> Well, but what else would a copy_file do in this situation? As the file
> does not fit into memory: Hohum, it has to read it again and copy it to
> the network adapter. It would be nice if the SCSI adapter (we are not
> talking about something else, do we?) could write the data directly to the
> network interface card. This is what I expect to happen in a workstation.
> But I doubt it will be ever possible with PC hardware.
The idea is that a kernel file_copy call could read ahead on a source
file, leave the data in page buffers, and write behind to the
destination file directly from there. There is potential for a
performance gain by avoiding the need for user-space access to the
data. Without user-mode access, however, this trick can only be
played from the kernel.
-- John Kodis.