15:00:00 <mackonstan> #startmeeting FD.io CSIT Project Meeting
15:00:00 <collab-meetbot> Meeting started Wed Feb 23 15:00:00 2022 UTC and is due to finish in 60 minutes.  The chair is mackonstan. Information about MeetBot at http://wiki.debian.org/MeetBot.
15:00:00 <collab-meetbot> Useful Commands: #action #agreed #help #info #idea #link #topic #startvote.
15:00:00 <collab-meetbot> The meeting name has been set to 'fd_io_csit_project_meeting'
15:00:10 <mackonstan> #info Maciek Konstantynowicz
15:01:58 <tifrank> #info Tibor Frank
15:02:00 <mackonstan> #topic Agenda bashing
15:02:06 <vrpolak> #info Vratko Polak.
15:03:30 <mackonstan> #topic Inputs from projects - VPP
15:03:41 <fan_zhang> #info Fan Zhang
15:03:43 <mackonstan> #chair
15:03:43 <collab-meetbot> Current chairs: mackonstan
15:03:59 <mackonstan> #info Andrew, v22.02 artifacts being pushed to packagecloud
15:04:16 <mackonstan> #info Andrew, into rls directory, should be done in couple hours
15:09:06 <mackonstan> #info Andrew, few fixes came late, yday, i) vxlan fixing a crash in masterthat changed meaning of api and introduced another problem, now reverted; ii) mtu callback related for memif, virtio, may have meaningful impact on jumbo tests;
15:10:37 <mackonstan> #info Fan, related to above, chatted with dpdk dev who authored mtu/mfs changes in dpdk. this was done to unify mfs/mtu handing across multiple nic models and taking care of encap/decap offload in nic's
15:12:08 <dwallacelf> #info Dave Wallace
15:15:26 <mackonstan> #info Fan, re dpdk performance degradation report by Vratko in vpp-dev: this could, but because of defaulting to 1518B mfs/mtu, avx2 rx_burst functional call in linear mode (using couple of mbufs, with additional check), previously vpp was receiving 256 frames in one go, now it's 64 frames.
15:17:24 <mackonstan> #info Peter, looking at dpdk init debug, after interfaces go up, one can see dpdk rx_burst working with avx2 in linear mode
15:19:22 <mackonstan> #info Fan, need to double click if it's really the root cause behind the vpp rc2 regressions reported by Vratko on vpp-dev, 5-15% (feature-simple tests) throughput drop
15:20:04 <mackonstan> #info Vratko, Maciek, I/O "heavy" regression, the more features one uses, the lower the regerssion; the simpler the config the higher regression.
15:20:50 <mackonstan> #topic Inputs from projects - TSC
15:23:02 <mackonstan> #info Maciek, Dave, hw budget allocation for dram for arm build servers, and mlx connectx5s for trex 100ge nics for clx testbeds
15:23:43 <mackonstan> #info Dave, TSC chair nomination period is coming to an end this week
15:23:56 <mackonstan> #info Dave, this will be followed by voting among TSC members
15:24:20 <mackonstan> #topic New or (to be) refactored tests
15:25:28 <mackonstan> #topic VPP RC1, RC2 hot patch(es) items
15:28:13 <mackonstan> #info Peter, i) jumbo frames are supported in af_xdp kernel code up to "memory alignment" ~3kB, no support for 9000B; ii) jumbo frames issue with vpp memif, bug to be tracked re support mtu;
15:29:46 <mackonstan> #info Vratko, iii) found the place where vpp sets default IP MTU to 9000B.
15:31:11 <mackonstan> #info Maciek, suggesting to discuss on csit-dev mailer how to re-design existing csit jumbo frame size tests
15:31:35 <mackonstan> #topic Releases CSIT-2202
15:32:01 <mackonstan> #info Tibor, all planned rc2 iterative tests are done; all but 2 coverage tests are done too.
15:32:12 <mackonstan> #info Tibor, all data is in master ver of report
15:34:21 <mackonstan> #info Tibor, failed tests, nothing unexpected, only known issues. Vratko working thru them, Viliam composed summary, sent to csit-report.
15:35:31 <mackonstan> #info Tibor, draft report dynamic content validation, still to be completed fully
15:35:50 <mackonstan> #info Tibor, 2n-cix and 3n-icx testbeds added
15:36:08 <mackonstan> #info Tibor, static content updates - rls notes, RCA
15:36:26 <mackonstan> #info Tibor, static content - need to update environment versions
15:37:42 <mackonstan> #info Tibor, 1st rls results expected to be making its way into master report draft on Mon or Tue next week
15:38:28 <mackonstan> #info Vratko, commenting on rc2 regressions, per email to vpp-dev
15:38:34 <mackonstan> #link https://lists.fd.io/g/vpp-dev/message/20888
15:38:59 <mackonstan> #info Vratko, tsh tests are affected by TRex calibration …
15:41:08 <mackonstan> #info Vratko, for some regressions need more then 5 iterative runs
15:47:13 <mackonstan> #topic Physical Infrastructure
15:49:56 <mackonstan> #info re delayed shipment of supermicro systems for ICX - 2 units expected next week per vexxhost ticket
15:50:03 <mackonstan> #link https://support.vexxhost.com/hc/en-us/requests/361959
15:50:52 <mackonstan> #info Peter, 2 ampere perf servers are in transit per latest DHL updates
15:51:39 <mackonstan> #topic Virtual Infrastructure, CI/CD
15:52:34 <mackonstan> #info Dave, Peter, s3 migration is happening in the background, vpp docs are taking time, csit is done
15:52:47 <mackonstan> #topic Environment, Framework
15:54:29 <mackonstan> #info Andrew, Vratko, been discussing improvements in the are of CSIT CLI and API usage, and tracking VPP API changes in automated fashion
15:55:26 <mackonstan> #topic Trending
16:12:32 <mackonstan> #endmeeting