On Tue, 5 Dec 1995, Michael Galassi wrote:

> The questions become, is the real benefit worth additional kernel
> bloating?   I'm not looking at size as much as interface complexity
> here.  Would the feature realy get used much given its NetBSD only
> support?  Can we reduce the syscall overhead to where performance
> is no longer an issue and provide a more generalized high performance
> threadlocking mechanism such that the atomicity is no longer an issue?

My question is: how is this better than mmapping the file and accessing 
it directly?  By adding the offset to the syscall you have already made 
your code incompatible with the rest of the world.  What do you get by 
using pread you don't get using mmap(), and do you still see a 5-10% 
performance advantage?

Eduardo