Avi Kivity wrote:
Anthony Liguori wrote:
I don't think it's established that PV/VF will have less latency than
using virtio-net. virtio-net requires a world switch to send a group
of packets. The cost of this (if it stays in kernel) is only a few
thousand cycles on the most modern processors.
Using VT-d means that for every DMA fetch that misses in the IOTLB,
you potentially have to do four memory fetches to main memory. There
will be additional packet latency using VT-d compared to native, it's
just not known how much at this time.
If the IOTLB has intermediate TLB entries like the processor, we're
talking just one or two fetches. That's a lot less than the cacheline
bouncing that virtio and kvm interrupt injection incur right now.
The PCI SIG Address Translation Service (ATS) specifies a way that uses
an Address Translation Cache (ATC) in the Endpoint to reduce the latency.
The Linux kernel support for ATS capability will come soon.
Thanks,
Yu
--
To unsubscribe from this list: send the line "unsubscribe linux-pci" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
