[ovs-dev] ovs patch interface

Ben Pfaff blp at nicira.com
Wed Sep 16 15:21:57 UTC 2015


On Wed, Sep 16, 2015 at 12:35:46PM +0800, Na Zhu wrote:
> Think about this case: a VM attaches to an OVS br-int through
> vhost(kernel), the OVS br-int interconnects with OVS br-eth through a pair
> of patch ports. The physical NIC eth0 is added to br-eth. A packet
> originated from the VM is eventually sent out form eth0. When the data path
> of OVS br-int forwards the packet from the TAP (associates with the VM)
> interface to the patch port, if the OVS patch port is implemented entirely
> inside OVS user space, in this case will it get performance penalty, since
> a switching from kernel space to user space seems to take place?

No.  Patch ports do not require an extra trip through userspace.



More information about the dev mailing list