> > 2016-07-19 2:53 GMT-07:00 Loftus, Ciara :
> > >
> > > The idea looks very good to me, thanks for working on it.
> > > Very high level comments:
> > Hi Daniele thanks for looking at this.
> >
> > >
> > > Do we need to be limited to pci devices? Perhaps we can accept the
> same
> > > string as r
> 2016-07-19 2:53 GMT-07:00 Loftus, Ciara :
> >
> > The idea looks very good to me, thanks for working on it.
> > Very high level comments:
> Hi Daniele thanks for looking at this.
>
> >
> > Do we need to be limited to pci devices? Perhaps we can accept the same
> > string as rte_eth_dev_attach()
2016-07-19 2:53 GMT-07:00 Loftus, Ciara :
> >
> > The idea looks very good to me, thanks for working on it.
> > Very high level comments:
> Hi Daniele thanks for looking at this.
>
> >
> > Do we need to be limited to pci devices? Perhaps we can accept the same
> > string as rte_eth_dev_attach().
>
> The idea looks very good to me, thanks for working on it.
> Very high level comments:
Hi Daniele thanks for looking at this.
>
> Do we need to be limited to pci devices? Perhaps we can accept the same
> string as rte_eth_dev_attach().
Can you elaborate? For physical devs the string is alway
The idea looks very good to me, thanks for working on it.
Very high level comments:
Do we need to be limited to pci devices? Perhaps we can accept the same
string as rte_eth_dev_attach().
Would it be possible to integrate this more with the hotplug patch? It
would be nice to avoid introducing
'dpdk' ports no longer have naming restrictions. Now, instead
of specifying the dpdk port ID as part of the name, the PCI
address of the device must be specified via the 'dpdk-pci'
option. eg.
ovs-vsctl add-port br0 my-port
ovs-vsctl set Interface my-port type=dpdk
ovs-vsctl set Interface my-port
