Friday, 2025-10-03

*** mtreinish_ is now known as mtreinish00:22
*** mhen_ is now known as mhen01:09
noonedeadpunksean-k-mooney: Uggla fwiw, I also have an implementation for parallel live migrations as well: https://review.opendev.org/c/openstack/nova/+/95578407:02
noonedeadpunkand yeah, I missed the specless one when was working on it :(07:03
bauzassounds to me a good PTG discussion anyway :)07:05
bauzasit looks like we have a momentum, it would be sad to not having anything for Gazpacho :)07:05
noonedeadpunkand regarding iothreads - I think I have yet another thing to add. or well. there is a specless blueprint already, and I have minimal implementation07:06
noonedeadpunkyeah, totally sounds like a good topic for the PTG07:06
Ugglanoonedeadpunk That's a bit sad, to have competing proposal. Anyway yes I agree let's discuss that at PTG.07:06
noonedeadpunkUggla: they are *exactly* the same07:07
noonedeadpunkso nothing sad I guess07:07
bauzasoh yeah, that just means this should be a good and important effort for this cycle :)07:08
noonedeadpunkI even come up with exactly same config name07:08
noonedeadpunkwithout seeing yours07:09
bauzasdo you read minds ? don't reply, I'm afraid of the answer07:09
Ugglasad because we have to choose one and for one of you, it is a "waste" of time.07:09
bauzaswere the competing blueprints both accepted ?07:09
noonedeadpunkneither was so far07:10
noonedeadpunkand one blueprint is specless07:10
noonedeadpunkanother has a spec07:10
bauzasif not, that's understandable that two different people can start working on a same feature, while nothing is communicated07:10
noonedeadpunkand given implementation is the same, I don;'t think much time was wasted07:10
noonedeadpunkbtw07:10
noonedeadpunkauthor of https://blueprints.launchpad.net/nova/+spec/libvirt-migrate-parallel voted positively on my implementation :)07:11
bauzasthat's cool07:11
noonedeadpunkSo they are at least aware of this07:11
noonedeadpunkbut regarding iothreads, I think I have one more thing to add on top of https://review.opendev.org/c/openstack/nova-specs/+/938823 and https://review.opendev.org/c/openstack/nova-specs/+/95163607:14
noonedeadpunkor well. let's discuss on PTG :D07:15
bauzasnot sure I understand the relationship between io threads and network IDs, but that's probably related to some network IO concern. Anyway, let's wrap that for the PTG07:15
noonedeadpunkif you get into umbrella of "improving guest performance and enable threading capabilities exposed by libvirt" - they are07:16
noonedeadpunkbut yeah07:16
noonedeadpunkit can be all formulated as one point in cycle-highlights :)07:16
bauzasglancing at https://review.opendev.org/c/openstack/nova-specs/+/938823/4/specs/2025.2/approved/network-id-query.rst, this was apparently a Nova API performance change, not something related to libvirt07:17
bauzasbut I can be wrong07:17
noonedeadpunkoh, I get the wrong spec then07:17
Ugglanoonedeadpunk, add this point (// live migration) the ptg agenda ? If not already done.07:20
noonedeadpunkdo you have a specific etherpad for PTG already?07:20
Ugglayes07:20
noonedeadpunkoph, it's in channel; topic07:21
Ugglanot updated yet in the channel07:21
Ugglahttps://etherpad.opendev.org/p/nova-2026.1-ptg07:21
noonedeadpunkok, and replacing 2025.2 with 2026.1 gives the new one07:21
*** ChanServ sets mode: +o Uggla07:26
noonedeadpunkdone, thanks!07:27
*** ChanServ changes topic to "This channel is for Nova development | development-planning: https://etherpad.opendev.org/p/nova-2026.1-status | this channel is logged at https://meetings.opendev.org/irclogs/%23openstack-nova/"07:29
*** ChanServ changes topic to "This channel is for Nova development | development-planning: https://etherpad.opendev.org/p/nova-2026.1-ptg | this channel is logged at https://meetings.opendev.org/irclogs/%23openstack-nova/"07:30
*** ChanServ sets mode: -o Uggla07:31
* Uggla open https://launchpad.net/nova/2026.109:28
opendevreviewBalazs Gibizer proposed openstack/placement master: Remove excessive logging from GET a_c  https://review.opendev.org/c/openstack/placement/+/96277509:39
opendevreviewBalazs Gibizer proposed openstack/placement master: Reproduce GET a_c slowness  https://review.opendev.org/c/openstack/placement/+/96259609:39
opendevreviewBalazs Gibizer proposed openstack/placement master: Prune search space with invalid prefixes  https://review.opendev.org/c/openstack/placement/+/96277609:39
gibisean-k-mooney: bauzas: I moved https://review.opendev.org/c/openstack/placement/+/962775 to the front of the bugfix series as it can land already while I'm cleaning up the rest. So if you have time I appreciate a review there09:40
bauzasgibi: I can try to look at it this afternoon09:42
bauzasI don't have a lot of context but I'll try to find it :)09:42
gibithat patch removes two debug logs that is it09:42
gibi:)09:42
gibithose debug logs generated gigabyte of logs 09:42
* bauzas needs to prepare himself for the gym in 10 mins09:42
gibiin certain queries09:42
bauzasahah I see, then hopefully it should be simple to review :)09:43
gibiit is :)09:43
gibithe rest is a lot more complex and not ready for final review09:43
* Uggla clean series and open https://launchpad.net/placement/2026.1 for placement09:44
bauzasyup, saw it 09:45
bauzas+2d09:45
gibithanks09:45
gibihave a nice session in the gym09:45
Ugglaping sean-k-mooney about https://launchpad.net/nova/2026.109:45
bauzaswell, it will be outside :)09:45
bauzasmore a cardio session than a gym 09:45
sean-k-mooney[m]Uggla:  that looks correct as do the status of the other serise +109:48
opendevreviewBalazs Gibizer proposed openstack/placement master: Reproduce GET a_c slowness bug/2126751  https://review.opendev.org/c/openstack/placement/+/96259610:05
opendevreviewBalazs Gibizer proposed openstack/placement master: Prune search space by invalid prefixes  https://review.opendev.org/c/openstack/placement/+/96277610:05
opendevreviewBalazs Gibizer proposed openstack/placement master: Prune search space by invalid prefixes  https://review.opendev.org/c/openstack/placement/+/96277610:13
sean-k-mooneybauzas: the only releationship is the same person was proposing both specs10:30
sean-k-mooneybauzas: masahito was interested in implente iothread, mapping io queue to iothread adnfilterign service by network in the last ptg10:31
sean-k-mooneymy io thread spec focuse just on the the simplest useful implemeation of iothread basicly spliting it out form the ioqueue work so it can be delivered independtly and incrementally10:32
sean-k-mooneybauzas: im hoping masahito or noonedeadpunk or anyone else who is interested will have time to work on some of these prosposals this cycle10:33
sean-k-mooneyif not i will proably try to impelment one of the propsosal but i woudl prefe to just help them by reviewing there work10:34
sean-k-mooneyi do think thses woudl be good enachnmemnt however so if there isnt a comunity effort to move them forward ill see if i can help more directly10:34
noonedeadpunkyeah, I think I should be able to pull couple of them11:12
opendevreviewMerged openstack/python-novaclient master: Use pre-commit for lint jobs  https://review.opendev.org/c/openstack/python-novaclient/+/95298713:01
opendevreviewMerged openstack/python-novaclient master: tests: Remove use of ddt  https://review.opendev.org/c/openstack/python-novaclient/+/95319313:10
opendevreviewIan Watson proposed openstack/nova master: Changing how placement updates are triggered in RT  https://review.opendev.org/c/openstack/nova/+/95568713:35
opendevreviewBalazs Gibizer proposed openstack/placement master: Prune a_c search space by invalid prefixes  https://review.opendev.org/c/openstack/placement/+/96277614:59
gibisean-k-mooney[m]: dansmith: ^^ now with a long commit message and a workaround flag15:00
sean-k-mooneygibi: so you runign with 21 because well that is what the bug report used. have you tried bumping to 32 PFs15:03
sean-k-mooneygibi: basiclly im wondering how much headroom this is geting us15:03
sean-k-mooney7 seconds for the 21_21 case is not bad 15:04
ratailorsean-k-mooney, gibi elodilles could you please review https://review.opendev.org/q/I04f6e1ba3eff443d40a13c6fe2d0b77a78a020e615:04
sean-k-mooneymuch better thne before you started im juust wonderign if it will explode at say 24_24 or can we push to 32+15:04
gibisean-k-mooney: yeah 21 is the magic number from the customer. I can add more cases.15:06
gibiplease leave a comment in the review so I won't forget15:06
sean-k-mooneya standard 2U server can typicaly hold 24 2.5" ssd's in the front which woould also need 96 pci lanes to support at full speed. given many chips top out at 96-128 lanes with some going ot the low 160s range 32 device is proably close to the max we woudl expct to see15:06
sean-k-mooneysure i can im ok with the current test uing the reproted worse case i just was wondering if you had playied aroudn with it15:07
sean-k-mooneyill pull it locally and try it15:07
sean-k-mooneybut ya 120+ second ot 6.9 is a very nice impovement15:08
gibisean-k-mooney: if it is two slow for 32/32 then try to decrease the max alocation candidates from 1000 to smaller15:08
gibis/two/too/15:08
sean-k-mooneybut 120+ to less then one in the non worse case is very promising15:08
gibiI have drop for the weekend in minutes so I won't be able to test it myself today15:09
sean-k-mooneygibi: oh ya that a good poitn if we can provide soem guiance on tuning the values for larger systems than that at least a workaroudn15:09
gibibtw up until 8/8 I tested the logic in devstack as well and the numbers are pretty similar15:09
sean-k-mooneycool ya i was ment to finish an hour ago so ill loop back to this on monday15:09
sean-k-mooneygibi: enjoy your weekend15:09
gibicool thanks15:10
gibisame to you15:10
opendevreviewNisha Brahmankar proposed openstack/nova master: Add graceful shutdown feature for nova-compute  https://review.opendev.org/c/openstack/nova/+/96297515:35
tkajinamI wonder if anyone disagrees with closing all xen related bugs by setting their status to Won't fix ?15:42
sean-k-mooneywell we deleted the driver and the libvirt xen suspprot a few years ago at this point15:44
sean-k-mooneyso i dont see why we woudl not set it to wont fix at this point or invlaid15:45
nisha04Hi nova core members,16:02
nisha04This is Nisha from LY Corporation, Japan. We got a green signal in the nova PTG 2025.2 to implement the graceful shutdown feature for nova-compute.  (https://etherpad.opendev.org/p/nova-2025.2-ptg#L1088) 16:02
nisha04We have the basic PoC code ready here: https://review.opendev.org/c/openstack/nova/+/96297516:02
nisha04I want to discuss the design choices and spec requirements. I will be attending the OpenInfra Summit in Paris this month. It would be great if we could discuss them in person during the summit. Are you attending the summit? If so, could you share preferable slots, if any, for a discussion.16:02
sean-k-mooneynisha04: some of the core will be tere i belive Uggla stephenfin and bauzas are trvelign/have talks16:14
sean-k-mooneyin general the full core team will not but there shoudl be an opteruntiy to have some level of dicusssion the PTG  is the week after as well so there is also that operunity16:14
nisha04sean-k-mooney: Thanks for the info. I just wanted to have a quick discussion and receive informal feedback. I will try to contact Uggla stephenfin and bauzas if they have any available time slot.16:20
Uggla@nisha04 I think we could find a slot at the OpenInfra Summit to do some kind of pre-check.16:20
UgglaBut I’d also like to have this as a topic at the PTG, since I know @gibi will be available and deeply involved.16:20
UgglaI can try to accommodate the timeslot as much as possible with your timezone.16:20
sean-k-mooneynisha04: bauzas is doing a contibuting to nova talk16:21
sean-k-mooneyi.e. how to contibute so you might be able to find them in the halway after16:21
sean-k-mooneybut ya ptg dicussion after woudl be good to allow all to partipate16:21
UgglaI'll be there too.16:22
nisha04Thanks a lot! I definitely want to bring this topic in the PTG for collective feedback since we are actively working on it now.16:24
nisha04I will also try to find you in the hallway during the summit and hope to have a quick chat sometime.16:24
Ugglanisha04, pretty sure we will find a slot to discuss.16:30
opendevreviewMerged openstack/placement master: Remove excessive logging from GET a_c  https://review.opendev.org/c/openstack/placement/+/96277517:28
dansmithmelwitt: finally got my devstack unfscked.. but now I've deployed without barbican18:33
dansmithI have several things commented out in my local.conf... is enable_service barbican enough or do I need more?18:33
opendevreviewsean mooney proposed openstack/placement master: [WIP] Fix copy_arr_if_needed() and add observability  https://review.opendev.org/c/openstack/placement/+/96300618:49
opendevreviewsean mooney proposed openstack/placement master: [WIP] Fix copy_arr_if_needed() and add observability  https://review.opendev.org/c/openstack/placement/+/96300618:53

Generated by irclog2html.py 4.0.0 by Marius Gedminas - find it at https://mg.pov.lt/irclog2html/!