linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Johannes Weiner <hannes@cmpxchg.org>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Tejun Heo <tj@kernel.org>, Suren Baghdasaryan <surenb@google.com>,
	Daniel Drake <drake@endlessm.com>,
	Vinayak Menon <vinmenon@codeaurora.org>,
	Christopher Lameter <cl@linux.com>,
	Mike Galbraith <efault@gmx.de>,
	Shakeel Butt <shakeelb@google.com>,
	Peter Enderborg <peter.enderborg@sony.com>,
	linux-mm@kvack.org, cgroups@vger.kernel.org,
	linux-kernel@vger.kernel.org, kernel-team@fb.com
Subject: Re: [PATCH 8/9] psi: pressure stall information for CPU, memory, and IO
Date: Mon, 6 Aug 2018 11:05:50 -0400	[thread overview]
Message-ID: <20180806150550.GA9888@cmpxchg.org> (raw)
In-Reply-To: <20180803165641.GA2476@hirez.programming.kicks-ass.net>

On Fri, Aug 03, 2018 at 06:56:41PM +0200, Peter Zijlstra wrote:
> On Wed, Aug 01, 2018 at 11:19:57AM -0400, Johannes Weiner wrote:
> > +static bool test_state(unsigned int *tasks, int cpu, enum psi_states state)
> > +{
> > +	switch (state) {
> > +	case PSI_IO_SOME:
> > +		return tasks[NR_IOWAIT];
> > +	case PSI_IO_FULL:
> > +		return tasks[NR_IOWAIT] && !tasks[NR_RUNNING];
> > +	case PSI_MEM_SOME:
> > +		return tasks[NR_MEMSTALL];
> > +	case PSI_MEM_FULL:
> > +		/*
> > +		 * Since we care about lost potential, things are
> > +		 * fully blocked on memory when there are no other
> > +		 * working tasks, but also when the CPU is actively
> > +		 * being used by a reclaimer and nothing productive
> > +		 * could run even if it were runnable.
> > +		 */
> > +		return tasks[NR_MEMSTALL] &&
> > +			(!tasks[NR_RUNNING] ||
> > +			 cpu_curr(cpu)->flags & PF_MEMSTALL);
> 
> I don't think you can do this, there is nothing that guarantees
> cpu_curr() still exists.

Argh, that's right. This needs an explicit count if we want to access
it locklessly. And you already said you didn't like that this is the
only state not derived purely from the task counters, so maybe this is
the way to go after all.

How about something like this (untested)?

diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
index b6ff46362eb3..afc39fbbf9dd 100644
--- a/include/linux/psi_types.h
+++ b/include/linux/psi_types.h
@@ -10,6 +10,7 @@ enum psi_task_count {
 	NR_IOWAIT,
 	NR_MEMSTALL,
 	NR_RUNNING,
+	NR_RECLAIMING,
 	NR_PSI_TASK_COUNTS,
 };
 
@@ -17,6 +18,7 @@ enum psi_task_count {
 #define TSK_IOWAIT	(1 << NR_IOWAIT)
 #define TSK_MEMSTALL	(1 << NR_MEMSTALL)
 #define TSK_RUNNING	(1 << NR_RUNNING)
+#define TSK_RECLAIMING	(1 << NR_RECLAIMING)
 
 /* Resources that workloads could be stalled on */
 enum psi_res {
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e53137df405b..90fd813dd7c2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3517,6 +3517,7 @@ static void __sched notrace __schedule(bool preempt)
 		 */
 		++*switch_count;
 
+		psi_switch(rq, prev, next);
 		trace_sched_switch(preempt, prev, next);
 
 		/* Also unlocks the rq: */
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index a20f885da66f..352c3a032ff0 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -209,8 +209,7 @@ static bool test_state(unsigned int *tasks, int cpu, enum psi_states state)
 		 * could run even if it were runnable.
 		 */
 		return tasks[NR_MEMSTALL] &&
-			(!tasks[NR_RUNNING] ||
-			 cpu_curr(cpu)->flags & PF_MEMSTALL);
+			(!tasks[NR_RUNNING] || tasks[NR_RECLAIMING]);
 	case PSI_CPU_SOME:
 		return tasks[NR_RUNNING] > 1;
 	case PSI_NONIDLE:
@@ -530,7 +529,7 @@ void psi_memstall_enter(unsigned long *flags)
 	update_rq_clock(rq);
 
 	current->flags |= PF_MEMSTALL;
-	psi_task_change(current, rq_clock(rq), 0, TSK_MEMSTALL);
+	psi_task_change(current, rq_clock(rq), 0, TSK_MEMSTALL|TSK_RECLAIMING);
 
 	rq_unlock_irq(rq, &rf);
 }
@@ -561,7 +560,7 @@ void psi_memstall_leave(unsigned long *flags)
 	update_rq_clock(rq);
 
 	current->flags &= ~PF_MEMSTALL;
-	psi_task_change(current, rq_clock(rq), TSK_MEMSTALL, 0);
+	psi_task_change(current, rq_clock(rq), TSK_MEMSTALL|TSK_RECLAIMING, 0);
 
 	rq_unlock_irq(rq, &rf);
 }
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index f3e0267eb47d..2babdd53715d 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -127,12 +127,26 @@ static inline void psi_ttwu_dequeue(struct task_struct *p)
 		__task_rq_unlock(rq, &rf);
 	}
 }
+
+static inline void psi_switch(struct rq *rq, struct task_struct *prev,
+			      struct task_struct *next)
+{
+	if (psi_disabled)
+		return;
+
+	if (unlikely(prev->flags & PF_MEMSTALL))
+		psi_task_change(prev, rq_clock(rq), TSK_RECLAIMING, 0);
+	if (unlikely(next->flags & PF_MEMSTALL))
+		psi_task_change(next, rq_clock(rq), 0, TSK_RECLAIMING);
+}
 #else /* CONFIG_PSI */
 static inline void psi_enqueue(struct rq *rq, struct task_struct *p,
 			       bool wakeup) {}
 static inline void psi_dequeue(struct rq *rq, struct task_struct *p,
 			       bool sleep) {}
 static inline void psi_ttwu_dequeue(struct task_struct *p) {}
+static inline void psi_switch(struct rq *rq, struct task_struct *prev,
+			      struct task_struct *next) {}
 #endif /* CONFIG_PSI */
 
 #ifdef CONFIG_SCHED_INFO

  reply	other threads:[~2018-08-06 15:03 UTC|newest]

Thread overview: 41+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-08-01 15:19 [PATCH 0/9] psi: pressure stall information for CPU, memory, and IO v3 Johannes Weiner
2018-08-01 15:19 ` [PATCH 1/9] mm: workingset: don't drop refault information prematurely Johannes Weiner
2018-08-01 15:19 ` [PATCH 2/9] mm: workingset: tell cache transitions from workingset thrashing Johannes Weiner
2018-08-01 21:56   ` Suren Baghdasaryan
2018-08-02 12:28     ` Johannes Weiner
2018-08-01 15:19 ` [PATCH 3/9] delayacct: track delays from thrashing cache pages Johannes Weiner
2018-08-01 15:19 ` [PATCH 4/9] sched: loadavg: consolidate LOAD_INT, LOAD_FRAC, CALC_LOAD Johannes Weiner
2018-08-01 15:19 ` [PATCH 5/9] sched: loadavg: make calc_load_n() public Johannes Weiner
2018-08-01 15:19 ` [PATCH 6/9] sched: sched.h: make rq locking and clock functions available in stats.h Johannes Weiner
2018-08-01 15:19 ` [PATCH 7/9] sched: introduce this_rq_lock_irq() Johannes Weiner
2018-08-01 15:19 ` [PATCH 8/9] psi: pressure stall information for CPU, memory, and IO Johannes Weiner
2018-08-03 16:56   ` Peter Zijlstra
2018-08-06 15:05     ` Johannes Weiner [this message]
2018-08-06 15:25       ` Peter Zijlstra
2018-08-06 15:40         ` Johannes Weiner
2018-08-06 15:19     ` Johannes Weiner
2018-08-06 16:03       ` Peter Zijlstra
2018-08-21 19:44     ` Johannes Weiner
2018-08-22  9:16       ` Peter Zijlstra
2018-08-03 17:07   ` Peter Zijlstra
2018-08-06 15:23     ` Johannes Weiner
2018-08-03 17:15   ` Peter Zijlstra
2018-08-03 17:21   ` Peter Zijlstra
2018-08-21 20:11     ` Johannes Weiner
2018-08-22  9:10       ` Peter Zijlstra
2018-08-22 17:28         ` Johannes Weiner
2018-08-01 15:19 ` [PATCH 9/9] psi: cgroup support Johannes Weiner
2018-08-07 11:50 ` [PATCH 0/9] psi: pressure stall information for CPU, memory, and IO v3 peter enderborg
2018-08-07 17:51   ` Johannes Weiner
  -- strict thread matches above, loose matches on Subject: below --
2018-08-28 17:22 [PATCH 0/9] psi: pressure stall information for CPU, memory, and IO v4 Johannes Weiner
2018-08-28 17:22 ` [PATCH 8/9] psi: pressure stall information for CPU, memory, and IO Johannes Weiner
2018-08-28 20:11   ` Randy Dunlap
2018-08-28 20:56     ` Johannes Weiner
2018-08-28 21:30       ` Randy Dunlap
2018-09-07 10:16   ` Peter Zijlstra
2018-09-07 10:21     ` Peter Zijlstra
2018-09-07 14:44     ` Johannes Weiner
2018-09-07 14:58       ` Peter Zijlstra
2018-09-07 17:50         ` Johannes Weiner
2018-09-07 10:24   ` Peter Zijlstra
2018-09-07 14:54     ` Johannes Weiner
2018-08-01 15:12 Johannes Weiner
2018-08-01 15:13 ` [PATCH 8/9] psi: pressure stall information for CPU, memory, and IO Johannes Weiner

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20180806150550.GA9888@cmpxchg.org \
    --to=hannes@cmpxchg.org \
    --cc=akpm@linux-foundation.org \
    --cc=cgroups@vger.kernel.org \
    --cc=cl@linux.com \
    --cc=drake@endlessm.com \
    --cc=efault@gmx.de \
    --cc=kernel-team@fb.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mingo@redhat.com \
    --cc=peter.enderborg@sony.com \
    --cc=peterz@infradead.org \
    --cc=shakeelb@google.com \
    --cc=surenb@google.com \
    --cc=tj@kernel.org \
    --cc=torvalds@linux-foundation.org \
    --cc=vinmenon@codeaurora.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).