On Fri 09-11-12 20:09:29, Sha Zhengju wrote: > On 11/09/2012 06:50 PM, Michal Hocko wrote: > >On Fri 09-11-12 18:23:07, Sha Zhengju wrote: [...] > >>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@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>