signal: re-add dead task accumulation stats.

We're going to split the process wide cpu accounting into two parts:

 - clocks; which can take all the time they want since they run
           from user context.

 - timers; which need constant time tracing but can affort the overhead
           because they're default off -- and rare.

The clock readout will go back to a full sum of the thread group, for this
we need to re-add the exit stats that were removed in the initial itimer
rework (f06febc9: timers: fix itimer/many thread hang).

Furthermore, since that full sum can be rather slow for large thread groups
and we have the complete dead task stats, revert the do_notify_parent time
computation.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Reviewed-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2127e95..2e0646a 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -559,7 +559,7 @@ struct signal_struct {
         * Live threads maintain their own counters and add to these
         * in __exit_signal, except for the group leader.
         */
-       cputime_t cutime, cstime;
+       cputime_t utime, stime, cutime, cstime;
        cputime_t gtime;
        cputime_t cgtime;
        unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
@@ -568,6 +568,14 @@ struct signal_struct {
        struct task_io_accounting ioac;
 
        /*
+        * Cumulative ns of schedule CPU time fo dead threads in the
+        * group, not including a zombie group leader, (This only differs
+        * from jiffies_to_ns(utime + stime) if sched_clock uses something
+        * other than jiffies.)
+        */
+       unsigned long long sum_sched_runtime;
+
+       /*
         * We don't bother to synchronize most readers of this at all,
         * because there is no reader checking a limit that actually needs
         * to get both rlim_cur and rlim_max atomically, and either one

diff --git a/kernel/exit.c b/kernel/exit.c
index f80dec3..efd30cc 100644 (file)
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -118,6 +118,8 @@ static void __exit_signal(struct task_struct *tsk)
                 * We won't ever get here for the group leader, since it
                 * will have been the last reference on the signal_struct.
                 */
+               sig->utime = cputime_add(sig->utime, task_utime(tsk));
+               sig->stime = cputime_add(sig->stime, task_stime(tsk));
                sig->gtime = cputime_add(sig->gtime, task_gtime(tsk));
                sig->min_flt += tsk->min_flt;
                sig->maj_flt += tsk->maj_flt;
@@ -126,6 +128,7 @@ static void __exit_signal(struct task_struct *tsk)
                sig->inblock += task_io_get_inblock(tsk);
                sig->oublock += task_io_get_oublock(tsk);
                task_io_accounting_add(&sig->ioac, &tsk->ioac);
+               sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
                sig = NULL; /* Marker for below. */
        }
 

diff --git a/kernel/fork.c b/kernel/fork.c
index 242a706..e8e854a 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -851,13 +851,14 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
        sig->tty_old_pgrp = NULL;
        sig->tty = NULL;
 
-       sig->cutime = sig->cstime = cputime_zero;
+       sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero;
        sig->gtime = cputime_zero;
        sig->cgtime = cputime_zero;
        sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
        sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
        sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
        task_io_accounting_init(&sig->ioac);
+       sig->sum_sched_runtime = 0;
        taskstats_tgid_init(sig);
 
        task_lock(current->group_leader);

diff --git a/kernel/signal.c b/kernel/signal.c
index b6b3676..2a74fe8 100644 (file)
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1367,7 +1367,6 @@ int do_notify_parent(struct task_struct *tsk, int sig)
        struct siginfo info;
        unsigned long flags;
        struct sighand_struct *psig;
-       struct task_cputime cputime;
        int ret = sig;
 
        BUG_ON(sig == -1);
@@ -1397,9 +1396,10 @@ int do_notify_parent(struct task_struct *tsk, int sig)
        info.si_uid = __task_cred(tsk)->uid;
        rcu_read_unlock();
 
-       thread_group_cputime(tsk, &cputime);
-       info.si_utime = cputime_to_jiffies(cputime.utime);
-       info.si_stime = cputime_to_jiffies(cputime.stime);
+       info.si_utime = cputime_to_clock_t(cputime_add(tsk->utime,
+                               tsk->signal->utime));
+       info.si_stime = cputime_to_clock_t(cputime_add(tsk->stime,
+                               tsk->signal->stime));
 
        info.si_status = tsk->exit_code & 0x7f;
        if (tsk->exit_code & 0x80)