#opnfv-cperf: cperf

Meeting started by dfarrell07 at 18:19:20 UTC (full logs).

Meeting summary

    1. mattw4 reports they have 50 cerros256 min instaces on a single compute node (dfarrell07, 18:20:40)
    2. raghu is looking at rally, getting that working (dfarrell07, 18:20:51)
    3. mattw4 and raghu are working on test scenarios (dfarrell07, 18:21:06)
    4. mattw4 had 30 compute nodes + instances running on a server with 64GB RAM (dfarrell07, 18:23:45)
    5. as the test gets bigger it takes longer for openstack to see the instances, like a min at most (dfarrell07, 18:24:03)
    6. at 30+ things start to break, will not dhcp, maybe bringing it back up will work but that's not so stable (dfarrell07, 18:24:29)
    7. with 6 systems in the cperf pod with 64GB ram each, we could get some crazy scale (dfarrell07, 18:25:05)
    8. because we're using linux bridges for container networking, it should be easy to put odl in a place that has lots of resources and still talk to it (dfarrell07, 18:25:25)
    9. acm is back from openf summit, welcome (dfarrell07, 18:27:25)
    10. acm had a very well attended talk on monday about vswitch perf results (dfarrell07, 18:27:38)
    11. acm talks about traffic gens they are looking at, some RHers have been doing stuff with moongen+??, now in vsperf (dfarrell07, 18:28:38)
    12. the ones they have played with are a bit hard to use, some strange results, but as it goes (dfarrell07, 18:28:59)
    13. discussion about scale issue with ODL vswitch scale issue, also on email (dfarrell07, 18:29:30)
    14. mattw4 talks about seeing some similar issues (dfarrell07, 18:33:54)
    15. talking about the 30 nodes, the flow dump from ofp is err small, so also dropping flows (dfarrell07, 18:36:57)
    16. we should push on ofp to actually fix this issue, we are very able to since we're seeing it in multi tests (dfarrell07, 18:38:40)
    17. mattw4 gives us a quick demo of the scale setup he has (dfarrell07, 18:38:51)
    18. mattw4's demo is fucking amazing, everyone swoons over automation, very cool ansible stuff (dfarrell07, 18:47:35)
    19. this is all very ready to be upstream, will be amazing in ci (dfarrell07, 18:47:45)
    20. mattw4 should send talks to open source summit north america if CFP is still open (dfarrell07, 18:48:11)


Meeting ended at 18:48:15 UTC (full logs).

Action items

  1. (none)


People present (lines said)

  1. dfarrell07 (23)
  2. collabot (3)
  3. mattw4 (2)


Generated by MeetBot 0.1.4.