Re: [PATCH] TCP Zero Copy for mmapped files

[Larry McVoy]

> > 1) Does not handle writes that straddle multiple VMAs
> 
> What exactly do you mean? In my test, files larger than a
> page were handled perfectly, as well.

	mmap(file1 at location [a,b)
	mmap(file2 at location [b,c)
	write(sock, a, (size_t)(c - a));

> However, I didn't like the VM waste either, but I believe there
> is no other way.

The VM cost hurts.  Badly.  Imagine that the network costs ZERO.  Then
the map/unmap/vm ops become the dominating term.  That's why it is a
fruitless approach, it still has a practical limit which is too low.