до сих пор ставлю в граб
kvm-amd npt=0
оно ещё нужно в qemu 2.5/2.6 или это hardware fail и оно не починится?
до сих пор добавляю
iommu=pt
блин, это не противоречит верхнему? и что ещё посоветуете?
полный граб:\
GRUB_CMDLINE_LINUX_DEFAULT=«elevator=deadline vfio-pci.ids=1002:6819,1002:aab0,1002:4383 amd_iommu=on iommu=1 iommu_inclusive_mapping=1 iommu=pt amd_iommu=fullflush cpufreq=dom0-kernel console=xvc console=tty xen-pciback.passthrough=1 kvm-amd npt=0»
какие то разъяснения:
The map and umap operation for each e/ingress packet is done by hw rather than sw, so
performance impact to DPDK should be minimum in my mind. If it actually impacst perf, say on 100G NIC,
I am sure it will be resolved in next generation Intel silicon. We will be performing some performance
tests with iommu = on to see any performance degradation. I cannot share the detailed performance
result here on the community, but I could tell if it really bring negative performance impact to DPDK.
Please stay tuned.