18:13:37 <dfarrell07> #startmeeting cperf
18:13:37 <collabot`> Meeting started Thu May 12 18:13:37 2016 UTC.  The chair is dfarrell07. Information about MeetBot at http://wiki.debian.org/MeetBot.
18:13:37 <collabot`> Useful Commands: #action #agreed #help #info #idea #link #topic.
18:13:37 <collabot`> The meeting name has been set to 'cperf'
18:14:16 <dfarrell07> #info dfarrell07 is at OPNFV plugfest with CPerf hat on (among other hats)
18:14:51 <dfarrell07> #info dfarrell07 is Working with Pan of SDNCTC on collab. Trying to get access to the perf testing tool source they use in their reports.
18:15:23 <dfarrell07> #info ODL perf whitepaper 1.1 is almost done, about to be sent to ONOS for review and then publication
18:17:28 <dfarrell07> #info Basically they released 1.5.1 with NB REST batching and stats-colleciton related perf fixes, want us to retest
18:17:38 <dfarrell07> #info Disagreement about testing methods, they use interal Java APIs and we think that's not useful for users, just devs
18:17:54 <dfarrell07> #info dfarrell07 Talked to jack about OPNFV POD 2, should be ready for our use
18:18:08 <dfarrell07> #info dfarrell07 continued to play with NSTAT a bit, not as much as I hoped
18:18:56 <dfarrell07> #info jamoluhrsen has continued with our hello world job, patch merged
18:19:08 <dfarrell07> #info our docker image isn't on DockerHub yet, so that'll fail until fixed
18:19:44 <jamoluhrsen> https://build.opnfv.org/ci/computer/intel-pod2/
18:20:27 <dfarrell07> #info POD 2 is broken, reports jamoluhrsen
18:20:34 <dfarrell07> #action dfarrell07 will follow up with Jack
18:20:41 <dfarrell07> #link https://build.opnfv.org/ci/computer/intel-pod2/
18:20:44 <dfarrell07> #undo
18:20:44 <collabot`> Removing item from minutes: <MeetBot.ircmeeting.items.Link object at 0x2fddd90>
18:20:50 <dfarrell07> #link https://build.opnfv.org/ci/computer/intel-pod2/ broken pod info
18:21:26 <dfarrell07> #info Nikos has continued with NSTAT perf testing, both for Li and Be
18:22:07 <dfarrell07> #info Be is better than Li in end-to-end flow perf for all topos and sizes, in extreme cases where Li fails Be wins. 1m flows and 5k switch topos for example. Be is making progress!
18:22:23 <dfarrell07> #info Nikos will likely publish updated PDF with these results early next week
18:22:39 <dfarrell07> #info Nikos is working on tool improvements, things releated to var size pkt ins
18:23:12 <dfarrell07> #info Testing above has to do with He OFP, not newer Li one
18:23:55 <dfarrell07> #info Previous intercom telco report has Li OFP design results for past tests, but went with "default" this time
18:24:59 <dfarrell07> #info Li doing better than Be on some NB REST tests, ignoring SB parts, just the RESTCONF perf
18:36:15 <dfarrell07> #link https://drive.google.com/file/d/0B_7IPKiQjuIZTkh5SVBkaWJvX3c SDNCTC perf report
18:37:51 <dfarrell07> #info Jamo points out that it's possible to write high-perf apps that exist inside the controller and would use the Java APIs, so we should be careful about saying that apps would only use NB REST APIs
18:39:08 <dfarrell07> #info abhijitkumbhare joined today, mostly to watch,  welcome!
18:39:16 <dfarrell07> #endmeeting