Earlier  
Later
New Search
Posted Nick Remark
#openstack-nova - 2018-11-07
17:32:25 dansmith you're talking about host caps in that case right? not how a guest's topo gets determined (by nova) but how libvirt reports the host topo?
17:32:49 tssurya yea the host caps (I think)
17:32:52 sean-k-mooney tssurya: if you talking about the guest topology the answer is dumbly
17:33:25 tssurya basically we had a live migration failure because the cpu_info didn't match
17:33:54 dansmith there are lots of reasons for that being possible, topo is one and flags being another
17:34:06 tssurya which we started investigating and reached the topo part
17:37:57 sean-k-mooney tssurya: so ya as dansmith mentioned libvirt gets this info from sysfs which the bios/uefi proved to the kernel based on probing the cpu. the kenrel can re probe this info if it really needs to but libvirt is just taking whatever the kernel provides
17:38:34 tssurya oh okay
17:39:07 sean-k-mooney tssurya: the toplogy info is here ls /sys/bus/cpu/devices/cpu0/topology/
17:39:13 sean-k-mooney the cpu flags are up one level
17:39:51 dansmith sean-k-mooney: live migration failing because of topology would only be if you're using pinned cpus and those cpus don't exist on the remote side right
17:39:52 dansmith ?
17:39:55 tssurya thanks, looking
17:40:15 sean-k-mooney dansmith: yes
17:40:51 tssurya yea we have something like 48 cores source out of which 24 are offline and 24 on destination, but the 24 offline is not reflected or something
17:40:53 openstackgerrit Jack Ding proposed openstack/nova master: Add HPET timer support for x86 guests https://review.openstack.org/605902
17:41:01 tssurya not sure if that makes sense
17:41:36 sean-k-mooney tssurya: have you excluded the offline cpus form the vcpu_pin_set
17:42:17 sean-k-mooney tssurya: use because they are offline does not mean they will not be in sys / virsh capablities
17:42:51 sean-k-mooney tssurya: but ya as dan said topology will only come into it if the cpus you were pinned too on the source are not present on the dest
17:43:14 sean-k-mooney tssurya: if they are present it could still be incorrect to do the migration but that is a sperate issue
18:05:53 cfriesen tssurya: as I'm sure you're aware, live migration with CPU pinning is currently broken. :)
18:06:50 tssurya sean-k-mooney: how do I exclude offline cpus from vcpu_pin_set (sorry I am a totally beginner in this stuff)
18:06:58 tssurya cfriesen: actually I wasn't :)
18:07:03 tssurya thanks for telling me
18:08:07 tssurya sean-k-mooney: because we were looking through the libvirt code and like you said it seems to be looping through all the cores even if they are offline
18:08:32 cfriesen tssurya: technically it's never been reliable. it will try to keep the same topology and host cpus on the dest node, even if those cpus/numa-nodes don't exist or are already in use by other instances.
18:09:40 cfriesen tssurya: there's work in progress to fix it finally by recalculating the resources on the dest as part of the live migration, so that might land in stein
18:10:16 tssurya cfriesen: ah good to know
18:25:12 openstackgerrit sean mooney proposed openstack/nova master: harden placement init under wsgi https://review.openstack.org/610034
18:25:31 sean-k-mooney gibi: ^ should have the exception behavior you wanted
18:29:28 sean-k-mooney gibi: the run_once contract is now expcitly stated too. the contract is different then i had planned but it will still work for my usecase and hopefully you find it more intuititve
18:34:05 cdent edleafe: if you get a chance to cast your eye on https://review.openstack.org/#/c/603955/ (cyborg interaction spec) I think it could do with it. The API bits need some stronger review and I've run out of time and I believe you've got some state on the cyborg stuff?
18:36:35 sean-k-mooney cdent: do you think the spec is close
18:37:17 sean-k-mooney cdent: i spend a lot of time going through it in detail initilly but i have not had time to go through the spec end to end in several interations
18:40:45 cdent sean-k-mooney: it's hard to say. a lot of the details are kind of lost on me. When I previously reveiwed it was mostly to look at the shape of the API, which I found a bit off (which is why I've asked edleafe to look as a fellow api-sig person).
18:42:21 edleafe cdent: It's on my plate. I've had the same experience as sean-k-mooney - it's hard to get through the entire thing
18:42:54 sean-k-mooney cdent: i have had similar feeling. i have tried to blance the "is the cyborg api correct" comments with is the workflow and datastuctre used correct in terms of the nova interaction
18:44:08 sean-k-mooney edleafe: there is still alot going on for a single spec but some of that context/complexity is unaviodable unfortunetly
18:44:24 edleafe sean-k-mooney: agreed
18:48:53 artom mriedem, oh hai, could you hit https://review.openstack.org/#/c/587248/1 and the one on top when you get a chance? It's the pike backport of a thing you +2'ed in queens
18:56:32 mriedem ok
19:00:19 mriedem done
19:12:21 artom Cheers!
19:27:12 mriedem super critical bug that needs fixing asap https://bugs.launchpad.net/nova/+bug/1802167
19:27:12 openstack Launchpad bug 1802167 in OpenStack Compute (nova) "nova-manage db purge -h has weird help for --before option" [Low,Triaged]
19:27:44 artom oh shiite im on that
19:27:59 sean-k-mooney artom: feels more like a stephenfin thing :)
19:29:10 mriedem let's not get stephen started on the cliff thing again
19:29:29 openstackgerrit Jack Ding proposed openstack/nova master: Add HPET timer support for x86 guests https://review.openstack.org/605902
19:29:33 mriedem or clint or clive or whatever manly naming library it is
19:30:17 mriedem efried_rollin: you can drop the -2 on https://review.openstack.org/#/c/605902/ - the hpet blueprint was approved
19:30:22 sean-k-mooney haha didnt he end up porting the stuff he wanted form the one we are not useing to the one we are upstream in the end
19:30:48 mriedem jackding: make sure to throw that in the runways queue when it's ready
19:31:04 mriedem runways reviews are just burning down the house right now
19:37:21 openstackgerrit sean mooney proposed openstack/os-vif master: always create ovs port during plug https://review.openstack.org/602384
19:37:22 openstackgerrit sean mooney proposed openstack/os-vif master: add isolate_vif config option https://review.openstack.org/612534
19:42:15 openstackgerrit sean mooney proposed openstack/os-vif stable/rocky: always create ovs port during plug https://review.openstack.org/609850
19:45:23 jackding mriedem: sure
19:49:10 artom mriedem, keith. I want novaclient to use python-keith
19:50:29 mriedem i had a shift manager at my part time high school job named keith,
19:50:39 mriedem oakleys, jorts, nascar shirts, tight mullet
19:50:41 mriedem that was a man
19:57:10 openstackgerrit sean mooney proposed openstack/os-vif stable/rocky: add isolate_vif config option https://review.openstack.org/616285
20:00:40 openstackgerrit sean mooney proposed openstack/os-vif stable/queens: always create ovs port during plug https://review.openstack.org/609851
20:17:45 efried_rollin mriedem_afk: done
20:33:13 efried mriedem_afk: That nova-next thing worked this time. And the job passed, but as expected, no significant difference in the size of the placement log.
22:19:09 openstackgerrit Merged openstack/nova stable/pike: Refactor _build_device_metadata https://review.openstack.org/587248
22:19:15 openstackgerrit Merged openstack/nova stable/pike: Consider hostdev devices when building metadata https://review.openstack.org/587249
22:31:29 openstackgerrit Merged openstack/nova master: Allow resource_provider_association_refresh=0 https://review.openstack.org/615606
22:38:52 openstackgerrit Merged openstack/nova master: Remove LazyLoad of Scheduler Clients https://review.openstack.org/615641
22:45:48 efried melwitt: That fixture merged. Are you going to propose a release or you want me to do it?
22:46:41 efried melwitt: Never mind, it seems to have already been done.
23:57:00 vishwana_ Hi, I was wondering if a single VM instance can have multiple interfaces from a single subnet? If yes, how would I enable it? Thanks in advance for your guidance
#openstack-nova - 2018-11-08
03:05:15 openstackgerrit Fan Zhang proposed openstack/nova master: Retry after hitting libvirt error VIR_ERR_OPERATION_INVALID in live migration. https://review.openstack.org/612272
04:20:05 openstackgerrit Merged openstack/nova master: Improve formats of the Compute API guide https://review.openstack.org/615809
08:03:44 openstackgerrit liuyamin proposed openstack/nova master: Fix version details API does not return 200 OK https://review.openstack.org/616444
08:34:27 openstackgerrit Balazs Gibizer proposed openstack/nova master: Test boot with more ports with bandwidth request https://review.openstack.org/573317
08:40:33 openstackgerrit Takashi NATSUME proposed openstack/nova master: Add API ref guideline for body text https://review.openstack.org/605628
08:40:41 openstackgerrit Takashi NATSUME proposed openstack/nova master: Add API ref guideline for body text https://review.openstack.org/605628
08:50:40 openstackgerrit Jeffrey Zhang proposed openstack/nova master: Add feature to flatten the volume from glance image snapshort https://review.openstack.org/616461
09:06:23 openstackgerrit Jeffrey Zhang proposed openstack/nova master: Add feature to flatten the volume from glance image snapshort https://review.openstack.org/616461
09:58:54 openstackgerrit Balazs Gibizer proposed openstack/nova master: Add extra unit test coverage for @run_once https://review.openstack.org/616485
10:01:05 gibi sean-k-mooney: I left some comments in https://review.openstack.org/#/c/610034 and proposed a followup ^^
10:35:59 openstackgerrit Balazs Gibizer proposed openstack/nova master: Send rp_uuid in the port binding https://review.openstack.org/569459
10:36:00 openstackgerrit Balazs Gibizer proposed openstack/nova master: Test boot with more ports with bandwidth request https://review.openstack.org/573317
11:56:20 sean-k-mooney gibi: hi
11:56:38 gibi sean-k-mooney: hi
11:56:58 sean-k-mooney i was under the impression that try finally was not legal in python but reading the reference docs on the try statement i apears to be
11:57:08 sean-k-mooney i can remove teh except blocks
11:57:28 gibi sean-k-mooney: yeah, try:finally: without except is totally valid
11:57:48 gibi sean-k-mooney: also if you want, you can squash my followup into your patch
11:58:29 sean-k-mooney i was just going to ask if i could add you as a co-author and do that to reduce the number of patches i need to backport
11:59:07 gibi sean-k-mooney: sure, that totally works for me
12:01:16 sean-k-mooney thanks ill make those change and resubmit once i finish makeing a cup of coffee. im alway happy to learn new things and til try finally is ok in python :)
12:11:39 gibi sean-k-mooney: :)
12:33:15 openstackgerrit sean mooney proposed openstack/nova master: Harden placement init under wsgi https://review.openstack.org/610034
13:13:58 sean-k-mooney gibi: i have cross ported the squashed patch to placement. can you abandon https://review.openstack.org/#/c/616485 when you get a chance
13:19:43 sean-k-mooney bauzas: if you have time today can you rereview https://review.openstack.org/#/c/610034/ i adressed your feedback for extra comments + some other nits. i would like to try and get this merged today if possible so i can backport it before everyone goes to the summit
13:25:05 bauzas sean-k-mooney: I can try :)

Earlier   Later