linux_dsm_epyc7002/kernel/sched/stop_task.c
Mike Galbraith 8f6189684e sched: Fix migration thread runtime bogosity
Make stop scheduler class do the same accounting as other classes,

Migration threads can be caught in the act while doing exec balancing,
leading to the below due to use of unmaintained ->se.exec_start.  The
load that triggered this particular instance was an apparently out of
control heavily threaded application that does system monitoring in
what equated to an exec bomb, with one of the VERY frequently migrated
tasks being ps.

%CPU   PID USER     CMD
99.3    45 root     [migration/10]
97.7    53 root     [migration/12]
97.0    57 root     [migration/13]
90.1    49 root     [migration/11]
89.6    65 root     [migration/15]
88.7    17 root     [migration/3]
80.4    37 root     [migration/8]
78.1    41 root     [migration/9]
44.2    13 root     [migration/2]

Signed-off-by: Mike Galbraith <mgalbraith@suse.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1344051854.6739.19.camel@marge.simpson.net
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2012-08-13 18:41:55 +02:00

129 lines
2.7 KiB
C

#include "sched.h"
/*
* stop-task scheduling class.
*
* The stop task is the highest priority task in the system, it preempts
* everything and will be preempted by nothing.
*
* See kernel/stop_machine.c
*/
#ifdef CONFIG_SMP
static int
select_task_rq_stop(struct task_struct *p, int sd_flag, int flags)
{
return task_cpu(p); /* stop tasks as never migrate */
}
#endif /* CONFIG_SMP */
static void
check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
{
/* we're never preempted */
}
static struct task_struct *pick_next_task_stop(struct rq *rq)
{
struct task_struct *stop = rq->stop;
if (stop && stop->on_rq) {
stop->se.exec_start = rq->clock_task;
return stop;
}
return NULL;
}
static void
enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags)
{
inc_nr_running(rq);
}
static void
dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags)
{
dec_nr_running(rq);
}
static void yield_task_stop(struct rq *rq)
{
BUG(); /* the stop task should never yield, its pointless. */
}
static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
{
struct task_struct *curr = rq->curr;
u64 delta_exec;
delta_exec = rq->clock_task - curr->se.exec_start;
if (unlikely((s64)delta_exec < 0))
delta_exec = 0;
schedstat_set(curr->se.statistics.exec_max,
max(curr->se.statistics.exec_max, delta_exec));
curr->se.sum_exec_runtime += delta_exec;
account_group_exec_runtime(curr, delta_exec);
curr->se.exec_start = rq->clock_task;
cpuacct_charge(curr, delta_exec);
}
static void task_tick_stop(struct rq *rq, struct task_struct *curr, int queued)
{
}
static void set_curr_task_stop(struct rq *rq)
{
struct task_struct *stop = rq->stop;
stop->se.exec_start = rq->clock_task;
}
static void switched_to_stop(struct rq *rq, struct task_struct *p)
{
BUG(); /* its impossible to change to this class */
}
static void
prio_changed_stop(struct rq *rq, struct task_struct *p, int oldprio)
{
BUG(); /* how!?, what priority? */
}
static unsigned int
get_rr_interval_stop(struct rq *rq, struct task_struct *task)
{
return 0;
}
/*
* Simple, special scheduling class for the per-CPU stop tasks:
*/
const struct sched_class stop_sched_class = {
.next = &rt_sched_class,
.enqueue_task = enqueue_task_stop,
.dequeue_task = dequeue_task_stop,
.yield_task = yield_task_stop,
.check_preempt_curr = check_preempt_curr_stop,
.pick_next_task = pick_next_task_stop,
.put_prev_task = put_prev_task_stop,
#ifdef CONFIG_SMP
.select_task_rq = select_task_rq_stop,
#endif
.set_curr_task = set_curr_task_stop,
.task_tick = task_tick_stop,
.get_rr_interval = get_rr_interval_stop,
.prio_changed = prio_changed_stop,
.switched_to = switched_to_stop,
};