All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Luis R. Rodriguez" <mcgrof@kernel.org>
To: peterz@infradead.org, paulmck@linux.vnet.ibm.com,
	oleg@redhat.com, josh@joshtriplett.org, rostedt@goodmis.org,
	mathieu.desnoyers@efficios.com, jiangshanlai@gmail.com
Cc: paul.gortmaker@windriver.com, boqun.feng@gmail.com,
	ebiederm@xmission.com, dmitry.torokhov@gmail.com,
	linux-kernel@vger.kernel.org,
	"Luis R. Rodriguez" <mcgrof@kernel.org>
Subject: [PATCH 1/2] swait: add idle variants which don't contribute to load average
Date: Tue, 20 Jun 2017 14:45:46 -0700	[thread overview]
Message-ID: <20170620214548.6602-2-mcgrof@kernel.org> (raw)
In-Reply-To: <20170620214548.6602-1-mcgrof@kernel.org>

There are cases where folks are using an interruptible swait when
using kthreads. This is rather confusing given you'd expect
interruptible waits to be -- interruptible, but kthreads are not
interruptible ! The reason for such practice though is to avoid
having these kthreads contribute to the system load average.

When systems are idle some kthreads may spend a lot of time blocking if
using swait_event_timeout(). This would contribute to the system load
average. On systems without preemption this would mean the load average
of an idle system is bumped to 2 instead of 0. On systems with PREEMPT=y
this would mean the load average of an idle system is bumped to 3
instead of 0.

This adds proper API using TASK_IDLE to make such goals explicit and
avoid confusion.

Suggested-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Tested-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org>
---
 include/linux/swait.h | 55 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)

diff --git a/include/linux/swait.h b/include/linux/swait.h
index 2c700694d50a..10b80900b509 100644
--- a/include/linux/swait.h
+++ b/include/linux/swait.h
@@ -194,4 +194,59 @@ do {									\
 	__ret;								\
 })
 
+#define __swait_event_idle(wq, condition)				\
+	(void)___swait_event(wq, condition, TASK_IDLE, 0, schedule())
+
+/**
+ * swait_event_idle - wait without system load contribution
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ *
+ * The process is put to sleep (TASK_IDLE) until the @condition evaluates to
+ * true. The @condition is checked each time the waitqueue @wq is woken up.
+ *
+ * This function is mostly used when a kthread or workqueue waits for some
+ * condition and doesn't want to contribute to system load. Signals are
+ * ignored.
+ */
+#define swait_event_idle(wq, condition)					\
+do {									\
+	if (condition)							\
+		break;							\
+	__swait_event_idle(wq, condition);				\
+} while (0)
+
+#define __swait_event_idle_timeout(wq, condition, timeout)		\
+	___swait_event(wq, ___wait_cond_timeout(condition),		\
+		       TASK_IDLE, timeout,				\
+		       __ret = schedule_timeout(__ret))
+
+/**
+ * swait_event_idle_timeout - wait up to timeout without load contribution
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ * @timeout: timeout at which we'll give up in jiffies
+ *
+ * The process is put to sleep (TASK_IDLE) until the @condition evaluates to
+ * true. The @condition is checked each time the waitqueue @wq is woken up.
+ *
+ * This function is mostly used when a kthread or workqueue waits for some
+ * condition and doesn't want to contribute to system load. Signals are
+ * ignored.
+ *
+ * Returns:
+ * 0 if the @condition evaluated to %false after the @timeout elapsed,
+ * 1 if the @condition evaluated to %true after the @timeout elapsed,
+ * or the remaining jiffies (at least 1) if the @condition evaluated
+ * to %true before the @timeout elapsed.
+ */
+#define swait_event_idle_timeout(wq, condition, timeout)		\
+({									\
+	long __ret = timeout;						\
+	if (!___wait_cond_timeout(condition))				\
+		__ret = __swait_event_idle_timeout(wq,			\
+						   condition, timeout);	\
+	__ret;								\
+})
+
 #endif /* _LINUX_SWAIT_H */
-- 
2.11.0

  reply	other threads:[~2017-06-20 21:46 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-06-14 23:06 [RFC] rcu: use killable versions of swait Luis R. Rodriguez
2017-06-14 23:43 ` Paul E. McKenney
2017-06-15 15:50   ` Luis R. Rodriguez
2017-06-15 16:22     ` Paul E. McKenney
2017-06-15 16:35       ` Luis R. Rodriguez
2017-06-15 16:55         ` Eric W. Biederman
2017-06-15 18:48           ` [RFC v2 0/2] swait: add idle to make idle-hacks on kthreads explicit Luis R. Rodriguez
2017-06-15 18:48             ` [RFC v2 1/2] swait: add idle variants which don't contribute to load average Luis R. Rodriguez
2017-06-16  0:47               ` Boqun Feng
2017-06-20 21:32                 ` Luis R. Rodriguez
2017-06-16 20:31               ` Eric W. Biederman
2017-06-19 17:53                 ` Paul E. McKenney
2017-06-15 18:48             ` [RFC v2 2/2] rcu: use idle versions of swait to make idle-hack clear Luis R. Rodriguez
2017-06-15 21:57             ` [RFC v2 0/2] swait: add idle to make idle-hacks on kthreads explicit Paul E. McKenney
2017-06-15 23:26               ` Luis R. Rodriguez
2017-06-15 23:43                 ` Paul E. McKenney
2017-06-16 20:37                   ` Eric W. Biederman
2017-06-19 17:54                     ` Paul E. McKenney
2017-06-20 21:45             ` [PATCH " Luis R. Rodriguez
2017-06-20 21:45               ` Luis R. Rodriguez [this message]
2017-06-20 21:45               ` [PATCH 2/2] rcu: use idle versions of swait to make idle-hack clear Luis R. Rodriguez
2017-06-21 16:48               ` [PATCH 0/2] swait: add idle to make idle-hacks on kthreads explicit Paul E. McKenney
2017-06-21 17:57                 ` Luis R. Rodriguez
2017-06-21 18:19                   ` Paul E. McKenney
2017-06-15 17:34         ` [RFC] rcu: use killable versions of swait Paul E. McKenney

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=20170620214548.6602-2-mcgrof@kernel.org \
    --to=mcgrof@kernel.org \
    --cc=boqun.feng@gmail.com \
    --cc=dmitry.torokhov@gmail.com \
    --cc=ebiederm@xmission.com \
    --cc=jiangshanlai@gmail.com \
    --cc=josh@joshtriplett.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=oleg@redhat.com \
    --cc=paul.gortmaker@windriver.com \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.