On Tue, Jun 29, 2021 at 12:13 PM Jason Wang <jasowang@xxxxxxxxxx> wrote:
If so, it might be hard to use umem. Because we can't use umem for
在 2021/6/28 下午6:32, Yongji Xie 写道:
Note that userspace should be unaware of the existence of the bounce buffer.The large barrier is bounce-buffer mapping: SPDK requires hugepagesI think we can support registering user space memory for bounce-buffer
for NVMe over PCIe and RDMA, so take some preallcoated hugepages to
map as bounce buffer is necessary. Or it's hard to avoid an extra
memcpy from bounce-buffer to hugepage.
If you can add an option to map hugepages as bounce-buffer,
then SPDK could also be a potential user of vduse.
use like XDP does. But this needs to pin the pages, so I didn't
consider it in this initial version.
coherent mapping which needs physical address contiguous space.
Thanks,
Yongji