| Posted | Nick | Remark | |
|---|---|---|---|
| #openstack-nova - 2017-04-21 | |||
| 14:12:07 | johnthetubaguy | mriedem: yeah, I couldn't think of how to finish my speach... and didn't think to use google because I was too nervous, lol | |
| 14:12:25 | mriedem | johnthetubaguy: was it pre-dinner or post-dinner? | |
| 14:12:30 | mriedem | or mid-dinner? | |
| 14:12:37 | johnthetubaguy | sort of mid I really | |
| 14:12:59 | sballe_ | morning | |
| 14:13:02 | mriedem | same for my forced impromptu speech | |
| 14:13:09 | johnthetubaguy | heh | |
| 14:13:14 | mriedem | i should have done jimmy from south park | |
| 14:13:18 | mriedem | "wow what a great audience!" | |
| 14:13:55 | sballe_ | I am looking for some documentation on how nova can schedule VMs with FPGAs as well as how FPGAs are represented in nove | |
| 14:13:59 | sballe_ | s/nova | |
| 14:14:17 | sballe_ | Any help is appreciated | |
| 14:14:49 | johnthetubaguy | mriedem: ildikov: maybe update the existing spec with a note about all that? | |
| 14:15:23 | ildikov | johnthetubaguy: that can work too | |
| 14:15:43 | johnthetubaguy | sballe_: we don't really support FPGA passthrough for VMs as such, although I think you could use ironic to give you the whole box including the FPGA | |
| 14:16:32 | mriedem | sballe_: they aren't | |
| 14:16:35 | sballe_ | couls I use nova to schedule flavors with accelerators? | |
| 14:16:48 | sballe_ | I see a lot of post with gpus | |
| 14:17:10 | johnthetubaguy | sballe_: so you can pass through a generic PCI device, maybe that would work? | |
| 14:17:13 | mriedem | sballe_: there is a project called 'cyborg' which you should probably start with | |
| 14:17:21 | mriedem | which is all about acceleration | |
| 14:17:31 | sballe_ | ok cool! thx for the help | |
| 14:17:35 | mriedem | sballe_: https://wiki.openstack.org/wiki/Cyborg | |
| 14:18:00 | mriedem | look for email threads in the openstack-dev mailing list tagged with [acceleration] | |
| 14:18:17 | johnthetubaguy | so I forgot about that thing, my email filters are a bit strong these days | |
| 14:18:26 | mriedem | sballe_: also https://review.openstack.org/#/c/318047/ | |
| 14:19:36 | mriedem | leakypipes: dansmith: johnthetubaguy: https://review.openstack.org/#/c/419185/ on down for bp/additional-notification-fields-for-searchlight is ready to go, has my +2 | |
| 14:20:16 | mriedem | johnthetubaguy: yeah we could amend the spec, | |
| 14:20:22 | mriedem | johnthetubaguy: you going to do that or want me to? | |
| 14:20:25 | mriedem | i'm happy to update it | |
| 14:20:36 | johnthetubaguy | mriedem: if you could, that would be great | |
| 14:20:43 | mriedem | will do | |
| 14:20:45 | sballe_ | mriedem: thx | |
| 14:20:50 | bauzas | mriedem: hola, quick q, when are you planning a stable/newton release ? :) | |
| 14:21:00 | bauzas | and oh snap, TGIF | |
| 14:21:03 | mriedem | bauzas: when you merge the regression fixes proposed to newton | |
| 14:21:22 | bauzas | mriedem: heh, roger. | |
| 14:21:53 | smcginnis | mriedem: Missed your question yesterday while travelling. | |
| 14:22:03 | smcginnis | mriedem: That session is to discuss the track chair process and issues. | |
| 14:22:52 | openstackgerrit | sahid proposed openstack/nova master: network: update pci request spec to handle trusted tags https://review.openstack.org/458820 | |
| 14:22:52 | openstackgerrit | sahid proposed openstack/nova master: libvirt: configure trust mode for vfs https://review.openstack.org/458514 | |
| 14:22:53 | openstackgerrit | sahid proposed openstack/nova master: network: add command to configure trusted mode for VFs https://review.openstack.org/458513 | |
| 14:24:22 | mriedem | smcginnis: what's a track chair? | |
| 14:24:28 | mriedem | those setting up the summit? | |
| 14:24:35 | mriedem | or those running a session? | |
| 14:24:52 | openstackgerrit | Alex Xu proposed openstack/python-novaclient master: Add `instance-uuid` flag to the migration-list https://review.openstack.org/458728 | |
| 14:24:58 | johnthetubaguy | pick the sessions | |
| 14:25:03 | mriedem | alex_xu: you beat me to it | |
| 14:25:06 | smcginnis | mriedem: Decising which sessions to accept for the official schedule. | |
| 14:25:09 | johnthetubaguy | mriedem: done it twice, its a pain | |
| 14:25:15 | mriedem | oh, i don't care about that session then :) | |
| 14:25:17 | smcginnis | johnthetubaguy: Yep. :) | |
| 14:25:21 | alex_xu | mriedem: hope you didn't start that | |
| 14:25:29 | mriedem | alex_xu: no i didn't, thanks for doing it | |
| 14:25:34 | alex_xu | mriedem: np | |
| 14:29:16 | mriedem | alex_xu: comments inline :) | |
| 14:29:19 | mriedem | otherwise looks good | |
| 14:30:36 | openstackgerrit | Lee Yarwood proposed openstack/nova master: libvirt: Always disconnect_volume after rebase failures https://review.openstack.org/458807 | |
| 14:31:37 | mriedem | bauwser: these https://review.openstack.org/#/c/457353/ https://review.openstack.org/#/c/448235/ https://review.openstack.org/#/c/458668/ https://review.openstack.org/#/c/456770/ https://review.openstack.org/#/c/448253/ | |
| 14:31:52 | bauwser | mriedem: reviewy reviewy | |
| 14:32:03 | mriedem | ask and ye shall receieve | |
| 14:32:05 | mriedem | *receive | |
| 14:32:26 | bauwser | mriedem: FWIW, I haven't touched the scheduler claims spec since I need time to think about | |
| 14:32:51 | mriedem | i haven't either | |
| 14:32:52 | bauwser | about the super extra cool problem you showed to the world with overhead values | |
| 14:33:04 | mriedem | don't thank me, thank some performance tester internal to huawei | |
| 14:33:33 | bauwser | mriedem: FWIW, my honest first opinion is that problem it's something that we should leave out of placement | |
| 14:33:35 | mriedem | i didn't know the overhead stuff existed before that | |
| 14:33:58 | bauwser | mriedem: that looks something not really useful for placement and very related to the hypervisor | |
| 14:34:28 | mriedem | you have to solve it with placement one way or the other, either by tracking overhead in allocations, or forcing extra reserved inventory to make up for the overhead | |
| 14:34:29 | bauwser | so, say we leave in a world where we're not trying to eat all the resources but still have reserved room for that, then it's not a problem for placement | |
| 14:34:30 | mriedem | right? | |
| 14:34:52 | mriedem | i don't think we can punt on this | |
| 14:35:55 | bauwser | mriedem: if we have rescheduling, would it be a problem ? | |
| 14:36:14 | bauwser | we already don't place instances by reviewing that value | |
| 14:36:25 | mriedem | we reschedule based on it though | |
| 14:36:29 | bauwser | of course | |
| 14:36:31 | mriedem | but we don't have reschedules with super conductor | |
| 14:36:34 | bauwser | but how much ? | |
| 14:36:38 | mriedem | idk how much | |
| 14:36:47 | bauwser | so, it's rather a problem about how to reschedule | |
| 14:36:53 | mriedem | well, | |
| 14:36:59 | mriedem | the point of claims in the scheduler is you don't need to reschedule | |
| 14:37:17 | bauwser | honestly, I think claiming in the scheduler couldn't remove the compute node verifying the resources too | |
| 14:37:31 | bauwser | because sometimes, things can be wrong | |
| 14:37:57 | bauwser | so, having claims in the scheduler is cool but like Pareto (or more) fixing 95% of the number of problems we have | |
| 14:38:08 | bauwser | should we fix 5% of the current problems by adding more ? | |
| 14:38:15 | bauwser | if we still reschedule | |
| 14:38:18 | mriedem | if you can't reschedule from the compute, then what? NoValidHost and put the instance into ERROR state? | |
| 14:38:35 | mriedem | ^ was one of the options i proposed in the spec | |
| 14:38:44 | bauwser | anyway, since not all the resources are yet set in the placement API (like NUMA), we would still need to reschedule, right ? | |
| 14:38:54 | mriedem | i said account for the overhead by updating the allocations once on the compute, but people didn't like that b/c of quotas | |
| 14:39:19 | bauwser | because we use allocations for quotas, and I agree with the majority | |
| 14:39:42 | bauwser | so, either we say we add that for inventories *and not allocations*, or we say it's not a problem | |
| 14:39:54 | bauwser | and we leave reschedules fix that self-healing | |
| 14:40:07 | mriedem | we don't have reschedules | |
| 14:40:29 | bauwser | that's what I'm not sure we can just say it won't exist in a cellsv2 world | |
| 14:40:29 | mriedem | i thought the consensus the other day was pad the RP inventory reserved amount | |
| 14:40:37 | mriedem | via the get_inventory() method on drivers that calculate overhead | |
| 14:40:41 | bauwser | mriedem: I think the consensus looks good by me | |