15:01:52 #startmeeting fdio-vpp 15:01:52 Meeting started Tue Jun 25 15:01:52 2019 UTC. The chair is DaveBarach. Information about MeetBot at http://wiki.debian.org/MeetBot. 15:01:52 Useful Commands: #action #agreed #help #info #idea #link #topic. 15:01:52 The meeting name has been set to 'fdio_vpp' 15:02:37 #topic CSIT (Maciek Reporting) 15:02:46 #info CSIT-1904.1 maintenance testing done, report published 15:02:55 #link https://docs.fd.io/csit/rls1904_1/report/introduction/introduction.html 15:03:21 #info Continuing work on VAT to PAPI migration, going okish, some "hiccups" with VPP API changes, but "mouth covering" with CSIT PAPI fixes :) 15:03:51 #info Really really need closer VPP-CSIT CI alignment, current proposed solution is "VPP API flag day" for CSIT, but it's taking long time... 15:04:03 #info Already missing VAT abstraction, just kidding ;) 15:04:14 #info Re vpp-csit-verify-device-master jobs voting status: currently blocked by broken CSIT-VPP PAPI, all IP tests failing 15:04:35 #info Trending tests partially broken, all IP tests failing 15:04:42 #info All will be back to normal once CSIT PAPI "mouth covering" exercise complete, ETA today/tomorrow CET 15:04:49 #link https://gerrit.fd.io/r/c/20278/ 15:04:57 #info Adding more performance tests: VXLAN, IPsec scale up to 60k tunnels 15:05:11 #info On a path/mission to disable VIRL: perf, dev/func tests environment alignment, will enable running perf test code as functional dev tests 15:05:47 #info CSIT-1908 plan wiki updated 15:05:56 #link https://wiki.fd.io/view/CSIT/csit1908_plan 15:06:29 #topic Sweetcomb 15:06:52 #info leverage VOM library for state reconciliation in Sweetcomb 15:07:44 #topic Host Stack (Florin) 15:08:24 #info TCP now supports tcp-output -> arbitrary next node 15:08:48 #info Adding tcp delivery rate estimation 15:09:14 #info needed for sophisticated congestion control algorithms 15:09:38 #info used for BBR, other proprietary congestion control algos 15:10:07 #info host stack: aggregate all applications into one place 15:10:23 #info echo-server/client built into vpp 15:10:40 #info move to "hoststack-plugins" 15:15:09 #topic Documentation (John D reporting) 15:15:18 #info main page making progress, waiting for feedback 15:15:34 #info waiting for LF to give us the DNS entries 15:16:07 #topic aarch64 (Honnappa reporting) 15:16:45 #info reached out to Damjan for specific patch concerns 15:17:09 #info working on c11 atomic based locks 15:18:03 #info LF lab: please use Thunderx-1'S not macciato-bin 15:20:58 #topic 19.04.1 (Dave Wallace reporting) 15:21:12 #info patches queued up, not planning to do another dot release until someone asks 15:21:39 #info 19.08 starts consuming csit resources the first week of August, 15:21:56 #info should decide in mid-July if we want to do another 19.04.X release 15:22:24 #topic 19.08 (Andrew Y reporting) 15:22:51 #info .py packaging improvements, shout out to Aloys 15:23:39 #topic API changes (Dave Wallace reporting) 15:23:56 #info CSIT will start checking for API changes 15:24:33 #info need to be able to take specific tests offline 15:25:42 #info will verify any api changes - if used messages actually change, 15:25:51 #info patches will get -1 15:32:12 #topic Table creation / feature enablement (Dave B) 15:35:09 #info small devices don't need huge virtual space consumers 15:35:41 #link https://gerrit.fd.io/r/20117 API Change patch to be merged soon 15:36:18 #info PaulV to push API Change patch which moves default values from PAPI Executor to API files. 15:37:03 #topic fd.io community events (TSC request for info) 15:38:09 #info previous events have been fd.io people talking to each other 15:38:18 #info not so helpful in terms of growing the community 15:38:58 #info one event per year community meeting might make sense 15:39:11 #info [Jerome T comments above] 15:40:32 #topic Infra (Ed Kern reporting) 15:40:54 #info a couple of jenkins issues last week, asked for root-cause 15:41:31 #info checkstyle commit message checker minor issue 15:41:56 #info Welcome swati to the infra team 15:44:34 #topic test-debug failures (Paul V) 15:47:23 #info packet generator causing "random" failures 15:49:31 #info dpdk drivers vs native driver interface creation vs. probing 15:56:01 #endmeeting