Re: the new VMt

From: Rik van Riel (riel@conectiva.com.br)
Date: Mon Sep 25 2000 - 11:16:29 EST


On Mon, 25 Sep 2000, Alan Cox wrote:

> > > GFP_KERNEL has to be able to fail for 2.4. Otherwise you can get
> > > everything jammed in kernel space waiting on GFP_KERNEL and if the
> > > swapper cannot make space you die.
> >
> > if one can get everything jammed waiting for GFP_KERNEL, and not being
> > able to deallocate anything, thats a VM or resource-limit bug. This
> > situation is just 1% RAM away from the 'root cannot log in', situation.
>
> Unless Im missing something here think about this case
>
> 2 active processes, no swap
>
> #1 #2
> kmalloc 32K kmalloc 16K
> OK OK
> kmalloc 16K kmalloc 32K
> block block
>
> so GFP_KERNEL has to be able to fail - it can wait for I/O in
> some cases with care, but when we have no pages left something
> has to give

The trick here is to:
1) keep some reserved pages around for PF_MEMALLOC tasks
   (we need this anyway)
2) set PF_MEMALLOC on the task you're killing for OOM,
   that way this task will either get the memory or
   fail (note that PF_MEMALLOC tasks don't wait)

This way the OOM-killed task will be able to exit quickly
and the rest of the system will not get killed as a side
effect.

regards,

Rik

--
"What you're running that piece of shit Gnome?!?!"
       -- Miguel de Icaza, UKUUG 2000

http://www.conectiva.com/ http://www.surriel.com/

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



This archive was generated by hypermail 2b29 : Sat Sep 30 2000 - 21:00:15 EST