vmalloc for zlib workspace

[Jörn Engel]

On Mon, 26 May 2003 14:38:28 +0100, David Woodhouse wrote:
> On Mon, 2003-05-26 at 13:35, Jörn Engel wrote:
> > A workmate of mine had another good point.  The mutex and workspace
> > could be two arrays instead, with one member per CPU.  That way, we
> > don't need a CONFIG_TINY option and the code scales automatically from
> > small embedded to multi-gigabyte SMP.
> 
> Assuming you add a preempt_disable()... in one of the pieces of code
> which was one of the main culprits for non-voluntary scheduling anyway.

Good point!

preempt_disable();
down();
//long processing time
up();
preempt_enable();

That way, preemption will be turned of on all CPUs for a long time,
doesn't sound too inviting.  But until preemption is able to be
(en|dis)abled for the current CPU only, I will ignore that problem.

Jörn

-- 
Sometimes, asking the right question is already the answer.
-- Unknown