2014-05-22 12:06, Burakov, Anatoly: > > We should discuss a way to request igb_uio or VFIO binding of a device. > > Why? The device can either be bound to VFIO or igb_uio. So unless you want > binding code in DPDK EAL (to avoid which the > pci_unbind/igb_uio_bind/dpdk_bind script was created in the first place), I > see no point in that. The dpdk_bind script already does that (you bind > either to igb_uio or to vfio-pci).
Yes, in some environments, it could be easier to be able to configure devices directly on application command line instead of having to call a python script. I think having a clear and extendable syntax to configure devices in command line could greatly improve usability. But it can be another step. > > This whole socket communication deserves a separated patch with protocol > > description. > > Agreed, I'll break it up and provide a more detailed explanation. Thanks. > > By the way, I'm not a big fan of the suffix "_socket" which can be > > misleading. But I have no other good naming idea. > > Would _mp_socket do? What do you think of _mp_sync or _mp_conf? Usage of the socket is to synchronize VFIO config between processes, right? > > So we have another thread to manage. > > I don't see where it is spawned? > > In rte_eal_pci_init(). Oh yes. Do you think you could merge the thread spawning in the patch adding it? > > You are defining some variables in a .h file. I think it is a problem. > > Well, they need to be shared between several .c files. So you should use an "extern" trick in order to have only one instance of the variables. But I think it's not a good practice. You probably need to group functions using these variables in one .c file. Or do I miss something? > > Here are some other relevant errors from checkpatch.pl: > Thanks, I'll fix those. Thank you -- Thomas
