15:01:55 <mackonstan> #startmeeting FD.io CSIT prroject meeting
15:01:55 <collabot`> Meeting started Wed Mar 25 15:01:55 2020 UTC.  The chair is mackonstan. Information about MeetBot at http://wiki.debian.org/MeetBot.
15:01:55 <collabot`> Useful Commands: #action #agreed #help #info #idea #link #topic.
15:01:55 <collabot`> The meeting name has been set to 'fd_io_csit_prroject_meeting'
15:01:59 <mackonstan> #chair
15:01:59 <collabot`> Current chairs: mackonstan
15:02:00 <jgelety> #info Jan Gelety
15:02:03 <tifrank> #info Tibor Frank
15:02:07 <pmikus> #info Peter Mikus
15:02:10 <vrpolak> #info Vratko Polak.
15:03:05 <dwallacelf> #info Dave Wallace
15:03:23 <mackonstan> #topic Agenda bashing
15:04:21 <mackonstan> #topic DST starts in Europe this coming weekend back to normal time difference
15:04:34 <mackonstan> #topic Physical labs, testbeds
15:05:05 <mackonstan> #info two 2n-skx testbeds out of production - tb22, tb23 - for use by Intel NPG guys t/shooting skx poor NDR performance
15:05:30 <mackonstan> #topic Inputs from projects - VPP
15:06:11 <mackonstan> #info DaveW - need to sync up with Andrew when ready to do 1908.2 - will update CSIT
15:07:03 <mackonstan> #info Maciek - Benoit has a patch adding mlx dpdk into VPP build, so it will be including in VPP build
15:08:45 <mackonstan> #info Vratko - will require enabling vfio-pci driver for mlx NICs should do the trick if it works out of the box, if not then someone/Peter would need to add keyword to handle the specifics
15:09:03 <mackonstan> #topic Inputs from projects - VSAP
15:09:12 <mackonstan> #info DaveW - no word from VSAP
15:09:25 <mackonstan> #topic Inputs from projects - TSC
15:09:56 <mackonstan> #info Some continuing discussion about Scapy/GPLv2 - need to ask individual contributors
15:10:10 <mackonstan> #info Ray is driving this
15:12:50 <mackonstan> #topic CNCF CNF Testbed
15:13:02 <mackonstan> #info Maciek still to reach out to Michael Pedersen
15:13:21 <mackonstan> #topic Releases CSIT-2001
15:14:13 <mackonstan> #info Jan - last two jobs on 3n-skx are running. This will finish the round of 10.
15:16:14 <mackonstan> #info rls to rls comparison tables got updated with root cause analysis notes
15:17:32 <mackonstan> #link https://docs.fd.io/csit/master/report/_static/vpp/performance-changes-3n-skx-2t1c-pdr.txt
15:27:12 <mackonstan> #info daily performance regressions progressions and failures are auto detected and info distributed over email via csit-report mailer
15:28:15 <mackonstan> #info and are also presented in graphs on trending pages: https://docs.fd.io/csit/master/trending/trending/ip4-2n-skx-xxv710.html
15:28:19 <mackonstan> #link https://docs.fd.io/csit/master/trending/trending/ip4-2n-skx-xxv710.html
15:28:41 <mackonstan> #info data available for download in csv format
15:28:54 <mackonstan> #link https://docs.fd.io/csit/master/trending/data/index.html
15:30:11 <mackonstan> #info currently the history duration is 3mths
15:35:11 <mackonstan> #info 1mth worth of history data compressed is ~1 GB;
15:36:08 <mackonstan> #info discussion about option to extend trending coverage to cover complete release period
15:38:14 <mackonstan> #info skx full tests - wait till skx issues resolved by/with Intel
15:38:42 <mackonstan> #topic Releases CSIT-1908
15:43:01 <mackonstan> #info Readiness of stable/1908 weekly coverage - Jan - weekly tests are running, new weekly job with mrr is running on oper branch (oper-rls1908-200325) on top of 1908.1, will be moving to the top of vpp stable/1908 tomorrow
15:43:10 <mackonstan> #info Jan will send email update
15:43:34 <mackonstan> #topic Release CSIT-2005
15:43:48 <mackonstan> #topic Operations
15:45:09 <mackonstan> #topic VPP code performance
15:45:54 <mackonstan> #info Peter - focusing on fixing vhost and vm issues, Mohsin helping on vpp side.
15:46:17 <mackonstan> #info Peter - AVF init failing after rebooting skx, t/shooting.
15:46:35 <mackonstan> #info Jan - one vxlan suite is failing, Juraj reported, already fixed.
15:49:26 <mackonstan> #info updated vpp native rdma code resulted in huge rate increase - 120 Mpps, currently max set by csit code for trex
15:49:29 <mackonstan> #link https://docs.fd.io/csit/master/trending/trending/ip4-2n-clx-cx556a.html
15:52:48 <mackonstan> #info Maciek - looks like `show run` papi is broken, stopped showing breakdown per worker
15:53:04 <mackonstan> #topic Developments
15:54:16 <mackonstan> #info Govind - upgrading Taishan to -72 is failing
16:02:11 <mackonstan> #info Looking to push the update of CSIT-2001 report with Skx data tomorrow, after RCA for progressions and regressions is completed.
16:02:17 <mackonstan> #endmeeting