sched: Turn off child_runs_first

Set child_runs_first default to off.

It hurts 'optimal' make -j<NR_CPUS> workloads as make jobs
get preempted by child tasks, reducing parallelism.

Note, this patch might make existing races in user
applications more prominent than before - so breakages
might be bisected to this commit.

Child-runs-first is broken on SMP to begin with, and we
already had it off briefly in v2.6.23 so most of the
offenders ought to be fixed. Would be nice not to revert
this commit but fix those apps finally ...

Signed-off-by: Mike Galbraith <efault@gmx.de>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1252486344.28645.18.camel@marge.simson.net>
[ made the sysctl independent of CONFIG_SCHED_DEBUG, in case
  people want to work around broken apps. ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3b7f43e3b7368909b15de8b7a77c8181742a8fb7..3a50e8222498c90ae42099f53d4645b0183fffff 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1820,8 +1820,8 @@ extern unsigned int sysctl_sched_min_granularity;
 extern unsigned int sysctl_sched_wakeup_granularity;
 extern unsigned int sysctl_sched_shares_ratelimit;
 extern unsigned int sysctl_sched_shares_thresh;
-#ifdef CONFIG_SCHED_DEBUG
 extern unsigned int sysctl_sched_child_runs_first;
+#ifdef CONFIG_SCHED_DEBUG
 extern unsigned int sysctl_sched_features;
 extern unsigned int sysctl_sched_migration_cost;
 extern unsigned int sysctl_sched_nr_migrate;

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index e386e5dfcdae1a1a7856bb96918c418b5f196ee8..af325a382b1b6988823be5835bb55052b16005b4 100644 (file)
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -48,10 +48,10 @@ unsigned int sysctl_sched_min_granularity = 4000000ULL;
 static unsigned int sched_nr_latency = 5;
 
 /*
- * After fork, child runs first. (default) If set to 0 then
+ * After fork, child runs first. If set to 0 (default) then
  * parent will (try to) run first.
  */
-const_debug unsigned int sysctl_sched_child_runs_first = 1;
+unsigned int sysctl_sched_child_runs_first __read_mostly;
 
 /*
  * sys_sched_yield() compat mode

diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 6c9836ef4b47be4df920e3830c1188a551d7d03d..25d6bf3383bea9f8d2f95caca8a34d5bb2df7808 100644 (file)
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -246,6 +246,14 @@ static int max_wakeup_granularity_ns = NSEC_PER_SEC;       /* 1 second */
 #endif
 
 static struct ctl_table kern_table[] = {
+       {
+               .ctl_name       = CTL_UNNUMBERED,
+               .procname       = "sched_child_runs_first",
+               .data           = &sysctl_sched_child_runs_first,
+               .maxlen         = sizeof(unsigned int),
+               .mode           = 0644,
+               .proc_handler   = &proc_dointvec,
+       },
 #ifdef CONFIG_SCHED_DEBUG
        {
                .ctl_name       = CTL_UNNUMBERED,
@@ -298,14 +306,6 @@ static struct ctl_table kern_table[] = {
                .strategy       = &sysctl_intvec,
                .extra1         = &zero,
        },
-       {
-               .ctl_name       = CTL_UNNUMBERED,
-               .procname       = "sched_child_runs_first",
-               .data           = &sysctl_sched_child_runs_first,
-               .maxlen         = sizeof(unsigned int),
-               .mode           = 0644,
-               .proc_handler   = &proc_dointvec,
-       },
        {
                .ctl_name       = CTL_UNNUMBERED,
                .procname       = "sched_features",