Re: L4Mach or Refactor Hurd Servers?

[Ian Duggan]

> Hmm. My understanding is that Spring was a research project, never
> intended to be released to real customers. Instead, the experience
> from it was used when doing Solaris. So that Spring preceded Solaris.
> Looking at the references in the overview I'm reading, it seems many
> Spring papers were published in -93, so I guess most of the work was
> done about ten years ago. But I don't really know the history.

I took what I said from the notes at the bottom of this page. The
presentation links at the top have some info as well.

http://sdg.lcs.mit.edu/~jchapin/6853-FT97/Notes/nov-19/nov-19.html


> Both needs some system support, be that in the kernel or in some
> special server. Having a single server responsible for all port
> rights/door handles is a little against my intuition (in particular if
> that server get's involved on every or most of the rpc calls), but
> perhaps that's the L4 way. Unless the L4 folks add some more useful,
> capability like, security mechanisms to the kernel.

Well, one advantage to having one server involved in all of the IPC
stuff is cache usage. The papers related to L4 indicate that one reason
that very small microkernels are better than large ones like Mach is
that they don't fill the cache completely as often. I think you might
get similar results if you could construct performance critical servers
to take advantage of this effect.

-- Ian

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Ian Duggan                    ian@ianduggan.net
                              http://www.ianduggan.net