Paul Menage wrote: > On 8/5/06, Srivatsa Vaddagiri <[EMAIL PROTECTED]> wrote: >> The other useful statistics (which is kind of inverse of this) is to know >> the "blocking" time on runqueue for different tasks. This other statistics >> should be available already in recent kernels (as part of delaystats >> feature) and is exported to user-space over netlink interface (which >> should be less expensive compared to /proc). > > I took a look at that - as far as I could see, the interface is > restricted to "tell me the stats for pid X now" and "send me stats > whenever a process exits". Neither of those provide the kind of > aggregation/tracking support that you can easily get with resource > groups. > > Paul >
You can get the pid or tgid stats. I could not go through your patch, I could not find the functions you patched. I'll comment once I can see them -- Balbir Singh, Linux Technology Center, IBM Software Labs ------------------------------------------------------------------------- Take Surveys. Earn Cash. Influence the Future of IT Join SourceForge.net's Techsay panel and you'll get the chance to share your opinions on IT & business topics through brief surveys -- and earn cash http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV _______________________________________________ ckrm-tech mailing list https://lists.sourceforge.net/lists/listinfo/ckrm-tech