On Mon, Jan 31, 2011 at 2:31 PM, Sri Ram Vemulpali
[off-list ref] wrote:

Hi all,

?This is regarding segment fault. Is there any feature that we can
allow kernel to kill only the thread that generate seg fault rather
than killing whole process in which it is running. Why is that we did
not implement in such way. Is there any specific reason. Thanks in
advance for explanation.

What is the guarantee that whole process isn't hosed up ? For example
let's say a global pointer became NULL and we died accessing it from 1
of the threads. I'm not sure if it would be better to have 'N'
coredumps as opposed to just 1.


-- 
Thanks -
Manish