Earlier  
Later
New Search
Posted Nick Remark
#openstack-nova - 2019-09-06
10:15:19 stephenfin I had this written off as being fixed by your series
10:15:29 artom So a non-NUMA instances landing on a host with vcpu_pin_set is... unlikely?
10:15:38 artom stephenfin, hah, I've just noticed that it's a thing
10:15:42 bauzas stephenfin: because the behaviour will change for those not RTFM'ing
10:15:53 stephenfin bauzas: Nope, it won't change
10:15:56 stephenfin *Break
10:15:58 stephenfin bauzas: see here
10:16:24 stephenfin bauzas: https://review.opendev.org/#/c/680107/3/nova/compute/manager.py@861
10:16:28 stephenfin I'm only warning
10:16:32 stephenfin Not raising
10:17:01 stephenfin bauzas: For those other two conditionals, not that I'm only checking the _new_ options (cpu_dedicated_set, cpu_shared_set)
10:17:03 bauzas see my comment
10:17:05 stephenfin *note
10:17:18 stephenfin Yup. The conditional is here https://review.opendev.org/#/c/680107/3/nova/compute/manager.py@827
10:17:29 openstackgerrit Luyao Zhong proposed openstack/nova master: db: Add resources column in instance_extra table https://review.opendev.org/678447
10:17:30 openstackgerrit Luyao Zhong proposed openstack/nova master: object: Introduce Resource and ResourceList objs https://review.opendev.org/678448
10:17:31 openstackgerrit Luyao Zhong proposed openstack/nova master: Add resources dict into _Provider https://review.opendev.org/678449
10:17:31 openstackgerrit Luyao Zhong proposed openstack/nova master: Retrieve the allocations early https://review.opendev.org/678450
10:17:32 openstackgerrit Luyao Zhong proposed openstack/nova master: Claim resources in resource tracker https://review.opendev.org/678452
10:17:32 openstackgerrit Luyao Zhong proposed openstack/nova master: libvirt: Enable driver discovering PMEM namespaces https://review.opendev.org/678453
10:17:32 openstackgerrit Luyao Zhong proposed openstack/nova master: libvirt: report VPMEM resources by provider tree https://review.opendev.org/678454
10:17:33 openstackgerrit Luyao Zhong proposed openstack/nova master: libvirt: Support VM creation with vpmems and vpmems cleanup https://review.opendev.org/678455
10:17:33 openstackgerrit Luyao Zhong proposed openstack/nova master: Parse vpmem related flavor extra spec https://review.opendev.org/678456
10:17:34 openstackgerrit Luyao Zhong proposed openstack/nova master: libvirt: Enable driver configuring PMEM namespaces https://review.opendev.org/679640
10:17:35 openstackgerrit Luyao Zhong proposed openstack/nova master: Add functional tests for virtual persistent memory https://review.opendev.org/678470
10:17:35 openstackgerrit Luyao Zhong proposed openstack/nova master: doc: attaching virtual persistent memory to guests https://review.opendev.org/680300
10:17:37 stephenfin and I early return here https://review.opendev.org/#/c/680107/3/nova/compute/manager.py@839
10:18:08 stephenfin so lines 841 etc. will only be triggered if the instance has a NUMA topology and that topology has pinning enabled
10:18:23 bauzas oh shit, that's what happen when you review in a crowded Starbucks place
10:18:31 bauzas you're totally right
10:18:46 stephenfin bauzas: but at least you've mediocre coffee on hand :P
10:18:57 stephenfin If it's not clear, I can rework to use an if-else
10:20:59 openstackgerrit Merged openstack/nova master: update allocation in binding profile during migrate https://review.opendev.org/656422
10:21:22 bauzas stephenfin: nah nah, it's cool
10:21:42 bauzas stephenfin: we could nitpick on getting an extra comment, but meh
10:22:28 bauzas and yeah Starbucks is mediocre, but that's the only place where you can guaranttee both decent wifi coverage and working outlets
10:22:53 stephenfin In the code or the commit message? I can do the latter in a follow-up
10:23:08 stephenfin Yeah, agreed. Costa just isn't the same (and it's UK only)
10:23:15 bauzas I wish I could afford a Regus usage :)
10:23:46 bauzas stephenfin: well, I was thinking of just a comment line in the code itself but that's gross
10:23:49 bauzas nevermind it
10:23:58 bauzas it's just me who can't read coee
10:24:01 bauzas code*
10:24:29 openstackgerrit Brin Zhang proposed openstack/python-novaclient master: Microversion 2.79: Add delete_on_termination to volume-attach API https://review.opendev.org/673485
10:24:47 stephenfin 'sall good :D
10:36:35 stephenfin artom: how do you decide to recalculate the '<cpuset>' values on a destination host in your series?
10:37:01 artom stephenfin, I currently don't, at all
10:37:21 sean-k-mooney you just always recaluate it right
10:37:25 sean-k-mooney as part of the claim
10:37:53 artom sean-k-mooney, no, currently it's not handled at all
10:38:02 sean-k-mooney which cpuset
10:38:05 artom But in theory it should happen when https://github.com/openstack/nova/blob/master/nova/virt/libvirt/driver.py#L4525-L4528
10:38:15 artom sean-k-mooney, the one in https://libvirt.org/formatdomain.html#elementsCPUAllocation
10:38:32 sean-k-mooney oh that should be the union of hte cores used for the vcpus
10:38:39 sean-k-mooney and should be updated
10:38:42 artom It only matters when an instance without a NUMA topology lands on a host with vcpu_pin
10:38:46 stephenfin alex_xu: You around today? I'm planning to work through the VPMEM series again, but is there any chance you could look at https://review.opendev.org/#/c/671800 ?
10:38:53 sean-k-mooney artom: yes
10:39:03 artom sean-k-mooney, right, so is that... a real thing?
10:39:10 artom We tell people to split them by aggregates
10:39:10 sean-k-mooney yes
10:39:17 stephenfin artom: wait for it
10:39:23 artom They don't?
10:39:29 sean-k-mooney you shoudl set vcpu_pin_set on all host ideally
10:39:37 stephenfin (sean-k-mooney is about to tell you that vcpu_pin_set has nothing to do with pinning and should always be set)
10:39:39 sean-k-mooney and it will be need for the new stuff stephenfin is working on
10:39:53 artom Haha
10:39:53 sean-k-mooney stephenfin: :)
10:40:18 openstackgerrit Gorka Eguileor proposed openstack/nova master: Use os-brick locking for volume attach and detach https://review.opendev.org/614190
10:40:19 stephenfin but yeah, vcpu_pin_set != pinning (or NUMA, for that matter)
10:40:24 stephenfin we use it for this stuff
10:40:36 sean-k-mooney its the set of core that the hypvervior may use for vms
10:40:41 stephenfin and also to decide how much VCPU inventory to report to placement
10:40:41 sean-k-mooney nothing more or less
10:41:05 sean-k-mooney yep its used for the inventory in the RT which is used for plamcent
10:41:22 stephenfin I don't agree with it being set by default, but yeah, it being set even when you don't have NUMA or pinning is a thing
10:41:25 artom OK, so it needs to be handled
10:41:30 stephenfin afraid so
10:41:38 sean-k-mooney stephenfin: you realise that for you vcpu work
10:41:51 sean-k-mooney we shoudl also be handelign shared and dedicated sets
10:42:03 artom sean-k-mooney, I'll most likely as you to test that bit when it's implemented
10:42:17 stephenfin sean-k-mooney: what do you mean?
10:42:18 artom Or if we can set it in the gate and show that working...
10:42:57 sean-k-mooney stephenfin: well for non pinned instance the cpuset will need to be updated based on the dest cpu_shared_set
10:43:24 sean-k-mooney and for pinned instnce it need to be updated based on the dedicated set
10:43:40 sean-k-mooney although the second half will be done by artoms exisitng code
10:44:07 stephenfin sean-k-mooney: Yeah, correct. That code has been updated here https://review.opendev.org/#/c/671800/28/nova/virt/libvirt/driver.py
10:44:42 openstackgerrit Luyao Zhong proposed openstack/nova master: object: Introduce Resource and ResourceList objs https://review.opendev.org/678448
10:44:43 openstackgerrit Luyao Zhong proposed openstack/nova master: Add resources dict into _Provider https://review.opendev.org/678449
10:44:43 openstackgerrit Luyao Zhong proposed openstack/nova master: Retrieve the allocations early https://review.opendev.org/678450
10:44:44 openstackgerrit Luyao Zhong proposed openstack/nova master: Claim resources in resource tracker https://review.opendev.org/678452
10:44:45 openstackgerrit Luyao Zhong proposed openstack/nova master: libvirt: Enable driver discovering PMEM namespaces https://review.opendev.org/678453
10:44:45 openstackgerrit Luyao Zhong proposed openstack/nova master: libvirt: report VPMEM resources by provider tree https://review.opendev.org/678454
10:44:46 openstackgerrit Luyao Zhong proposed openstack/nova master: libvirt: Support VM creation with vpmems and vpmems cleanup https://review.opendev.org/678455
10:44:46 openstackgerrit Luyao Zhong proposed openstack/nova master: Parse vpmem related flavor extra spec https://review.opendev.org/678456
10:44:47 openstackgerrit Luyao Zhong proposed openstack/nova master: libvirt: Enable driver configuring PMEM namespaces https://review.opendev.org/679640
10:44:47 openstackgerrit Luyao Zhong proposed openstack/nova master: Add functional tests for virtual persistent memory https://review.opendev.org/678470
10:44:48 openstackgerrit Luyao Zhong proposed openstack/nova master: doc: attaching virtual persistent memory to guests https://review.opendev.org/680300
10:46:22 sean-k-mooney by the way people know that cpuset in the vcpu element is funtionally the same as generatin vcpuin elemnt for each core pinning the core to the set of host core set in vcpu pin set
10:46:31 artom stephenfin, sean-k-mooney, actually, while we're on the topic, I thought you could get CPU pinning with https://libvirt.org/formatdomain.html#elementsCPUTuning without NUMA pinning with https://libvirt.org/formatdomain.html#elementsNUMATuning

Earlier   Later