On Wed, Nov 17, 2004 at 11:50:36AM +0100, Chris Ross wrote:

Marcelo Tosatti escreveu:

quoted

On Wed, Nov 17, 2004 at 04:06:48AM -0200, Marcelo Tosatti wrote:
Before the swap token patches went in you remember spurious OOM reports  
or things were working fine then?

The oom killer problems arose before and independently of the 
token-based-thrashing patches. I know this because I took a special 
interest in the tbtc patches too (which is why my test machine came to 
have 64MB RAM but 1GB swap).

So even when reaping referenced pages on zero priority scanning 
the OOM killer might be triggered in extreme cases. And as the 
number of tasks increases the chances things go wrong increase.

Please test Andrew's patch, its hopefully good enough for most 
scenarios. Extreme cases are probably still be problematic.

What are the "tbtc" patches ? 

Your testing is of huge value Chris. Thanks.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"aart@kvack.org"> aart@kvack.org </a>