mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-04 21:16:39 +07:00
eb414681d5
When systems are overcommitted and resources become contended, it's hard to tell exactly the impact this has on workload productivity, or how close the system is to lockups and OOM kills. In particular, when machines work multiple jobs concurrently, the impact of overcommit in terms of latency and throughput on the individual job can be enormous. In order to maximize hardware utilization without sacrificing individual job health or risk complete machine lockups, this patch implements a way to quantify resource pressure in the system. A kernel built with CONFIG_PSI=y creates files in /proc/pressure/ that expose the percentage of time the system is stalled on CPU, memory, or IO, respectively. Stall states are aggregate versions of the per-task delay accounting delays: cpu: some tasks are runnable but not executing on a CPU memory: tasks are reclaiming, or waiting for swapin or thrashing cache io: tasks are waiting for io completions These percentages of walltime can be thought of as pressure percentages, and they give a general sense of system health and productivity loss incurred by resource overcommit. They can also indicate when the system is approaching lockup scenarios and OOMs. To do this, psi keeps track of the task states associated with each CPU and samples the time they spend in stall states. Every 2 seconds, the samples are averaged across CPUs - weighted by the CPUs' non-idle time to eliminate artifacts from unused CPUs - and translated into percentages of walltime. A running average of those percentages is maintained over 10s, 1m, and 5m periods (similar to the loadaverage). [hannes@cmpxchg.org: doc fixlet, per Randy] Link: http://lkml.kernel.org/r/20180828205625.GA14030@cmpxchg.org [hannes@cmpxchg.org: code optimization] Link: http://lkml.kernel.org/r/20180907175015.GA8479@cmpxchg.org [hannes@cmpxchg.org: rename psi_clock() to psi_update_work(), per Peter] Link: http://lkml.kernel.org/r/20180907145404.GB11088@cmpxchg.org [hannes@cmpxchg.org: fix build] Link: http://lkml.kernel.org/r/20180913014222.GA2370@cmpxchg.org Link: http://lkml.kernel.org/r/20180828172258.3185-9-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Daniel Drake <drake@endlessm.com> Tested-by: Suren Baghdasaryan <surenb@google.com> Cc: Christopher Lameter <cl@linux.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Johannes Weiner <jweiner@fb.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Enderborg <peter.enderborg@sony.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vinayak Menon <vinmenon@codeaurora.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
254 lines
7.4 KiB
C
254 lines
7.4 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 (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 (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 (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 (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 */
|