2007-07-09 18:51:58 +02:00
|
|
|
/*
|
|
|
|
* Completely Fair Scheduling (CFS) Class (SCHED_NORMAL/SCHED_BATCH)
|
|
|
|
*
|
|
|
|
* Copyright (C) 2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
|
|
|
|
*
|
|
|
|
* Interactivity improvements by Mike Galbraith
|
|
|
|
* (C) 2007 Mike Galbraith <efault@gmx.de>
|
|
|
|
*
|
|
|
|
* Various enhancements by Dmitry Adamushko.
|
|
|
|
* (C) 2007 Dmitry Adamushko <dmitry.adamushko@gmail.com>
|
|
|
|
*
|
|
|
|
* Group scheduling enhancements by Srivatsa Vaddagiri
|
|
|
|
* Copyright IBM Corporation, 2007
|
|
|
|
* Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
|
|
|
|
*
|
|
|
|
* Scaled math optimizations by Thomas Gleixner
|
|
|
|
* Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de>
|
2007-08-25 18:41:53 +02:00
|
|
|
*
|
|
|
|
* Adaptive scheduling granularity, math enhancements by Peter Zijlstra
|
|
|
|
* Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
|
2007-07-09 18:51:58 +02:00
|
|
|
*/
|
|
|
|
|
2007-10-15 17:00:02 +02:00
|
|
|
/*
|
|
|
|
* Tunables that become constants when CONFIG_SCHED_DEBUG is off:
|
|
|
|
*/
|
|
|
|
#ifdef CONFIG_SCHED_DEBUG
|
|
|
|
# define const_debug __read_mostly
|
|
|
|
#else
|
|
|
|
# define const_debug static const
|
|
|
|
#endif
|
|
|
|
|
2007-07-09 18:51:58 +02:00
|
|
|
/*
|
2007-08-25 18:41:53 +02:00
|
|
|
* Targeted preemption latency for CPU-bound tasks:
|
|
|
|
* (default: 20ms, units: nanoseconds)
|
2007-07-09 18:51:58 +02:00
|
|
|
*
|
2007-08-25 18:41:53 +02:00
|
|
|
* NOTE: this latency value is not the same as the concept of
|
|
|
|
* 'timeslice length' - timeslices in CFS are of variable length.
|
|
|
|
* (to see the precise effective timeslice length of your workload,
|
|
|
|
* run vmstat and monitor the context-switches field)
|
2007-07-09 18:51:58 +02:00
|
|
|
*
|
|
|
|
* On SMP systems the value of this is multiplied by the log2 of the
|
|
|
|
* number of CPUs. (i.e. factor 2x on 2-way systems, 3x on 4-way
|
|
|
|
* systems, 4x on 8-way systems, 5x on 16-way systems, etc.)
|
2007-08-25 18:41:53 +02:00
|
|
|
* Targeted preemption latency for CPU-bound tasks:
|
2007-07-09 18:51:58 +02:00
|
|
|
*/
|
2007-10-15 17:00:02 +02:00
|
|
|
const_debug unsigned int sysctl_sched_latency = 20000000ULL;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* After fork, child runs first. (default) If set to 0 then
|
|
|
|
* parent will (try to) run first.
|
|
|
|
*/
|
|
|
|
const_debug unsigned int sysctl_sched_child_runs_first = 1;
|
2007-08-25 18:41:53 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Minimal preemption granularity for CPU-bound tasks:
|
|
|
|
* (default: 2 msec, units: nanoseconds)
|
|
|
|
*/
|
2007-08-25 18:41:53 +02:00
|
|
|
unsigned int sysctl_sched_min_granularity __read_mostly = 2000000ULL;
|
2007-07-09 18:51:58 +02:00
|
|
|
|
2007-09-19 23:34:46 +02:00
|
|
|
/*
|
|
|
|
* sys_sched_yield() compat mode
|
|
|
|
*
|
|
|
|
* This option switches the agressive yield implementation of the
|
|
|
|
* old scheduler back on.
|
|
|
|
*/
|
|
|
|
unsigned int __read_mostly sysctl_sched_compat_yield;
|
|
|
|
|
2007-07-09 18:51:58 +02:00
|
|
|
/*
|
|
|
|
* SCHED_BATCH wake-up granularity.
|
2007-08-24 20:39:10 +02:00
|
|
|
* (default: 25 msec, units: nanoseconds)
|
2007-07-09 18:51:58 +02:00
|
|
|
*
|
|
|
|
* This option delays the preemption effects of decoupled workloads
|
|
|
|
* and reduces their over-scheduling. Synchronous workloads will still
|
|
|
|
* have immediate wakeup/sleep latencies.
|
|
|
|
*/
|
2007-10-15 17:00:02 +02:00
|
|
|
const_debug unsigned int sysctl_sched_batch_wakeup_granularity = 25000000UL;
|
2007-07-09 18:51:58 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* SCHED_OTHER wake-up granularity.
|
|
|
|
* (default: 1 msec, units: nanoseconds)
|
|
|
|
*
|
|
|
|
* This option delays the preemption effects of decoupled workloads
|
|
|
|
* and reduces their over-scheduling. Synchronous workloads will still
|
|
|
|
* have immediate wakeup/sleep latencies.
|
|
|
|
*/
|
2007-10-15 17:00:02 +02:00
|
|
|
const_debug unsigned int sysctl_sched_wakeup_granularity = 1000000UL;
|
2007-07-09 18:51:58 +02:00
|
|
|
|
|
|
|
unsigned int sysctl_sched_runtime_limit __read_mostly;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Debugging: various feature bits
|
|
|
|
*/
|
|
|
|
enum {
|
|
|
|
SCHED_FEAT_FAIR_SLEEPERS = 1,
|
|
|
|
SCHED_FEAT_SLEEPER_AVG = 2,
|
|
|
|
SCHED_FEAT_SLEEPER_LOAD_AVG = 4,
|
|
|
|
SCHED_FEAT_PRECISE_CPU_LOAD = 8,
|
|
|
|
SCHED_FEAT_START_DEBIT = 16,
|
|
|
|
SCHED_FEAT_SKIP_INITIAL = 32,
|
|
|
|
};
|
|
|
|
|
2007-10-15 17:00:02 +02:00
|
|
|
const_debug unsigned int sysctl_sched_features =
|
2007-07-09 18:51:58 +02:00
|
|
|
SCHED_FEAT_FAIR_SLEEPERS *1 |
|
2007-08-12 18:08:19 +02:00
|
|
|
SCHED_FEAT_SLEEPER_AVG *0 |
|
2007-07-09 18:51:58 +02:00
|
|
|
SCHED_FEAT_SLEEPER_LOAD_AVG *1 |
|
|
|
|
SCHED_FEAT_PRECISE_CPU_LOAD *1 |
|
|
|
|
SCHED_FEAT_START_DEBIT *1 |
|
|
|
|
SCHED_FEAT_SKIP_INITIAL *0;
|
|
|
|
|
|
|
|
extern struct sched_class fair_sched_class;
|
|
|
|
|
|
|
|
/**************************************************************
|
|
|
|
* CFS operations on generic schedulable entities:
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
|
|
|
|
|
|
/* cpu runqueue to which this cfs_rq is attached */
|
|
|
|
static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
|
|
|
|
{
|
|
|
|
return cfs_rq->rq;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* currently running entity (if any) on this cfs_rq */
|
|
|
|
static inline struct sched_entity *cfs_rq_curr(struct cfs_rq *cfs_rq)
|
|
|
|
{
|
|
|
|
return cfs_rq->curr;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* An entity is a task if it doesn't "own" a runqueue */
|
|
|
|
#define entity_is_task(se) (!se->my_q)
|
|
|
|
|
|
|
|
static inline void
|
|
|
|
set_cfs_rq_curr(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|
|
|
{
|
|
|
|
cfs_rq->curr = se;
|
|
|
|
}
|
|
|
|
|
|
|
|
#else /* CONFIG_FAIR_GROUP_SCHED */
|
|
|
|
|
|
|
|
static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
|
|
|
|
{
|
|
|
|
return container_of(cfs_rq, struct rq, cfs);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct sched_entity *cfs_rq_curr(struct cfs_rq *cfs_rq)
|
|
|
|
{
|
|
|
|
struct rq *rq = rq_of(cfs_rq);
|
|
|
|
|
|
|
|
if (unlikely(rq->curr->sched_class != &fair_sched_class))
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
return &rq->curr->se;
|
|
|
|
}
|
|
|
|
|
|
|
|
#define entity_is_task(se) 1
|
|
|
|
|
|
|
|
static inline void
|
|
|
|
set_cfs_rq_curr(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
|
|
|
|
|
|
|
|
#endif /* CONFIG_FAIR_GROUP_SCHED */
|
|
|
|
|
|
|
|
static inline struct task_struct *task_of(struct sched_entity *se)
|
|
|
|
{
|
|
|
|
return container_of(se, struct task_struct, se);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/**************************************************************
|
|
|
|
* Scheduling class tree data structure manipulation methods:
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Enqueue an entity into the rb-tree:
|
|
|
|
*/
|
|
|
|
static inline void
|
|
|
|
__enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|
|
|
{
|
|
|
|
struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
|
|
|
|
struct rb_node *parent = NULL;
|
|
|
|
struct sched_entity *entry;
|
|
|
|
s64 key = se->fair_key;
|
|
|
|
int leftmost = 1;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Find the right place in the rbtree:
|
|
|
|
*/
|
|
|
|
while (*link) {
|
|
|
|
parent = *link;
|
|
|
|
entry = rb_entry(parent, struct sched_entity, run_node);
|
|
|
|
/*
|
|
|
|
* We dont care about collisions. Nodes with
|
|
|
|
* the same key stay together.
|
|
|
|
*/
|
|
|
|
if (key - entry->fair_key < 0) {
|
|
|
|
link = &parent->rb_left;
|
|
|
|
} else {
|
|
|
|
link = &parent->rb_right;
|
|
|
|
leftmost = 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Maintain a cache of leftmost tree entries (it is frequently
|
|
|
|
* used):
|
|
|
|
*/
|
|
|
|
if (leftmost)
|
|
|
|
cfs_rq->rb_leftmost = &se->run_node;
|
|
|
|
|
|
|
|
rb_link_node(&se->run_node, parent, link);
|
|
|
|
rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
|
|
|
|
update_load_add(&cfs_rq->load, se->load.weight);
|
|
|
|
cfs_rq->nr_running++;
|
|
|
|
se->on_rq = 1;
|
2007-09-05 14:32:49 +02:00
|
|
|
|
|
|
|
schedstat_add(cfs_rq, wait_runtime, se->wait_runtime);
|
2007-07-09 18:51:58 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline void
|
|
|
|
__dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|
|
|
{
|
|
|
|
if (cfs_rq->rb_leftmost == &se->run_node)
|
|
|
|
cfs_rq->rb_leftmost = rb_next(&se->run_node);
|
|
|
|
rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
|
|
|
|
update_load_sub(&cfs_rq->load, se->load.weight);
|
|
|
|
cfs_rq->nr_running--;
|
|
|
|
se->on_rq = 0;
|
2007-09-05 14:32:49 +02:00
|
|
|
|
|
|
|
schedstat_add(cfs_rq, wait_runtime, -se->wait_runtime);
|
2007-07-09 18:51:58 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct rb_node *first_fair(struct cfs_rq *cfs_rq)
|
|
|
|
{
|
|
|
|
return cfs_rq->rb_leftmost;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
|
|
|
|
{
|
|
|
|
return rb_entry(first_fair(cfs_rq), struct sched_entity, run_node);
|
|
|
|
}
|
|
|
|
|
|
|
|
/**************************************************************
|
|
|
|
* Scheduling class statistics methods:
|
|
|
|
*/
|
|
|
|
|
2007-08-25 18:41:53 +02:00
|
|
|
/*
|
|
|
|
* Calculate the preemption granularity needed to schedule every
|
|
|
|
* runnable task once per sysctl_sched_latency amount of time.
|
|
|
|
* (down to a sensible low limit on granularity)
|
|
|
|
*
|
|
|
|
* For example, if there are 2 tasks running and latency is 10 msecs,
|
|
|
|
* we switch tasks every 5 msecs. If we have 3 tasks running, we have
|
|
|
|
* to switch tasks every 3.33 msecs to get a 10 msecs observed latency
|
|
|
|
* for each task. We do finer and finer scheduling up to until we
|
|
|
|
* reach the minimum granularity value.
|
|
|
|
*
|
|
|
|
* To achieve this we use the following dynamic-granularity rule:
|
|
|
|
*
|
|
|
|
* gran = lat/nr - lat/nr/nr
|
|
|
|
*
|
|
|
|
* This comes out of the following equations:
|
|
|
|
*
|
|
|
|
* kA1 + gran = kB1
|
|
|
|
* kB2 + gran = kA2
|
|
|
|
* kA2 = kA1
|
|
|
|
* kB2 = kB1 - d + d/nr
|
|
|
|
* lat = d * nr
|
|
|
|
*
|
|
|
|
* Where 'k' is key, 'A' is task A (waiting), 'B' is task B (running),
|
|
|
|
* '1' is start of time, '2' is end of time, 'd' is delay between
|
|
|
|
* 1 and 2 (during which task B was running), 'nr' is number of tasks
|
|
|
|
* running, 'lat' is the the period of each task. ('lat' is the
|
|
|
|
* sched_latency that we aim for.)
|
|
|
|
*/
|
|
|
|
static long
|
|
|
|
sched_granularity(struct cfs_rq *cfs_rq)
|
|
|
|
{
|
|
|
|
unsigned int gran = sysctl_sched_latency;
|
|
|
|
unsigned int nr = cfs_rq->nr_running;
|
|
|
|
|
|
|
|
if (nr > 1) {
|
|
|
|
gran = gran/nr - gran/nr/nr;
|
2007-08-25 18:41:53 +02:00
|
|
|
gran = max(gran, sysctl_sched_min_granularity);
|
2007-08-25 18:41:53 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
return gran;
|
|
|
|
}
|
|
|
|
|
2007-07-09 18:51:58 +02:00
|
|
|
/*
|
|
|
|
* We rescale the rescheduling granularity of tasks according to their
|
|
|
|
* nice level, but only linearly, not exponentially:
|
|
|
|
*/
|
|
|
|
static long
|
|
|
|
niced_granularity(struct sched_entity *curr, unsigned long granularity)
|
|
|
|
{
|
|
|
|
u64 tmp;
|
|
|
|
|
2007-08-09 11:16:52 +02:00
|
|
|
if (likely(curr->load.weight == NICE_0_LOAD))
|
|
|
|
return granularity;
|
2007-07-09 18:51:58 +02:00
|
|
|
/*
|
2007-08-09 11:16:52 +02:00
|
|
|
* Positive nice levels get the same granularity as nice-0:
|
2007-07-09 18:51:58 +02:00
|
|
|
*/
|
2007-08-09 11:16:52 +02:00
|
|
|
if (likely(curr->load.weight < NICE_0_LOAD)) {
|
|
|
|
tmp = curr->load.weight * (u64)granularity;
|
|
|
|
return (long) (tmp >> NICE_0_SHIFT);
|
|
|
|
}
|
2007-07-09 18:51:58 +02:00
|
|
|
/*
|
2007-08-09 11:16:52 +02:00
|
|
|
* Negative nice level tasks get linearly finer
|
2007-07-09 18:51:58 +02:00
|
|
|
* granularity:
|
|
|
|
*/
|
2007-08-09 11:16:52 +02:00
|
|
|
tmp = curr->load.inv_weight * (u64)granularity;
|
2007-07-09 18:51:58 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* It will always fit into 'long':
|
|
|
|
*/
|
2007-09-05 14:32:49 +02:00
|
|
|
return (long) (tmp >> (WMULT_SHIFT-NICE_0_SHIFT));
|
2007-07-09 18:51:58 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline void
|
|
|
|
limit_wait_runtime(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|
|
|
{
|
|
|
|
long limit = sysctl_sched_runtime_limit;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Niced tasks have the same history dynamic range as
|
|
|
|
* non-niced tasks:
|
|
|
|
*/
|
|
|
|
if (unlikely(se->wait_runtime > limit)) {
|
|
|
|
se->wait_runtime = limit;
|
|
|
|
schedstat_inc(se, wait_runtime_overruns);
|
|
|
|
schedstat_inc(cfs_rq, wait_runtime_overruns);
|
|
|
|
}
|
|
|
|
if (unlikely(se->wait_runtime < -limit)) {
|
|
|
|
se->wait_runtime = -limit;
|
|
|
|
schedstat_inc(se, wait_runtime_underruns);
|
|
|
|
schedstat_inc(cfs_rq, wait_runtime_underruns);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void
|
|
|
|
__add_wait_runtime(struct cfs_rq *cfs_rq, struct sched_entity *se, long delta)
|
|
|
|
{
|
|
|
|
se->wait_runtime += delta;
|
|
|
|
schedstat_add(se, sum_wait_runtime, delta);
|
|
|
|
limit_wait_runtime(cfs_rq, se);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void
|
|
|
|
add_wait_runtime(struct cfs_rq *cfs_rq, struct sched_entity *se, long delta)
|
|
|
|
{
|
|
|
|
schedstat_add(cfs_rq, wait_runtime, -se->wait_runtime);
|
|
|
|
__add_wait_runtime(cfs_rq, se, delta);
|
|
|
|
schedstat_add(cfs_rq, wait_runtime, se->wait_runtime);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Update the current task's runtime statistics. Skip current tasks that
|
|
|
|
* are not in our scheduling class.
|
|
|
|
*/
|
|
|
|
static inline void
|
2007-10-15 17:00:03 +02:00
|
|
|
__update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
|
|
|
|
unsigned long delta_exec)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
2007-10-15 17:00:03 +02:00
|
|
|
unsigned long delta, delta_fair, delta_mine;
|
2007-07-09 18:51:58 +02:00
|
|
|
struct load_weight *lw = &cfs_rq->load;
|
|
|
|
unsigned long load = lw->weight;
|
|
|
|
|
2007-08-02 17:41:40 +02:00
|
|
|
schedstat_set(curr->exec_max, max((u64)delta_exec, curr->exec_max));
|
2007-07-09 18:51:58 +02:00
|
|
|
|
|
|
|
curr->sum_exec_runtime += delta_exec;
|
|
|
|
cfs_rq->exec_clock += delta_exec;
|
|
|
|
|
2007-08-09 11:16:46 +02:00
|
|
|
if (unlikely(!load))
|
|
|
|
return;
|
|
|
|
|
2007-07-09 18:51:58 +02:00
|
|
|
delta_fair = calc_delta_fair(delta_exec, lw);
|
|
|
|
delta_mine = calc_delta_mine(delta_exec, curr->load.weight, lw);
|
|
|
|
|
sched: fix sleeper bonus limit
There is an Amarok song switch time increase (regression) under
hefty load.
What is happening is that sleeper_bonus is never consumed, and only
rarely goes below runtime_limit, so for the most part, Amarok isn't
getting any bonus at all. We're keeping sleeper_bonus right at
runtime_limit (sched_latency == sched_runtime_limit == 40ms) forever, ie
we don't consume if we're lower that that, and don't add if we're above
it. One Amarok thread waking (or anybody else) will push us past the
threshold, so the next thread waking gets nada, but will reap pain from
the previous thread waking until we drop back to runtime_limit. It
looks to me like under load, some random task gets a bonus, and
everybody else pays, whether deserving or not.
This diff fixed the regression for me at any load rate.
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
2007-08-28 12:53:24 +02:00
|
|
|
if (cfs_rq->sleeper_bonus > sysctl_sched_min_granularity) {
|
2007-08-24 20:39:10 +02:00
|
|
|
delta = min((u64)delta_mine, cfs_rq->sleeper_bonus);
|
2007-08-24 20:39:10 +02:00
|
|
|
delta = min(delta, (unsigned long)(
|
|
|
|
(long)sysctl_sched_runtime_limit - curr->wait_runtime));
|
2007-07-09 18:51:58 +02:00
|
|
|
cfs_rq->sleeper_bonus -= delta;
|
|
|
|
delta_mine -= delta;
|
|
|
|
}
|
|
|
|
|
|
|
|
cfs_rq->fair_clock += delta_fair;
|
|
|
|
/*
|
|
|
|
* We executed delta_exec amount of time on the CPU,
|
|
|
|
* but we were only entitled to delta_mine amount of
|
|
|
|
* time during that period (if nr_running == 1 then
|
|
|
|
* the two values are equal)
|
|
|
|
* [Note: delta_mine - delta_exec is negative]:
|
|
|
|
*/
|
|
|
|
add_wait_runtime(cfs_rq, curr, delta_mine - delta_exec);
|
|
|
|
}
|
|
|
|
|
2007-08-09 11:16:47 +02:00
|
|
|
static void update_curr(struct cfs_rq *cfs_rq)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
|
|
|
struct sched_entity *curr = cfs_rq_curr(cfs_rq);
|
2007-10-15 17:00:03 +02:00
|
|
|
u64 now = rq_of(cfs_rq)->clock;
|
2007-07-09 18:51:58 +02:00
|
|
|
unsigned long delta_exec;
|
|
|
|
|
|
|
|
if (unlikely(!curr))
|
|
|
|
return;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Get the amount of time the current task was running
|
|
|
|
* since the last time we changed load (this cannot
|
|
|
|
* overflow on 32 bits):
|
|
|
|
*/
|
2007-10-15 17:00:03 +02:00
|
|
|
delta_exec = (unsigned long)(now - curr->exec_start);
|
2007-07-09 18:51:58 +02:00
|
|
|
|
2007-10-15 17:00:03 +02:00
|
|
|
__update_curr(cfs_rq, curr, delta_exec);
|
|
|
|
curr->exec_start = now;
|
2007-07-09 18:51:58 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline void
|
2007-08-09 11:16:47 +02:00
|
|
|
update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
|
|
|
se->wait_start_fair = cfs_rq->fair_clock;
|
2007-08-09 11:16:47 +02:00
|
|
|
schedstat_set(se->wait_start, rq_of(cfs_rq)->clock);
|
2007-07-09 18:51:58 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We calculate fair deltas here, so protect against the random effects
|
|
|
|
* of a multiplication overflow by capping it to the runtime limit:
|
|
|
|
*/
|
|
|
|
#if BITS_PER_LONG == 32
|
|
|
|
static inline unsigned long
|
|
|
|
calc_weighted(unsigned long delta, unsigned long weight, int shift)
|
|
|
|
{
|
|
|
|
u64 tmp = (u64)delta * weight >> shift;
|
|
|
|
|
|
|
|
if (unlikely(tmp > sysctl_sched_runtime_limit*2))
|
|
|
|
return sysctl_sched_runtime_limit*2;
|
|
|
|
return tmp;
|
|
|
|
}
|
|
|
|
#else
|
|
|
|
static inline unsigned long
|
|
|
|
calc_weighted(unsigned long delta, unsigned long weight, int shift)
|
|
|
|
{
|
|
|
|
return delta * weight >> shift;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Task is being enqueued - update stats:
|
|
|
|
*/
|
2007-08-09 11:16:47 +02:00
|
|
|
static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
|
|
|
s64 key;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Are we enqueueing a waiting task? (for current tasks
|
|
|
|
* a dequeue/enqueue event is a NOP)
|
|
|
|
*/
|
|
|
|
if (se != cfs_rq_curr(cfs_rq))
|
2007-08-09 11:16:47 +02:00
|
|
|
update_stats_wait_start(cfs_rq, se);
|
2007-07-09 18:51:58 +02:00
|
|
|
/*
|
|
|
|
* Update the key:
|
|
|
|
*/
|
|
|
|
key = cfs_rq->fair_clock;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Optimize the common nice 0 case:
|
|
|
|
*/
|
|
|
|
if (likely(se->load.weight == NICE_0_LOAD)) {
|
|
|
|
key -= se->wait_runtime;
|
|
|
|
} else {
|
|
|
|
u64 tmp;
|
|
|
|
|
|
|
|
if (se->wait_runtime < 0) {
|
|
|
|
tmp = -se->wait_runtime;
|
|
|
|
key += (tmp * se->load.inv_weight) >>
|
|
|
|
(WMULT_SHIFT - NICE_0_SHIFT);
|
|
|
|
} else {
|
|
|
|
tmp = se->wait_runtime;
|
2007-08-09 11:16:52 +02:00
|
|
|
key -= (tmp * se->load.inv_weight) >>
|
|
|
|
(WMULT_SHIFT - NICE_0_SHIFT);
|
2007-07-09 18:51:58 +02:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
se->fair_key = key;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Note: must be called with a freshly updated rq->fair_clock.
|
|
|
|
*/
|
|
|
|
static inline void
|
2007-10-15 17:00:03 +02:00
|
|
|
__update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se,
|
|
|
|
unsigned long delta_fair)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
2007-08-09 11:16:47 +02:00
|
|
|
schedstat_set(se->wait_max, max(se->wait_max,
|
|
|
|
rq_of(cfs_rq)->clock - se->wait_start));
|
2007-07-09 18:51:58 +02:00
|
|
|
|
|
|
|
if (unlikely(se->load.weight != NICE_0_LOAD))
|
|
|
|
delta_fair = calc_weighted(delta_fair, se->load.weight,
|
|
|
|
NICE_0_SHIFT);
|
|
|
|
|
|
|
|
add_wait_runtime(cfs_rq, se, delta_fair);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void
|
2007-08-09 11:16:47 +02:00
|
|
|
update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
|
|
|
unsigned long delta_fair;
|
|
|
|
|
2007-08-28 12:53:24 +02:00
|
|
|
if (unlikely(!se->wait_start_fair))
|
|
|
|
return;
|
|
|
|
|
2007-07-09 18:51:58 +02:00
|
|
|
delta_fair = (unsigned long)min((u64)(2*sysctl_sched_runtime_limit),
|
|
|
|
(u64)(cfs_rq->fair_clock - se->wait_start_fair));
|
|
|
|
|
2007-10-15 17:00:03 +02:00
|
|
|
__update_stats_wait_end(cfs_rq, se, delta_fair);
|
2007-07-09 18:51:58 +02:00
|
|
|
|
|
|
|
se->wait_start_fair = 0;
|
2007-08-02 17:41:40 +02:00
|
|
|
schedstat_set(se->wait_start, 0);
|
2007-07-09 18:51:58 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline void
|
2007-08-09 11:16:48 +02:00
|
|
|
update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
2007-08-09 11:16:47 +02:00
|
|
|
update_curr(cfs_rq);
|
2007-07-09 18:51:58 +02:00
|
|
|
/*
|
|
|
|
* Mark the end of the wait period if dequeueing a
|
|
|
|
* waiting task:
|
|
|
|
*/
|
|
|
|
if (se != cfs_rq_curr(cfs_rq))
|
2007-08-09 11:16:47 +02:00
|
|
|
update_stats_wait_end(cfs_rq, se);
|
2007-07-09 18:51:58 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We are picking a new current task - update its stats:
|
|
|
|
*/
|
|
|
|
static inline void
|
2007-08-09 11:16:47 +02:00
|
|
|
update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
|
|
|
/*
|
|
|
|
* We are starting a new run period:
|
|
|
|
*/
|
2007-08-09 11:16:47 +02:00
|
|
|
se->exec_start = rq_of(cfs_rq)->clock;
|
2007-07-09 18:51:58 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We are descheduling a task - update its stats:
|
|
|
|
*/
|
|
|
|
static inline void
|
2007-08-09 11:16:48 +02:00
|
|
|
update_stats_curr_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
|
|
|
se->exec_start = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**************************************************
|
|
|
|
* Scheduling class queueing methods:
|
|
|
|
*/
|
|
|
|
|
2007-10-15 17:00:03 +02:00
|
|
|
static void __enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se,
|
|
|
|
unsigned long delta_fair)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
2007-10-15 17:00:03 +02:00
|
|
|
unsigned long load = cfs_rq->load.weight;
|
2007-07-09 18:51:58 +02:00
|
|
|
long prev_runtime;
|
|
|
|
|
2007-08-24 20:39:10 +02:00
|
|
|
/*
|
|
|
|
* Do not boost sleepers if there's too much bonus 'in flight'
|
|
|
|
* already:
|
|
|
|
*/
|
|
|
|
if (unlikely(cfs_rq->sleeper_bonus > sysctl_sched_runtime_limit))
|
|
|
|
return;
|
|
|
|
|
2007-07-09 18:51:58 +02:00
|
|
|
if (sysctl_sched_features & SCHED_FEAT_SLEEPER_LOAD_AVG)
|
|
|
|
load = rq_of(cfs_rq)->cpu_load[2];
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Fix up delta_fair with the effect of us running
|
|
|
|
* during the whole sleep period:
|
|
|
|
*/
|
|
|
|
if (sysctl_sched_features & SCHED_FEAT_SLEEPER_AVG)
|
|
|
|
delta_fair = div64_likely32((u64)delta_fair * load,
|
|
|
|
load + se->load.weight);
|
|
|
|
|
|
|
|
if (unlikely(se->load.weight != NICE_0_LOAD))
|
|
|
|
delta_fair = calc_weighted(delta_fair, se->load.weight,
|
|
|
|
NICE_0_SHIFT);
|
|
|
|
|
|
|
|
prev_runtime = se->wait_runtime;
|
|
|
|
__add_wait_runtime(cfs_rq, se, delta_fair);
|
|
|
|
delta_fair = se->wait_runtime - prev_runtime;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Track the amount of bonus we've given to sleepers:
|
|
|
|
*/
|
|
|
|
cfs_rq->sleeper_bonus += delta_fair;
|
|
|
|
}
|
|
|
|
|
2007-08-09 11:16:48 +02:00
|
|
|
static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
|
|
|
struct task_struct *tsk = task_of(se);
|
|
|
|
unsigned long delta_fair;
|
|
|
|
|
|
|
|
if ((entity_is_task(se) && tsk->policy == SCHED_BATCH) ||
|
|
|
|
!(sysctl_sched_features & SCHED_FEAT_FAIR_SLEEPERS))
|
|
|
|
return;
|
|
|
|
|
|
|
|
delta_fair = (unsigned long)min((u64)(2*sysctl_sched_runtime_limit),
|
|
|
|
(u64)(cfs_rq->fair_clock - se->sleep_start_fair));
|
|
|
|
|
2007-10-15 17:00:03 +02:00
|
|
|
__enqueue_sleeper(cfs_rq, se, delta_fair);
|
2007-07-09 18:51:58 +02:00
|
|
|
|
|
|
|
se->sleep_start_fair = 0;
|
|
|
|
|
|
|
|
#ifdef CONFIG_SCHEDSTATS
|
|
|
|
if (se->sleep_start) {
|
2007-08-09 11:16:47 +02:00
|
|
|
u64 delta = rq_of(cfs_rq)->clock - se->sleep_start;
|
2007-07-09 18:51:58 +02:00
|
|
|
|
|
|
|
if ((s64)delta < 0)
|
|
|
|
delta = 0;
|
|
|
|
|
|
|
|
if (unlikely(delta > se->sleep_max))
|
|
|
|
se->sleep_max = delta;
|
|
|
|
|
|
|
|
se->sleep_start = 0;
|
|
|
|
se->sum_sleep_runtime += delta;
|
|
|
|
}
|
|
|
|
if (se->block_start) {
|
2007-08-09 11:16:47 +02:00
|
|
|
u64 delta = rq_of(cfs_rq)->clock - se->block_start;
|
2007-07-09 18:51:58 +02:00
|
|
|
|
|
|
|
if ((s64)delta < 0)
|
|
|
|
delta = 0;
|
|
|
|
|
|
|
|
if (unlikely(delta > se->block_max))
|
|
|
|
se->block_max = delta;
|
|
|
|
|
|
|
|
se->block_start = 0;
|
|
|
|
se->sum_sleep_runtime += delta;
|
2007-10-02 14:13:08 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Blocking time is in units of nanosecs, so shift by 20 to
|
|
|
|
* get a milliseconds-range estimation of the amount of
|
|
|
|
* time that the task spent sleeping:
|
|
|
|
*/
|
|
|
|
if (unlikely(prof_on == SLEEP_PROFILING)) {
|
|
|
|
profile_hits(SLEEP_PROFILING, (void *)get_wchan(tsk),
|
|
|
|
delta >> 20);
|
|
|
|
}
|
2007-07-09 18:51:58 +02:00
|
|
|
}
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
|
|
|
static void
|
2007-08-09 11:16:48 +02:00
|
|
|
enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
|
|
|
/*
|
|
|
|
* Update the fair clock.
|
|
|
|
*/
|
2007-08-09 11:16:47 +02:00
|
|
|
update_curr(cfs_rq);
|
2007-07-09 18:51:58 +02:00
|
|
|
|
|
|
|
if (wakeup)
|
2007-08-09 11:16:48 +02:00
|
|
|
enqueue_sleeper(cfs_rq, se);
|
2007-07-09 18:51:58 +02:00
|
|
|
|
2007-08-09 11:16:47 +02:00
|
|
|
update_stats_enqueue(cfs_rq, se);
|
2007-07-09 18:51:58 +02:00
|
|
|
__enqueue_entity(cfs_rq, se);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void
|
2007-08-09 11:16:48 +02:00
|
|
|
dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
2007-08-09 11:16:48 +02:00
|
|
|
update_stats_dequeue(cfs_rq, se);
|
2007-07-09 18:51:58 +02:00
|
|
|
if (sleep) {
|
|
|
|
se->sleep_start_fair = cfs_rq->fair_clock;
|
|
|
|
#ifdef CONFIG_SCHEDSTATS
|
|
|
|
if (entity_is_task(se)) {
|
|
|
|
struct task_struct *tsk = task_of(se);
|
|
|
|
|
|
|
|
if (tsk->state & TASK_INTERRUPTIBLE)
|
2007-08-09 11:16:47 +02:00
|
|
|
se->sleep_start = rq_of(cfs_rq)->clock;
|
2007-07-09 18:51:58 +02:00
|
|
|
if (tsk->state & TASK_UNINTERRUPTIBLE)
|
2007-08-09 11:16:47 +02:00
|
|
|
se->block_start = rq_of(cfs_rq)->clock;
|
2007-07-09 18:51:58 +02:00
|
|
|
}
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
__dequeue_entity(cfs_rq, se);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Preempt the current task with a newly woken task if needed:
|
|
|
|
*/
|
2007-09-05 14:32:49 +02:00
|
|
|
static void
|
2007-07-09 18:51:58 +02:00
|
|
|
__check_preempt_curr_fair(struct cfs_rq *cfs_rq, struct sched_entity *se,
|
|
|
|
struct sched_entity *curr, unsigned long granularity)
|
|
|
|
{
|
|
|
|
s64 __delta = curr->fair_key - se->fair_key;
|
2007-09-05 14:32:49 +02:00
|
|
|
unsigned long ideal_runtime, delta_exec;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* ideal_runtime is compared against sum_exec_runtime, which is
|
|
|
|
* walltime, hence do not scale.
|
|
|
|
*/
|
|
|
|
ideal_runtime = max(sysctl_sched_latency / cfs_rq->nr_running,
|
|
|
|
(unsigned long)sysctl_sched_min_granularity);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If we executed more than what the latency constraint suggests,
|
|
|
|
* reduce the rescheduling granularity. This way the total latency
|
|
|
|
* of how much a task is not scheduled converges to
|
|
|
|
* sysctl_sched_latency:
|
|
|
|
*/
|
|
|
|
delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
|
|
|
|
if (delta_exec > ideal_runtime)
|
|
|
|
granularity = 0;
|
2007-07-09 18:51:58 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Take scheduling granularity into account - do not
|
|
|
|
* preempt the current task unless the best task has
|
|
|
|
* a larger than sched_granularity fairness advantage:
|
2007-09-05 14:32:49 +02:00
|
|
|
*
|
|
|
|
* scale granularity as key space is in fair_clock.
|
2007-07-09 18:51:58 +02:00
|
|
|
*/
|
2007-09-05 14:32:49 +02:00
|
|
|
if (__delta > niced_granularity(curr, granularity))
|
2007-07-09 18:51:58 +02:00
|
|
|
resched_task(rq_of(cfs_rq)->curr);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void
|
2007-08-09 11:16:48 +02:00
|
|
|
set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
|
|
|
/*
|
|
|
|
* Any task has to be enqueued before it get to execute on
|
|
|
|
* a CPU. So account for the time it spent waiting on the
|
|
|
|
* runqueue. (note, here we rely on pick_next_task() having
|
|
|
|
* done a put_prev_task_fair() shortly before this, which
|
|
|
|
* updated rq->fair_clock - used by update_stats_wait_end())
|
|
|
|
*/
|
2007-08-09 11:16:47 +02:00
|
|
|
update_stats_wait_end(cfs_rq, se);
|
2007-08-09 11:16:47 +02:00
|
|
|
update_stats_curr_start(cfs_rq, se);
|
2007-07-09 18:51:58 +02:00
|
|
|
set_cfs_rq_curr(cfs_rq, se);
|
2007-10-15 17:00:02 +02:00
|
|
|
#ifdef CONFIG_SCHEDSTATS
|
|
|
|
/*
|
|
|
|
* Track our maximum slice length, if the CPU's load is at
|
|
|
|
* least twice that of our own weight (i.e. dont track it
|
|
|
|
* when there are only lesser-weight tasks around):
|
|
|
|
*/
|
|
|
|
if (rq_of(cfs_rq)->ls.load.weight >= 2*se->load.weight) {
|
|
|
|
se->slice_max = max(se->slice_max,
|
|
|
|
se->sum_exec_runtime - se->prev_sum_exec_runtime);
|
|
|
|
}
|
|
|
|
#endif
|
2007-09-05 14:32:49 +02:00
|
|
|
se->prev_sum_exec_runtime = se->sum_exec_runtime;
|
2007-07-09 18:51:58 +02:00
|
|
|
}
|
|
|
|
|
2007-08-09 11:16:48 +02:00
|
|
|
static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
|
|
|
struct sched_entity *se = __pick_next_entity(cfs_rq);
|
|
|
|
|
2007-08-09 11:16:48 +02:00
|
|
|
set_next_entity(cfs_rq, se);
|
2007-07-09 18:51:58 +02:00
|
|
|
|
|
|
|
return se;
|
|
|
|
}
|
|
|
|
|
2007-08-09 11:16:48 +02:00
|
|
|
static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
|
|
|
/*
|
|
|
|
* If still on the runqueue then deactivate_task()
|
|
|
|
* was not called and update_curr() has to be done:
|
|
|
|
*/
|
|
|
|
if (prev->on_rq)
|
2007-08-09 11:16:47 +02:00
|
|
|
update_curr(cfs_rq);
|
2007-07-09 18:51:58 +02:00
|
|
|
|
2007-08-09 11:16:48 +02:00
|
|
|
update_stats_curr_end(cfs_rq, prev);
|
2007-07-09 18:51:58 +02:00
|
|
|
|
|
|
|
if (prev->on_rq)
|
2007-08-09 11:16:47 +02:00
|
|
|
update_stats_wait_start(cfs_rq, prev);
|
2007-07-09 18:51:58 +02:00
|
|
|
set_cfs_rq_curr(cfs_rq, NULL);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
|
|
|
|
{
|
|
|
|
struct sched_entity *next;
|
2007-08-09 11:16:47 +02:00
|
|
|
|
2007-07-09 18:51:58 +02:00
|
|
|
/*
|
|
|
|
* Dequeue and enqueue the task to update its
|
|
|
|
* position within the tree:
|
|
|
|
*/
|
2007-08-09 11:16:48 +02:00
|
|
|
dequeue_entity(cfs_rq, curr, 0);
|
2007-08-09 11:16:48 +02:00
|
|
|
enqueue_entity(cfs_rq, curr, 0);
|
2007-07-09 18:51:58 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Reschedule if another task tops the current one.
|
|
|
|
*/
|
|
|
|
next = __pick_next_entity(cfs_rq);
|
|
|
|
if (next == curr)
|
|
|
|
return;
|
|
|
|
|
2007-09-05 14:32:49 +02:00
|
|
|
__check_preempt_curr_fair(cfs_rq, next, curr,
|
|
|
|
sched_granularity(cfs_rq));
|
2007-07-09 18:51:58 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/**************************************************
|
|
|
|
* CFS operations on tasks:
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
|
|
|
|
|
|
/* Walk up scheduling entities hierarchy */
|
|
|
|
#define for_each_sched_entity(se) \
|
|
|
|
for (; se; se = se->parent)
|
|
|
|
|
|
|
|
static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
|
|
|
|
{
|
|
|
|
return p->se.cfs_rq;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* runqueue on which this entity is (to be) queued */
|
|
|
|
static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
|
|
|
|
{
|
|
|
|
return se->cfs_rq;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* runqueue "owned" by this group */
|
|
|
|
static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
|
|
|
|
{
|
|
|
|
return grp->my_q;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Given a group's cfs_rq on one cpu, return its corresponding cfs_rq on
|
|
|
|
* another cpu ('this_cpu')
|
|
|
|
*/
|
|
|
|
static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
|
|
|
|
{
|
|
|
|
/* A later patch will take group into account */
|
|
|
|
return &cpu_rq(this_cpu)->cfs;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Iterate thr' all leaf cfs_rq's on a runqueue */
|
|
|
|
#define for_each_leaf_cfs_rq(rq, cfs_rq) \
|
|
|
|
list_for_each_entry(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
|
|
|
|
|
|
|
|
/* Do the two (enqueued) tasks belong to the same group ? */
|
|
|
|
static inline int is_same_group(struct task_struct *curr, struct task_struct *p)
|
|
|
|
{
|
|
|
|
if (curr->se.cfs_rq == p->se.cfs_rq)
|
|
|
|
return 1;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
#else /* CONFIG_FAIR_GROUP_SCHED */
|
|
|
|
|
|
|
|
#define for_each_sched_entity(se) \
|
|
|
|
for (; se; se = NULL)
|
|
|
|
|
|
|
|
static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
|
|
|
|
{
|
|
|
|
return &task_rq(p)->cfs;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
|
|
|
|
{
|
|
|
|
struct task_struct *p = task_of(se);
|
|
|
|
struct rq *rq = task_rq(p);
|
|
|
|
|
|
|
|
return &rq->cfs;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* runqueue "owned" by this group */
|
|
|
|
static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
|
|
|
|
{
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
|
|
|
|
{
|
|
|
|
return &cpu_rq(this_cpu)->cfs;
|
|
|
|
}
|
|
|
|
|
|
|
|
#define for_each_leaf_cfs_rq(rq, cfs_rq) \
|
|
|
|
for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
|
|
|
|
|
|
|
|
static inline int is_same_group(struct task_struct *curr, struct task_struct *p)
|
|
|
|
{
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
#endif /* CONFIG_FAIR_GROUP_SCHED */
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The enqueue_task method is called before nr_running is
|
|
|
|
* increased. Here we update the fair scheduling stats and
|
|
|
|
* then put the task into the rbtree:
|
|
|
|
*/
|
2007-08-09 11:16:48 +02:00
|
|
|
static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
|
|
|
struct cfs_rq *cfs_rq;
|
|
|
|
struct sched_entity *se = &p->se;
|
|
|
|
|
|
|
|
for_each_sched_entity(se) {
|
|
|
|
if (se->on_rq)
|
|
|
|
break;
|
|
|
|
cfs_rq = cfs_rq_of(se);
|
2007-08-09 11:16:48 +02:00
|
|
|
enqueue_entity(cfs_rq, se, wakeup);
|
2007-07-09 18:51:58 +02:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The dequeue_task method is called before nr_running is
|
|
|
|
* decreased. We remove the task from the rbtree and
|
|
|
|
* update the fair scheduling stats:
|
|
|
|
*/
|
2007-08-09 11:16:48 +02:00
|
|
|
static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
|
|
|
struct cfs_rq *cfs_rq;
|
|
|
|
struct sched_entity *se = &p->se;
|
|
|
|
|
|
|
|
for_each_sched_entity(se) {
|
|
|
|
cfs_rq = cfs_rq_of(se);
|
2007-08-09 11:16:48 +02:00
|
|
|
dequeue_entity(cfs_rq, se, sleep);
|
2007-07-09 18:51:58 +02:00
|
|
|
/* Don't dequeue parent if it has other entities besides us */
|
|
|
|
if (cfs_rq->load.weight)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2007-09-19 23:34:46 +02:00
|
|
|
* sched_yield() support is very simple - we dequeue and enqueue.
|
|
|
|
*
|
|
|
|
* If compat_yield is turned on then we requeue to the end of the tree.
|
2007-07-09 18:51:58 +02:00
|
|
|
*/
|
|
|
|
static void yield_task_fair(struct rq *rq, struct task_struct *p)
|
|
|
|
{
|
|
|
|
struct cfs_rq *cfs_rq = task_cfs_rq(p);
|
2007-09-19 23:34:46 +02:00
|
|
|
struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
|
|
|
|
struct sched_entity *rightmost, *se = &p->se;
|
|
|
|
struct rb_node *parent;
|
2007-07-09 18:51:58 +02:00
|
|
|
|
|
|
|
/*
|
2007-09-19 23:34:46 +02:00
|
|
|
* Are we the only task in the tree?
|
|
|
|
*/
|
|
|
|
if (unlikely(cfs_rq->nr_running == 1))
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (likely(!sysctl_sched_compat_yield)) {
|
|
|
|
__update_rq_clock(rq);
|
|
|
|
/*
|
|
|
|
* Dequeue and enqueue the task to update its
|
|
|
|
* position within the tree:
|
|
|
|
*/
|
|
|
|
dequeue_entity(cfs_rq, &p->se, 0);
|
|
|
|
enqueue_entity(cfs_rq, &p->se, 0);
|
|
|
|
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* Find the rightmost entry in the rbtree:
|
2007-07-09 18:51:58 +02:00
|
|
|
*/
|
2007-09-19 23:34:46 +02:00
|
|
|
do {
|
|
|
|
parent = *link;
|
|
|
|
link = &parent->rb_right;
|
|
|
|
} while (*link);
|
|
|
|
|
|
|
|
rightmost = rb_entry(parent, struct sched_entity, run_node);
|
|
|
|
/*
|
|
|
|
* Already in the rightmost position?
|
|
|
|
*/
|
|
|
|
if (unlikely(rightmost == se))
|
|
|
|
return;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Minimally necessary key value to be last in the tree:
|
|
|
|
*/
|
|
|
|
se->fair_key = rightmost->fair_key + 1;
|
|
|
|
|
|
|
|
if (cfs_rq->rb_leftmost == &se->run_node)
|
|
|
|
cfs_rq->rb_leftmost = rb_next(&se->run_node);
|
|
|
|
/*
|
|
|
|
* Relink the task to the rightmost position:
|
|
|
|
*/
|
|
|
|
rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
|
|
|
|
rb_link_node(&se->run_node, parent, link);
|
|
|
|
rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
|
2007-07-09 18:51:58 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Preempt the current task with a newly woken task if needed:
|
|
|
|
*/
|
|
|
|
static void check_preempt_curr_fair(struct rq *rq, struct task_struct *p)
|
|
|
|
{
|
|
|
|
struct task_struct *curr = rq->curr;
|
|
|
|
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
|
|
|
|
unsigned long gran;
|
|
|
|
|
|
|
|
if (unlikely(rt_prio(p->prio))) {
|
2007-08-09 11:16:47 +02:00
|
|
|
update_rq_clock(rq);
|
2007-08-09 11:16:47 +02:00
|
|
|
update_curr(cfs_rq);
|
2007-07-09 18:51:58 +02:00
|
|
|
resched_task(curr);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
gran = sysctl_sched_wakeup_granularity;
|
|
|
|
/*
|
|
|
|
* Batch tasks prefer throughput over latency:
|
|
|
|
*/
|
|
|
|
if (unlikely(p->policy == SCHED_BATCH))
|
|
|
|
gran = sysctl_sched_batch_wakeup_granularity;
|
|
|
|
|
|
|
|
if (is_same_group(curr, p))
|
|
|
|
__check_preempt_curr_fair(cfs_rq, &p->se, &curr->se, gran);
|
|
|
|
}
|
|
|
|
|
2007-08-09 11:16:48 +02:00
|
|
|
static struct task_struct *pick_next_task_fair(struct rq *rq)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
|
|
|
struct cfs_rq *cfs_rq = &rq->cfs;
|
|
|
|
struct sched_entity *se;
|
|
|
|
|
|
|
|
if (unlikely(!cfs_rq->nr_running))
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
do {
|
2007-08-09 11:16:48 +02:00
|
|
|
se = pick_next_entity(cfs_rq);
|
2007-07-09 18:51:58 +02:00
|
|
|
cfs_rq = group_cfs_rq(se);
|
|
|
|
} while (cfs_rq);
|
|
|
|
|
|
|
|
return task_of(se);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Account for a descheduled task:
|
|
|
|
*/
|
2007-08-09 11:16:49 +02:00
|
|
|
static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
|
|
|
struct sched_entity *se = &prev->se;
|
|
|
|
struct cfs_rq *cfs_rq;
|
|
|
|
|
|
|
|
for_each_sched_entity(se) {
|
|
|
|
cfs_rq = cfs_rq_of(se);
|
2007-08-09 11:16:48 +02:00
|
|
|
put_prev_entity(cfs_rq, se);
|
2007-07-09 18:51:58 +02:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/**************************************************
|
|
|
|
* Fair scheduling class load-balancing methods:
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Load-balancing iterator. Note: while the runqueue stays locked
|
|
|
|
* during the whole iteration, the current task might be
|
|
|
|
* dequeued so the iterator has to be dequeue-safe. Here we
|
|
|
|
* achieve that by always pre-iterating before returning
|
|
|
|
* the current task:
|
|
|
|
*/
|
|
|
|
static inline struct task_struct *
|
|
|
|
__load_balance_iterator(struct cfs_rq *cfs_rq, struct rb_node *curr)
|
|
|
|
{
|
|
|
|
struct task_struct *p;
|
|
|
|
|
|
|
|
if (!curr)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
p = rb_entry(curr, struct task_struct, se.run_node);
|
|
|
|
cfs_rq->rb_load_balance_curr = rb_next(curr);
|
|
|
|
|
|
|
|
return p;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct task_struct *load_balance_start_fair(void *arg)
|
|
|
|
{
|
|
|
|
struct cfs_rq *cfs_rq = arg;
|
|
|
|
|
|
|
|
return __load_balance_iterator(cfs_rq, first_fair(cfs_rq));
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct task_struct *load_balance_next_fair(void *arg)
|
|
|
|
{
|
|
|
|
struct cfs_rq *cfs_rq = arg;
|
|
|
|
|
|
|
|
return __load_balance_iterator(cfs_rq, cfs_rq->rb_load_balance_curr);
|
|
|
|
}
|
|
|
|
|
2007-08-09 11:16:46 +02:00
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
2007-07-09 18:51:58 +02:00
|
|
|
static int cfs_rq_best_prio(struct cfs_rq *cfs_rq)
|
|
|
|
{
|
|
|
|
struct sched_entity *curr;
|
|
|
|
struct task_struct *p;
|
|
|
|
|
|
|
|
if (!cfs_rq->nr_running)
|
|
|
|
return MAX_PRIO;
|
|
|
|
|
|
|
|
curr = __pick_next_entity(cfs_rq);
|
|
|
|
p = task_of(curr);
|
|
|
|
|
|
|
|
return p->prio;
|
|
|
|
}
|
2007-08-09 11:16:46 +02:00
|
|
|
#endif
|
2007-07-09 18:51:58 +02:00
|
|
|
|
sched: simplify move_tasks()
The move_tasks() function is currently multiplexed with two distinct
capabilities:
1. attempt to move a specified amount of weighted load from one run
queue to another; and
2. attempt to move a specified number of tasks from one run queue to
another.
The first of these capabilities is used in two places, load_balance()
and load_balance_idle(), and in both of these cases the return value of
move_tasks() is used purely to decide if tasks/load were moved and no
notice of the actual number of tasks moved is taken.
The second capability is used in exactly one place,
active_load_balance(), to attempt to move exactly one task and, as
before, the return value is only used as an indicator of success or failure.
This multiplexing of sched_task() was introduced, by me, as part of the
smpnice patches and was motivated by the fact that the alternative, one
function to move specified load and one to move a single task, would
have led to two functions of roughly the same complexity as the old
move_tasks() (or the new balance_tasks()). However, the new modular
design of the new CFS scheduler allows a simpler solution to be adopted
and this patch addresses that solution by:
1. adding a new function, move_one_task(), to be used by
active_load_balance(); and
2. making move_tasks() a single purpose function that tries to move a
specified weighted load and returns 1 for success and 0 for failure.
One of the consequences of these changes is that neither move_one_task()
or the new move_tasks() care how many tasks sched_class.load_balance()
moves and this enables its interface to be simplified by returning the
amount of load moved as its result and removing the load_moved pointer
from the argument list. This helps simplify the new move_tasks() and
slightly reduces the amount of work done in each of
sched_class.load_balance()'s implementations.
Further simplification, e.g. changes to balance_tasks(), are possible
but (slightly) complicated by the special needs of load_balance_fair()
so I've left them to a later patch (if this one gets accepted).
NB Since move_tasks() gets called with two run queue locks held even
small reductions in overhead are worthwhile.
[ mingo@elte.hu ]
this change also reduces code size nicely:
text data bss dec hex filename
39216 3618 24 42858 a76a sched.o.before
39173 3618 24 42815 a73f sched.o.after
Signed-off-by: Peter Williams <pwil3058@bigpond.net.au>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2007-08-09 11:16:46 +02:00
|
|
|
static unsigned long
|
2007-07-09 18:51:58 +02:00
|
|
|
load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
|
2007-08-09 11:16:46 +02:00
|
|
|
unsigned long max_nr_move, unsigned long max_load_move,
|
|
|
|
struct sched_domain *sd, enum cpu_idle_type idle,
|
|
|
|
int *all_pinned, int *this_best_prio)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
|
|
|
struct cfs_rq *busy_cfs_rq;
|
|
|
|
unsigned long load_moved, total_nr_moved = 0, nr_moved;
|
|
|
|
long rem_load_move = max_load_move;
|
|
|
|
struct rq_iterator cfs_rq_iterator;
|
|
|
|
|
|
|
|
cfs_rq_iterator.start = load_balance_start_fair;
|
|
|
|
cfs_rq_iterator.next = load_balance_next_fair;
|
|
|
|
|
|
|
|
for_each_leaf_cfs_rq(busiest, busy_cfs_rq) {
|
2007-08-09 11:16:46 +02:00
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
2007-07-09 18:51:58 +02:00
|
|
|
struct cfs_rq *this_cfs_rq;
|
2007-08-10 23:05:11 +02:00
|
|
|
long imbalance;
|
2007-07-09 18:51:58 +02:00
|
|
|
unsigned long maxload;
|
|
|
|
|
|
|
|
this_cfs_rq = cpu_cfs_rq(busy_cfs_rq, this_cpu);
|
|
|
|
|
2007-08-10 23:05:11 +02:00
|
|
|
imbalance = busy_cfs_rq->load.weight - this_cfs_rq->load.weight;
|
2007-07-09 18:51:58 +02:00
|
|
|
/* Don't pull if this_cfs_rq has more load than busy_cfs_rq */
|
|
|
|
if (imbalance <= 0)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
/* Don't pull more than imbalance/2 */
|
|
|
|
imbalance /= 2;
|
|
|
|
maxload = min(rem_load_move, imbalance);
|
|
|
|
|
2007-08-09 11:16:46 +02:00
|
|
|
*this_best_prio = cfs_rq_best_prio(this_cfs_rq);
|
|
|
|
#else
|
2007-08-10 23:05:11 +02:00
|
|
|
# define maxload rem_load_move
|
2007-08-09 11:16:46 +02:00
|
|
|
#endif
|
2007-07-09 18:51:58 +02:00
|
|
|
/* pass busy_cfs_rq argument into
|
|
|
|
* load_balance_[start|next]_fair iterators
|
|
|
|
*/
|
|
|
|
cfs_rq_iterator.arg = busy_cfs_rq;
|
|
|
|
nr_moved = balance_tasks(this_rq, this_cpu, busiest,
|
|
|
|
max_nr_move, maxload, sd, idle, all_pinned,
|
2007-08-09 11:16:46 +02:00
|
|
|
&load_moved, this_best_prio, &cfs_rq_iterator);
|
2007-07-09 18:51:58 +02:00
|
|
|
|
|
|
|
total_nr_moved += nr_moved;
|
|
|
|
max_nr_move -= nr_moved;
|
|
|
|
rem_load_move -= load_moved;
|
|
|
|
|
|
|
|
if (max_nr_move <= 0 || rem_load_move <= 0)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
sched: simplify move_tasks()
The move_tasks() function is currently multiplexed with two distinct
capabilities:
1. attempt to move a specified amount of weighted load from one run
queue to another; and
2. attempt to move a specified number of tasks from one run queue to
another.
The first of these capabilities is used in two places, load_balance()
and load_balance_idle(), and in both of these cases the return value of
move_tasks() is used purely to decide if tasks/load were moved and no
notice of the actual number of tasks moved is taken.
The second capability is used in exactly one place,
active_load_balance(), to attempt to move exactly one task and, as
before, the return value is only used as an indicator of success or failure.
This multiplexing of sched_task() was introduced, by me, as part of the
smpnice patches and was motivated by the fact that the alternative, one
function to move specified load and one to move a single task, would
have led to two functions of roughly the same complexity as the old
move_tasks() (or the new balance_tasks()). However, the new modular
design of the new CFS scheduler allows a simpler solution to be adopted
and this patch addresses that solution by:
1. adding a new function, move_one_task(), to be used by
active_load_balance(); and
2. making move_tasks() a single purpose function that tries to move a
specified weighted load and returns 1 for success and 0 for failure.
One of the consequences of these changes is that neither move_one_task()
or the new move_tasks() care how many tasks sched_class.load_balance()
moves and this enables its interface to be simplified by returning the
amount of load moved as its result and removing the load_moved pointer
from the argument list. This helps simplify the new move_tasks() and
slightly reduces the amount of work done in each of
sched_class.load_balance()'s implementations.
Further simplification, e.g. changes to balance_tasks(), are possible
but (slightly) complicated by the special needs of load_balance_fair()
so I've left them to a later patch (if this one gets accepted).
NB Since move_tasks() gets called with two run queue locks held even
small reductions in overhead are worthwhile.
[ mingo@elte.hu ]
this change also reduces code size nicely:
text data bss dec hex filename
39216 3618 24 42858 a76a sched.o.before
39173 3618 24 42815 a73f sched.o.after
Signed-off-by: Peter Williams <pwil3058@bigpond.net.au>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2007-08-09 11:16:46 +02:00
|
|
|
return max_load_move - rem_load_move;
|
2007-07-09 18:51:58 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* scheduler tick hitting a task of our scheduling class:
|
|
|
|
*/
|
|
|
|
static void task_tick_fair(struct rq *rq, struct task_struct *curr)
|
|
|
|
{
|
|
|
|
struct cfs_rq *cfs_rq;
|
|
|
|
struct sched_entity *se = &curr->se;
|
|
|
|
|
|
|
|
for_each_sched_entity(se) {
|
|
|
|
cfs_rq = cfs_rq_of(se);
|
|
|
|
entity_tick(cfs_rq, se);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Share the fairness runtime between parent and child, thus the
|
|
|
|
* total amount of pressure for CPU stays equal - new tasks
|
|
|
|
* get a chance to run but frequent forkers are not allowed to
|
|
|
|
* monopolize the CPU. Note: the parent runqueue is locked,
|
|
|
|
* the child is not running yet.
|
|
|
|
*/
|
2007-08-09 11:16:49 +02:00
|
|
|
static void task_new_fair(struct rq *rq, struct task_struct *p)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
|
|
|
struct cfs_rq *cfs_rq = task_cfs_rq(p);
|
2007-08-28 12:53:24 +02:00
|
|
|
struct sched_entity *se = &p->se, *curr = cfs_rq_curr(cfs_rq);
|
2007-07-09 18:51:58 +02:00
|
|
|
|
|
|
|
sched_info_queued(p);
|
|
|
|
|
2007-08-28 12:53:24 +02:00
|
|
|
update_curr(cfs_rq);
|
2007-08-09 11:16:47 +02:00
|
|
|
update_stats_enqueue(cfs_rq, se);
|
2007-07-09 18:51:58 +02:00
|
|
|
/*
|
|
|
|
* Child runs first: we let it run before the parent
|
|
|
|
* until it reschedules once. We set up the key so that
|
|
|
|
* it will preempt the parent:
|
|
|
|
*/
|
2007-08-28 12:53:24 +02:00
|
|
|
se->fair_key = curr->fair_key -
|
2007-08-28 12:53:24 +02:00
|
|
|
niced_granularity(curr, sched_granularity(cfs_rq)) - 1;
|
2007-07-09 18:51:58 +02:00
|
|
|
/*
|
|
|
|
* The first wait is dominated by the child-runs-first logic,
|
|
|
|
* so do not credit it with that waiting time yet:
|
|
|
|
*/
|
|
|
|
if (sysctl_sched_features & SCHED_FEAT_SKIP_INITIAL)
|
2007-08-28 12:53:24 +02:00
|
|
|
se->wait_start_fair = 0;
|
2007-07-09 18:51:58 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* The statistical average of wait_runtime is about
|
|
|
|
* -granularity/2, so initialize the task with that:
|
|
|
|
*/
|
2007-09-05 14:32:49 +02:00
|
|
|
if (sysctl_sched_features & SCHED_FEAT_START_DEBIT)
|
2007-08-28 12:53:24 +02:00
|
|
|
se->wait_runtime = -(sched_granularity(cfs_rq) / 2);
|
2007-07-09 18:51:58 +02:00
|
|
|
|
|
|
|
__enqueue_entity(cfs_rq, se);
|
2007-10-15 17:00:02 +02:00
|
|
|
resched_task(rq->curr);
|
2007-07-09 18:51:58 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
#ifdef CONFIG_FAIR_GROUP_SCHED
|
|
|
|
/* Account for a task changing its policy or group.
|
|
|
|
*
|
|
|
|
* This routine is mostly called to set cfs_rq->curr field when a task
|
|
|
|
* migrates between groups/classes.
|
|
|
|
*/
|
|
|
|
static void set_curr_task_fair(struct rq *rq)
|
|
|
|
{
|
2007-08-24 20:39:10 +02:00
|
|
|
struct sched_entity *se = &rq->curr->se;
|
2007-08-09 11:16:47 +02:00
|
|
|
|
2007-08-09 11:16:51 +02:00
|
|
|
for_each_sched_entity(se)
|
|
|
|
set_next_entity(cfs_rq_of(se), se);
|
2007-07-09 18:51:58 +02:00
|
|
|
}
|
|
|
|
#else
|
|
|
|
static void set_curr_task_fair(struct rq *rq)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/*
|
|
|
|
* All the scheduling class methods:
|
|
|
|
*/
|
|
|
|
struct sched_class fair_sched_class __read_mostly = {
|
|
|
|
.enqueue_task = enqueue_task_fair,
|
|
|
|
.dequeue_task = dequeue_task_fair,
|
|
|
|
.yield_task = yield_task_fair,
|
|
|
|
|
|
|
|
.check_preempt_curr = check_preempt_curr_fair,
|
|
|
|
|
|
|
|
.pick_next_task = pick_next_task_fair,
|
|
|
|
.put_prev_task = put_prev_task_fair,
|
|
|
|
|
|
|
|
.load_balance = load_balance_fair,
|
|
|
|
|
|
|
|
.set_curr_task = set_curr_task_fair,
|
|
|
|
.task_tick = task_tick_fair,
|
|
|
|
.task_new = task_new_fair,
|
|
|
|
};
|
|
|
|
|
|
|
|
#ifdef CONFIG_SCHED_DEBUG
|
2007-08-09 11:16:47 +02:00
|
|
|
static void print_cfs_stats(struct seq_file *m, int cpu)
|
2007-07-09 18:51:58 +02:00
|
|
|
{
|
|
|
|
struct cfs_rq *cfs_rq;
|
|
|
|
|
2007-08-09 11:16:51 +02:00
|
|
|
for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
|
2007-08-09 11:16:47 +02:00
|
|
|
print_cfs_rq(m, cpu, cfs_rq);
|
2007-07-09 18:51:58 +02:00
|
|
|
}
|
|
|
|
#endif
|