| Posted | Nick | Remark | |
|---|---|---|---|
| #openstack-nova - 2019-09-03 | |||
| 13:54:08 | donnyd | sean-k-mooney: How many OS do we want to support with NUMA? | |
| 13:54:17 | donnyd | ubuntu+centos | |
| 13:54:26 | artom | It's why there's a massive difference between my gross and net salary | |
| 13:54:35 | artom | But then there's a whole bunch of possible deductions after the fact | |
| 13:54:51 | artom | Registered retirement savings plans, daycare/school, etc etc | |
| 13:55:02 | artom | So they adjust at the end of the year | |
| 13:55:06 | artom | (well, April) | |
| 13:55:14 | sean-k-mooney | donnyd: ubunut is enough | |
| 13:55:18 | donnyd | kk | |
| 13:55:21 | sean-k-mooney | if you add centos thats fine too | |
| 13:55:27 | bauzas | artom: you wouldn't be surprised with our local tax filings then | |
| 13:55:50 | artom | bauzas, eh, I still think Quebec's is more complex | |
| 13:55:56 | sean-k-mooney | donnyd: we just need 1 flaovr on your end and we can create lables as we need them in project-config | |
| 13:56:06 | bauzas | artom: I personnally doubt that but okay | |
| 13:56:27 | artom | But... je fais mon bourgeois, I bring all the paperwork to an account, pay her some money, and if I pay her enough money, get some more money back from the govt after | |
| 13:56:59 | bauzas | yeah that's where US and Canadian folks are smarter than us | |
| 13:57:02 | sean-k-mooney | artom: ya we can file a p12 if we want to for that. but most things are handeled automatically | |
| 13:57:21 | bauzas | for us, we rather prefer to complain about how complicated our filings are | |
| 13:58:07 | artom | bauzas, speaking of complaining, I vividly remember a French woman in the local Ikea | |
| 13:58:19 | artom | You know that guttural sigh that you guys do? That "hhrrrrooooo" | |
| 13:58:26 | bauzas | and you don't imagine how much are forgetting to ask for a specific incentive they're allowed to | |
| 13:58:33 | artom | Dixit woman: "hrrroooo, qu'est ce c'est mal foutu" | |
| 13:58:40 | bauzas | LOL | |
| 13:59:04 | bhagyashris | mriedem: Hi, I would like your insights on https://review.opendev.org/#/c/612626/ | |
| 13:59:18 | bauzas | artom: I assume it's a very typical French person that's becoming rare : someone not living close to an Ikea store | |
| 13:59:36 | bauzas | I know those people exist, but I never met them yet | |
| 14:00:26 | luyao | efried: comments addressed for patch series https://review.opendev.org/#/q/topic:bp/virtual-persistent-memory+(status:open), thanks for reviewing | |
| 14:00:34 | bauzas | and I personnally consider my house as an Ikea showroom | |
| 14:02:24 | bauzas | stephenfin: not sure you saw my comment on https://review.opendev.org/#/c/679745/1 | |
| 14:02:45 | sean-k-mooney | efried: so as intersting as ^ is i take it you dont intend to run for PTL again or do you plan to serve for another term | |
| 14:05:10 | bauzas | there is still 24 hours left | |
| 14:05:15 | bauzas | -ish | |
| 14:05:30 | sean-k-mooney | artom: let me know when you push your local version so i can test. im still getting the same error with the same vcpu_pin_set on each host | |
| 14:05:36 | bauzas | oh dear no | |
| 14:05:38 | donnyd | https://www.irccloud.com/pastebin/nh6VDxYb/ | |
| 14:05:42 | bauzas | PTL Nominations Aug 27, 2019 23:45 UTC Sep 03, 2019 23:45 UTC | |
| 14:05:51 | sean-k-mooney | bauzas: there are like 9 hours left | |
| 14:05:55 | donnyd | https://www.irccloud.com/pastebin/1dwaNShp/ | |
| 14:05:57 | bauzas | well, we can afford a PTL designation | |
| 14:06:00 | donnyd | sean-k-mooney: ^^^ | |
| 14:06:09 | donnyd | LMK if those look right to you | |
| 14:06:24 | stephenfin | bauzas: I didn't, but looking at it now I don't think that's we should do that there | |
| 14:06:31 | sean-k-mooney | donnyd: yep they look fine | |
| 14:06:46 | stephenfin | That's a much bigger discussion that what that patch is trying to fix (namely, making sure it's enabled for all the libvirt functional tests) | |
| 14:06:57 | donnyd | project config stuff will be up in a minute | |
| 14:07:16 | bauzas | stephenfin: I don't disagree, I'm just saying that enabling NUMATopologyFilter on *all* libvirt tests is a massive hammer with little justification | |
| 14:07:42 | sean-k-mooney | donnyd: cool ping me when you push it. | |
| 14:07:58 | bauzas | stephenfin: so, honestly, that's why the question is more widely like : if we go with enabling the filter for all tests, then why not enabling it by default ? | |
| 14:08:12 | sean-k-mooney | donnyd: i can proably make the job work on the smaller memory node too or use one of each | |
| 14:08:17 | bauzas | and I know this is a debatable question :) | |
| 14:08:24 | stephenfin | bauzas: It's already enabled for all but two of them, are it _should_ be enabled for one of those two | |
| 14:08:46 | dansmith | artom: so the multi-numa nfv thing is running live migrations with your patches yeah? | |
| 14:08:48 | efried | sean-k-mooney: I haven't decided yet. | |
| 14:09:14 | cdent | dansmith for ptl! | |
| 14:09:14 | sean-k-mooney | dansmith: yes im using depens on to pull in his patches | |
| 14:09:27 | stephenfin | It was enabled for all these tests in test_pci_sriov_servers.py and test_numa_servers.py. It should have been enabled for test_rt_servers.py. The only other one is test_reshape.py. I can disable it for that one, if you'd like? | |
| 14:09:42 | sean-k-mooney | dansmith: if you use depends-on in the same repo it create a merge commit assumeing there is not merge conflcits and runs on that | |
| 14:09:48 | stephenfin | or set it explicitly on the other three. Either one is good with me | |
| 14:09:49 | bauzas | stephenfin: uh | |
| 14:09:51 | dansmith | sean-k-mooney: yeah, I see that's mechanically true, but ... you guys have gone through and seen that it's working? | |
| 14:09:53 | openstackgerrit | Artom Lifshitz proposed openstack/nova master: LM: Use Claims to update numa-related XML on the source https://review.opendev.org/635229 | |
| 14:09:54 | openstackgerrit | Artom Lifshitz proposed openstack/nova master: NUMA live migration support https://review.opendev.org/634606 | |
| 14:09:54 | openstackgerrit | Artom Lifshitz proposed openstack/nova master: Deprecate CONF.workarounds.enable_numa_live_migration https://review.opendev.org/640021 | |
| 14:09:55 | openstackgerrit | Artom Lifshitz proposed openstack/nova master: Functional tests for NUMA live migration https://review.opendev.org/672595 | |
| 14:10:00 | sean-k-mooney | dansmith: yes | |
| 14:10:01 | artom | sean-k-mooney, ^^ | |
| 14:10:11 | sean-k-mooney | i have used it in the past | |
| 14:10:17 | artom | dansmith, yeah, huge props to sean-k-mooney for getting it set up (and donnyd's hardware!) | |
| 14:10:23 | dansmith | artom: does it look like it's all working? | |
| 14:10:23 | donnyd | https://review.opendev.org/679789 | |
| 14:10:35 | donnyd | I don't think I forgot anything | |
| 14:10:39 | sean-k-mooney | dansmith: hugepages are not fully working yet | |
| 14:10:44 | artom | dansmith, needs to run against the latest PSes, as it found issues with hugepages | |
| 14:10:50 | dansmith | artom: okay cool | |
| 14:11:11 | bauzas | stephenfin: honestly, dunno what to say | |
| 14:11:51 | bauzas | stephenfin: maybe just add a little more explanation in the commit msg and then I'll consider having the option set for all libvirt tests to be good enough | |
| 14:12:02 | sean-k-mooney | artom: does that patch have the fixes for hugepages. ill test it locally while we wait for ci | |
| 14:12:32 | donnyd | cdent: which part of FN do you think is faster. I know disk access should be in orders of magnitude faster from local NVME (in raid0) | |
| 14:13:01 | sean-k-mooney | damb raid0 i guess for ci it makes sense | |
| 14:13:02 | stephenfin | bauzas: Sure, lemme do that | |
| 14:13:19 | stephenfin | efried: yo, any chance you could sign these off for me? https://review.opendev.org/#/c/678902 https://review.opendev.org/#/c/678861 ? | |
| 14:13:24 | donnyd | sean-k-mooney: yea if something fails.. it just restarts the job on another hypervisor | |
| 14:13:34 | donnyd | so speed is the name of the game for CI... | |
| 14:13:40 | cdent | donnyd: it does seem like it mostly related to disk speed. Where I see it the most is: a) getting log files from the swift hosted on FN, b) the placement performance are consistently faster there | |
| 14:13:40 | sean-k-mooney | donnyd: devstack is hugely io bound | |
| 14:13:55 | efried | stephenfin: looking | |
| 14:14:07 | stephenfin | bauzas: Need any help with https://review.opendev.org/#/c/678902, btw? That's probably the trickiest patch of the series | |
| 14:14:17 | donnyd | I would never do that for prod things - but for CI.. go as fast as possible is where I went with it | |
| 14:14:37 | sean-k-mooney | donnyd: well ci is kind of prod. | |
| 14:14:42 | stephenfin | Well, it looks tricky cos it's big. It's not really though | |
| 14:14:53 | sean-k-mooney | donnyd: but i have no issue with raid0 as long as you dont put your database on it | |
| 14:15:00 | bauzas | stephenfin: not sure I understand your question ? Why should I need help on something I reviewed ? | |
| 14:15:05 | luyao | dansmith: Could you look at https://review.opendev.org/#/c/678448/9 and https://review.opendev.org/#/c/678447/https://review.opendev.org/635229. Thanks. | |
| 14:15:12 | donnyd | sean-k-mooney: but if I lose something its not like losing a customers long running instance I can't get back | |
| 14:15:22 | stephenfin | bauzas: Damn, I meant https://review.opendev.org/#/c/671800/ | |
| 14:15:24 | sean-k-mooney | donnyd: ya that is ture | |
| 14:15:47 | donnyd | umm.. no.. the controller is setup a little bit more robust | |
| 14:15:52 | sean-k-mooney | donnyd: the could model however is to keep data in sepereate data volumes that are attached to a stateles instance. | |
| 14:16:02 | bauzas | stephenfin: oh this one is too hairy for now, I'll look at it tomorrow morning :) | |
| 14:16:05 | stephenfin | If you modify the address bar in Firefox, it doesn't change as you navigate pages until you refresh the page | |