| Posted | Nick | Remark | |
|---|---|---|---|
| #openstack-nova - 2017-10-17 | |||
| 18:57:20 | sean-k-mooney | gregwork: ah you dont have hugepages requested for the vm | |
| 18:58:12 | sdague | mriedem: done. I was a little surprised you wanted some of those back to newton, but that's fine | |
| 18:58:35 | gregwork | sean-k-mooney: have you seen that error before ? | |
| 18:58:42 | gregwork | the one i posted in the pastebin | |
| 18:58:49 | mriedem | sdague: the bfv one was needed for another thing someone was reporting in newton but w/o better debug couldn't be determined | |
| 18:59:23 | gregwork | sean-k-mooney: im using the mellanox rhosp11 plugin which has configured ofed on my nodes and we are pushing a nutron dpdk config | |
| 18:59:23 | sdague | mriedem: ok | |
| 18:59:48 | gregwork | sean-k-mooney: the deploy works great, but when i spawn instances i get that error in qemu-kvm on the compute node | |
| 19:00:03 | gregwork | sean-k-mooney: networking doesnt appear to be working (most likely due to that error) | |
| 19:00:14 | gregwork | vm boots and all but is an island | |
| 19:00:15 | sean-k-mooney | gregwork: the one you posted is indicating that the guest memory is not backed by file descriptor backed memory that is mapped shared | |
| 19:00:26 | gregwork | sean-k-mooney: yar | |
| 19:01:26 | sean-k-mooney | vhost user requires file decriptor backed shared memeory that is preallocated and locked to work | |
| 19:01:51 | sean-k-mooney | in ocata that means the guest must use hugepage backed memory or it will boot but have no networking | |
| 19:02:17 | gregwork | what am i missing from a flavor pov? im reading about some keys i need to set | |
| 19:02:47 | sean-k-mooney | yes you need to add hw:mem_page_size=large | |
| 19:03:12 | mriedem | gregwork: https://docs.openstack.org/nova/pike/admin/huge-pages.html | |
| 19:04:17 | dansmith | efried: I assume you're good with this since you pushed the latest edit? https://review.openstack.org/#/c/470575 | |
| 19:04:30 | dansmith | efried: no +1 so just wanted to make sure before I sent it to oblivio | |
| 19:04:33 | dansmith | *oblivion | |
| 19:04:45 | efried | dansmith oblivio away | |
| 19:04:56 | dansmith | efried: are you going to rebase the rest? | |
| 19:05:16 | efried | I could, if they need it. Do they need it? | |
| 19:05:21 | sean-k-mooney | mriedem: sfinucan wrote a section about vhost-user/dpdk also in the docs im trying to find that | |
| 19:05:22 | dansmith | I think so | |
| 19:05:27 | efried | ight. | |
| 19:05:31 | dansmith | efried: I think your edit(s) orphaned them | |
| 19:05:42 | openstackgerrit | Eric Fried proposed openstack/nova master: Send Allocations to spawn https://review.openstack.org/511879 | |
| 19:05:49 | efried | dansmith On it. Meanwhile ^ | |
| 19:06:14 | dansmith | efried: no, meanwhile lunch | |
| 19:06:21 | mriedem | sean-k-mooney: probably in the networking guide | |
| 19:06:24 | efried | dansmith Enjoy | |
| 19:06:56 | mriedem | https://docs.openstack.org/ocata/networking-guide/config-ovs-dpdk.html | |
| 19:07:43 | openstackgerrit | Eric Fried proposed openstack/nova master: placement: add nested resource providers https://review.openstack.org/377138 | |
| 19:07:43 | openstackgerrit | Eric Fried proposed openstack/nova master: placement: integrate ProviderTree to report client https://review.openstack.org/415921 | |
| 19:07:44 | openstackgerrit | Eric Fried proposed openstack/nova master: placement: adds REST API for nested providers https://review.openstack.org/384807 | |
| 19:07:44 | openstackgerrit | Eric Fried proposed openstack/nova master: placement: allow filter providers in tree https://review.openstack.org/377215 | |
| 19:07:45 | openstackgerrit | Eric Fried proposed openstack/nova master: placement: update client to set parent provider https://review.openstack.org/385693 | |
| 19:08:09 | efried | dansmith Done ^ | |
| 19:08:39 | sean-k-mooney | mriedem: gregwork yep https://docs.openstack.org/ocata/networking-guide/config-ovs-dpdk.html was what i was looking for | |
| 19:10:23 | gregwork | reading now | |
| 19:10:57 | sean-k-mooney | gregwork: that rather crypti libvirt warning + the complete lack of networking are the only signs that this requirement was not met | |
| 19:12:16 | sean-k-mooney | gregwork: by the way if you are on ubuntu you might need to aslo need to run sudo apparmor_parser -R /etc/apparmor.d/usr.sbin.libvirtd and restart libvirtd | |
| 19:12:58 | sean-k-mooney | the reason for this is apparmor may block acess to /var/run/openvswitch when qemu tries to create/connect to the vhost user socket | |
| 19:14:30 | sean-k-mooney | if you request hugepages and it fails to boot check dmesg to see if app armor blocked it and remove teh libvirt prfile and restart the libvirt service if it did | |
| 19:20:01 | openstackgerrit | Eric Fried proposed openstack/nova master: placement: allow filter providers in tree https://review.openstack.org/377215 | |
| 19:20:02 | openstackgerrit | Eric Fried proposed openstack/nova master: placement: update client to set parent provider https://review.openstack.org/385693 | |
| 19:20:02 | openstackgerrit | Eric Fried proposed openstack/nova master: placement: adds REST API for nested providers https://review.openstack.org/384807 | |
| 19:20:03 | openstackgerrit | Eric Fried proposed openstack/nova master: Reformat _get_all_with_shared https://review.openstack.org/512799 | |
| 19:21:29 | gregwork | sean-k-mooney: on rhel7 with rhosp11 | |
| 19:22:05 | sean-k-mooney | gregwork: ah ok. selinux might complain in a similar way but i think that issue only happens on ubuntu | |
| 19:22:25 | openstackgerrit | Eric Fried proposed openstack/nova master: placement: Reformat _get_all_with_shared https://review.openstack.org/512799 | |
| 19:22:31 | sean-k-mooney | you can set selinux to permmissive if it dose as a workaround | |
| 19:22:50 | gregwork | sean-k-mooney: what hardware are you using | |
| 19:23:05 | gregwork | sean-k-mooney: we are testing connect x-5 100gbe dual qsfp cards | |
| 19:23:18 | dansmith | efried: thanks | |
| 19:23:26 | efried | yahyoubetcha. | |
| 19:23:36 | efried | Also addressed cdent -1 in the middle of that series | |
| 19:23:50 | dansmith | gregwork: sean-k-mooney: your discussion seems unrelated to nova dev (see topic), maybe you could take it to #openstack? | |
| 19:24:00 | dansmith | efried: cool | |
| 19:24:03 | sean-k-mooney | gregwork: i have tested i350,e1000,x520 and xl70(both 4*10 and 2*40G) | |
| 19:24:22 | gregwork | dansmith: sure | |
| 19:24:30 | efried | dansmith You should eat slower. Gonna give yourself indigestion. | |
| 19:24:30 | sean-k-mooney | dansmith: sure :) | |
| 19:24:37 | gregwork | actually ill just msg you directly if you dont mind | |
| 19:24:41 | dansmith | efried: I'm parallelizing | |
| 19:24:48 | efried | efficient | |
| 19:31:12 | mlavalle | johnthetubaguy, mriedem: any chance you could take a look again on https://review.openstack.org/#/c/375580/? | |
| 19:31:30 | mriedem | 0 chance miguel | |
| 19:31:43 | mriedem | i've had the tab open all morning :) | |
| 19:33:09 | mriedem | should be able to get to it before parent / teacher conferences this afternoon, which are not going to go well | |
| 19:33:13 | mriedem | dansmith: ^ you know why | |
| 19:33:23 | dansmith | lol | |
| 19:33:28 | dansmith | wish I could go | |
| 19:34:32 | mlavalle | mriedem: thanks. good luck with the parent / teacher conference :-) I remember those days | |
| 19:37:18 | efried | sean-k-mooney Took another swing at the bandwidth spec | |
| 19:43:26 | melwitt | mriedem: I wonder if the problem is with cryptsetup and not luks (in your recreate patch). in the bug report lisali mentioned dmcrypt which would imply cryptsetup IIUC | |
| 19:43:41 | sean-k-mooney | efried: cool thanks ill review it with rodolfo tomorow when im back in the office | |
| 19:43:41 | melwitt | the hard reboot is only in the luks test | |
| 19:44:41 | melwitt | mriedem: ah but I see in the bug summary he uses LUKS in the repro steps. nvm | |
| 19:44:43 | mriedem | melwitt: i'll check the logs when they are available to make sure it's not something like reboot failed but the instance wasn't put into ERROR state | |
| 19:47:45 | mriedem | mlavalle: before you scamper off, | |
| 19:47:48 | mriedem | i have a question for you | |
| 19:48:00 | mriedem | https://bugs.launchpad.net/neutron/+bug/1718605 | |
| 19:48:01 | openstack | Launchpad bug 1718605 in neutron "[RFE] Support regex matching when filtering port with IP address" [Wishlist,Triaged] - Assigned to Zhenyu Zheng (zhengzhenyu) | |
| 19:48:14 | mriedem | mlavalle: would ^ be exposed via a new networking API extension? | |
| 19:48:26 | mriedem | i want to assert that it would be | |
| 19:48:35 | mriedem | so nova can tell if neutron is new enough to filter ports by an ip regex | |
| 19:49:47 | mlavalle | mriedem: yes, that makes sense | |
| 19:49:56 | mriedem | ok cool | |
| 19:50:06 | mlavalle | otherwise you don't know who you are talking about | |
| 19:50:14 | mlavalle | talking to^^^^ | |
| 19:50:36 | mlavalle | good thing you left a comment in the RFE | |
| 19:50:42 | mriedem | \o/ | |
| 19:50:54 | mlavalle | I'll make sure we talk about it in the drivers meeting | |
| 19:51:02 | mriedem | ok | |
| 19:59:29 | openstackgerrit | Matt Riedemann proposed openstack/nova-specs master: Improve the performance of filtering instances by IP. https://review.openstack.org/509326 | |
| 20:00:35 | melwitt | mriedem: looks like reboot succeeded, weird http://logs.openstack.org/60/512760/1/check/legacy-tempest-dsvm-neutron-scenario-multinode-lvm-multibackend/b6880f6/logs/screen-n-cpu.txt.gz#_Oct_17_19_08_20_972474 | |
| 20:02:03 | mriedem | are you sure that's the right request? | |
| 20:02:45 | melwitt | not totally sure but it's the only hard reboot in nova-api | |