Earlier  
Later
New Search
Posted Nick Remark
#openstack-nova - 2019-11-14
20:41:52 sean-k-mooney good
20:43:35 mriedem random crap is the best kind of nfv crap
20:44:12 openstackgerrit Archit Modi proposed openstack/nova stable/queens: Revert "openstack server create" to "nova boot" in nova docs https://review.opendev.org/693239
20:45:39 amodi mriedem: https://review.opendev.org/#/c/694357/2 i think this is ready to be merged and then the above ^^ one
20:45:59 openstackgerrit Eric Fried proposed openstack/nova-specs master: Spec: Ussuri: Encrypted Emulated Virtual TPM https://review.opendev.org/686804
20:47:56 efried johnthetubaguy, mriedem (as approvers of the original stein spec), dansmith (because we've been talking about it): This spec ^ is ready for your discerning eyes. Please and thank you.
20:48:24 efried jroll: minor updates, fyi ^
20:48:36 jroll noted
20:51:20 openstackgerrit Matt Riedemann proposed openstack/nova stable/queens: Revert "openstack server create" to "nova boot" in nova docs https://review.opendev.org/693239
20:52:11 mriedem amodi: done
20:52:27 amodi thanks!
20:52:36 mriedem efried: i don't even remember approving those. i think it was someone that hacked my account.
20:53:23 efried mriedem: This ain't discover card. You ARE responsible for charges made on your account.
20:58:12 openstackgerrit Matt Riedemann proposed openstack/nova master: Reset vm_state to original value if rebuild claim fails https://review.opendev.org/692185
21:27:24 tonyb mriedem, sean-k-mooney: Not if I do my job right. It'll be everyone's problem
21:28:30 sean-k-mooney power i could live with if they gave me a machine. im not sure i would have room for a mainframe in my hallway
21:29:09 sean-k-mooney so z is not a think i want to deal with
21:29:16 openstackgerrit Eric Fried proposed openstack/nova master: WIP: Add emulated TPM support to Nova https://review.opendev.org/631363
21:29:16 openstackgerrit Eric Fried proposed openstack/nova master: Add support for resize and cold migration of emulated TPM files https://review.opendev.org/639934
21:30:14 tonyb sean-k-mooney: Well I'd hope you have access to some at work, at home you're on your own but https://www.raptorcs.com/TALOSII/ is about the same price I paid for my x86_64 dev box
21:30:55 sean-k-mooney ya i have seen those before
21:36:07 sean-k-mooney tonyb: im sure there is a less painful way to get acesss to hardware at work but i generally do all my deve either my my personal server i bought or on my laptop in a vm where i fake out numa toploiges with libvirt
21:36:36 sean-k-mooney technically i could also just fake a power system that way too i guess i just would be slow without kvm
21:37:22 tonyb sean-k-mooney: Yes it works but is slow
21:38:02 sean-k-mooney ya its just because kvm only supprot acclerate of your native instruction set
21:39:05 tonyb yeah TCG is nice but slow
21:39:38 sean-k-mooney have you played with the multi threaded tcg backend e.g. mttcg
21:39:55 sean-k-mooney thats actully not bad in the little i have used it
21:40:03 tonyb No, I didn't know that existed
21:40:17 sean-k-mooney you need really new qemu
21:40:35 tonyb I have F30, is that new enough?
21:40:35 sean-k-mooney it was added for acclerating other architure mainly arm
21:41:04 sean-k-mooney i can check. it getts enabeld automaticaly if you cpu model is supproted
21:41:19 tonyb I'll go googling ;p
21:41:50 sean-k-mooney oh looks like you can force it too now https://wiki.qemu.org/Features/tcg-multithread
21:43:00 sean-k-mooney looks like aarch64 was in 2.9
21:43:11 sean-k-mooney not sure if power has been added
21:48:42 sean-k-mooney look like mips,arm,aarch64,x86_64 and aplha have support in the latest version but no power supprot at elast form the release notes
21:48:57 tonyb Pfft
21:57:51 openstackgerrit Merged openstack/nova master: Join migration_context and flavor in Migration.instance https://review.opendev.org/689846
21:57:57 openstackgerrit Merged openstack/nova master: Improve metadata server performance with large security groups https://review.opendev.org/656084
22:04:34 sean-k-mooney ...
22:04:51 sean-k-mooney i was just about to push and then call it a day and now i have a merg conflcit
22:06:48 openstackgerrit sean mooney proposed openstack/nova master: support pci numa affinity policies in flavor and image https://review.opendev.org/674072
22:06:54 openstackgerrit Matt Riedemann proposed openstack/nova stable/train: Join migration_context and flavor in Migration.instance https://review.opendev.org/694408
22:07:33 sean-k-mooney ill fix that tomorrow but it now has the func tests and artoms nits adressed
22:07:39 openstackgerrit Matt Riedemann proposed openstack/nova stable/train: Improve metadata server performance with large security groups https://review.opendev.org/694409
22:18:47 sean-k-mooney actully it looks trivial ill fix it now
22:19:37 openstackgerrit sean mooney proposed openstack/nova master: support pci numa affinity policies in flavor and image https://review.opendev.org/674072
23:30:06 openstackgerrit Matt Riedemann proposed openstack/nova master: WIP: Store instance action event exc_val fault details https://review.opendev.org/694428
#openstack-nova - 2019-11-15
00:43:13 openstackgerrit Matt Riedemann proposed openstack/nova master: WIP: Expose instance action event details out of the API https://review.opendev.org/694430
02:20:29 openstackgerrit Merged openstack/nova master: Move compute_node_to_inventory_dict to test-only code https://review.opendev.org/693438
02:20:35 openstackgerrit Merged openstack/nova master: Remove get_minimum_version mocks from test_resource_tracker https://review.opendev.org/693439
02:20:43 openstackgerrit Merged openstack/nova stable/queens: doc: fix and clarify --block-device usage in user docs https://review.opendev.org/694357
02:59:56 openstackgerrit Merged openstack/nova master: Stop using NoAuthMiddleware in tests https://review.opendev.org/687416
03:10:17 openstackgerrit Merged openstack/nova master: Remove TODO from ComputeTaskManager._live_migrate https://review.opendev.org/693696
04:31:02 openstackgerrit Archit Modi proposed openstack/nova stable/pike: doc: fix and clarify --block-device usage in user docs https://review.opendev.org/694450
05:41:05 openstackgerrit Brin Zhang proposed openstack/nova-specs master: Add resources metadata of instance https://review.opendev.org/663563
06:45:33 openstackgerrit Brin Zhang proposed openstack/nova-specs master: Add resources metadata of instance https://review.opendev.org/663563
07:18:39 openstackgerrit Shilpa Devharakar proposed openstack/nova master: Ignore root_gb if instance is booted from volume https://review.opendev.org/612626
07:18:39 openstackgerrit Shilpa Devharakar proposed openstack/nova master: Handle new is_volume_backend join column query https://review.opendev.org/694462
07:18:40 openstackgerrit Shilpa Devharakar proposed openstack/nova master: Instance object changes for the new 'is_volume_backed' expected_attr https://review.opendev.org/694463
08:08:32 bauzas good morning Nova
08:39:17 awalende Hello, I have trouble passing through an nvidia t4 card to my guests on Rocky. nova-compute log reports the final resource as: pci_stats=[PciDevicePool(count=1,numa_node=1,product_id='1eb8',tags={dev_type='type-PF'},vendor_id='10de')]
08:40:57 awalende However, when I set the alias as alias={"name":"T4","vendor_id":"10de","product_id":"1eb8"} on the controller and alias={"name":"T4","vendor_id":"10de", "product_id":"1eb8"} on compute node does not work
08:41:30 awalende Also I wonder, why it is declared as a "PF". I clearly inserted an PCIe card
08:42:16 stephenfin awalende: How have you configured the PCI whitelist in nova.conf?
08:42:40 awalende passthrough_whitelist={"vendor_id":"10de"}
08:45:16 stephenfin awalende: So this is interesting. The Tesla T4 supports SR-IOV https://www.nvidia.com/content/dam/en-zz/Solutions/Data-Center/tesla-t4/t4-tensor-core-product-brief.pdf
08:46:21 stephenfin and because we're detecting that, we're flagging it as a PF https://github.com/openstack/nova/blob/master/nova/virt/libvirt/driver.py#L6562-L6565
08:46:44 awalende So there is probably a difference passing them through as other regular gpus?
08:47:45 awalende Can we pass them even at all?
08:47:54 stephenfin Possibly. I could be wrong, but I do recall that type-PF devices were disabled by default because you typically wouldn't want to use them when you talk about NICs
08:47:59 stephenfin but it can be enabled
08:48:08 stephenfin do you want to pass through the PF or the VF?
08:48:23 awalende the whole hardware
08:48:53 awalende I guess probably the PF....so the usecase is, we want to pass the whole card to the guest. so that they have to install nvidia drivers by themselfs on the guest machine
08:49:09 awalende like we did with our older Tesla V100 cards
08:50:06 stephenfin Seems like you could get better resource utilization if you passed through the VFs though (since apparently that would give you up to 16 devices)
08:50:11 stephenfin That doesn't matter for now though
08:51:03 stephenfin If you want to use type-PF devices, I _think_ you need to either (a) set the 'device_type' flag in the 'alias' config option or (b) make sure the VFs are not whitelisted
08:51:46 awalende ye we already tried to set 'device_type' but it didn't make a difference :(
08:52:06 stephenfin have you tried (b)?
08:52:16 stephenfin to do that, you'll need to also set the 'product_id' in the 'passthrough_whitelist'
08:52:44 stephenfin to whatever the product_id of the PF is, assuming the PF and VF have different product_id's (they should)
08:52:54 awalende my colleague means he "maybe" tried it as well. We try it again and let you know
08:53:23 stephenfin If they don't, you're going to need to use the 'address' field, I'm afraid
08:53:31 stephenfin okay, do please
08:53:59 stephenfin sean-k-mooney might be able to help too but they're definitely fast asleep atm :)
08:54:13 awalende How do you make sure that "VFs are not whitelisted"?
08:55:08 bauzas the T4 ?
08:55:19 bauzas awalende: which grid driver are you using ?
08:55:25 bauzas GRID8 ?
08:55:53 awalende no driver at all, we plugged the T4 into our hypervisor nodes and want to pass them through to guests
08:56:05 stephenfin awalende: If SR-IOV is enabled on the device, you will have additional PCI devices appearing at e.g. 'lspci'
08:56:19 awalende one moment
08:57:06 stephenfin 'lspci | grep -i nvidia' should flag them, I'd imagine
08:57:07 bauzas oh right, then that's normal
08:57:26 bauzas Nvidia plans to deliver virtual GPUs as VFs later
08:57:36 bauzas I guess they already started to expose the GPU as a PF

Earlier   Later