Files
ubports_kernel_google_msm/include/linux
Hidetoshi Seto 0cf55e1ec0 sched, cputime: Introduce thread_group_times()
This is a real fix for problem of utime/stime values decreasing
described in the thread:

   http://lkml.org/lkml/2009/11/3/522

Now cputime is accounted in the following way:

 - {u,s}time in task_struct are increased every time when the thread
   is interrupted by a tick (timer interrupt).

 - When a thread exits, its {u,s}time are added to signal->{u,s}time,
   after adjusted by task_times().

 - When all threads in a thread_group exits, accumulated {u,s}time
   (and also c{u,s}time) in signal struct are added to c{u,s}time
   in signal struct of the group's parent.

So {u,s}time in task struct are "raw" tick count, while
{u,s}time and c{u,s}time in signal struct are "adjusted" values.

And accounted values are used by:

 - task_times(), to get cputime of a thread:
   This function returns adjusted values that originates from raw
   {u,s}time and scaled by sum_exec_runtime that accounted by CFS.

 - thread_group_cputime(), to get cputime of a thread group:
   This function returns sum of all {u,s}time of living threads in
   the group, plus {u,s}time in the signal struct that is sum of
   adjusted cputimes of all exited threads belonged to the group.

The problem is the return value of thread_group_cputime(),
because it is mixed sum of "raw" value and "adjusted" value:

  group's {u,s}time = foreach(thread){{u,s}time} + exited({u,s}time)

This misbehavior can break {u,s}time monotonicity.
Assume that if there is a thread that have raw values greater
than adjusted values (e.g. interrupted by 1000Hz ticks 50 times
but only runs 45ms) and if it exits, cputime will decrease (e.g.
-5ms).

To fix this, we could do:

  group's {u,s}time = foreach(t){task_times(t)} + exited({u,s}time)

But task_times() contains hard divisions, so applying it for
every thread should be avoided.

This patch fixes the above problem in the following way:

 - Modify thread's exit (= __exit_signal()) not to use task_times().
   It means {u,s}time in signal struct accumulates raw values instead
   of adjusted values.  As the result it makes thread_group_cputime()
   to return pure sum of "raw" values.

 - Introduce a new function thread_group_times(*task, *utime, *stime)
   that converts "raw" values of thread_group_cputime() to "adjusted"
   values, in same calculation procedure as task_times().

 - Modify group's exit (= wait_task_zombie()) to use this introduced
   thread_group_times().  It make c{u,s}time in signal struct to
   have adjusted values like before this patch.

 - Replace some thread_group_cputime() by thread_group_times().
   This replacements are only applied where conveys the "adjusted"
   cputime to users, and where already uses task_times() near by it.
   (i.e. sys_times(), getrusage(), and /proc/<PID>/stat.)

This patch have a positive side effect:

 - Before this patch, if a group contains many short-life threads
   (e.g. runs 0.9ms and not interrupted by ticks), the group's
   cputime could be invisible since thread's cputime was accumulated
   after adjusted: imagine adjustment function as adj(ticks, runtime),
     {adj(0, 0.9) + adj(0, 0.9) + ....} = {0 + 0 + ....} = 0.
   After this patch it will not happen because the adjustment is
   applied after accumulated.

v2:
 - remove if()s, put new variables into signal_struct.

Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Spencer Candland <spencer@bluehost.com>
Cc: Americo Wang <xiyou.wangcong@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
LKML-Reference: <4B162517.8040909@jp.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-02 17:32:40 +01:00
..
2009-09-23 07:39:29 -07:00
2009-06-18 08:46:47 +10:00
2009-09-09 11:19:00 -04:00
2009-09-19 02:14:45 -04:00
2009-06-17 00:36:36 -04:00
2009-09-20 16:09:20 +05:30
2009-09-08 17:42:50 -07:00
2009-04-01 08:59:23 -07:00
2009-06-01 06:21:13 +00:00
2009-04-23 10:06:35 +01:00
2009-06-11 21:36:09 -04:00
2009-07-12 12:22:34 -07:00
2009-09-23 11:01:25 -07:00
2009-07-14 20:29:57 +08:00
2009-06-11 21:36:06 -04:00
2009-09-18 09:48:52 -07:00
2009-06-22 10:12:30 +01:00
2009-05-18 14:46:26 +01:00
2009-04-03 14:53:32 -07:00
2009-09-14 17:41:42 -07:00
2009-06-17 09:33:49 -07:00
2009-07-08 09:18:05 -07:00
2009-03-16 08:32:27 -06:00
2009-09-12 14:48:40 +02:00
2009-06-15 21:30:25 -07:00
2009-06-18 13:04:05 -07:00
2009-09-01 01:13:31 -07:00
2009-09-01 17:52:57 -07:00
2009-04-02 19:04:53 -07:00
2009-09-11 12:54:58 -07:00
2009-08-19 23:08:24 +04:00
2009-07-26 19:25:44 -07:00
2009-06-29 08:59:10 +10:00
2009-06-02 00:45:24 -07:00
2009-07-31 08:55:48 +02:00
2009-09-23 07:39:41 -07:00
2009-06-18 13:03:56 -07:00
2009-09-26 10:17:19 -07:00
2009-04-21 13:41:48 -07:00
2009-04-21 13:41:48 -07:00
2009-08-29 15:53:00 +02:00
2009-09-30 00:32:06 -04:00
2009-09-23 07:39:58 -07:00
2009-09-19 13:13:17 -07:00
2009-09-26 10:17:19 -07:00
2009-09-22 07:17:33 -07:00
2009-09-18 21:22:08 +02:00
2009-04-06 16:06:26 +01:00
2009-06-23 20:21:39 +01:00
2009-07-30 16:03:45 +09:30
2009-10-06 00:26:27 -04:00
2009-04-28 07:37:28 +02:00
2009-06-16 19:47:48 -07:00
2009-09-23 07:39:41 -07:00
2009-09-22 07:17:35 -07:00
2009-06-16 08:40:20 +02:00
2009-04-29 17:32:35 -07:00
2009-07-08 09:31:56 -07:00
2009-06-11 21:36:02 -04:00
2009-03-20 10:48:14 -07:00
2009-09-21 15:14:51 +02:00
2009-06-17 18:02:11 -07:00
2009-06-17 18:02:11 -07:00
2009-09-26 10:17:19 -07:00
2009-06-17 12:24:34 -07:00
2009-06-17 18:02:11 -07:00
2009-03-10 20:33:18 -04:00
2009-06-15 21:44:43 -07:00
2009-04-01 08:59:13 -07:00
2009-04-01 08:59:13 -07:00
2009-04-24 08:54:21 +02:00
2009-09-22 07:17:47 -07:00
2009-10-04 15:05:10 -07:00
2009-03-13 16:09:12 -07:00
2009-06-18 13:04:04 -07:00
2009-07-29 19:10:36 -07:00
2009-12-02 09:55:33 +01:00
2009-09-23 07:39:41 -07:00
2009-03-30 15:22:01 +02:00
2009-06-11 21:36:12 -04:00
2009-03-26 02:18:35 +01:00
2009-08-23 19:13:02 -07:00
2009-06-24 08:17:06 -04:00
2009-09-01 12:48:21 -04:00
2009-05-09 10:49:41 -04:00
2009-04-01 08:59:24 -07:00
2009-04-08 14:33:38 -07:00
2009-08-28 19:57:30 -04:00
2009-04-13 15:04:29 -07:00
2009-10-30 12:25:12 -07:00
2009-06-15 15:50:49 +02:00
2009-04-21 19:40:00 -07:00
2009-04-27 02:45:02 -07:00
2009-03-27 12:18:56 -04:00
2009-08-31 18:08:51 +02:00
2009-05-12 11:11:48 +02:00
2009-10-29 07:39:25 -07:00
2009-04-02 19:05:01 -07:00
2009-07-06 13:57:03 -07:00
2009-09-02 01:03:43 -07:00
2009-08-30 22:26:34 +02:00
2009-09-23 06:46:23 -07:00
2009-09-23 18:13:10 -07:00
2009-08-26 12:39:29 +01:00
2009-09-23 22:26:32 +09:30
2009-09-22 07:17:30 -07:00
2009-09-19 13:13:25 -07:00
2009-09-19 13:13:26 -07:00
2009-09-15 16:51:30 +02:00