Messages in this thread | | | Date | Sun, 8 Sep 2013 12:59:33 +0200 | From | Frederic Weisbecker <> | Subject | Re: [sched next] overflowed cpu time for kernel threads in /proc/PID/stat |
| |
On Sat, Aug 31, 2013 at 10:01:17PM +0300, Sergey Senozhatsky wrote: > On (08/31/13 01:04), Frederic Weisbecker wrote: > > But stime should always be below rtime due to the calculation done by scale_stime() > > which roughly sums up to: > > > > stime = (stime / stime + utime) * rtime > > > > So this shouldn't happen. > > > > I couldn't manage to reproduce it though. Can you still trigger it with latest -next? > > > > Thanks. > > Hello, > I can't pull current -next (away from good network connection for a > couple of days). What I have is 3.11.0-rc7-next-20130829: > > ps aux | grep rcu > root 8 0.0 0.0 0 0 ? S Aug30 0:00 [rcuc/0] > root 9 0.0 0.0 0 0 ? S Aug30 0:00 [rcub/0] > root 10 21376376 0.0 0 0 ? S Aug30 21114581:36 [rcu_preempt] > root 11 21376376 0.0 0 0 ? S Aug30 21114581:35 [rcuop/0] > root 12 21376376 0.0 0 0 ? S Aug30 21114581:35 [rcuop/1] > > cat /proc/10/stat > 10 (rcu_preempt) S 2 0 0 0 -1 2129984 0 0 0 0 1844674407370 715 0 0 20 0 1 0 10 0 0 18446744073709551615 0 0 0 0 0 0 0 2147483647 0 18446744073709551615 0 0 17 0 0 0 0 0 0 0 0 0 0 0 0 0 0 > > -ss
Sorry, I did not realize this message was posted before you tested the patch.
| |