Earlier  
Posted Nick Remark
#openstack-nova - 2022-08-03
13:38:30 opendevreview Balazs Gibizer proposed openstack/nova master: Unparent PciDeviceSpec from PciAddressSpec https://review.opendev.org/c/openstack/nova/+/844491
13:38:31 opendevreview Balazs Gibizer proposed openstack/nova master: Clean up mapping input to address spec types https://review.opendev.org/c/openstack/nova/+/845765
13:38:31 opendevreview Balazs Gibizer proposed openstack/nova master: Remove dead code from PhysicalPciAddress https://review.opendev.org/c/openstack/nova/+/844628
13:38:32 opendevreview Balazs Gibizer proposed openstack/nova master: Fix type annotation of pci.Whitelist class https://review.opendev.org/c/openstack/nova/+/845780
13:38:32 opendevreview Balazs Gibizer proposed openstack/nova master: Remove unused PF checking from get_function_by_ifname https://review.opendev.org/c/openstack/nova/+/845775
13:38:33 opendevreview Balazs Gibizer proposed openstack/nova master: Move __str__ to the PciAddressSpec base class https://review.opendev.org/c/openstack/nova/+/845781
13:39:39 gibi pheww rebased out the pci serieses from the merge conflict
14:41:25 opendevreview Balazs Gibizer proposed openstack/nova master: Do not mutate migration context for rollback_live_migration_at_destination https://review.opendev.org/c/openstack/nova/+/851832
14:41:25 opendevreview Balazs Gibizer proposed openstack/nova master: Reproducer for bug 1982497 https://review.opendev.org/c/openstack/nova/+/850672
14:41:26 opendevreview Balazs Gibizer proposed openstack/nova master: Prevent instance.save() under mutated migration context https://review.opendev.org/c/openstack/nova/+/850746
15:29:32 melwitt gibi: ack, will look
15:31:13 gibi thanks
15:51:19 sean-k-mooney[m] gibi are you going with dans suggetion to just remove all the save or proceeding with the decorator for now
15:51:31 sean-k-mooney[m] or both
15:51:50 sean-k-mooney[m] backport decorator adn then remove saves on master only?
15:51:53 gibi sean-k-mooney[m]: I proposed a decorator now and fixed the rebuild case by hand with apply and revert
15:52:22 sean-k-mooney[m] ok
15:52:34 gibi I feel that changing the contract between the compute manager and the virt drivers is a bit much for me for now
15:52:49 sean-k-mooney[m] ack
15:52:52 gibi the decorator will catch all the problematic cases
15:53:16 gibi and we have two of those one that is fixed by the bugfix and the other was as simple one with rebuild
15:53:20 sean-k-mooney[m] ill review tomorrow but i assume you are just logging the issue for now and not saving
15:53:29 gibi wait
15:53:38 gibi so for the rollback live migration
15:53:49 gibi I was able to remove the mutated migration context and keep the save
15:54:05 sean-k-mooney[m] ok
15:54:15 gibi the vpmem cleanup that needed the mutation contex can be done based on the domain and not based on the instance.resources storage
15:54:30 gibi this solves our current bug I believe
15:54:51 gibi the decorator is added in a followup to catch new cases by raising at save() if it is called under a mutated context
15:55:10 gibi and that revealed a second place where we do this, at rebuild
15:55:17 gibi but that was fairly simple to fix
15:56:49 sean-k-mooney[m] oh ok so you have resolved the current incorrect uses
15:56:55 gibi yes
15:56:55 sean-k-mooney[m] and new incorrect uses will raise
15:56:57 gibi yes
15:57:01 sean-k-mooney[m] so we wont merge it
15:57:03 sean-k-mooney[m] ok
15:57:19 sean-k-mooney[m] that a liit more context then im prepared to digest to review today
15:57:27 sean-k-mooney[m] but ill look back on this tomorrow
15:58:07 gibi ack
15:58:37 gibi artom and dansmith are also on it to keep me honest :)
15:58:49 dansmith yeah will try to look a bit later
15:59:46 sean-k-mooney[m] ok if dansmith and melwitt are able to review it i would prefer not to add another context switch to my current list
16:00:01 sean-k-mooney[m] but if this is urgent i can
16:01:55 gibi I don't think that it is super urgent
16:01:55 melwitt sean-k-mooney[m]: sure, I can look
16:03:14 gibi thank you all
16:37:54 frickler dansmith: melwitt: could you also have a look at https://review.opendev.org/c/openstack/nova/+/851909 pls? would be good to be able to have wider testing of latest sdk, currently this is blocking getting it into u-c
16:39:38 dansmith hmm, I guess that's needed because of when we talk to placement
16:42:15 dansmith frickler: +W
16:50:50 frickler thx
17:26:45 opendevreview Jan Hartkopf proposed openstack/nova master: add support for updating server's user_data https://review.opendev.org/c/openstack/nova/+/816157
17:44:34 opendevreview Merged openstack/placement master: Func test for os-traits and os-resource-classes lib sync https://review.opendev.org/c/openstack/placement/+/851966
17:44:38 opendevreview Merged openstack/nova master: Fix mocking SafeConnectedTestCase https://review.opendev.org/c/openstack/nova/+/851909
17:49:01 stephenfin gibi: Is that PCI series ready for review?
18:59:30 spatel does nova support sound adaptor ?
19:19:55 wolsen[m] gibi: bauzas: sorry I've been slow to respond on that patch set (the mdev devices libvirt 7.x one - https://review.opendev.org/c/openstack/nova/+/838976) - I 'm reading the backscroll now and see you commented that you need something for me. I'm jugging various things at the moment but will review feedback shortly
19:21:21 wolsen[m] looks like an update around the FUP patch that bauzas had posted
#openstack-nova - 2022-08-04
03:12:23 opendevreview OpenStack Proposal Bot proposed openstack/nova master: Imported Translations from Zanata https://review.opendev.org/c/openstack/nova/+/851337
06:56:21 opendevreview Brett Milford proposed openstack/nova master: Handle "no RAM info was set" migration case https://review.opendev.org/c/openstack/nova/+/852002
07:15:14 gibi stephenfin: re PCI series: I still had issues after the unittest.mock and double mocking change. But the content is ready up until https://review.opendev.org/c/openstack/nova/+/850546 . The rest top of that has TODOs in the commit message
07:15:57 gibi wolsen[m]: yes, I think only the FUP patch needs update the rest is OK to land
07:16:50 gibi stephenfin: I probably need to change the first patch in the series https://review.opendev.org/c/openstack/nova/+/844627 due to the double mocking stuff
07:26:39 ignazio Hello, I have very slow performances in live migration when instances using memory heavily (for example java application servers). I used converce mode in nova.conf and it does not seem to solve. If I migrate an instance with 8GB ram it takes more than 20 minutes. If I migrate again it takes few seconds. Do you think it is related to memory access ?
07:29:50 ignazio Any help, please ?
07:44:48 opendevreview ribaudr proposed openstack/nova master: [WIP] Attach Manila shares via virtiofs (db) https://review.opendev.org/c/openstack/nova/+/831193
07:44:49 opendevreview ribaudr proposed openstack/nova master: [WIP] Attach Manila shares via virtiofs (manila abstraction) https://review.opendev.org/c/openstack/nova/+/831194
07:44:49 opendevreview ribaudr proposed openstack/nova master: [WIP] Attach Manila shares via virtiofs (objects) https://review.opendev.org/c/openstack/nova/+/839401
07:44:50 opendevreview ribaudr proposed openstack/nova master: [WIP] Attach Manila shares via virtiofs (api) https://review.opendev.org/c/openstack/nova/+/836830
07:44:50 opendevreview ribaudr proposed openstack/nova master: [WIP] Attach Manila shares via virtiofs (drivers) https://review.opendev.org/c/openstack/nova/+/833090
07:44:51 opendevreview ribaudr proposed openstack/nova master: [WIP] Add metadata for shares https://review.opendev.org/c/openstack/nova/+/850500
07:44:51 opendevreview ribaudr proposed openstack/nova master: [WIP] Bump compute version and check shares support https://review.opendev.org/c/openstack/nova/+/850499
07:44:52 opendevreview ribaudr proposed openstack/nova master: [WIP] Add instance.share_detach notification https://review.opendev.org/c/openstack/nova/+/851028
07:44:52 opendevreview ribaudr proposed openstack/nova master: [WIP] Add instance.share_attach notification https://review.opendev.org/c/openstack/nova/+/850501
07:44:54 opendevreview ribaudr proposed openstack/nova master: [WIP] Add instance.power_on_error notification https://review.opendev.org/c/openstack/nova/+/852084
07:44:54 opendevreview ribaudr proposed openstack/nova master: [WIP] Add shares to InstancePayload https://review.opendev.org/c/openstack/nova/+/851029
07:44:56 opendevreview ribaudr proposed openstack/nova master: [WIP] Add libvirt test to ensure metadata are working. https://review.opendev.org/c/openstack/nova/+/852086
07:44:56 opendevreview ribaudr proposed openstack/nova master: [WIP] Add helper methods to attach/detach shares https://review.opendev.org/c/openstack/nova/+/852085
07:44:58 opendevreview ribaudr proposed openstack/nova master: Change microversion to 2.93 https://review.opendev.org/c/openstack/nova/+/852088
07:44:58 opendevreview ribaudr proposed openstack/nova master: [WIP] Add virt/libvirt error test cases https://review.opendev.org/c/openstack/nova/+/852087
07:46:04 gibi ignazio: if the workload in the guest continuously dirtying the memory on the source host then libvirt continously needs to retransmitt the dirtied memory pages to the dest.
07:46:33 gibi ignazio: you can try post-copy live migration
07:46:44 gibi https://docs.openstack.org/nova/pike/admin/live-migration-usage.html
07:46:54 gibi https://docs.openstack.org/nova/latest/admin/live-migration-usage.html
07:46:54 gibi ahh
07:47:35 ignazio gibi: I have already tries post-copy instead converge with the same results
07:47:41 gibi with post-copy the guest will be activated on the dest earlier in the process and libvirt will copy the memory from the inactive guest from the source
07:48:09 ignazio Do you think hugepage can help ?
07:48:37 ignazio I read page size flavor deafaul is 4k. Is true ?
07:49:05 gibi have you checked that the network used by libvirt for transferring the memory data has enough bandwidth?
07:49:28 gibi I'm not sure if hugepage will make a difference. yes the default small page on x86 is 4k
07:51:04 ignazio So, if I migrate an istance it spend a lot of time searching memory to migrate. When I migrate back it takes few seconds .
07:52:25 ignazio Probably after the first migration, the destination host reorganize the memory. I do not know very much the tlb mechanism
08:10:33 gibi moving back is an idependent process, there is no way to remember the past memeory content
08:23:01 ignazio <giby> the instance is using heavily the ram also on the first destination host after the first live migration. What I mean, because if I migrate again it takes few seconds ?
08:31:51 opendevreview Merged openstack/placement master: Clarify trait filtering in the API doc https://review.opendev.org/c/openstack/placement/+/825501
08:44:42 ignazio <gibi> I have 10Gbs bandwiths available
08:44:54 gibi I'm out of ideas :/ sorry
08:45:35 ignazio <gibi> thanks
09:22:52 gibi bauzas_away: o/

Earlier   Later