3bbcbc8039
Mel Gorman reports a hackbench regression with psi that would prohibit shipping the suse kernel with it default-enabled, but he'd still like users to be able to opt in at little to no cost to others. With the current combination of CONFIG_PSI and the psi_disabled bool set from the commandline, this is a challenge. Do the following things to make it easier: 1. Add a config option CONFIG_PSI_DEFAULT_DISABLED that allows distros to enable CONFIG_PSI in their kernel but leave the feature disabled unless a user requests it at boot-time. To avoid double negatives, rename psi_disabled= to psi=. 2. Make psi_disabled a static branch to eliminate any branch costs when the feature is disabled. In terms of numbers before and after this patch, Mel says: : The following is a comparision using CONFIG_PSI=n as a baseline against : your patch and a vanilla kernel : : 4.20.0-rc4 4.20.0-rc4 4.20.0-rc4 : kconfigdisable-v1r1 vanilla psidisable-v1r1 : Amean 1 1.3100 ( 0.00%) 1.3923 ( -6.28%) 1.3427 ( -2.49%) : Amean 3 3.8860 ( 0.00%) 4.1230 * -6.10%* 3.8860 ( -0.00%) : Amean 5 6.8847 ( 0.00%) 8.0390 * -16.77%* 6.7727 ( 1.63%) : Amean 7 9.9310 ( 0.00%) 10.8367 * -9.12%* 9.9910 ( -0.60%) : Amean 12 16.6577 ( 0.00%) 18.2363 * -9.48%* 17.1083 ( -2.71%) : Amean 18 26.5133 ( 0.00%) 27.8833 * -5.17%* 25.7663 ( 2.82%) : Amean 24 34.3003 ( 0.00%) 34.6830 ( -1.12%) 32.0450 ( 6.58%) : Amean 30 40.0063 ( 0.00%) 40.5800 ( -1.43%) 41.5087 ( -3.76%) : Amean 32 40.1407 ( 0.00%) 41.2273 ( -2.71%) 39.9417 ( 0.50%) : : It's showing that the vanilla kernel takes a hit (as the bisection : indicated it would) and that disabling PSI by default is reasonably : close in terms of performance for this particular workload on this : particular machine so; Link: http://lkml.kernel.org/r/20181127165329.GA29728@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Tested-by: Mel Gorman <mgorman@techsingularity.net> Reported-by: Mel Gorman <mgorman@techsingularity.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> (cherry picked from commit e0c274472d5d27f277af722e017525e0b33784cd) Bug: 127712811 Test: lmkd in PSI mode Change-Id: I6cb666fa351e8901df82e4d6931bfec0c5ce230d Signed-off-by: Suren Baghdasaryan <surenb@google.com>
253 lines
7.5 KiB
C
253 lines
7.5 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
|
|
#ifdef CONFIG_SCHEDSTATS
|
|
|
|
/*
|
|
* Expects runqueue lock to be held for atomicity of update
|
|
*/
|
|
static inline void
|
|
rq_sched_info_arrive(struct rq *rq, unsigned long long delta)
|
|
{
|
|
if (rq) {
|
|
rq->rq_sched_info.run_delay += delta;
|
|
rq->rq_sched_info.pcount++;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Expects runqueue lock to be held for atomicity of update
|
|
*/
|
|
static inline void
|
|
rq_sched_info_depart(struct rq *rq, unsigned long long delta)
|
|
{
|
|
if (rq)
|
|
rq->rq_cpu_time += delta;
|
|
}
|
|
|
|
static inline void
|
|
rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)
|
|
{
|
|
if (rq)
|
|
rq->rq_sched_info.run_delay += delta;
|
|
}
|
|
#define schedstat_enabled() static_branch_unlikely(&sched_schedstats)
|
|
#define __schedstat_inc(var) do { var++; } while (0)
|
|
#define schedstat_inc(var) do { if (schedstat_enabled()) { var++; } } while (0)
|
|
#define __schedstat_add(var, amt) do { var += (amt); } while (0)
|
|
#define schedstat_add(var, amt) do { if (schedstat_enabled()) { var += (amt); } } while (0)
|
|
#define __schedstat_set(var, val) do { var = (val); } while (0)
|
|
#define schedstat_set(var, val) do { if (schedstat_enabled()) { var = (val); } } while (0)
|
|
#define schedstat_val(var) (var)
|
|
#define schedstat_val_or_zero(var) ((schedstat_enabled()) ? (var) : 0)
|
|
|
|
#else /* !CONFIG_SCHEDSTATS: */
|
|
static inline void rq_sched_info_arrive (struct rq *rq, unsigned long long delta) { }
|
|
static inline void rq_sched_info_dequeued(struct rq *rq, unsigned long long delta) { }
|
|
static inline void rq_sched_info_depart (struct rq *rq, unsigned long long delta) { }
|
|
# define schedstat_enabled() 0
|
|
# define __schedstat_inc(var) do { } while (0)
|
|
# define schedstat_inc(var) do { } while (0)
|
|
# define __schedstat_add(var, amt) do { } while (0)
|
|
# define schedstat_add(var, amt) do { } while (0)
|
|
# define __schedstat_set(var, val) do { } while (0)
|
|
# define schedstat_set(var, val) do { } while (0)
|
|
# define schedstat_val(var) 0
|
|
# define schedstat_val_or_zero(var) 0
|
|
#endif /* CONFIG_SCHEDSTATS */
|
|
|
|
#ifdef CONFIG_PSI
|
|
/*
|
|
* PSI tracks state that persists across sleeps, such as iowaits and
|
|
* memory stalls. As a result, it has to distinguish between sleeps,
|
|
* where a task's runnable state changes, and requeues, where a task
|
|
* and its state are being moved between CPUs and runqueues.
|
|
*/
|
|
static inline void psi_enqueue(struct task_struct *p, bool wakeup)
|
|
{
|
|
int clear = 0, set = TSK_RUNNING;
|
|
|
|
if (static_branch_likely(&psi_disabled))
|
|
return;
|
|
|
|
if (!wakeup || p->sched_psi_wake_requeue) {
|
|
if (p->flags & PF_MEMSTALL)
|
|
set |= TSK_MEMSTALL;
|
|
if (p->sched_psi_wake_requeue)
|
|
p->sched_psi_wake_requeue = 0;
|
|
} else {
|
|
if (p->in_iowait)
|
|
clear |= TSK_IOWAIT;
|
|
}
|
|
|
|
psi_task_change(p, clear, set);
|
|
}
|
|
|
|
static inline void psi_dequeue(struct task_struct *p, bool sleep)
|
|
{
|
|
int clear = TSK_RUNNING, set = 0;
|
|
|
|
if (static_branch_likely(&psi_disabled))
|
|
return;
|
|
|
|
if (!sleep) {
|
|
if (p->flags & PF_MEMSTALL)
|
|
clear |= TSK_MEMSTALL;
|
|
} else {
|
|
if (p->in_iowait)
|
|
set |= TSK_IOWAIT;
|
|
}
|
|
|
|
psi_task_change(p, clear, set);
|
|
}
|
|
|
|
static inline void psi_ttwu_dequeue(struct task_struct *p)
|
|
{
|
|
if (static_branch_likely(&psi_disabled))
|
|
return;
|
|
/*
|
|
* Is the task being migrated during a wakeup? Make sure to
|
|
* deregister its sleep-persistent psi states from the old
|
|
* queue, and let psi_enqueue() know it has to requeue.
|
|
*/
|
|
if (unlikely(p->in_iowait || (p->flags & PF_MEMSTALL))) {
|
|
struct rq_flags rf;
|
|
struct rq *rq;
|
|
int clear = 0;
|
|
|
|
if (p->in_iowait)
|
|
clear |= TSK_IOWAIT;
|
|
if (p->flags & PF_MEMSTALL)
|
|
clear |= TSK_MEMSTALL;
|
|
|
|
rq = __task_rq_lock(p, &rf);
|
|
psi_task_change(p, clear, 0);
|
|
p->sched_psi_wake_requeue = 1;
|
|
__task_rq_unlock(rq, &rf);
|
|
}
|
|
}
|
|
|
|
static inline void psi_task_tick(struct rq *rq)
|
|
{
|
|
if (static_branch_likely(&psi_disabled))
|
|
return;
|
|
|
|
if (unlikely(rq->curr->flags & PF_MEMSTALL))
|
|
psi_memstall_tick(rq->curr, cpu_of(rq));
|
|
}
|
|
#else /* CONFIG_PSI */
|
|
static inline void psi_enqueue(struct task_struct *p, bool wakeup) {}
|
|
static inline void psi_dequeue(struct task_struct *p, bool sleep) {}
|
|
static inline void psi_ttwu_dequeue(struct task_struct *p) {}
|
|
static inline void psi_task_tick(struct rq *rq) {}
|
|
#endif /* CONFIG_PSI */
|
|
|
|
#ifdef CONFIG_SCHED_INFO
|
|
static inline void sched_info_reset_dequeued(struct task_struct *t)
|
|
{
|
|
t->sched_info.last_queued = 0;
|
|
}
|
|
|
|
/*
|
|
* We are interested in knowing how long it was from the *first* time a
|
|
* task was queued to the time that it finally hit a CPU, we call this routine
|
|
* from dequeue_task() to account for possible rq->clock skew across CPUs. The
|
|
* delta taken on each CPU would annul the skew.
|
|
*/
|
|
static inline void sched_info_dequeued(struct rq *rq, struct task_struct *t)
|
|
{
|
|
unsigned long long now = rq_clock(rq), delta = 0;
|
|
|
|
if (unlikely(sched_info_on()))
|
|
if (t->sched_info.last_queued)
|
|
delta = now - t->sched_info.last_queued;
|
|
sched_info_reset_dequeued(t);
|
|
t->sched_info.run_delay += delta;
|
|
|
|
rq_sched_info_dequeued(rq, delta);
|
|
}
|
|
|
|
/*
|
|
* Called when a task finally hits the CPU. We can now calculate how
|
|
* long it was waiting to run. We also note when it began so that we
|
|
* can keep stats on how long its timeslice is.
|
|
*/
|
|
static void sched_info_arrive(struct rq *rq, struct task_struct *t)
|
|
{
|
|
unsigned long long now = rq_clock(rq), delta = 0;
|
|
|
|
if (t->sched_info.last_queued)
|
|
delta = now - t->sched_info.last_queued;
|
|
sched_info_reset_dequeued(t);
|
|
t->sched_info.run_delay += delta;
|
|
t->sched_info.last_arrival = now;
|
|
t->sched_info.pcount++;
|
|
|
|
rq_sched_info_arrive(rq, delta);
|
|
}
|
|
|
|
/*
|
|
* This function is only called from enqueue_task(), but also only updates
|
|
* the timestamp if it is already not set. It's assumed that
|
|
* sched_info_dequeued() will clear that stamp when appropriate.
|
|
*/
|
|
static inline void sched_info_queued(struct rq *rq, struct task_struct *t)
|
|
{
|
|
if (unlikely(sched_info_on())) {
|
|
if (!t->sched_info.last_queued)
|
|
t->sched_info.last_queued = rq_clock(rq);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Called when a process ceases being the active-running process involuntarily
|
|
* due, typically, to expiring its time slice (this may also be called when
|
|
* switching to the idle task). Now we can calculate how long we ran.
|
|
* Also, if the process is still in the TASK_RUNNING state, call
|
|
* sched_info_queued() to mark that it has now again started waiting on
|
|
* the runqueue.
|
|
*/
|
|
static inline void sched_info_depart(struct rq *rq, struct task_struct *t)
|
|
{
|
|
unsigned long long delta = rq_clock(rq) - t->sched_info.last_arrival;
|
|
|
|
rq_sched_info_depart(rq, delta);
|
|
|
|
if (t->state == TASK_RUNNING)
|
|
sched_info_queued(rq, t);
|
|
}
|
|
|
|
/*
|
|
* Called when tasks are switched involuntarily due, typically, to expiring
|
|
* their time slice. (This may also be called when switching to or from
|
|
* the idle task.) We are only called when prev != next.
|
|
*/
|
|
static inline void
|
|
__sched_info_switch(struct rq *rq, struct task_struct *prev, struct task_struct *next)
|
|
{
|
|
/*
|
|
* prev now departs the CPU. It's not interesting to record
|
|
* stats about how efficient we were at scheduling the idle
|
|
* process, however.
|
|
*/
|
|
if (prev != rq->idle)
|
|
sched_info_depart(rq, prev);
|
|
|
|
if (next != rq->idle)
|
|
sched_info_arrive(rq, next);
|
|
}
|
|
|
|
static inline void
|
|
sched_info_switch(struct rq *rq, struct task_struct *prev, struct task_struct *next)
|
|
{
|
|
if (unlikely(sched_info_on()))
|
|
__sched_info_switch(rq, prev, next);
|
|
}
|
|
|
|
#else /* !CONFIG_SCHED_INFO: */
|
|
# define sched_info_queued(rq, t) do { } while (0)
|
|
# define sched_info_reset_dequeued(t) do { } while (0)
|
|
# define sched_info_dequeued(rq, t) do { } while (0)
|
|
# define sched_info_depart(rq, t) do { } while (0)
|
|
# define sched_info_arrive(rq, next) do { } while (0)
|
|
# define sched_info_switch(rq, t, next) do { } while (0)
|
|
#endif /* CONFIG_SCHED_INFO */
|