Earlier  
Later
New Search
Posted Nick Remark
#openstack-nova - 2018-02-26
16:30:44 dansmith I think it _has_ to be before the versioned space
16:30:51 dansmith no /v2.1 I think
16:30:56 openstackgerrit Eric Berglund proposed openstack/nova master: WIP: PowerVM Driver: Network interface attach/detach https://review.openstack.org/546813
16:32:19 efried This should be a mordred question. I think he has strong opinions on whether the 'v2.1' should be present in the URI at all, ever (even for discovry).
17:19:10 openstackgerrit Merged openstack/nova-specs master: Update Provider Tree https://review.openstack.org/540111
17:35:39 openstackgerrit Merged openstack/nova stable/ocata: libvirt: Don't VIR_MIGRATE_NON_SHARED_INC without migrate_disks https://review.openstack.org/519636
17:59:18 openstackgerrit Lee Yarwood proposed openstack/nova stable/pike: libvirt: Block swap volume attempts with encrypted volumes https://review.openstack.org/543569
21:00:11 openstackgerrit Merged openstack/nova master: Clarify wording in listing instance actions for deleted instances https://review.openstack.org/548055
21:00:46 openstackgerrit Merged openstack/nova master: Clarify update_provider_tree docstring https://review.openstack.org/545495
22:18:11 openstackgerrit Marcin Juszkiewicz proposed openstack/nova master: Allow to configure amount of PCIe ports https://review.openstack.org/545034
23:13:02 openstackgerrit Maciej Jozefczyk proposed openstack/nova master: Do not normalize allocation_ratios https://review.openstack.org/532924
#openstack-nova - 2018-02-27
03:33:58 vivsoni mriedem: hi
03:34:34 vivsoni mriedem: related to https://blueprints.launchpad.net/cinder/+spec/implement-force-detach-for-safe-cleanup
03:34:50 vivsoni force_detach
03:36:34 itlinux hello nova team.. I wonder what's the new command to add a floating ip address to a port.. I used to have this with neutron but since things changed I will ask first here..
06:28:34 openstackgerrit Michael Still proposed openstack/nova master: Convert users of tune2fs to privsep. https://review.openstack.org/519484
06:28:34 openstackgerrit Michael Still proposed openstack/nova master: Move makefs to privsep https://review.openstack.org/527510
06:40:10 openstackgerrit sahid proposed openstack/nova-specs master: virt: allow instances to be booted with trusted VFs https://review.openstack.org/485522
07:11:19 openstackgerrit sahid proposed openstack/nova-specs master: update: introducing isolate emulthreads on host https://review.openstack.org/511188
07:11:43 openstackgerrit sahid proposed openstack/nova-specs master: libvirt: add support for virtio-net rx/tx queue sizes https://review.openstack.org/539605
08:20:57 openstackgerrit yuanyue proposed openstack/nova master: Whether to use config drive depends on instance.configdrive https://review.openstack.org/485930
09:20:54 mriedem we should be ok to recheck ocata and pike patches now
09:21:42 alex_xu bauzas: yesterday, I listen you talk about the late bind with the accelerator with cyborg, but I didn't get the point, what the benefit of that, would you remind me that
09:31:55 mriedem dansmith: i'm guessing you want to get this in pike https://review.openstack.org/#/c/542748/
09:32:32 openstackgerrit Chris Dent proposed openstack/nova master: WIP: Use nova.db.api directly https://review.openstack.org/543262
09:32:33 openstackgerrit Chris Dent proposed openstack/nova master: Move db MAX constants to own file https://review.openstack.org/543469
09:34:02 bauzas alex_xu: so I had a long chat with the Cyborg folks
09:34:21 bauzas alex_xu: tl;dr: they want to dynamically program FPGAs
09:34:42 bauzas alex_xu: but they also focus on other accelerators discovery
09:36:06 bauzas so, the problem they had was that they wanted to dynamically modify the FPGAs if Placement was saying "no sorry"
09:36:45 alex_xu bauzas: ah, that is wasting, I guess that is the point of late binding
09:37:04 bauzas instead, I proposed that Cyborg would keep track of the accelerated resources, incl. reprogramming if necessary, and Nova should only care about making sure that an instance that asks for that resource will get it
09:37:52 bauzas how the binding would be done is for the moment undefined
09:39:30 alex_xu bauzas: got it
09:40:37 alex_xu bauzas: the cyborg create accelerator, then return uuid, then nova boot instance with that accelerator uuid, and nova will get 'resource class' and 'trait' by that uuid from the cyborg API, then pass to the placement, that is the process?
09:40:48 alex_xu first part of the process
09:42:24 bauzas alex_xu: that's basically the workflow I see, but the last steps are a bit unclear to me
09:42:26 efried alex_xu: The way I understood it, cyborg will actually go as far as creating the allocation in placement.
09:42:52 efried ...unless bauzas your subsequent discussions yielded different revelations.
09:43:14 gibi alex_xu: the flow you described is pretty similar to what I would imagined for neutron ports with bandwidth resources
09:43:48 alex_xu efried: I guess so, bauzas may proposal another one, since I join cyborg session very late, and hear that
09:44:09 openstackgerrit Chris Dent proposed openstack/nova master: WIP: experiment with setting placement error codes https://review.openstack.org/546177
09:44:10 gibi efried: if nova get back allocation candidates from placement including the accelerator then nova can create the allocation easily in placement for the accelerator as well
09:45:11 alex_xu gibi: yea, I think I get that impression from the bindwidth spec. Then I try to think about how cyborg tell nova which resource request to
09:45:13 efried gibi: That would be true, BUT I'm not certain this workflow involves assigning the accelerator at spawn time. I think we were only talking about post-deploy attach.
09:46:34 alex_xu efried: if cyborg create allocation, that will be a lot of race?
09:46:55 efried alex_xu: Not if cyborg is the Source Of Truth for managing the accelerator resource.
09:47:18 gibi alex_xu, efried: I if the scenario is post-deploy attach then I can accept that cyborg creates the allocation as in this case no need for asking for allocation candidates
09:48:03 efried gibi: Maybe. That would be up to cyborg and how they want to manage the RPs.
09:48:19 efried gibi: But Nova wouldn't, that's true.
09:49:04 gibi efried: do you mean a compute host might have more than one accelearator and cyborg want to select from that pool during post-deploy attach?
09:49:45 efried gibi: For sure.
09:49:46 gibi efried: yes, if there is cyborg calls allocation candidate API then cyborg can create the allocation too
09:50:24 efried gibi: Especially if we're talking about "regions" or whatever the VF equivalent is for FPGA.
09:51:16 efried gibi: And maybe cyborg wants to precreate those. Or maybe not.
09:51:42 efried gibi: But surely there could be more than one FPGA on the system in any case.
09:51:45 alex_xu gibi: sorry, what is post-deploy attach?
09:51:57 openstackgerrit Takashi NATSUME proposed openstack/nova master: Transform live_migration.post.dest notifications https://review.openstack.org/469784
09:51:58 efried gibi: And IIUC, cyborg wants to manage not just FPGAs but other accelerators too.
09:52:11 openstackgerrit Takashi NATSUME proposed openstack/nova master: Transform live_migration.post.dest notifications https://review.openstack.org/469784
09:52:31 efried alex_xu: Meaning nova does spawn with CPU/Mem/disk, and then after that's finished and the instance is already created, cyborg comes along and attaches the FPGA
09:53:23 gibi alex_xu: I think about it like adding volumes to an existing VMs
09:53:43 efried ^
09:53:52 efried or attach_interface()
09:54:03 alex_xu efried: gibi, got it
09:54:05 efried 'cept not done by nova :) So gibi's example is much better :)
09:54:32 alex_xu so the cyborg calling the allocation candidates API to get a accelerator from the pool of the host?
09:54:39 gibi efried: thanks, I think I got it. post-deploy sounds like an easy shortcut for not getting tangled into the nova boot process
09:54:46 alex_xu since the instance already boot up on specific host
09:54:48 efried gibi: ++
09:55:26 efried alex_xu: Yes. TBH, I'm not completely sure how one would call GET /allocation_candidates in such a way that it restricts to a certain host.
09:55:57 alex_xu efried: the we have parameter like in_tree?
09:55:59 gibi efried: it might be part of the 'anchor a request' discussion
09:56:04 efried alex_xu: Just so.
09:56:36 openstackgerrit Stephen Finucane proposed openstack/nova master: Stop using mox in virt/xenapi/image/test_vdi_through_dev.py https://review.openstack.org/342682
09:56:37 efried alex_xu: It depends to some extent on how the accelerators are modeled. If they're included in the compute node's provider tree, then yes, ?in_tree=<compute_uuid> on GET /allocation_candidates would be very appropriate.
09:57:18 alex_xu efried: yea
09:57:33 efried alex_xu: And/or if the accelerator is made part of an aggregate (not sure if that makes sense ever, but it extends to the more general model for e.g. bandwidth providers) then member_of
09:57:47 efried The latter is a Rocky bp. The former is not (yet).
09:58:42 Kevin_Zheng Any idea how Nova can consume resource reported by cyborg?
09:59:20 alex_xu efried: I didn't get the accelerator is made part of an aggregate. The aggregate in Nova?
09:59:51 openstackgerrit Chris Dent proposed openstack/nova master: WIP: Move resource provider objects into placement hierarchy https://review.openstack.org/540049
09:59:52 openstackgerrit Chris Dent proposed openstack/nova master: Optional separate database for placement API https://review.openstack.org/362766
09:59:52 openstackgerrit Chris Dent proposed openstack/nova master: Isolate placement database config https://review.openstack.org/541435
10:00:05 alex_xu Kevin_Zheng: depends on the direction we go I guess, with bauzas way, it can be done by cyborg API to return some resource class and traits. With the post-deploy attach, that is cyborg own thing
10:00:10 bauzas folks, I'm in the Scientifig WG room so I can't follow the convo
10:00:21 efried alex_xu: It probably doesn't make sense for accelerators to be modeled as true sharing providers.
10:00:23 alex_xu bauzas: no worries
10:00:43 efried alex_xu: Though be aware that sharing providers aren't the only possible use case for aggregates.
10:01:20 efried alex_xu: In the case of accelerators, which are pieces of hardware physically attached to the host, it most likely makes sense for them to be somewhere in the compute node's provider tree.
10:02:25 efried alex_xu: But for something like a bandwidth provider, where the component doing the work is maybe an external switch that manages traffic from multiple hosts, a sharing provider might be totally appropriate. (I need to reread the network bandwidth provider spec.)
10:02:26 alex_xu efried: yea, I can't image how accelerators shared between hosts
10:02:35 gibi Kevin_Zheng: as a wild alternative there is flavor extra_spec https://specs.openstack.org/openstack/nova-specs/specs/pike/implemented/custom-resource-classes-in-flavors.html
10:03:08 alex_xu efried: ah, that sounds make sense for bindwidth
10:03:10 gibi efried: correct, a TOR switch would be a shared provider
10:03:11 efried gibi: Here's a not-so-secret secret - that's how PowerVM is planning to do accelerator attach.
10:03:24 efried at least tentatively
10:03:35 bauzas efried: how the FPGA accelerators are modeled looks to me a Cyborg-only discusion
10:03:51 efried gibi: Though we may or may not need custom RCs.
10:03:54 gibi efried: We had our internal plans to do bandwidth with flavor extra_spec but it got voted down internally

Earlier   Later