On Fri, May 30, 2014 at 10:14:17AM +0100, Daniel P. Berrange wrote: > On Thu, May 29, 2014 at 10:32:46AM +0200, Michal Privoznik wrote: > > A PCI device can be associated with a specific NUMA node. Later, when > > a guest is pinned to one NUMA node the PCI device can be assigned on > > different NUMA node. This makes DMA transfers travel across nodes and > > thus results in suboptimal performance. We should expose the NUMA node > > locality for PCI devices so management applications can make better > > decisions. > > > > Signed-off-by: Michal Privoznik <mprivozn@xxxxxxxxxx> > > --- > > > > Notes: > > All the machines I have tried this on had only -1 in the > > numa_node file. From the kernel sources it seems that this is the > > default, so I'm not printing the <numa/> element into the XML in > > this case. But I'd like to hear your opinion. > > Yes, I believe '-1' means that there is no NUMA locality info > available for the device, so it makes sense to skip this. Confirmed in the kernel source include/linux/numa.h:#define NUMA_NO_NODE (-1) Is used when the ACPI tables don't specify any NUMA node for the PCI device, or when the NUMA node is not online. Regards, Daniel -- |: http://berrange.com -o- http://www.flickr.com/photos/dberrange/ :| |: http://libvirt.org -o- http://virt-manager.org :| |: http://autobuild.org -o- http://search.cpan.org/~danberr/ :| |: http://entangle-photo.org -o- http://live.gnome.org/gtk-vnc :| -- libvir-list mailing list libvir-list@xxxxxxxxxx https://www.redhat.com/mailman/listinfo/libvir-list