forked from luck/tmp_suning_uos_patched
sched: Set an initial value of runnable avg for new forked task
We need to initialize the se.avg.{decay_count, load_avg_contrib} for a new forked task. Otherwise random values of above variables cause a mess when a new task is enqueued: enqueue_task_fair enqueue_entity enqueue_entity_load_avg and make fork balancing imbalance due to incorrect load_avg_contrib. Further more, Morten Rasmussen notice some tasks were not launched at once after created. So Paul and Peter suggest giving a start value for new task runnable avg time same as sched_slice(). PeterZ said: > So the 'problem' is that our running avg is a 'floating' average; ie. it > decays with time. Now we have to guess about the future of our newly > spawned task -- something that is nigh impossible seeing these CPU > vendors keep refusing to implement the crystal ball instruction. > > So there's two asymptotic cases we want to deal well with; 1) the case > where the newly spawned program will be 'nearly' idle for its lifetime; > and 2) the case where its cpu-bound. > > Since we have to guess, we'll go for worst case and assume its > cpu-bound; now we don't want to make the avg so heavy adjusting to the > near-idle case takes forever. We want to be able to quickly adjust and > lower our running avg. > > Now we also don't want to make our avg too light, such that it gets > decremented just for the new task not having had a chance to run yet -- > even if when it would run, it would be more cpu-bound than not. > > So what we do is we make the initial avg of the same duration as that we > guess it takes to run each task on the system at least once -- aka > sched_slice(). > > Of course we can defeat this with wakeup/fork bombs, but in the 'normal' > case it should be good enough. Paul also contributed most of the code comments in this commit. Signed-off-by: Alex Shi <alex.shi@intel.com> Reviewed-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Reviewed-by: Paul Turner <pjt@google.com> [peterz; added explanation of sched_slice() usage] Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1371694737-29336-4-git-send-email-alex.shi@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
parent
fa6bddeb14
commit
a75cdaa915
|
@ -1611,10 +1611,6 @@ static void __sched_fork(struct task_struct *p)
|
|||
p->se.vruntime = 0;
|
||||
INIT_LIST_HEAD(&p->se.group_node);
|
||||
|
||||
#ifdef CONFIG_SMP
|
||||
p->se.avg.runnable_avg_period = 0;
|
||||
p->se.avg.runnable_avg_sum = 0;
|
||||
#endif
|
||||
#ifdef CONFIG_SCHEDSTATS
|
||||
memset(&p->se.statistics, 0, sizeof(p->se.statistics));
|
||||
#endif
|
||||
|
@ -1758,6 +1754,8 @@ void wake_up_new_task(struct task_struct *p)
|
|||
set_task_cpu(p, select_task_rq(p, SD_BALANCE_FORK, 0));
|
||||
#endif
|
||||
|
||||
/* Initialize new task's runnable average */
|
||||
init_task_runnable_average(p);
|
||||
rq = __task_rq_lock(p);
|
||||
activate_task(rq, p, 0);
|
||||
p->on_rq = 1;
|
||||
|
|
|
@ -680,6 +680,26 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|||
return calc_delta_fair(sched_slice(cfs_rq, se), se);
|
||||
}
|
||||
|
||||
#ifdef CONFIG_SMP
|
||||
static inline void __update_task_entity_contrib(struct sched_entity *se);
|
||||
|
||||
/* Give new task start runnable values to heavy its load in infant time */
|
||||
void init_task_runnable_average(struct task_struct *p)
|
||||
{
|
||||
u32 slice;
|
||||
|
||||
p->se.avg.decay_count = 0;
|
||||
slice = sched_slice(task_cfs_rq(p), &p->se) >> 10;
|
||||
p->se.avg.runnable_avg_sum = slice;
|
||||
p->se.avg.runnable_avg_period = slice;
|
||||
__update_task_entity_contrib(&p->se);
|
||||
}
|
||||
#else
|
||||
void init_task_runnable_average(struct task_struct *p)
|
||||
{
|
||||
}
|
||||
#endif
|
||||
|
||||
/*
|
||||
* Update the current task's runtime statistics. Skip current tasks that
|
||||
* are not in our scheduling class.
|
||||
|
@ -1527,6 +1547,10 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
|
|||
* We track migrations using entity decay_count <= 0, on a wake-up
|
||||
* migration we use a negative decay count to track the remote decays
|
||||
* accumulated while sleeping.
|
||||
*
|
||||
* Newly forked tasks are enqueued with se->avg.decay_count == 0, they
|
||||
* are seen by enqueue_entity_load_avg() as a migration with an already
|
||||
* constructed load_avg_contrib.
|
||||
*/
|
||||
if (unlikely(se->avg.decay_count <= 0)) {
|
||||
se->avg.last_runnable_update = rq_clock_task(rq_of(cfs_rq));
|
||||
|
|
|
@ -1048,6 +1048,8 @@ extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime
|
|||
|
||||
extern void update_idle_cpu_load(struct rq *this_rq);
|
||||
|
||||
extern void init_task_runnable_average(struct task_struct *p);
|
||||
|
||||
#ifdef CONFIG_PARAVIRT
|
||||
static inline u64 steal_ticks(u64 steal)
|
||||
{
|
||||
|
|
Loading…
Reference in New Issue
Block a user