Page table optimizations in Linux and FreeBSD

[Jamie Lokier]

Jeff Garzik wrote:
> Forwarded without no comment other than it's a good read:

I noticed was where they say: if process forks into A and B, and both A
and B write to the fresh COW pages, then the original page is not
released to the system.  It's wasted.  That is, not until all the COW
pages in a VM area have been written to (it uses a counter).

Ew.

There's also a bit on page pre-zeroing, and another bit on how it's not
actually implemented.

The do mention pre-faulting and pre-emptive page out.  I don't know if
we do pre-faulting but I believe we do pre-emptive page out now.

-- Jamie

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo en vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/