On Fri, Aug 25, 2017 at 04:08:54PM +0200, Jan Tluka wrote:

There's no reason to pin guest's interfaces to a CPU. Only host's interfaces should be pinned.

Signed-off-by: Jan Tluka jtluka@redhat.com

recipes/regression_tests/phase3/2_virt_ovs_vxlan.py | 2 +- recipes/regression_tests/phase3/vxlan_multicast.py | 1 - 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/recipes/regression_tests/phase3/2_virt_ovs_vxlan.py b/recipes/regression_tests/phase3/2_virt_ovs_vxlan.py index 1899711..ad3bccf 100644 --- a/recipes/regression_tests/phase3/2_virt_ovs_vxlan.py +++ b/recipes/regression_tests/phase3/2_virt_ovs_vxlan.py @@ -73,7 +73,7 @@ if nperf_cpupin: h2_if = host2.get_interface("if1")

 #this will pin devices irqs to cpu #0

• for m, d in [(host1, h1_if), (host2, h2_if), (guest1, g1_nic), (guest2, g2_nic), (guest3, g3_nic), (guest4, g4_nic)]:

• for m, d in [(host1, h1_if), (host2, h2_if)]: pin_dev_irqs(m, d, 0)

nperf_opts = "" diff --git a/recipes/regression_tests/phase3/vxlan_multicast.py b/recipes/regression_tests/phase3/vxlan_multicast.py index 31596fc..f9bff44 100644 --- a/recipes/regression_tests/phase3/vxlan_multicast.py +++ b/recipes/regression_tests/phase3/vxlan_multicast.py @@ -56,7 +56,6 @@ test_if3.set_mtu(mtu) if nperf_cpupin: m1.run("service irqbalance stop") m2.run("service irqbalance stop")

• g1.run("service irqbalance stop")

  m1_phy1 = m1.get_interface("eth1") m2_phy1 = m2.get_interface("eth1")

-- 2.9.5 _______________________________________________ LNST-developers mailing list -- lnst-developers@lists.fedorahosted.org To unsubscribe send an email to lnst-developers-leave@lists.fedorahosted.org

pushed, thanks -Ondrej