On Fri 09-11-12 20:09:29, Sha Zhengju wrote:

On 11/09/2012 06:50 PM, Michal Hocko wrote:

quoted

On Fri 09-11-12 18:23:07, Sha Zhengju wrote:

[...]

quoted

quoted

Another one I'm hesitating is numa stats, it seems the output is
beginning to get more and more....

NUMA stats are basically per node - per zone LRU data and that the
for(NR_LRU_LISTS) can be easily extended to cover that.

Yes, the numa_stat cgroup file has done works here. I'll add the numa
stats if you don't feel improper.

I just described how it can be done, I am not saying it is really
needed. What does per-node information tells you during OOM?
memcg OOM is triggered when we hit the hard limit not when we are not
able to fulfill allocation because of the node restriction.
But maybe your use case would benefit from this...
-- 
Michal Hocko
SUSE Labs

--
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:"dont@kvack.org"> email@kvack.org </a>