53:10 I have great interest in networking with FPGA, as a telco-carrier. ut there is not clear demand for interaction with neutron. 03:53:23 s/ut/but/ 03:54:19 I have looked into OVS card base FPGA before. 03:54:21 xinranwang: ok, I'll list the constraints in etherpad, it may include misunderstanding, pointing out is welcome and happy for me :) 03:54:28 it can works with DPDK. 03:54:28 s_shogo: The question is, does the networking solution require basic resources like MAC/IP addresses, and more advanced things like security groups and VXLAN config? These things are best left to neutron, rather than Cyborg replicating them. 03:55:39 s_shogo: thanks, I am willing to see it. We can check if we also met them :P 03:56:47 OK, anything else for today? 03:57:45 Sundar: Yes, I have intrests in smart NICs network adapter base FPGA, things like that. 03:57:53 nothing else. thanks! 03:58:07 Great. Glad to hear the widespread interest. 03:58:27 The current application in networking in FPGA is limited, so these parameters could be applied via application or operation. 03:59:19 s_shogo and Yumeng: For my interest, are you more interested in OVS offload or in offloading apps like vRAN or vEPC? 04:00:31 Sundar: Yes, I have interested in them. These performance is critical for telco-carrier. 04:01:20 SO, you are interested in both types? 04:01:55 OCS offload is quite different architecturally from application offload 04:01:58 *OVS 04:02:13 The former is from the host, latter from VM. 04:02:22 Cyborg has to do different things for both 04:02:43 We have a OVS offload card. 04:04:20 can do some scenarios on it. 04:04:50 Anyway, we are past the time. We can cover this in next meeting. 04:04:56 Thanks, everybody! Have a good day. :) 04:05:02 bye 04:05:07 #topic endmeeting 04:05:10 bye. 04:05:16 bye 04:05:19 bye 04:05:46 bye 04:55:30 The last message was failed to send... 04:58:17 I think there are several patterns in connecting OVS-accelerator (direct virtio, SR-IOV+DPDK, using tc flower,etc), and that effects cyborg and driver's operation. 04:58:46 Anyway , I would like to discuss them in next chance:) 09:07:03 chenker proposed openstack/cyborg master: Fix attach_handle status error when creating vm successfully https://review.opendev.org/689617 01:17:21 chenker proposed openstack/cyborg master: Fix attach_handle status error when creating vm successfully https://review.opendev.org/689617 14:22:20 chenker proposed openstack/cyborg master: Fix attach_handle status error when creating vm successfully https://review.opendev.org/689617 14:38:07 chenker proposed openstack/cyborg master: Fix attach_handle status error when creating vm successfully https://review.opendev.org/689617 04:11:02 kangyufei proposed openstack/cyborg master: Switch to Ussuri jobs https://review.opendev.org/689924 05:49:36 kangyufei proposed openstack/python-cyborgclient master: Switch to Ussuri jobs https://review.opendev.org/689940 08:29:54 Merged openstack/cyborg master: Fix attach_handle status error when creating vm successfully https://review.opendev.org/689617 08:24:36 chenker proposed openstack/cyborg master: Remove useless glance api_servers define https://review.opendev.org/685542 08:24:36 chenker proposed openstack/cyborg master: Simplify devstack script for generating cyborg.conf https://review.opendev.org/690509 08:26:50 chenker proposed openstack/cyborg master: Simplify devstack script for generating cyborg.conf https://review.opendev.org/690509 08:50:12 chenker proposed openstack/cyborg master: Update docstring for apply_patch https://review.opendev.org/690517 10:29:15 YumengBao proposed openstack/cyborg master: Update api-ref: deprecate v1 add v2 device_profile section https://review.opendev.org/690539 02:53:34 YumengBao proposed openstack/cyborg master: Update api-ref: deprecate v1 add v2 device_profile section https://review.opendev.org/690539 03:01:55 Sundar: Error: Can't start another meeting, one is in progress. Use #endmeeting first. 03:02:02 #endmeeting