rcu.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: paulmck@kernel.org
To: rcu@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, kernel-team@fb.com,
	mingo@kernel.org, jiangshanlai@gmail.com,
	akpm@linux-foundation.org, mathieu.desnoyers@efficios.com,
	josh@joshtriplett.org, tglx@linutronix.de, peterz@infradead.org,
	rostedt@goodmis.org, dhowells@redhat.com, edumazet@google.com,
	fweisbec@gmail.com, oleg@redhat.com, joel@joelfernandes.org,
	"Paul E. McKenney" <paulmck@kernel.org>
Subject: [PATCH tip/core/rcu 4/4] rcu-tasks: Make the units of ->init_fract be jiffies
Date: Thu,  5 Nov 2020 15:39:33 -0800	[thread overview]
Message-ID: <20201105233933.20748-4-paulmck@kernel.org> (raw)
In-Reply-To: <20201105233900.GA20676@paulmck-ThinkPad-P72>

From: "Paul E. McKenney" <paulmck@kernel.org>

Currently, the units of ->init_fract are milliseconds while those of
->gp_sleep are jiffies.  For consistency with each other and with the
argument of schedule_timeout_idle(), this commit changes the units of
->init_fract to jiffies.

This change does affect the backoff algorithm, but only on systems where
HZ is not 1000, and even there the change makes more sense, given that the
current setup would "back off" to the same number of jiffies repeatedly.
In contrast, with this change, the number of jiffies waited increases
on each pass throught the loop in the rcu_tasks_wait_gp() function.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 kernel/rcu/tasks.h | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 0b45989..35bdcfd 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -335,8 +335,6 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
 
 	// Start off with initial wait and slowly back off to 1 HZ wait.
 	fract = rtp->init_fract;
-	if (fract > HZ)
-		fract = HZ;
 
 	while (!list_empty(&holdouts)) {
 		bool firstreport;
@@ -345,10 +343,10 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
 
 		/* Slowly back off waiting for holdouts */
 		set_tasks_gp_state(rtp, RTGS_WAIT_SCAN_HOLDOUTS);
-		schedule_timeout_idle(HZ/fract);
+		schedule_timeout_idle(fract);
 
-		if (fract > 1)
-			fract--;
+		if (fract < HZ)
+			fract++;
 
 		rtst = READ_ONCE(rcu_task_stall_timeout);
 		needreport = rtst > 0 && time_after(jiffies, lastreport + rtst);
@@ -557,7 +555,7 @@ EXPORT_SYMBOL_GPL(rcu_barrier_tasks);
 static int __init rcu_spawn_tasks_kthread(void)
 {
 	rcu_tasks.gp_sleep = HZ / 10;
-	rcu_tasks.init_fract = 10;
+	rcu_tasks.init_fract = HZ / 10;
 	rcu_tasks.pregp_func = rcu_tasks_pregp_step;
 	rcu_tasks.pertask_func = rcu_tasks_pertask;
 	rcu_tasks.postscan_func = rcu_tasks_postscan;
@@ -1178,12 +1176,12 @@ static int __init rcu_spawn_tasks_trace_kthread(void)
 {
 	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) {
 		rcu_tasks_trace.gp_sleep = HZ / 10;
-		rcu_tasks_trace.init_fract = 10;
+		rcu_tasks_trace.init_fract = HZ / 10;
 	} else {
 		rcu_tasks_trace.gp_sleep = HZ / 200;
 		if (rcu_tasks_trace.gp_sleep <= 0)
 			rcu_tasks_trace.gp_sleep = 1;
-		rcu_tasks_trace.init_fract = HZ / 5;
+		rcu_tasks_trace.init_fract = HZ / 200;
 		if (rcu_tasks_trace.init_fract <= 0)
 			rcu_tasks_trace.init_fract = 1;
 	}
-- 
2.9.5


      parent reply	other threads:[~2020-11-05 23:39 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-11-05 23:39 [PATCH tip/core/rcu 0/4] RCU-tasks updates for v5.11 Paul E. McKenney
2020-11-05 23:39 ` [PATCH tip/core/rcu 1/4] rcutorture: Make preemptible TRACE02 enable lockdep paulmck
2020-11-05 23:39 ` [PATCH tip/core/rcu 2/4] rcu-tasks: Convert rcu_tasks_wait_gp() for-loop to while-loop paulmck
2020-11-05 23:39 ` [PATCH tip/core/rcu 3/4] rcutorture: Make grace-period kthread report match RCU flavor being tested paulmck
2020-12-15  8:40   ` Geert Uytterhoeven
2020-12-15 18:24     ` Paul E. McKenney
2020-12-16  9:31       ` Geert Uytterhoeven
2020-12-16 16:48         ` Paul E. McKenney
2020-12-27 16:49           ` Paul E. McKenney
2020-11-05 23:39 ` paulmck [this message]

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=20201105233933.20748-4-paulmck@kernel.org \
    --to=paulmck@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=dhowells@redhat.com \
    --cc=edumazet@google.com \
    --cc=fweisbec@gmail.com \
    --cc=jiangshanlai@gmail.com \
    --cc=joel@joelfernandes.org \
    --cc=josh@joshtriplett.org \
    --cc=kernel-team@fb.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=mingo@kernel.org \
    --cc=oleg@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rcu@vger.kernel.org \
    --cc=rostedt@goodmis.org \
    --cc=tglx@linutronix.de \
    /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).