| Posted | Nick | Remark | |
|---|---|---|---|
| #openstack-cyborg - 2018-08-30 | |||
| 21:25:59 | Sundar | Most of it is Nova virt or Cyborg. I am still pondering what os-acc can do that is not device-specific (and so in Cyborg) or hypervisor-specific (and so in Nova virt) | |
| 21:26:59 | efried | Sundar: as a touchpoint/router and future extension point for those pieces of the requests, it may be useful. | |
| 21:27:05 | efried | but I'm really not sure. | |
| 21:27:30 | Sundar | Yes, I agree. That's what I was thinking | |
| 21:28:21 | efried | not sure it makes much sense for the calls from os-acc to cyborg API/conductor to be asynchronous if it's just going to poll for them to complete right away... | |
| 21:29:37 | Sundar | The calls may take milliseconds to possibly seconds, depending on whether Glance bitstreams need to fetched, one or more FPGAs need to be programmed, etc | |
| 21:30:20 | efried | so? | |
| 21:30:27 | Sundar | That is why it is async | |
| 21:30:31 | efried | The caller is blocking on their completion anyway | |
| 21:30:39 | efried | So why does it matter if they take "a long time"? | |
| 21:30:48 | Sundar | Ah, the n-cpu could do other things while this is blocked, right? | |
| 21:30:53 | efried | could it? | |
| 21:31:06 | efried | I guess. | |
| 21:31:18 | Sundar | The allocation of other resources -- networking, storage -- could go in parallel | |
| 21:31:21 | efried | Just sounds like it would make things pretty complicated. | |
| 21:31:36 | efried | If n-cpu wanted to parallelize, it could send that request off in its own thread. | |
| 21:31:46 | efried | But having it be async *forces* n-cpu to deal with that async-ness. | |
| 21:31:49 | efried | Anyway, this is really a nit. | |
| 21:31:59 | efried | not a substantive thing. | |
| 21:32:03 | Sundar | The n-cpu to os-acc could be async too. | |
| 21:32:15 | Sundar | So, os-acc deals with the async weirdness. | |
| 21:32:59 | Sundar | Hmm, well, os-acc to Cyborg can be sync if os-acc itself is called in an async way | |
| 21:33:13 | Sundar | Just wondering if a REST API call cna really block for seconds | |
| 21:33:48 | efried | absolutely. | |
| 21:34:10 | efried | I'm sure there's a connection timeout at the HTTP level. But seconds shouldn't be a problem. | |
| 21:34:16 | Sundar | Are there precedents in OpenStack where a REST API blocks for seconds? | |
| 21:35:57 | efried | I have no idea. | |
| 21:36:10 | efried | That might be something edleafe and/or cdent would know. | |
| 21:37:22 | Sundar | OK. Another note: The proposal calls for persisting VAN objects in Cyborg db, but Nova db maintains the association between the instance and its VAN UUIDs . That s because, on a VM suspend for example, Nova would need to call os-acc to detach VANs but not deallocate them | |
| 21:37:55 | Sundar | Never mind, the detach would be in Nova virt. | |
| 21:38:03 | Sundar | But you get the point | |
| 21:38:29 | Sundar | On a termination, Nova virt would detach each VAN and then call os-acc to release the resources | |
| 21:38:47 | efried | right, some kind of handle (i.e. the VAN UUID) would need to be associated with the instance in the nova db. | |
| 21:38:54 | Sundar | Yes | |
| 21:39:14 | efried | As long as we can query cyborg with the UUID to get the rest of the VAN info, the UUID should be the only thing we need to store, I would think. | |
| 21:39:21 | Sundar | Yes | |
| 21:42:33 | Sundar | Good. Since we are in agreement, I'll write this up in the spec. | |
| 21:43:55 | efried | Sundar: Note that I'm only one person, and my stake in the details we've just discussed is not an especially strong one. | |
| 21:45:20 | Sundar | We need some path to get this converged. I am incorporating sean-mooney's comments and responding to them. But, if somebody else were to come along in a month, we can't keep waiting. | |
| 21:45:40 | Sundar | I hope to get this closed during the PTG or at most a week after | |
| 21:46:25 | Sundar | I requested melwitt for a PTG session. Could I ask for your help in ensuring that all Nova feedback is given by that time? | |
| 22:13:03 | efried | hah | |
| 22:13:14 | efried | You're asking me to move mountains. | |
| 22:14:25 | efried | There's no way to force all the stakeholders to review a thing. And there's no way to prevent taking weeks or months to revise something with the collaboration of many people only to have someone who should have been involved from the start come along and throw a huge monkey wrench in the works. | |
| 22:16:04 | efried | I think your best bet is to be ready to present an overview of the architecture at the PTG, counting on at least some key players in the audience to have *not* reviewed the specs, and talk out some of the issues there. | |
| 22:16:08 | efried | Sundar: ^ | |
| #openstack-cyborg - 2018-09-02 | |||
| 03:02:52 | openstackgerrit | Sundar Nadathur proposed openstack/cyborg master: Cyborg/Nova/Glance interaction in compute node, including os-acc. https://review.openstack.org/577438 | |
| #openstack-cyborg - 2018-09-04 | |||
| 03:21:14 | openstackgerrit | zhulingjie proposed openstack/cyborg-specs master: fix bug link in readme https://review.openstack.org/599484 | |
| 03:21:15 | openstackgerrit | zhulingjie proposed openstack/python-cyborgclient master: fix bug link in readme https://review.openstack.org/599486 | |
| 03:21:17 | openstackgerrit | zhulingjie proposed openstack/cyborg master: fix bug link in readme https://review.openstack.org/599489 | |
| 06:01:17 | openstackgerrit | wangzhh proposed openstack/cyborg master: Add gpu driver https://review.openstack.org/574075 | |
| #openstack-cyborg - 2018-09-05 | |||
| 00:09:05 | openstackgerrit | Sundar Nadathur proposed openstack/cyborg master: Cyborg/Nova/Glance interaction in compute node, including os-acc. https://review.openstack.org/577438 | |
| 01:32:44 | openstackgerrit | Sundar Nadathur proposed openstack/cyborg master: Cyborg/Nova/Glance interaction in compute node, including os-acc. https://review.openstack.org/577438 | |
| 08:00:03 | openstackgerrit | Xinran WANG proposed openstack/cyborg master: Improve Intel FPGA driver https://review.openstack.org/599956 | |
| 08:06:48 | openstackgerrit | Xinran WANG proposed openstack/cyborg master: Improve Intel FPGA driver https://review.openstack.org/599960 | |
| 14:03:13 | zhipeng | #startmeeting openstack-cyborg | |
| 14:03:14 | openstack | Meeting started Wed Sep 5 14:03:13 2018 UTC and is due to finish in 60 minutes. The chair is zhipeng. Information about MeetBot at http://wiki.debian.org/MeetBot. | |
| 14:03:15 | openstack | Useful Commands: #action #agreed #help #info #idea #link #topic #startvote. | |
| 14:03:18 | openstack | The meeting name has been set to 'openstack_cyborg' | |
| 14:03:25 | Li_Liu | #info Li_Liu | |
| 14:03:44 | wangzhh | #info wangzhh | |
| 14:03:46 | zhipeng | #info Howard | |
| 14:04:38 | wangzhh | Hi Howard, do u get the visa? | |
| 14:04:41 | wangzhh | :) | |
| 14:04:51 | dolpher | #info dolpher | |
| 14:05:22 | zhipeng | wangzhh yes got it lol | |
| 14:05:47 | zhipeng | #topic Stein PTG agenda crafting | |
| 14:05:55 | zhipeng | #link https://etherpad.openstack.org/p/cyborg-ptg-stein | |
| 14:06:07 | Sundar | #info Sundar | |
| 14:06:13 | wangzhh | Congratulations. | |
| 14:06:48 | zhipeng | as Li Liu mentioned, it seems that Nova team already planned a cross-project meeting with cyborg | |
| 14:06:53 | zhipeng | on Thursday right ? | |
| 14:07:13 | Li_Liu | yes | |
| 14:07:23 | Coco_gao | #info Coco_gao | |
| 14:07:39 | Li_Liu | Thursday "Cross Project Day" 11:10am - lunch: Cyborg/Nova cross project session | |
| 14:07:42 | Sundar | zhipeng: The main cross-project Nova/Cyborg needs to be on Cyborg time. Nova team will have a spill over time in case the discusions don;t complete | |
| 14:08:07 | Li_Liu | Is it in Cyborg's room or Nova's room? | |
| 14:08:19 | Sundar | We need to arrange for a session on Mon/Tue and let Nova team know ahead of time | |
| 14:08:52 | Sundar | Cyborg's room on Mon/Tue. The Thu slot is in Nova's room but that is a second follow-up | |
| 14:09:11 | Sundar | We do not expect all discussions to complete in 1 hour session | |
| 14:09:37 | zhipeng | okey then what I would propose is that | |
| 14:09:42 | zhipeng | we concentrate on Monday | |
| 14:09:52 | zhipeng | and use Tuesday for spillovers | |
| 14:10:20 | Coco_gao | Agree | |
| 14:10:43 | zhipeng | I need to jump over the public cloud wg session as well, on Tuesday | |
| 14:10:53 | Sundar | zhipeng: Sure. We could arrange for the Nova session on mon afternoon? Hopefully that's enough time for folks to come in to the PTG venue | |
| 14:11:09 | zhipeng | That's good enough for me :) | |
| 14:11:18 | Sundar | Cool :) | |
| 14:11:32 | Li_Liu | So the main discussion will be happening on Mon and Tues? | |
| 14:11:39 | Sundar | Good to know you will be there :) | |
| 14:11:46 | zhipeng | The main one will be on Monday | |
| 14:11:50 | Li_Liu | ok | |
| 14:11:52 | Coco_gao | Do we have an outline about the meeting with nova? | |
| 14:12:04 | Li_Liu | I will take Monday off at least | |
| 14:12:26 | zhipeng | So some update, Li Liu will not make it to Denver unfortunately due to work conflict at company | |
| 14:12:27 | Sundar | I broadly wrote it as os-acc. The workflow itself is still a matter of contention. | |
| 14:12:32 | zhipeng | and I got a late hail marry | |
| 14:12:37 | zhipeng | so I will stand in for Li | |
| 14:12:43 | zhipeng | to organize the meetings | |
| 14:12:48 | zhipeng | and dinners :) | |