| Posted | Nick | Remark | |
|---|---|---|---|
| #openstack-cyborg - 2018-09-27 | |||
| 19:34:03 | efried | That's what gibi proposed his spec for. | |
| 19:34:14 | Sundar | Yea, I got that | |
| 19:34:30 | efried | Because in placement, *while* we're calculating allocation candidates (but not after), we know which request group corresponds to which bit of each allocation request. | |
| 19:34:57 | efried | We just don't carry that information forward to the response, or preserve it internally in any way. | |
| 19:34:58 | Sundar | A related issue is that, if VRAM were not a standard resource, you may say accel:VRAM=2048 or something | |
| 19:35:33 | efried | um, rather not. If it's not a standard resource, it can be CUSTOM_VRAM, but it should still be tracked in placement. | |
| 19:35:51 | Sundar | Now, the accel extra spec has to go with the rest of the request group, for the device to be suitably configured during bind | |
| 19:36:01 | efried | If not, you're setting yourself up for resource contention problems that placement was expressly design to obviate. | |
| 19:37:26 | Sundar | OK, that was not a good example. What if I wnat to assign the GPU to host software like DPDK for cryptography, rather than to a VM? Then the dev prof may say accel:assign-to-host=true | |
| 19:38:43 | Sundar | This is not a trait | |
| 19:38:52 | Sundar | because it is not meant for scheduling, | |
| 19:39:02 | Sundar | only to control how the assignment is done | |
| 19:39:20 | efried | I don't understand that use case. But yeah, traits are another useful way to expose the problem. | |
| 19:40:52 | efried | If I ask for resource1=VGPU:1&required1=CUSTOM_FOO&resource2=VGPU:1, and I get back two allocations from different providers, I need to go figure out (based on traits? or what I already know about the providers?) which VGPU I'm supposed to apply to CUSTOM_FOO. | |
| 19:41:30 | efried | again, it's not sooper hard, but once you generalize it out, you end up essentially having to duplicate a ton of the placement logic. | |
| 19:42:03 | Sundar | Yes | |
| 19:43:48 | Sundar | OK, it still comes down to how gibi solved this problem, I suppose. I'll dig around. | |
| 19:44:04 | efried | *this* problem I don't think gibi solved. | |
| 19:44:08 | efried | He solved the renumbering problem. | |
| 19:44:50 | efried | I believe his PoC behaved quite similarly to what you're proposing - the resources/required gizmos live in the profile (the binding profile? or port? in his case) | |
| 19:45:18 | efried | and then he has to renumber those groups when he folds the profile in with the other flavor stuff. | |
| 19:45:38 | efried | They wrote up a blog post that walked through the PoC, and I think some of that becomes clear in the demo | |
| 19:46:11 | efried | https://rubasov.github.io/2018/09/21/openstack-qos-min-bw-demo.html | |
| 19:47:09 | efried | yeah, search for resource_request in the above doc and you'll see what I'm talking about. | |
| 19:48:02 | efried | each port profile looks like it gets to ask for resources for a single port. (I guess the actual VIF/VNIC resource is implicit? Not sure how that's working.) | |
| 19:48:14 | efried | So the resources/required keys are unnumbered in the port profile. | |
| 19:49:05 | efried | And then (not sure if this is in the doc, but I know it's true because it was in the original spec and I confirmed by asking the question in the room when they did the demo) those get numbered in a non-conflicting way when they get folded into the rest of the request. | |
| 19:55:33 | efried | Sundar: switching screens; ping me if you want to talk more. | |
| #openstack-cyborg - 2018-09-28 | |||
| 07:09:54 | openstackgerrit | YumengBao proposed openstack/os-acc master: Update os-acc doc https://review.openstack.org/604960 | |
| 11:20:32 | openstackgerrit | Xinran WANG proposed openstack/os-acc master: Add a parser to help nova parse the input device spec to cyborg. https://review.openstack.org/606036 | |
| #openstack-cyborg - 2018-09-29 | |||
| 16:17:04 | openstackgerrit | zhulingjie proposed openstack/cyborg-specs master: Update the Placement API link https://review.openstack.org/606603 | |
| #openstack-cyborg - 2018-09-30 | |||
| 02:05:10 | openstackgerrit | YumengBao proposed openstack/os-acc master: Update os-acc doc https://review.openstack.org/604960 | |
| #openstack-cyborg - 2018-10-04 | |||
| 04:55:35 | openstackgerrit | Sundar Nadathur proposed openstack/cyborg-specs master: Specification for device profiles. https://review.openstack.org/602978 | |
| 22:13:15 | openstackgerrit | Sundar Nadathur proposed openstack/cyborg-specs master: Update index with Stein specs. https://review.openstack.org/608095 | |
| #openstack-cyborg - 2018-10-05 | |||
| 00:03:56 | openstackgerrit | Sundar Nadathur proposed openstack/cyborg-specs master: Specification for device profiles. https://review.openstack.org/602978 | |
| 00:07:25 | openstackgerrit | Sundar Nadathur proposed openstack/cyborg-specs master: Specification for Cyborg Nova Placement interaction. https://review.openstack.org/603545 | |
| 02:00:42 | openstackgerrit | Merged openstack/cyborg-specs master: Update index with Stein specs. https://review.openstack.org/608095 | |
| 10:26:09 | openstackgerrit | Sundar Nadathur proposed openstack/cyborg-specs master: Specification for instance operations with accelerators. https://review.openstack.org/605237 | |
| 10:39:49 | openstackgerrit | Sundar Nadathur proposed openstack/cyborg-specs master: Specification for device profiles. https://review.openstack.org/602978 | |
| 10:41:57 | openstackgerrit | Sundar Nadathur proposed openstack/cyborg-specs master: Specification for Cyborg Nova Placement interaction. https://review.openstack.org/603545 | |
| #openstack-cyborg - 2018-10-08 | |||
| 09:54:22 | openstackgerrit | Sundar Nadathur proposed openstack/cyborg-specs master: Specification for Cyborg API workflows for instance operations. https://review.openstack.org/608624 | |
| 10:44:13 | openstackgerrit | YumengBao proposed openstack/cyborg master: Fix installation guide error https://review.openstack.org/608633 | |
| #openstack-cyborg - 2018-10-09 | |||
| 01:29:28 | jiapei | https://www.irccloud.com/pastebin/6rJoAMJz/ | |
| 03:00:07 | openstackgerrit | Nguyen Van Trung proposed openstack/cyborg master: Don't quote {posargs} in tox.ini https://review.openstack.org/608812 | |
| 08:47:28 | openstackgerrit | wangzhh proposed openstack/cyborg master: Add "Report device data to cyborg" https://review.openstack.org/596691 | |
| 08:58:25 | openstackgerrit | YumengBao proposed openstack/cyborg master: Update devstack installation guide https://review.openstack.org/608883 | |
| 12:10:13 | openstackgerrit | wangzhh proposed openstack/cyborg master: Add gpu driver https://review.openstack.org/574075 | |
| 12:12:31 | openstackgerrit | wangzhh proposed openstack/cyborg master: Add gpu driver https://review.openstack.org/574075 | |
| #openstack-cyborg - 2018-10-10 | |||
| 14:06:23 | Li_Liu | FYI, this week's cyborg meeting is on ZOOM | |
| 14:07:12 | Li_Liu | https://zoom.us/j/6637468814 | |
| 14:15:25 | edleafe | I won't be able to join the zoom conference, so please post a summary of any decisions made or questions raised, either here or in a post to the mailing list. | |
| #openstack-cyborg - 2018-10-11 | |||
| 04:00:08 | Sundar | @edleafe: I made a presentation of the suggested Cyborg device/data model, and explained the workflow from the PTG. | |
| 04:00:15 | Sundar | #link https://docs.google.com/presentation/d/1Anud3Qbcb0P3G245HpHduHhslx1MJljGD6wqPDy7o9E/edit?usp=sharing | |
| 04:27:19 | openstackgerrit | Li Liu proposed openstack/cyborg master: Let the fpga programming api call cyborg agent https://review.openstack.org/596507 | |
| 04:32:13 | openstackgerrit | Li Liu proposed openstack/cyborg master: Let the fpga programming api call cyborg agent https://review.openstack.org/596507 | |
| 10:28:49 | openstackgerrit | Xinran WANG proposed openstack/cyborg master: Resource report to placement https://review.openstack.org/601150 | |
| #openstack-cyborg - 2018-10-12 | |||
| 03:28:12 | openstackgerrit | Li Liu proposed openstack/cyborg master: Added Glance Client for Image downloading https://review.openstack.org/609906 | |
| 14:09:14 | openstackgerrit | Chuck Short proposed openstack/os-acc master: Change python3.5 job to python3.7 job on Stein+ https://review.openstack.org/610046 | |
| 14:09:40 | openstackgerrit | Chuck Short proposed openstack/os-acc master: Change python3.5 job to python3.7 job on Stein+ https://review.openstack.org/610046 | |
| #openstack-cyborg - 2018-10-14 | |||
| 04:14:35 | openstackgerrit | Li Liu proposed openstack/cyborg master: Added Glance Client for Image downloading https://review.openstack.org/609906 | |
| #openstack-cyborg - 2018-10-15 | |||
| 15:09:18 | mriedem | i'm not sure if anyone here has put any thought into the upgrade checkers goal https://storyboard.openstack.org/#!/story/2003657 | |
| 15:09:24 | mriedem | there are no upgrade release notes for cyborg | |
| 15:09:41 | mriedem | and with the project being so new, i don't know if it has had anything yet like even config option deprecation/removal | |
| 16:23:41 | openstackgerrit | Corey Bryant proposed openstack/os-acc master: Change python3.5 job to python3.7 job on Stein+ https://review.openstack.org/610046 | |
| #openstack-cyborg - 2018-10-16 | |||
| 05:40:52 | openstackgerrit | Sundar Nadathur proposed openstack/cyborg-specs master: Specification for Cyborg API workflows for instance operations. https://review.openstack.org/608624 | |
| #openstack-cyborg - 2018-10-17 | |||
| 02:44:22 | openstackgerrit | Li Liu proposed openstack/cyborg master: Added Glance Client for Image downloading https://review.openstack.org/609906 | |
| 14:03:16 | sum12 | meeting ? | |
| 14:05:10 | Li_Liu | yup | |
| 14:05:18 | Li_Liu | let's wait for few more min | |
| 14:06:18 | Li_Liu | #startmeeting openstack-cyborg | |
| 14:06:18 | openstack | Meeting started Wed Oct 17 14:06:18 2018 UTC and is due to finish in 60 minutes. The chair is Li_Liu. Information about MeetBot at http://wiki.debian.org/MeetBot. | |
| 14:06:19 | openstack | Useful Commands: #action #agreed #help #info #idea #link #topic #startvote. | |
| 14:06:21 | openstack | The meeting name has been set to 'openstack_cyborg' | |
| 14:06:29 | Li_Liu | #topic Roll Call | |
| 14:06:37 | Sundar | #info Sundar | |
| 14:06:38 | Li_Liu | #info Li_Liu | |
| 14:06:51 | wangzhh | #info wangzhh | |
| 14:07:51 | Li_Liu | Let's wait for shaohe | |
| 14:08:07 | Sundar | What is the agenda? | |
| 14:08:32 | Li_Liu | We will go over all the pending patches and tasks. and discuss the demo plan for the summit | |
| 14:08:48 | Sundar | I'd like to bring up the need to get reviews for: https://review.openstack.org/#/q/status:open+project:openstack/cyborg-specs | |
| 14:09:00 | Sundar | Next week is Stein-1 milestone | |
| 14:09:30 | Li_Liu | yes | |
| 14:09:50 | Li_Liu | we should get the pending one merged as much as we could | |
| 14:11:18 | Li_Liu | ok, let's get started first | |
| 14:11:35 | Li_Liu | #topic Pending patches | |
| 14:11:51 | Li_Liu | https://review.openstack.org/#/q/status:open%20project:openstack/cyborg | |
| 14:11:56 | Sundar | May be we can start with wangzhh's patch on drivers | |
| 14:12:16 | Sundar | https://review.openstack.org/#/c/596691/ ? | |
| 14:12:30 | Li_Liu | Added Glance Client for Image downloading --- Please help review this so that we can merge. The summit demo needs this one | |
| 14:12:55 | wangzhh | Of course. My patch is based on ovo now. | |
| 14:13:38 | wangzhh | And Sundar, I have sent an email about your questions. Did u get it? | |
| 14:14:27 | Sundar | wangzhh: Sorry, don't remember seeing it. When was it sent? | |
| 14:15:03 | Li_Liu_ | I am back | |
| 14:15:04 | shaohe_feng | #info shaohe_feng_ | |
| 14:15:07 | Li_Liu_ | did I miss anything? | |
| 14:15:17 | Li_Liu_ | Hi shaohe | |
| 14:15:23 | shaohe_feng | morning Li_Liu_ | |
| 14:15:47 | wangzhh | SundarMaybe this morning for you. | |
| 14:16:19 | xinran | #info xinran | |