2014-05-27 16:21, Burakov, Anatoly:
> > You are defining some variables in a .h file. I think it is a problem.
>
> I have managed to move everything to .c files, except for "struct
> mapped_pci_res_list *pci_res_list;" - which I need in both uio and vfio .c
> files. I don't think I'll be able to
Hi Thomas,
> You are defining some variables in a .h file. I think it is a problem.
I have managed to move everything to .c files, except for "struct
mapped_pci_res_list *pci_res_list;" - which I need in both uio and vfio .c
files. I don't think I'll be able to move it out of the eal_pci_init h
VFIO is kernel 3.6+ only, and so is only compiled when DPDK config
option CONFIG_RTE_EAL_VFIO is enabled, and kernel 3.6 or higher is
detected, thus preventing compile failures on older kernels if VFIO is
enabled in config (and it is, by default).
Since VFIO cannot be used to map the same device t
2014-05-22 12:37, Burakov, Anatoly:
> > 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 g
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 th
Hi Anatoly,
It seems to be the main patch, so I have many comments.
2014-05-19 16:51, Anatoly Burakov:
> VFIO is kernel 3.6+ only, and so is only compiled when DPDK config
> option CONFIG_RTE_EAL_VFIO is enabled, and kernel 3.6 or higher is
> detected, thus preventing compile failures on older ke
Hi Thomas,
> Yes I agree. But I stopped on the name for another thing: it's not really
> specific to vfio. Actually, vfio uses it for synchronization. But wouldn't it
> be
> more generic?
OK, _mp_sync it is then.
Best regards,
Anatoly Burakov
DPDK SW Engineer
Hi Thomas,
> 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
Hi Thomas,
> How did you test this feature?
> Did you see some performance differences with igb_uio?
The same way everything else is tested - bind a NIC to the driver and see if it
works :-)
As for performance differences, potentially it can be degraded a bit because of
mandatory IOMMU involve
VFIO is kernel 3.6+ only, and so is only compiled when DPDK config
option CONFIG_RTE_EAL_VFIO is enabled, and kernel 3.6 or higher is
detected, thus preventing compile failures on older kernels if VFIO is
enabled in config (and it is, by default).
Since VFIO cannot be used to map the same device t
10 matches
Mail list logo
