Messages in this thread | | | Date | Thu, 18 Nov 2010 18:10:01 +0100 | From | Oleg Nesterov <> | Subject | Re: [RFC][PATCH v2 5/7] taskstats: Improve cumulative CPU time accounting |
| |
Sorry for delay.
On 11/16, Michael Holzheu wrote: > > On Sat, 2010-11-13 at 19:38 +0100, Oleg Nesterov wrote: > > First of all, let me repeat, I am not going to discuss whether we need > > these changes or not, I do not know even if I understand your motivation. > > Sorry, if I was not clear enough with my descriptions. Let me try to > describe my motivation again:
Yes, more or less I see what this patch does (I hope ;).
> 2. Because of reparent to init, there are situations where it is > not clear to which tasks the CPU time of dead tasks between > two snapshots has been accounted. This is a problem for example 2.
Yes, I see.
But I must admit, _personally_ I am not sure this problem worth the trouble. And, I already mentioned daemonize() case, IOW I am not sure it is _always_ right to choose exiting_parent->parent for accounting. To me, this can be equally confusing. A user sees the running deamon with ppid = 1, then this daemon exits and top reports the "unrelated" process as cpu consumer.
But once again. I am _not_ against this patch. I never know when it comes to new features. Certainly you know better if this suits top.
What I actually meant is: dear CC list, please look at this change and comment ;)
Oleg.
| |