Re: Notebooks

Linus Torvalds (torvalds@transmeta.com)
Wed, 19 Aug 1998 09:51:49 -0700 (PDT)


On Wed, 19 Aug 1998, David S. Miller wrote:
>
> That doesn't mean that I like the slab code. I've never been very
> thrilled about how is blithely assumes that it's ok to just allocate
> higher orders of pages, and this just made it even more clear that that
> was not a good design choice in the slab code.
>
> Task struct/kstack allocations make the same blithful assumption, what
> is the difference?

David, maybe the difference is that when the stack allocation fails, it
doesn't lock up the whole machine in a endless loop? Think about it for a
moment.

And yes, it wasn't "slab" that locked the machine. But it was certainly
slab that made it almost impossible to see from the sources that it was
going to do a multi-page-order allocation and that it was a lot more
dangerous than it used to be in 2.0.x..

That code _worked_ in 2.0.x. Not because the 2.0.x memory management was
any better than the current one, like some people have tried to maintain.
But because of the current slab code.

Linus

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