Subject: Re: Prototype kernel continuation-passing for NetBSD
To: Bill Studenmund <wrstuden@netbsd.org>
From: Jonathan Stone <jonathan@dsg.stanford.edu>
List: tech-kern
Date: 03/26/2004 17:39:45
Bill,

I will have another crack at splice(2) very, very soon; but as I said,
the references to curproc in our uipc code broke my first, quick try.

Yes, I have direct implementation experience with something very, very
similar to kcont(9), that implemented sendfile() and splice().

For various reasons, I'm waiting until I can clean up a whole bunch of
curproc uses before taking another pass at splice(2). That'll give us
something concrete to read and discuss design points, without
referencing any proprietary code. I'd much prefer to avoid the latter.