Hi,

  first of all, sorry for not being up to date with how the OOM killer

works. I think there used to be a kernel config option to disable

OOM killer and instead kill the process which actually asks for the

memory and supposedly caused the memory lack. That is what I would

like to have on my system. I a have a 1GB RAM laptop and use t-coffee

software from http://www.tcoffee.org/Projects_home_page/t_coffee_home_page.html

to do some science. ;) 
# grep Killed /tmp/dmesg.killed.txt

Killed process 5733 (seamonkey-bin)

Killed process 10011 (t_coffee)

Killed process 5647 (FvwmPager)

Killed process 5659 (xterm)

#
Killing just t_coffee would have been enough.
$ perl -e 'print ">one\n"; print "ATGCCGTAAATGCATG"x100000; print "\n>two"; print "GGGGCCCCAT"x1000; print "\n"' > testcase.txt

$ t_coffee testcase.txt

... [you should run out of memory soon]
So, how can I change the behaviour or kernel?

Please Cc: me in replies. Thanks.

Martin

On Fri, 07 Dec 2007 10:25:23 +0100
The OOM killer triggers where there is no way to fulfill a page request.

Something has to go and there is no real notion of "right" or "wrong"

process at that point.
You can either set no overcommit in which case you'll get failed malloc

and similar rather than allow overcommit, or you can set the OOM priority

of tasks yourself so that your specific app of choice always dies first.
Alan

--