| Posted | Nick | Remark | |
|---|---|---|---|
| #openstack-cyborg - 2020-05-28 | |||
| 03:16:04 | Yumeng | And added a topic schedule in the etherpad , which is to show what topics will be discussed on which day | |
| 03:17:07 | Yumeng | not sure if all of you will attend all the meetings, so please add your name and indicate the time you will attend . If the topic schedule does not match your time, just update there or ping me | |
| 03:18:08 | Sundar | The PTG time is very late for me. If you can schedule Cyborg-Nova-Neutron part in the first hour, I can join for that hour. | |
| 03:18:52 | s_shogo | ok, thanks for good coordination, Yumeng | |
| 03:19:03 | Yumeng | Sundar, Cyborg - Neutron - Nova Cross Project Session | |
| 03:19:48 | Yumeng | Is this a good time for you. This room is booked by nova and shared with us. | |
| 03:20:01 | Sundar | Oh it is June 5 1400 UTC i.e. 7 am for me. That's fine. | |
| 03:20:39 | Yumeng | ok. that's great. So we don't need to change it. | |
| 03:21:27 | Sundar | What IRC channel should I join? | |
| 03:21:47 | Yumeng | Thanks s_shogo! So schedule things are done. | |
| 03:22:13 | Yumeng | Sundar, it's zoom link instead of IRC | |
| 03:22:45 | Sundar | Could you add the zoom link here , or in the etherpad? | |
| 03:22:59 | Yumeng | I didn't get zoom room URL from community, I will add them to etherpad once I got them | |
| 03:23:13 | Yumeng | Sundar,yes sure/ | |
| 03:23:40 | Sundar | Thanks, Yumeng | |
| 03:23:56 | Yumeng | My pleasure.^^ | |
| 03:24:19 | Yumeng | So if nothing else, we've done today's meeting. | |
| 03:24:56 | Yumeng | #topic AoB | |
| 03:25:44 | Yumeng | Just one more check, nothing else wants to bring up, right? | |
| 03:26:28 | Yumeng | Seems yes. So let's wrap up this meeting and I'll see you next week at PTG. | |
| 03:26:49 | Yumeng | Thank your everyone. Have a good day/night! | |
| 03:26:50 | Yumeng | BYe | |
| 03:26:53 | Yumeng | bye | |
| 03:26:54 | s_shogo | Bye | |
| 03:26:59 | songwenping__ | Bye | |
| 03:27:03 | Sundar | Bye | |
| 03:27:33 | Yumeng | #endmeeting | |
| 03:27:35 | openstack | Meeting ended Thu May 28 03:27:33 2020 UTC. Information about MeetBot at http://wiki.debian.org/MeetBot . (v 0.1.4) | |
| 03:27:36 | openstack | Minutes: http://eavesdrop.openstack.org/meetings/openstack_cyborg/2020/openstack_cyborg.2020-05-28-03.03.html | |
| 03:27:37 | openstack | Minutes (text): http://eavesdrop.openstack.org/meetings/openstack_cyborg/2020/openstack_cyborg.2020-05-28-03.03.txt | |
| 03:27:38 | openstack | Log: http://eavesdrop.openstack.org/meetings/openstack_cyborg/2020/openstack_cyborg.2020-05-28-03.03.log.html | |
| 03:34:06 | chenke | bye | |
| #openstack-cyborg - 2020-05-30 | |||
| 14:37:54 | openstackgerrit | Andreas Jaeger proposed openstack/cyborg-specs master: Switch to newer openstackdocstheme and reno versions https://review.opendev.org/731956 | |
| #openstack-cyborg - 2020-06-02 | |||
| 06:08:26 | Sundar | Hello all | |
| 06:08:46 | Yumeng | hello | |
| 06:08:57 | brinzhang | Sundar means add two nova APIs to support bind and unbinding ARQs? | |
| 06:09:09 | songwenping_ | Hello all | |
| 06:09:11 | chenke | Hi I move here. | |
| 06:09:17 | brinzhang | hello all | |
| 06:10:05 | Sundar | brinzhang -- That is not clear to me. If we can do HTTP PATCH on the server object, we can apply or remove devic eprofiles. | |
| 06:10:14 | Sundar | SO I think it is one API only | |
| 06:10:56 | brinzhang | Yeah, one or two all ok for me | |
| 06:11:22 | Sundar | Second problem is with libvirt/qemu -- I don;t think we can add PCI interfaces to a running VM. We have to stop it first, regenerate the doain XML and then restart the server | |
| 06:11:38 | Sundar | *domain XML | |
| 06:12:50 | Sundar | What is the openstack CLI command you are thinking of? | |
| 06:13:24 | Sundar | One option is to avoid all this, and just do a resize with a different flavor, which has a different device profile | |
| 06:13:31 | Sundar | Then no need to change Nova API at all | |
| 06:13:39 | songwenping_ | Sundar, I have test the case of add and remove PCI interfaces to a running VM like this https://review.opendev.org/#/c/729945/5/nova/virt/libvirt/driver.py | |
| 06:14:51 | Sundar | songwenping_ : How does this work? How will libvirt change the domain XML on the fly? | |
| 06:14:52 | brinzhang | Sundar, I mean I want add two nova api to support binding and unbinding arqs from nova. that we can use "nova bind-accelerators and/or unbind-accelerators" | |
| 06:15:44 | brinzhang | this need a spec to nova team | |
| 06:16:12 | Sundar | brinzhang: The Nova CLI is old. In the new openstack CLI, we say: $ openstack server create --flavor myflavor ..., where myflavor has the device profile. What is the openstack CLI you plan to use for hot attach/detach? | |
| 06:17:02 | songwenping_ | `guest.detach_device(hostdevPCI, persistent=True, live=True)' this function with "live=True" param can work for running VM. | |
| 06:17:33 | songwenping_ | we can dumpxml the VM and see the hostdev PCI attach. | |
| 06:17:37 | brinzhang | Sundar, they are same, we should do completed the cli in novaclinet and then to openstackclient to support, otherwise we cannt completed this feature in Nova | |
| 06:18:26 | brinzhang | Sundar: binding/unbinding will be an independent operation in nova | |
| 06:19:09 | brinzhang | Now we dont consider to support resize operation, that will be out of my control | |
| 06:19:19 | brinzhang | I think | |
| 06:19:53 | Sundar | brinzhang: will you pass a device profile to this CLI? if so, will one VM have 2 or more associated device profiles? | |
| 06:21:58 | brinzhang | Sundar: maybe you are right, but I am sure I can answer your question, I dont know does it need pass device_profile to the CLI | |
| 06:22:14 | Sundar | songwenping_: Great. I found this: https://libvirt.org/pci-hotplug.html Thanks for the pointer. | |
| 06:23:15 | brinzhang | If we want to bind an ARQ to an instance that its flavor has not accel:device_profile, maybe we should pass it. | |
| 06:24:34 | brinzhang | with unbind, I think we should judge the instance does have the accel:device_profile, access unbind or reject. | |
| 06:25:07 | songwenping_ | Yeah, right Sundar. Libvirt has supported hotplug for PCI devices. | |
| 06:25:41 | Sundar | IMHO, it is better to support resize: it covers hot-add and is more generally useful also. It allows us to keep the model that one VM has one device profile. | |
| 06:26:24 | Sundar | It is a standrd Nova operation: so less resistance, and may be we can even get help from Nova developers | |
| 06:27:01 | shaohe_feng | Libvirt has supported hotplug for PCI devices for a long time-_- | |
| 06:27:10 | Sundar | brinzhang: on a resize, does Nova scheduler get involved? If so, can it pick a different host? | |
| 06:27:37 | brinzhang | Sundar, resize may need to change host,that not easy to control, I know it should support, but it need time | |
| 06:27:43 | xinranwang | I think it will do re-schedule | |
| 06:27:45 | Sundar | Libvirt does not support it for the default config: looks like you have to specify a different cpu model q35. | |
| 06:29:20 | Sundar | brinzhang: we already have the scheduler flow for device profiles and ARQs. Why do you think it is difficult? | |
| 06:30:59 | Yumeng | brinzhang: I think unshelve will also do re-schedule, right? | |
| 06:31:48 | brinzhang | unshelve jsut need to re-create ARQs, it's easy to get | |
| 06:32:38 | brinzhang | I am not search into resize, so I can not answer clearly. | |
| 06:32:48 | Sundar | We can bring this up in the Nova discussion. | |
| 06:33:35 | Sundar | Anyway, we need to tlak to them about other VM ops for accelerators. | |
| 06:33:39 | Sundar | *talk | |
| 06:33:42 | shaohe_feng | Sundar: a question about schedule. You have bring up a discussion about this: | |
| 06:33:52 | brinzhang | This release we have rebuild/evcaute, suspend/resume, shelve/unshelve, I think it's enough to do in V | |
| 06:34:03 | shaohe_feng | add a new filter for dynamic program | |
| 06:34:23 | shaohe_feng | let cyborg do the filter, right? | |
| 06:34:41 | Sundar | shaohe_feng: not sue what you are referring to | |
| 06:34:50 | brinzhang | In https://review.opendev.org/#/c/729945/5/api-guide/source/accelerator-support.rst we record the operations supported in cyborg | |
| 06:36:07 | Yumeng | brinzhang: I think we can also start to support resize, chenke can investigate in. anyway, we can start discuss with nova during the session. | |
| 06:36:28 | brinzhang | agree | |
| 06:37:53 | brinzhang | after chenke talked with nova team, I think we can get more info about resize. | |
| 06:38:19 | shaohe_feng | such as, currently the function of the FPGA is ovs with 4 VF, but no VM uses it. and now on more FPGA available , we can select this one ovs PFGA as IPsec with 2 NICs, and change its function. | |
| 06:38:52 | shaohe_feng | ^ Sundar so this need a scheduler improvement, right? | |
| 06:39:05 | shaohe_feng | and you bring up to add a new filter. | |
| 06:39:13 | shaohe_feng | I remember. | |
| 06:40:49 | Sundar | shaohe_feng: That doesn;t involve the Nova scheduler. We can define a device profile with a trait that selects that type of FPGA, and an accel:bitstream that refers to ipsec. Then Placement may return some FPGA with ovs image if it is free. But Cyborg will notice it does not have ipsec and do the programming. | |
| 06:41:36 | Sundar | What we don't have is this: | |
| 06:42:05 | shaohe_feng | yes, that's the current flow in cyborg at present | |
| 06:42:13 | Sundar | Say, we have two free FPGAs, one with ovs and with ipsec. In this case, we want the scheduler to pick the one with ipsec preferentially. That is not there today. | |
| 06:43:05 | Sundar | The scheduler has a weigher but it selects among hosts, not among allocation candidates from Placement | |
| 06:43:13 | shaohe_feng | you can not fill ovs or ipsec in the trait | |
| 06:43:44 | Yumeng | brinzhang: I was curious, given "unshelve jsut need to re-create ARQs, it's easy to get", does that mean shelve operation does not actually release the accelerator in hypervisor, the accelerator is still a claimed allocation, that's why there is no re-scheduler in unshelve. | |
| 06:44:00 | shaohe_feng | but the weigher also not support for FPGA, right? | |
| 06:44:00 | Yumeng | please correct me if I was wrong | |