14:02:27 #startmeeting Weekly CSIT Project Meeting 14:02:27 Meeting started Wed Jul 4 14:02:27 2018 UTC. The chair is mackonstan. Information about MeetBot at http://wiki.debian.org/MeetBot. 14:02:27 Useful Commands: #action #agreed #help #info #idea #link #topic. 14:02:27 The meeting name has been set to 'weekly_csit_project_meeting' 14:02:39 #info mackonstan 14:02:41 #info Peter Mikus 14:02:46 #info Jan Gelety 14:02:56 #topic Agenda bashing 14:03:23 #info Marek Gradzki 14:03:30 #chair 14:03:30 Current chairs: mackonstan 14:04:23 #info Juraj Linkes 14:05:41 #topic VPP update 14:05:50 #info api freeze on 9-Jul 14:09:51 #info Damjan adding memory heap allocation with numa affinity to workers, expecting positive impact on performance 14:09:56 #topic HC update 14:13:41 #info Marek - API freeze in 2 weeks time, want to discuss impact of VIRL migration on HC tests. 14:13:59 #topic CSIT operational status 14:14:04 #info no issues reported 14:14:19 #topic VPP code performance 14:16:13 #info ipsec scale tests failing, ip scale tests failing 14:18:17 #topic Releases 14:22:58 #topic New integration tests 14:23:19 #info VPP_Device - weekly TWS calls to continue 14:26:24 #info VPP_Path: CSIT_VIRL migration - Jan - progressing okay, issues with vpp classify tests (test_classifier.py) 14:26:36 #link https://docs.google.com/spreadsheets/d/1PciV8XN9v1qHbIRUpFJoqyES29_vik7lcFDl73G1usc/edit?usp=sharing 14:33:00 #info Juraj - issues with testing tap in VPP make_test, not supported. Should consider using VPP_Device for tap driver tests. 14:34:40 #info Juraj - looking into parallelising VPP_make_test execution. Collaborating with Klement. 14:35:03 #info HC test topology 14:35:08 #link https://docs.fd.io/csit/master/report/honeycomb_functional_tests/overview.html 14:39:10 #info HC got tested in Containers, so not expecting any major issue 14:39:46 #info consider using VPP_Device for HC functional tests 14:44:03 #info more details to be covered on the next TWS VPP_Device call 14:44:34 #topic VPP code performance monitoring 14:45:32 #info Per VPP patch tests - Vratko - burst MRR tests are still being tuned to yield more precise detection 14:49:56 #info PAL is already prepared for processing burst MRR results 14:51:38 #topic VAT to PAPI 14:53:32 #info for CSIT_VIRL this is already addressed by moving to VPP make test 14:54:23 #info for VPP_Path_Device performance tests - would require refactoring L1 KWs 14:54:31 #topic Tests 14:55:17 #info MLRsearch - expecting to move to MLR in 18.07 14:56:02 #info Vratko - provided prototype MLR tests for Skylake 2-node testbeds 14:56:19 #topic TRex 14:58:28 #info Peter - hitting issues with xxv710 2p25GE, would need to use similar trick as with xl710 2p40ge. 14:58:41 #topic New FD.io CSIT lab 14:59:59 #info 4 * mcx556a-edat NICs just arrived 15:00:20 #info Peter - issues with 3 servers => 3 tickets open 15:00:41 #info failures affecting 3 testbeds :( 15:01:36 #info Arm - Juraj - performance testbeds are finally coming together, hoping for 3-Nde perf testbed ready next week 15:03:42 #topic DMM CSIT status 15:04:07 #info Sharath - ubuntu1604 jobs work, centos7 jobs fail. 15:26:29 #endmeeting