Thursday, 2020-11-05

*** donhw_ has joined #openvswitch00:10
*** donhw has quit IRC00:10
*** tbachman has joined #openvswitch00:29
*** rcernin has quit IRC01:43
*** rcernin_ has joined #openvswitch01:43
*** dcbw has quit IRC01:43
*** acidfu_ has joined #openvswitch01:58
*** acidfoo has quit IRC02:00
*** ihrachys has quit IRC02:15
*** rcernin_ has quit IRC03:24
*** rcernin_ has joined #openvswitch03:35
*** rcernin_ has quit IRC03:47
*** rcernin has joined #openvswitch04:20
*** rcernin has quit IRC05:13
*** rcernin has joined #openvswitch05:15
*** mmichelson has quit IRC05:21
*** mmichelson has joined #openvswitch05:22
*** mmichelson_ has joined #openvswitch05:25
*** mmichelson has quit IRC05:27
*** rcernin has quit IRC06:37
*** rcernin has joined #openvswitch06:50
*** dholler has joined #openvswitch06:53
*** eelco has joined #openvswitch07:08
*** rcernin has quit IRC07:12
*** rcernin has joined #openvswitch07:34
*** rcernin has quit IRC07:43
*** slaweq has joined #openvswitch07:54
*** dholler has quit IRC07:55
*** ralonsoh has joined #openvswitch07:59
*** dholler has joined #openvswitch08:08
*** mdgray has joined #openvswitch08:12
*** elvira has joined #openvswitch08:38
*** thaller_ has quit IRC08:59
*** thaller_ has joined #openvswitch09:00
*** jaicaa has quit IRC09:01
*** jaicaa has joined #openvswitch09:02
*** mbarroso has joined #openvswitch09:05
*** mdgray has quit IRC09:11
*** mdgray has joined #openvswitch09:12
*** donhw has joined #openvswitch09:18
*** donhw_ has quit IRC09:21
*** Gorian has quit IRC09:30
*** thaller_ has quit IRC09:35
*** thaller_ has joined #openvswitch09:36
*** thaller_ has quit IRC09:42
*** thaller_ has joined #openvswitch09:43
*** thaller_ has quit IRC09:52
*** thaller_ has joined #openvswitch09:52
*** dholler has quit IRC11:37
*** dholler has joined #openvswitch11:50
*** tbachman has quit IRC11:58
*** JamesBenson has joined #openvswitch12:10
*** zhouhan_ has quit IRC12:26
*** zhouhan has joined #openvswitch12:26
*** ihrachys has joined #openvswitch12:32
*** dholler has quit IRC12:38
*** dholler has joined #openvswitch13:01
*** tbachman has joined #openvswitch13:28
*** bostondriver has joined #openvswitch13:30
*** dmarchand has quit IRC13:37
*** dmarchand has joined #openvswitch13:37
kklimonda_Hi, what's the status of OVS offload for OVN? What vendors have support for all features required by OVN (I guess GENEVE+CT at least looking at flows?). I'm currently in contact with mellanox, but they haven't yet responded regarding OVN in particular. Are there other vendors I could look into if I'm interested in that?13:45
*** thaller_ has quit IRC13:51
*** thaller_ has joined #openvswitch13:51
*** _mdgray_ has joined #openvswitch14:00
*** mdgray has quit IRC14:03
fblkklimonda_: if you are using the kernel data path, then OVN will use OVS which uses the kernel support. So, all you need is to check if the NIC has offloading support in the kernel.14:13
*** dmellado has quit IRC14:16
kklimonda_fbl: ok, but what exactly can be offloaded given that dp flows in ovn use ct, and ct is not supported on all cards as far as I can tell?14:18
kklimonda_I'm literally asking for recommendations on which cards are most likely to have enough offload support to work well with flows created by ovn14:19
kklimonda_(sorry, that probably sound to harsh - must drink more coffee)14:19
*** dmellado has joined #openvswitch14:20
kklimonda_or perhaps I misunderstand how ovs offloading works with kernel dp?14:23
kklimonda_I assumed that datapath flows are offloaded to the nic, and I've been looking at ovs offload support from various vendors but perhaps that's only for ovs-dpdk (or even something else I'm not aware of?)14:24
ihrachysin ovn, we use CFI flag as a marker for vlan tagged traffic to drop; what's the backstory for this flag being used as the marker? was its meaning overloaded for ovs (ovn?) needs somehow? I couldn't immediately see the relationship between its original protocol definition and the way it's being used there.14:44
ihrachyshm... half the message lost... "between its original protocol definition and the way it's used in ovs"14:45
*** thaller__ has joined #openvswitch14:53
*** thaller_ has quit IRC14:56
*** acidfoo_ has joined #openvswitch14:58
*** acidfu_ has quit IRC15:01
*** aconole has quit IRC15:04
*** _mdgray_ has quit IRC15:16
*** mdgray has joined #openvswitch15:18
*** mbarroso_netcont has joined #openvswitch15:18
*** matteo| has joined #openvswitch15:19
*** mbarroso has quit IRC15:21
*** mbarroso_netcont has quit IRC15:29
*** mbarroso has joined #openvswitch15:29
*** matteo| has quit IRC15:42
*** cpaelzer__ has joined #openvswitch15:50
*** cpaelzer has quit IRC15:51
*** spatel has joined #openvswitch16:04
spatelFolk, need advice from experts to deploy openvswitch with dpdk16:05
spatelMy compute node has only 2x10G Intel nic and i have configure openvswitch+dpdk on this compute node for performance.16:06
spatelcurrently i have nic-1 currently in dpdk and nic-2 for managment traffic.16:06
spatelHow do i bond them to gather if i need redendency ? (i know if i have 3rd nic then its easy )16:07
*** dmellado has quit IRC16:11
*** dmellado has joined #openvswitch16:13
*** aconole has joined #openvswitch16:13
*** eelco has quit IRC16:14
*** dcbw has joined #openvswitch16:51
*** mbarroso has quit IRC17:10
*** JamesBen_ has joined #openvswitch17:11
*** JamesBenson has quit IRC17:14
*** elvira has quit IRC17:28
*** aconole has quit IRC17:35
*** stee has joined #openvswitch17:37
*** mmichelson_ has quit IRC18:01
*** mmichelson has joined #openvswitch18:02
*** ryzhyk has joined #openvswitch18:13
*** blp has joined #openvswitch18:13
blphi!18:14
*** dceara has joined #openvswitch18:14
numanshello18:15
ihrachyshi18:15
blpSorry about the testsuite bug when not building with ddlog. It was supposed to work, but I had not tested it. I'll resubmit soon.18:15
numansblp, no worries.18:16
numansmmichelson, starting the meeting ?18:16
mmichelsonnumans, sorry Will do18:16
numansmmichelson, no worries. If I start, I need to stay till the end :)18:17
mmichelson#startmeeting ovn_community_development_discussion18:17
openstackMeeting started Thu Nov  5 18:17:25 2020 UTC and is due to finish in 60 minutes.  The chair is mmichelson. Information about MeetBot at http://wiki.debian.org/MeetBot.18:17
openstackUseful Commands: #action #agreed #help #info #idea #link #topic #startvote.18:17
openstackThe meeting name has been set to 'ovn_community_development_discussion'18:17
ryzhykhi!18:17
mmichelsonHi everyone18:17
numansHi18:17
dcearaHi18:17
imaximetshi18:17
mmichelsonLooks like we have a lot of people here today!18:18
mmichelsonWho would like to go first?18:18
blpI can go.18:18
blpI have posted two versions of the final DDlog series.18:18
blpNuman has provided some feedback on it, and I will post v3 soon.18:19
flaviofhi all18:19
blpI think that's my report, but perhaps there are questions.18:19
flaviofblp I got a question/ask...18:20
blpflaviof: go ahead18:20
flaviofblp would you be ok helping me with this change on northd using ddlog:18:20
blpOh, yes, in general I'm available to help with that kind of question.18:21
flaviofhttps://patchwork.ozlabs.org/project/ovn/patch/20201103221834.25541-2-flavio@flaviof.com/18:21
flaviofI will take tomorrow to learn more about ddlog and use that as an excuse to learn ddlog northd :)18:22
*** aconole has joined #openvswitch18:22
blpflaviof: I guess this must have been posted to the list. I'll take a look at it.18:22
numansblp, dceara found one problem while compiling ovn with ddlog - http://paste.openstack.org/show/799751/. Can you plz take a look. If we configure ovs disabling avx512, ovn compilation succeeds - http://paste.openstack.org/show/799752/18:22
blpnumans: Wow, that is mysterious at first glance. How do I reproduce the original failure?18:24
numansblp, its reproducible with ovs master and ovn + ddlog patches.18:24
numansdceara and I tried on fedora. I'm not sure if there are any distro/package related stuff.18:25
blpnumans: That's how I build ovs, so the question is really "what stands out about how dceara is building ovs and/or ovn"?18:25
dcearablp: I think it's great that DDlog made it on the mailing list!  As numans pointed out, I just tried building OVS + OVN master branch + ddlog on Fedora 32 on a machine with AVX-512.18:25
imaximetsblp, dceara seems to have avx512 support in compiler/cpu.18:26
dcearaimaximets: right, only then libopenvswitchavx512 gets compiled18:26
blpdceara: So that patch is one that triggers the problem?18:26
blpdceara: I mean, building ovs master with http://paste.openstack.org/show/799752/ makes the problem show in ovn?18:27
numansblp, no. building ovs with  http://paste.openstack.org/show/799752/ resolves the problem.18:27
dcearablp: No, that's the only way to make it compile, i.e., to remove AVX support in OVS so that the rust compiler doesn't get libopenvswitchavx512 passed as argument.18:27
imaximetsblp, looking at line 'process didn't exit successfully:' it seems that '-L' is missing before the path to libopenvswitchavx512.la.18:28
dcearaimaximets: I'm not sure, I see '-L /mnt/alt_home/numans/workspace_cpp/ovs/lib/.libs'18:28
blpdceara: Oh, I see, I didn't realize that avx512 support had been added to ovs. I understand now.18:28
imaximetsdceara, yep, but -L should be before /mnt/alt_home/numans/workspace_cpp/ovs/lib/libopenvswitchavx512.la too.18:29
blp-L is for a directory but a .la file is not a directory.18:29
blpOK, I'll have a look at this. I need to pull the latest ovs master, I guess I'm behind.18:30
imaximetsblp, oh, sorry.  Ignore my comments then.18:31
blpI'm also using Fedora for my dev machine FWIW.18:31
dcearablp: One more thing, on the same system 16 OVN e2e tests were failing: 65 67 73 81 91 101 145 175 189 207 270 275 281 292 326 348 42318:31
dcearablp: I can share more details on the mailing list.18:31
blpOK, please do.18:32
dcearablp: ack.18:32
*** donhw_ has joined #openvswitch18:33
blpOK, so I have my to-do list, then. Who's next?18:34
mmichelsonI can jump in if it's OK18:34
flaviofblp thanks for the testing helpers (4afe409e9) super cleaner .at tests now!18:34
flaviofmmichelson: go ahead18:34
blpmmichelson: You're in charge of the meeting, of course you can go head.18:34
numansblp++ for the testing helpers.18:34
mmichelsonI checked the calendar, and we're supposed to have soft freeze for ovn 20.12 tomorrow. I think that it kind of snuck up on us. So instead, how would people feel about pushing it out one additional week to the 13th?18:35
dcearammichelson: ++18:35
numans++18:35
mmichelsonTo correct this for 2021, I'm adding calendar reminders two weeks in advance of soft freeze dates so I can send announcements out with plenty of warning18:35
*** donhw has quit IRC18:35
dceara(although Friday 13th..)18:35
blpflaviof: you're welcome for the helpers!18:35
blpmmichelson: good idea18:36
mmichelsonOK cool18:36
flaviofdceara: it will not be full moon. Hope that is ok18:37
flaviofmmichelson ++18:37
mmichelsonIn addition to that, I'm working on a patch that will allow for users to choose which CT zone to use for SNAT on gateway routers. I made a simpler version of the patch last week to be tested by some RH people in OpenShift that would allow for the default CT zone (0) to be used18:37
mmichelsonBut this new version is a bit more complicated since it needs to ensure that we don't have CT zone conflicts when the user chooses their zone.18:38
mmichelsonAnd I would love to have feedback on v3 of the unit test patch series.18:38
mmichelsonI think that's about it for m.e18:38
ihrachyscan I?18:39
ihrachystwo things. first is I am low key sitting on v11 of multiple controllers / virtual chassis patch so reviews are welcome: https://patchwork.ozlabs.org/project/ovn/patch/20201102231419.539520-1-ihrachys@redhat.com/ probably numans if possible since he already checked it the last time18:40
numansihrachys, ack.18:40
numansihrachys, I'll take a look. thanks for v1118:41
ihrachysand the other is, above in the chat I was asking about why CFI flag is forced to 1 and used as a marker for vlan tag present. I suspect there's some back story that I should be aware of.18:41
blpihrachys: This is in OVS? It's because that's how the Linux kernel did it at the time.18:41
*** ralonsoh has quit IRC18:41
ihrachyssince I am going to touch the flow in another patch18:41
ihrachysblp: vlan.present transformed into tci==0x1000/0x1000 mask check, yes.18:42
ihrachysso the flag was overloaded with other meaning different from protocol?18:42
* numans waves and disappears. bye18:42
blpihrachys: Yes, because in Ethernet this bit was always required to be zero. OVS runs on Ethernet. Then the Ethernet folks changed their mind. https://en.wikipedia.org/wiki/IEEE_802.1Q#cite_note-818:43
ihrachysoh I was reading the page but missed the bottom note *facepalm*18:44
ihrachysthanks for the tip, that's all from me :)18:44
*** thaller__ is now known as thaller18:45
blpAnyone else?18:46
dcearaI can go next if that's OK.18:46
imaximetsblp, the conversation around following patch might shed some light on why some things around avx512 in ovs done as they are done: https://patchwork.ozlabs.org/project/openvswitch/patch/1594759760-20400-1-git-send-email-gvrose8192@gmail.com/  Just in case.18:46
blpimaximets: Thanks for the background.18:47
imaximetsdceara, sorry, go ahead.18:48
dcearaWe had a customer issue come over this week (from OpenStack) where we were hitting the 4K resubmit limit in OVS (again).  We had partially fixed this in the past and now we fixed all remaining cases (I hope).18:48
blpI can hardly imagine the performance is great if OVS is doing >4000 resubmits.18:48
dcearaWell, it's actually not true what I said above, there's still traffic that might hit the multicast group that floods to a lot of ports.18:49
blpAnyone else?18:50
imaximetsI have a small update.18:50
flaviof#link https://github.com/ovn-org/ovn/commit/8c6a5bc21847dab8ccbe18ab1e4b563ddca13379  dceara18:51
flaviofimaximets: pls go ahead18:51
imaximets2 weeks ago I talked about debugging memory consumption of ovsdb-server.  It turned out to be few issues combined.18:51
imaximets1. raft log could be huge in memory.18:52
imaximets2. backlogs on raft connections could grow significantly18:52
imaximets3. libc doesn't return all that memory back to system.18:52
imaximetsThere was a patch set to address all these issues. 3 of 5 patches already merged.18:53
imaximetsLast 2 patches reviewed and will be merged soon.18:53
blpThat's all good news!18:53
imaximetsI'm also backporting all these fixes down to 2.13 as we agreed on a list.18:54
*** dholler has quit IRC18:54
blpAnything else?18:55
blpI have to go in 5 minutes.18:55
imaximetsThat's all from me.18:55
blpOK, thanks a lot everyone, I have my to-do list for today. Talk to you next week!18:58
*** blp has left #openvswitch18:58
flaviofbye all!18:59
dcearabye!18:59
imaximetsbye.18:59
mmichelson#endmeeting19:00
openstackMeeting ended Thu Nov  5 19:00:26 2020 UTC.  Information about MeetBot at http://wiki.debian.org/MeetBot . (v 0.1.4)19:00
openstackMinutes:        http://eavesdrop.openstack.org/meetings/ovn_community_development_discussion/2020/ovn_community_development_discussion.2020-11-05-18.17.html19:00
openstackMinutes (text): http://eavesdrop.openstack.org/meetings/ovn_community_development_discussion/2020/ovn_community_development_discussion.2020-11-05-18.17.txt19:00
openstackLog:            http://eavesdrop.openstack.org/meetings/ovn_community_development_discussion/2020/ovn_community_development_discussion.2020-11-05-18.17.log.html19:00
*** ryzhyk has quit IRC19:06
*** dceara has quit IRC19:33
*** acidfoo_ has quit IRC20:13
*** mdgray has quit IRC20:34
*** rcernin has joined #openvswitch21:27
*** acidfoo_ has joined #openvswitch21:35
*** acidfoo_ has quit IRC21:40
*** rcernin has quit IRC21:53
*** rcernin has joined #openvswitch21:55
*** thaller has quit IRC22:00
*** slaweq has quit IRC22:06
*** bostondriver has quit IRC22:09
*** rcernin has quit IRC22:57
*** rcernin has joined #openvswitch23:01
*** spatel has quit IRC23:18
*** spatel has joined #openvswitch23:20
*** spatel has quit IRC23:25

Generated by irclog2html.py 2.17.2 by Marius Gedminas - find it at https://mg.pov.lt/irclog2html/!