Zero Copy I: User-Mode Perspective

One of the problems with the sendfile system call, in general, is the lack of a standard implementation, as there is for the open system call. Sendfile implementations in Linux, Solaris or HP-UX are quite different. This poses a problem for developers who wish to use zero copy in their network data transmission code.

One of the implementation differences is Linux provides a sendfile that defines an interface for transmitting data between two file descriptors (file-to-file) and (file-to-socket). HP-UX and Solaris, on the other hand, can be used only for file-to-socket submissions.

The second difference is Linux doesn't implement vectored transfers. Solaris sendfile and HP-UX sendfile have extra parameters that eliminate overhead associated with prepending headers to the data being transmitted.

The implementation of zero copy under Linux is far from finished and is likely to change in the near future. More functionality should be added. For example, the sendfile call doesn't support vectored transfers, and servers such as Samba and Apache have to use multiple sendfile calls with the TCP_CORK flag set. This flag tells the system more data is coming through in the next sendfile calls. TCP_CORK also is incompatible with TCP_NODELAY and is used when we want to prepend or append headers to the data. This is a perfect example of where a vectored call would eliminate the need for multiple sendfile calls and delays mandated by the current implementation.

One rather unpleasant limitation in the current sendfile is it cannot be used when transferring files greater than 2GB. Files of such size are not all that uncommon today, and it's rather disappointing having to duplicate all that data on its way out. Because both sendfile and mmap methods are unusable in this case, a sendfile64 would be really handy in a future kernel version.

Despite some drawbacks, zero-copy sendfile is a useful feature, and I hope you have found this article informative enough to start using it in your programs. If you have a more in-depth interest in the subject, keep an eye out for my second article, titled “Zero Copy II: Kernel Perspective”, where I will dig a bit more into the kernel internals of zero copy.

Further Information