[PATCH, v8 0/3] *** SUBJECT HERE ***

[PATCH, v8 0/3] *** SUBJECT HERE ***

[Kirill A. Shutsemov]

From: Kirill A. Shutemov <kirill@shutemov.name>

*** BLURB HERE ***

Kirill A. Shutemov (3):
  hrtimer: introduce effective timer slack
  hrtimer: implement PR_GET_EFFECTIVE_TIMERSLACK
  cgroups: introduce timer slack controller

 Documentation/cgroups/timer_slack.txt |   64 +++++++++++++++++
 fs/select.c                           |    7 +--
 include/linux/cgroup_subsys.h         |    6 ++
 include/linux/prctl.h                 |    6 ++
 include/linux/sched.h                 |   10 +++
 init/Kconfig                          |    8 ++
 kernel/Makefile                       |    1 +
 kernel/cgroup_timer_slack.c           |  124 +++++++++++++++++++++++++++++++++
 kernel/fork.c                         |    4 +
 kernel/futex.c                        |    4 +-
 kernel/hrtimer.c                      |    2 +-
 kernel/sys.c                          |    3 +
 12 files changed, 231 insertions(+), 8 deletions(-)
 create mode 100644 Documentation/cgroups/timer_slack.txt
 create mode 100644 kernel/cgroup_timer_slack.c

-- 
1.7.4.1

[PATCH, v8 0/3] *** SUBJECT HERE ***

[Kirill A. Shutsemov]

From: Kirill A. Shutemov <kirill-oKw7cIdHH8eLwutG50LtGA@public.gmane.org>

*** BLURB HERE ***

Kirill A. Shutemov (3):
  hrtimer: introduce effective timer slack
  hrtimer: implement PR_GET_EFFECTIVE_TIMERSLACK
  cgroups: introduce timer slack controller

 Documentation/cgroups/timer_slack.txt |   64 +++++++++++++++++
 fs/select.c                           |    7 +--
 include/linux/cgroup_subsys.h         |    6 ++
 include/linux/prctl.h                 |    6 ++
 include/linux/sched.h                 |   10 +++
 init/Kconfig                          |    8 ++
 kernel/Makefile                       |    1 +
 kernel/cgroup_timer_slack.c           |  124 +++++++++++++++++++++++++++++++++
 kernel/fork.c                         |    4 +
 kernel/futex.c                        |    4 +-
 kernel/hrtimer.c                      |    2 +-
 kernel/sys.c                          |    3 +
 12 files changed, 231 insertions(+), 8 deletions(-)
 create mode 100644 Documentation/cgroups/timer_slack.txt
 create mode 100644 kernel/cgroup_timer_slack.c

-- 
1.7.4.1

[PATCH, v8 1/3] hrtimer: introduce effective timer slack

[Kirill A. Shutsemov]

From: Kirill A. Shutemov <kirill-oKw7cIdHH8eLwutG50LtGA@public.gmane.org>

task_get_effective_timer_slack() returns timer slack value to be used
to configure per-task timers. It can be equal or higher than task's
timer slack value.

For now task_get_effective_timer_slack() returns timer_slack_ns of the
task. Timer slack cgroup controller will implement a bit more
sophisticated logic.

Signed-off-by: Kirill A. Shutemov <kirill-oKw7cIdHH8eLwutG50LtGA@public.gmane.org>
---
 fs/select.c           |    7 ++-----
 include/linux/sched.h |    6 ++++++
 kernel/fork.c         |    4 ++++
 kernel/futex.c        |    4 ++--
 kernel/hrtimer.c      |    2 +-
 5 files changed, 15 insertions(+), 8 deletions(-)

diff --git a/fs/select.c b/fs/select.c
index e56560d..712a122 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -69,7 +69,6 @@ static long __estimate_accuracy(struct timespec *tv)
 
 long select_estimate_accuracy(struct timespec *tv)
 {
-	unsigned long ret;
 	struct timespec now;
 
 	/*
@@ -81,10 +80,8 @@ long select_estimate_accuracy(struct timespec *tv)
 
 	ktime_get_ts(&now);
 	now = timespec_sub(*tv, now);
-	ret = __estimate_accuracy(&now);
-	if (ret < current->timer_slack_ns)
-		return current->timer_slack_ns;
-	return ret;
+	return clamp_t(long, __estimate_accuracy(&now),
+			task_get_effective_timer_slack(current), LONG_MAX);
 }
 
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 777d8a5..44f6f55 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2620,6 +2620,12 @@ static inline unsigned long rlimit_max(unsigned int limit)
 	return task_rlimit_max(current, limit);
 }
 
+static inline unsigned long task_get_effective_timer_slack(
+		struct task_struct *tsk)
+{
+	return tsk->timer_slack_ns;
+}
+
 #endif /* __KERNEL__ */
 
 #endif
diff --git a/kernel/fork.c b/kernel/fork.c
index 25e4291..4958de9 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1089,6 +1089,10 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	memset(&p->rss_stat, 0, sizeof(p->rss_stat));
 #endif
 
+	/*
+	 * Save current task's (not effective) timer slack value as default
+	 * timer slack value for new task.
+	 */
 	p->default_timer_slack_ns = current->timer_slack_ns;
 
 	task_io_accounting_init(&p->ioac);
diff --git a/kernel/futex.c b/kernel/futex.c
index b766d28..e5811c4 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1845,7 +1845,7 @@ static int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
 				      HRTIMER_MODE_ABS);
 		hrtimer_init_sleeper(to, current);
 		hrtimer_set_expires_range_ns(&to->timer, *abs_time,
-					     current->timer_slack_ns);
+				     task_get_effective_timer_slack(current));
 	}
 
 retry:
@@ -2242,7 +2242,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 				      HRTIMER_MODE_ABS);
 		hrtimer_init_sleeper(to, current);
 		hrtimer_set_expires_range_ns(&to->timer, *abs_time,
-					     current->timer_slack_ns);
+				     task_get_effective_timer_slack(current));
 	}
 
 	/*
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 0c8d7c0..ffc9a8d 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1542,7 +1542,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
 	int ret = 0;
 	unsigned long slack;
 
-	slack = current->timer_slack_ns;
+	slack = task_get_effective_timer_slack(current);
 	if (rt_task(current))
 		slack = 0;
 
-- 
1.7.4.1

[PATCH, v8 1/3] hrtimer: introduce effective timer slack

[Kirill A. Shutsemov]

From: Kirill A. Shutemov <kirill@shutemov.name>

task_get_effective_timer_slack() returns timer slack value to be used
to configure per-task timers. It can be equal or higher than task's
timer slack value.

For now task_get_effective_timer_slack() returns timer_slack_ns of the
task. Timer slack cgroup controller will implement a bit more
sophisticated logic.

Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
---
 fs/select.c           |    7 ++-----
 include/linux/sched.h |    6 ++++++
 kernel/fork.c         |    4 ++++
 kernel/futex.c        |    4 ++--
 kernel/hrtimer.c      |    2 +-
 5 files changed, 15 insertions(+), 8 deletions(-)

diff --git a/fs/select.c b/fs/select.c
index e56560d..712a122 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -69,7 +69,6 @@ static long __estimate_accuracy(struct timespec *tv)
 
 long select_estimate_accuracy(struct timespec *tv)
 {
-	unsigned long ret;
 	struct timespec now;
 
 	/*
@@ -81,10 +80,8 @@ long select_estimate_accuracy(struct timespec *tv)
 
 	ktime_get_ts(&now);
 	now = timespec_sub(*tv, now);
-	ret = __estimate_accuracy(&now);
-	if (ret < current->timer_slack_ns)
-		return current->timer_slack_ns;
-	return ret;
+	return clamp_t(long, __estimate_accuracy(&now),
+			task_get_effective_timer_slack(current), LONG_MAX);
 }
 
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 777d8a5..44f6f55 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2620,6 +2620,12 @@ static inline unsigned long rlimit_max(unsigned int limit)
 	return task_rlimit_max(current, limit);
 }
 
+static inline unsigned long task_get_effective_timer_slack(
+		struct task_struct *tsk)
+{
+	return tsk->timer_slack_ns;
+}
+
 #endif /* __KERNEL__ */
 
 #endif
diff --git a/kernel/fork.c b/kernel/fork.c
index 25e4291..4958de9 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1089,6 +1089,10 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	memset(&p->rss_stat, 0, sizeof(p->rss_stat));
 #endif
 
+	/*
+	 * Save current task's (not effective) timer slack value as default
+	 * timer slack value for new task.
+	 */
 	p->default_timer_slack_ns = current->timer_slack_ns;
 
 	task_io_accounting_init(&p->ioac);
diff --git a/kernel/futex.c b/kernel/futex.c
index b766d28..e5811c4 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1845,7 +1845,7 @@ static int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
 				      HRTIMER_MODE_ABS);
 		hrtimer_init_sleeper(to, current);
 		hrtimer_set_expires_range_ns(&to->timer, *abs_time,
-					     current->timer_slack_ns);
+				     task_get_effective_timer_slack(current));
 	}
 
 retry:
@@ -2242,7 +2242,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 				      HRTIMER_MODE_ABS);
 		hrtimer_init_sleeper(to, current);
 		hrtimer_set_expires_range_ns(&to->timer, *abs_time,
-					     current->timer_slack_ns);
+				     task_get_effective_timer_slack(current));
 	}
 
 	/*
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 0c8d7c0..ffc9a8d 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1542,7 +1542,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
 	int ret = 0;
 	unsigned long slack;
 
-	slack = current->timer_slack_ns;
+	slack = task_get_effective_timer_slack(current);
 	if (rt_task(current))
 		slack = 0;
 
-- 
1.7.4.1

[PATCH, v8 2/3] hrtimer: implement PR_GET_EFFECTIVE_TIMERSLACK

[Kirill A. Shutsemov]

From: Kirill A. Shutemov <kirill-oKw7cIdHH8eLwutG50LtGA@public.gmane.org>

PR_GET_EFFECTIVE_TIMERSLACK allows process to know its effective timer
slack value.

Signed-off-by: Kirill A. Shutemov <kirill-oKw7cIdHH8eLwutG50LtGA@public.gmane.org>
---
 include/linux/prctl.h |    6 ++++++
 kernel/sys.c          |    3 +++
 2 files changed, 9 insertions(+), 0 deletions(-)

diff --git a/include/linux/prctl.h b/include/linux/prctl.h
index a3baeb2..3199458 100644
--- a/include/linux/prctl.h
+++ b/include/linux/prctl.h
@@ -102,4 +102,10 @@
 
 #define PR_MCE_KILL_GET 34
 
+/*
+ * Get effective timerslack value for the process.
+ * It can be higher than PR_GET_TIMERSLACK.
+ */
+#define PR_GET_EFFECTIVE_TIMERSLACK 35
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/kernel/sys.c b/kernel/sys.c
index 18da702..b2ec8bf 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1693,6 +1693,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		case PR_GET_TIMERSLACK:
 			error = current->timer_slack_ns;
 			break;
+		case PR_GET_EFFECTIVE_TIMERSLACK:
+			error = task_get_effective_timer_slack(current);
+			break;
 		case PR_SET_TIMERSLACK:
 			if (arg2 <= 0)
 				current->timer_slack_ns =
-- 
1.7.4.1

[PATCH, v8 2/3] hrtimer: implement PR_GET_EFFECTIVE_TIMERSLACK

[Kirill A. Shutsemov]

From: Kirill A. Shutemov <kirill@shutemov.name>

PR_GET_EFFECTIVE_TIMERSLACK allows process to know its effective timer
slack value.

Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
---
 include/linux/prctl.h |    6 ++++++
 kernel/sys.c          |    3 +++
 2 files changed, 9 insertions(+), 0 deletions(-)

diff --git a/include/linux/prctl.h b/include/linux/prctl.h
index a3baeb2..3199458 100644
--- a/include/linux/prctl.h
+++ b/include/linux/prctl.h
@@ -102,4 +102,10 @@
 
 #define PR_MCE_KILL_GET 34
 
+/*
+ * Get effective timerslack value for the process.
+ * It can be higher than PR_GET_TIMERSLACK.
+ */
+#define PR_GET_EFFECTIVE_TIMERSLACK 35
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/kernel/sys.c b/kernel/sys.c
index 18da702..b2ec8bf 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1693,6 +1693,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		case PR_GET_TIMERSLACK:
 			error = current->timer_slack_ns;
 			break;
+		case PR_GET_EFFECTIVE_TIMERSLACK:
+			error = task_get_effective_timer_slack(current);
+			break;
 		case PR_SET_TIMERSLACK:
 			if (arg2 <= 0)
 				current->timer_slack_ns =
-- 
1.7.4.1

[PATCH, v8 3/3] cgroups: introduce timer slack controller

[Kirill A. Shutsemov]

From: Kirill A. Shutemov <kirill-oKw7cIdHH8eLwutG50LtGA@public.gmane.org>

Every task_struct has timer_slack_ns value. This value uses to round up
poll() and select() timeout values. This feature can be useful in
mobile environment where combined wakeups are desired.

cgroup subsys "timer_slack" implement timer slack controller. It
provides a way to set minimal timer slack value for a group of tasks.
If a task belongs to a cgroup with minimal timer slack value higher than
task's value, cgroup's value will be applied.

Idea-by: Jacob Pan <jacob.jun.pan-VuQAYsv1563Yd54FQh9/CA@public.gmane.org>
Signed-off-by: Kirill A. Shutemov <kirill-oKw7cIdHH8eLwutG50LtGA@public.gmane.org>
---
 Documentation/cgroups/timer_slack.txt |   64 +++++++++++++++++
 include/linux/cgroup_subsys.h         |    6 ++
 include/linux/sched.h                 |    4 +
 init/Kconfig                          |    8 ++
 kernel/Makefile                       |    1 +
 kernel/cgroup_timer_slack.c           |  124 +++++++++++++++++++++++++++++++++
 6 files changed, 207 insertions(+), 0 deletions(-)
 create mode 100644 Documentation/cgroups/timer_slack.txt
 create mode 100644 kernel/cgroup_timer_slack.c

diff --git a/Documentation/cgroups/timer_slack.txt b/Documentation/cgroups/timer_slack.txt
new file mode 100644
index 0000000..b1494ff
--- /dev/null
+++ b/Documentation/cgroups/timer_slack.txt
@@ -0,0 +1,64 @@
+Timer Slack Controller
+=====================
+
+Overview
+--------
+
+Every task_struct has timer_slack_ns value. This value uses to round up
+poll() and select() timeout values. This feature can be useful in
+mobile environment where combined wakeups are desired.
+
+cgroup subsys "timer_slack" implements timer slack controller. It
+provides a way to set minimal timer slack value for a group of tasks.
+If a task belongs to a cgroup with minimal timer slack value higher than
+task's value, cgroup's value will be applied.
+
+User interface
+--------------
+
+To get timer slack controller functionality you need to enable it in
+kernel configuration:
+
+CONFIG_CGROUP_TIMER_SLACK=y
+
+The controller provides two files:
+
+# mount -t cgroup -o timer_slack none /sys/fs/cgroup
+# ls /sys/fs/cgroup/timer_slack.*
+/sys/fs/cgroup/timer_slack.effective_slack_ns
+/sys/fs/cgroup/timer_slack.min_slack_ns
+
+By default timer_slack.min_slack_ns is 0:
+
+# cat /sys/fs/cgroup/timer_slack.min_slack_ns
+0
+
+You can set it to some value:
+
+# echo 50000 > /sys/fs/cgroup/timer_slack.min_slack_ns
+# cat /sys/fs/cgroup/timer_slack.min_slack_ns
+50000
+
+Tasks still can set task's value below 50000 using prctl(), but in this
+case cgroup's value will be applied.
+
+Timer slack controller supports hierarchical groups.
+
+# mkdir /sys/fs/cgroup/a
+# cat /sys/fs/cgroup/a/timer_slack.min_slack_ns
+50000
+# echo 70000 > /sys/fs/cgroup/a/timer_slack.min_slack_ns
+# cat /sys/fs/cgroup/a/timer_slack.min_slack_ns
+70000
+
+You can set any value you want, but effective value will the highest value
+up by hierarchy. You can see effective timer slack value for the cgroup from
+timer_slack.effective_slack_ns file:
+
+# cat /sys/fs/cgroup/a/timer_slack.effective_slack_ns
+70000
+# echo 100000 > /sys/fs/cgroup/timer_slack.min_slack_ns
+# cat /sys/fs/cgroup/a/timer_slack.min_slack_ns
+70000
+# cat /sys/fs/cgroup/a/timer_slack.effective_slack_ns
+100000
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index ccefff0..e399228 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -66,3 +66,9 @@ SUBSYS(blkio)
 #endif
 
 /* */
+
+#ifdef CONFIG_CGROUP_TIMER_SLACK
+SUBSYS(timer_slack)
+#endif
+
+/* */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 44f6f55..c10da5d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2620,11 +2620,15 @@ static inline unsigned long rlimit_max(unsigned int limit)
 	return task_rlimit_max(current, limit);
 }
 
+#ifdef CONFIG_CGROUP_TIMER_SLACK
+extern unsigned long task_get_effective_timer_slack(struct task_struct *tsk);
+#else
 static inline unsigned long task_get_effective_timer_slack(
 		struct task_struct *tsk)
 {
 	return tsk->timer_slack_ns;
 }
+#endif
 
 #endif /* __KERNEL__ */
 
diff --git a/init/Kconfig b/init/Kconfig
index be788c0..bbc4d9c 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -596,6 +596,14 @@ config CGROUP_FREEZER
 	  Provides a way to freeze and unfreeze all tasks in a
 	  cgroup.
 
+config CGROUP_TIMER_SLACK
+	bool "Timer slack cgroup controller"
+	help
+	  Provides a way to set minimal timer slack value for tasks in
+	  a cgroup.
+	  It's useful in mobile devices where certain background apps
+	  are attached to a cgroup and combined wakeups are desired.
+
 config CGROUP_DEVICE
 	bool "Device controller for cgroups"
 	help
diff --git a/kernel/Makefile b/kernel/Makefile
index 353d3fe..0b60239 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -61,6 +61,7 @@ obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o
 obj-$(CONFIG_COMPAT) += compat.o
 obj-$(CONFIG_CGROUPS) += cgroup.o
 obj-$(CONFIG_CGROUP_FREEZER) += cgroup_freezer.o
+obj-$(CONFIG_CGROUP_TIMER_SLACK) += cgroup_timer_slack.o
 obj-$(CONFIG_CPUSETS) += cpuset.o
 obj-$(CONFIG_CGROUP_NS) += ns_cgroup.o
 obj-$(CONFIG_UTS_NS) += utsname.o
diff --git a/kernel/cgroup_timer_slack.c b/kernel/cgroup_timer_slack.c
new file mode 100644
index 0000000..9824807
--- /dev/null
+++ b/kernel/cgroup_timer_slack.c
@@ -0,0 +1,124 @@
+/*
+ * cgroup_timer_slack.c - control group timer slack subsystem
+ *
+ * Copyright Nokia Corparation, 2011
+ * Author: Kirill A. Shutemov
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/cgroup.h>
+#include <linux/slab.h>
+
+struct cgroup_subsys timer_slack_subsys;
+struct tslack_cgroup {
+	struct cgroup_subsys_state css;
+	unsigned long min_slack_ns;
+};
+
+static struct tslack_cgroup *cgroup_to_tslack(struct cgroup *cgroup)
+{
+	struct cgroup_subsys_state *css;
+
+	css = cgroup_subsys_state(cgroup, timer_slack_subsys.subsys_id);
+	return container_of(css, struct tslack_cgroup, css);
+}
+
+static struct cgroup_subsys_state *tslack_create(struct cgroup_subsys *subsys,
+		struct cgroup *cgroup)
+{
+	struct tslack_cgroup *tslack_cgroup;
+
+	tslack_cgroup = kmalloc(sizeof(*tslack_cgroup), GFP_KERNEL);
+	if (!tslack_cgroup)
+		return ERR_PTR(-ENOMEM);
+
+	if (cgroup->parent) {
+		struct tslack_cgroup *parent;
+
+		parent = cgroup_to_tslack(cgroup->parent);
+		tslack_cgroup->min_slack_ns = parent->min_slack_ns;
+	} else
+		tslack_cgroup->min_slack_ns = 0UL;
+
+	return &tslack_cgroup->css;
+}
+
+static void tslack_destroy(struct cgroup_subsys *tslack_cgroup,
+		struct cgroup *cgroup)
+{
+	kfree(cgroup_to_tslack(cgroup));
+}
+
+static u64 tslack_read_min(struct cgroup *cgroup, struct cftype *cft)
+{
+	return cgroup_to_tslack(cgroup)->min_slack_ns;
+}
+
+static int tslack_write_min(struct cgroup *cgroup, struct cftype *cft, u64 val)
+{
+	if (val > ULONG_MAX)
+		return -EINVAL;
+
+	cgroup_to_tslack(cgroup)->min_slack_ns = val;
+
+	return 0;
+}
+
+static u64 tslack_read_effective(struct cgroup *cgroup, struct cftype *cft)
+{
+	unsigned long min;
+
+	min = cgroup_to_tslack(cgroup)->min_slack_ns;
+	while (cgroup->parent) {
+		cgroup = cgroup->parent;
+		min = max(cgroup_to_tslack(cgroup)->min_slack_ns, min);
+	}
+
+	return min;
+}
+
+static struct cftype files[] = {
+	{
+		.name = "min_slack_ns",
+		.read_u64 = tslack_read_min,
+		.write_u64 = tslack_write_min,
+	},
+	{
+		.name = "effective_slack_ns",
+		.read_u64 = tslack_read_effective,
+	},
+};
+
+static int tslack_populate(struct cgroup_subsys *subsys, struct cgroup *cgroup)
+{
+	return cgroup_add_files(cgroup, subsys, files, ARRAY_SIZE(files));
+}
+
+struct cgroup_subsys timer_slack_subsys = {
+	.name		= "timer_slack",
+	.subsys_id	= timer_slack_subsys_id,
+	.create		= tslack_create,
+	.destroy	= tslack_destroy,
+	.populate	= tslack_populate,
+};
+
+unsigned long task_get_effective_timer_slack(struct task_struct *tsk)
+{
+	struct cgroup *cgroup;
+	unsigned long slack;
+
+	rcu_read_lock();
+	cgroup = task_cgroup(tsk, timer_slack_subsys.subsys_id);
+	slack = tslack_read_effective(cgroup, NULL);
+	rcu_read_unlock();
+
+	return max(tsk->timer_slack_ns, slack);
+}
-- 
1.7.4.1

[PATCH, v8 3/3] cgroups: introduce timer slack controller

[Kirill A. Shutsemov]

From: Kirill A. Shutemov <kirill@shutemov.name>

Every task_struct has timer_slack_ns value. This value uses to round up
poll() and select() timeout values. This feature can be useful in
mobile environment where combined wakeups are desired.

cgroup subsys "timer_slack" implement timer slack controller. It
provides a way to set minimal timer slack value for a group of tasks.
If a task belongs to a cgroup with minimal timer slack value higher than
task's value, cgroup's value will be applied.

Idea-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
---
 Documentation/cgroups/timer_slack.txt |   64 +++++++++++++++++
 include/linux/cgroup_subsys.h         |    6 ++
 include/linux/sched.h                 |    4 +
 init/Kconfig                          |    8 ++
 kernel/Makefile                       |    1 +
 kernel/cgroup_timer_slack.c           |  124 +++++++++++++++++++++++++++++++++
 6 files changed, 207 insertions(+), 0 deletions(-)
 create mode 100644 Documentation/cgroups/timer_slack.txt
 create mode 100644 kernel/cgroup_timer_slack.c

diff --git a/Documentation/cgroups/timer_slack.txt b/Documentation/cgroups/timer_slack.txt
new file mode 100644
index 0000000..b1494ff
--- /dev/null
+++ b/Documentation/cgroups/timer_slack.txt
@@ -0,0 +1,64 @@
+Timer Slack Controller
+=====================
+
+Overview
+--------
+
+Every task_struct has timer_slack_ns value. This value uses to round up
+poll() and select() timeout values. This feature can be useful in
+mobile environment where combined wakeups are desired.
+
+cgroup subsys "timer_slack" implements timer slack controller. It
+provides a way to set minimal timer slack value for a group of tasks.
+If a task belongs to a cgroup with minimal timer slack value higher than
+task's value, cgroup's value will be applied.
+
+User interface
+--------------
+
+To get timer slack controller functionality you need to enable it in
+kernel configuration:
+
+CONFIG_CGROUP_TIMER_SLACK=y
+
+The controller provides two files:
+
+# mount -t cgroup -o timer_slack none /sys/fs/cgroup
+# ls /sys/fs/cgroup/timer_slack.*
+/sys/fs/cgroup/timer_slack.effective_slack_ns
+/sys/fs/cgroup/timer_slack.min_slack_ns
+
+By default timer_slack.min_slack_ns is 0:
+
+# cat /sys/fs/cgroup/timer_slack.min_slack_ns
+0
+
+You can set it to some value:
+
+# echo 50000 > /sys/fs/cgroup/timer_slack.min_slack_ns
+# cat /sys/fs/cgroup/timer_slack.min_slack_ns
+50000
+
+Tasks still can set task's value below 50000 using prctl(), but in this
+case cgroup's value will be applied.
+
+Timer slack controller supports hierarchical groups.
+
+# mkdir /sys/fs/cgroup/a
+# cat /sys/fs/cgroup/a/timer_slack.min_slack_ns
+50000
+# echo 70000 > /sys/fs/cgroup/a/timer_slack.min_slack_ns
+# cat /sys/fs/cgroup/a/timer_slack.min_slack_ns
+70000
+
+You can set any value you want, but effective value will the highest value
+up by hierarchy. You can see effective timer slack value for the cgroup from
+timer_slack.effective_slack_ns file:
+
+# cat /sys/fs/cgroup/a/timer_slack.effective_slack_ns
+70000
+# echo 100000 > /sys/fs/cgroup/timer_slack.min_slack_ns
+# cat /sys/fs/cgroup/a/timer_slack.min_slack_ns
+70000
+# cat /sys/fs/cgroup/a/timer_slack.effective_slack_ns
+100000
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index ccefff0..e399228 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -66,3 +66,9 @@ SUBSYS(blkio)
 #endif
 
 /* */
+
+#ifdef CONFIG_CGROUP_TIMER_SLACK
+SUBSYS(timer_slack)
+#endif
+
+/* */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 44f6f55..c10da5d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2620,11 +2620,15 @@ static inline unsigned long rlimit_max(unsigned int limit)
 	return task_rlimit_max(current, limit);
 }
 
+#ifdef CONFIG_CGROUP_TIMER_SLACK
+extern unsigned long task_get_effective_timer_slack(struct task_struct *tsk);
+#else
 static inline unsigned long task_get_effective_timer_slack(
 		struct task_struct *tsk)
 {
 	return tsk->timer_slack_ns;
 }
+#endif
 
 #endif /* __KERNEL__ */
 
diff --git a/init/Kconfig b/init/Kconfig
index be788c0..bbc4d9c 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -596,6 +596,14 @@ config CGROUP_FREEZER
 	  Provides a way to freeze and unfreeze all tasks in a
 	  cgroup.
 
+config CGROUP_TIMER_SLACK
+	bool "Timer slack cgroup controller"
+	help
+	  Provides a way to set minimal timer slack value for tasks in
+	  a cgroup.
+	  It's useful in mobile devices where certain background apps
+	  are attached to a cgroup and combined wakeups are desired.
+
 config CGROUP_DEVICE
 	bool "Device controller for cgroups"
 	help
diff --git a/kernel/Makefile b/kernel/Makefile
index 353d3fe..0b60239 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -61,6 +61,7 @@ obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o
 obj-$(CONFIG_COMPAT) += compat.o
 obj-$(CONFIG_CGROUPS) += cgroup.o
 obj-$(CONFIG_CGROUP_FREEZER) += cgroup_freezer.o
+obj-$(CONFIG_CGROUP_TIMER_SLACK) += cgroup_timer_slack.o
 obj-$(CONFIG_CPUSETS) += cpuset.o
 obj-$(CONFIG_CGROUP_NS) += ns_cgroup.o
 obj-$(CONFIG_UTS_NS) += utsname.o
diff --git a/kernel/cgroup_timer_slack.c b/kernel/cgroup_timer_slack.c
new file mode 100644
index 0000000..9824807
--- /dev/null
+++ b/kernel/cgroup_timer_slack.c
@@ -0,0 +1,124 @@
+/*
+ * cgroup_timer_slack.c - control group timer slack subsystem
+ *
+ * Copyright Nokia Corparation, 2011
+ * Author: Kirill A. Shutemov
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/cgroup.h>
+#include <linux/slab.h>
+
+struct cgroup_subsys timer_slack_subsys;
+struct tslack_cgroup {
+	struct cgroup_subsys_state css;
+	unsigned long min_slack_ns;
+};
+
+static struct tslack_cgroup *cgroup_to_tslack(struct cgroup *cgroup)
+{
+	struct cgroup_subsys_state *css;
+
+	css = cgroup_subsys_state(cgroup, timer_slack_subsys.subsys_id);
+	return container_of(css, struct tslack_cgroup, css);
+}
+
+static struct cgroup_subsys_state *tslack_create(struct cgroup_subsys *subsys,
+		struct cgroup *cgroup)
+{
+	struct tslack_cgroup *tslack_cgroup;
+
+	tslack_cgroup = kmalloc(sizeof(*tslack_cgroup), GFP_KERNEL);
+	if (!tslack_cgroup)
+		return ERR_PTR(-ENOMEM);
+
+	if (cgroup->parent) {
+		struct tslack_cgroup *parent;
+
+		parent = cgroup_to_tslack(cgroup->parent);
+		tslack_cgroup->min_slack_ns = parent->min_slack_ns;
+	} else
+		tslack_cgroup->min_slack_ns = 0UL;
+
+	return &tslack_cgroup->css;
+}
+
+static void tslack_destroy(struct cgroup_subsys *tslack_cgroup,
+		struct cgroup *cgroup)
+{
+	kfree(cgroup_to_tslack(cgroup));
+}
+
+static u64 tslack_read_min(struct cgroup *cgroup, struct cftype *cft)
+{
+	return cgroup_to_tslack(cgroup)->min_slack_ns;
+}
+
+static int tslack_write_min(struct cgroup *cgroup, struct cftype *cft, u64 val)
+{
+	if (val > ULONG_MAX)
+		return -EINVAL;
+
+	cgroup_to_tslack(cgroup)->min_slack_ns = val;
+
+	return 0;
+}
+
+static u64 tslack_read_effective(struct cgroup *cgroup, struct cftype *cft)
+{
+	unsigned long min;
+
+	min = cgroup_to_tslack(cgroup)->min_slack_ns;
+	while (cgroup->parent) {
+		cgroup = cgroup->parent;
+		min = max(cgroup_to_tslack(cgroup)->min_slack_ns, min);
+	}
+
+	return min;
+}
+
+static struct cftype files[] = {
+	{
+		.name = "min_slack_ns",
+		.read_u64 = tslack_read_min,
+		.write_u64 = tslack_write_min,
+	},
+	{
+		.name = "effective_slack_ns",
+		.read_u64 = tslack_read_effective,
+	},
+};
+
+static int tslack_populate(struct cgroup_subsys *subsys, struct cgroup *cgroup)
+{
+	return cgroup_add_files(cgroup, subsys, files, ARRAY_SIZE(files));
+}
+
+struct cgroup_subsys timer_slack_subsys = {
+	.name		= "timer_slack",
+	.subsys_id	= timer_slack_subsys_id,
+	.create		= tslack_create,
+	.destroy	= tslack_destroy,
+	.populate	= tslack_populate,
+};
+
+unsigned long task_get_effective_timer_slack(struct task_struct *tsk)
+{
+	struct cgroup *cgroup;
+	unsigned long slack;
+
+	rcu_read_lock();
+	cgroup = task_cgroup(tsk, timer_slack_subsys.subsys_id);
+	slack = tslack_read_effective(cgroup, NULL);
+	rcu_read_unlock();
+
+	return max(tsk->timer_slack_ns, slack);
+}
-- 
1.7.4.1

Re: [PATCH, v8 0/3] *** SUBJECT HERE ***

[Kirill A. Shutemov]

On Thu, Mar 03, 2011 at 04:19:04PM +0200, Kirill A. Shutsemov wrote:
> From: Kirill A. Shutemov <kirill-oKw7cIdHH8eLwutG50LtGA@public.gmane.org>
> 
> *** BLURB HERE ***

Oops.

Changelog:

v8:
 - change hiearchy rules
 - introduce timer_slack.effective_slack_ns
 - get_task_timer_slack() -> task_get_effective_timer_slack()
 - task_get_effective_timer_slack() splited in separate patch
 - implement PR_GET_EFFECTIVE_TIMERSLACK

v7:
 - totally reworked interface and rewritten from scratch
   (See Documentation/cgroups/timer_slack.txt for more information)
v6:
 - add documentation
 - use notifier_call_chain() instead of check hook
 - fix validate_change()
 - cleanup
v5:
 - -EBUSY on writing to timer_slack.min_slack_ns/max_slack_ns if a child has
   wider min-max range
v4:
 - hierarchy support
 - drop dummy_timer_slack_check()
 - workaround lockdep false (?) positive
 - allow 0 as timer slack value
v3:
 - rework interface
 - s/EXPORT_SYMBOL/EXPORT_SYMBOL_GPL/
v2:
 - fixed with CONFIG_CGROUP_TIMER_SLACK=y
v1:
 - initial revision

> Kirill A. Shutemov (3):
>   hrtimer: introduce effective timer slack
>   hrtimer: implement PR_GET_EFFECTIVE_TIMERSLACK
>   cgroups: introduce timer slack controller
> 
>  Documentation/cgroups/timer_slack.txt |   64 +++++++++++++++++
>  fs/select.c                           |    7 +--
>  include/linux/cgroup_subsys.h         |    6 ++
>  include/linux/prctl.h                 |    6 ++
>  include/linux/sched.h                 |   10 +++
>  init/Kconfig                          |    8 ++
>  kernel/Makefile                       |    1 +
>  kernel/cgroup_timer_slack.c           |  124 +++++++++++++++++++++++++++++++++
>  kernel/fork.c                         |    4 +
>  kernel/futex.c                        |    4 +-
>  kernel/hrtimer.c                      |    2 +-
>  kernel/sys.c                          |    3 +
>  12 files changed, 231 insertions(+), 8 deletions(-)
>  create mode 100644 Documentation/cgroups/timer_slack.txt
>  create mode 100644 kernel/cgroup_timer_slack.c
> 
> -- 
> 1.7.4.1
> 

-- 
 Kirill A. Shutemov

Re: [PATCH, v8 0/3] *** SUBJECT HERE ***

[Kirill A. Shutemov]

On Thu, Mar 03, 2011 at 04:19:04PM +0200, Kirill A. Shutsemov wrote:
> From: Kirill A. Shutemov <kirill@shutemov.name>
> 
> *** BLURB HERE ***

Oops.

Changelog:

v8:
 - change hiearchy rules
 - introduce timer_slack.effective_slack_ns
 - get_task_timer_slack() -> task_get_effective_timer_slack()
 - task_get_effective_timer_slack() splited in separate patch
 - implement PR_GET_EFFECTIVE_TIMERSLACK

v7:
 - totally reworked interface and rewritten from scratch
   (See Documentation/cgroups/timer_slack.txt for more information)
v6:
 - add documentation
 - use notifier_call_chain() instead of check hook
 - fix validate_change()
 - cleanup
v5:
 - -EBUSY on writing to timer_slack.min_slack_ns/max_slack_ns if a child has
   wider min-max range
v4:
 - hierarchy support
 - drop dummy_timer_slack_check()
 - workaround lockdep false (?) positive
 - allow 0 as timer slack value
v3:
 - rework interface
 - s/EXPORT_SYMBOL/EXPORT_SYMBOL_GPL/
v2:
 - fixed with CONFIG_CGROUP_TIMER_SLACK=y
v1:
 - initial revision

> Kirill A. Shutemov (3):
>   hrtimer: introduce effective timer slack
>   hrtimer: implement PR_GET_EFFECTIVE_TIMERSLACK
>   cgroups: introduce timer slack controller
> 
>  Documentation/cgroups/timer_slack.txt |   64 +++++++++++++++++
>  fs/select.c                           |    7 +--
>  include/linux/cgroup_subsys.h         |    6 ++
>  include/linux/prctl.h                 |    6 ++
>  include/linux/sched.h                 |   10 +++
>  init/Kconfig                          |    8 ++
>  kernel/Makefile                       |    1 +
>  kernel/cgroup_timer_slack.c           |  124 +++++++++++++++++++++++++++++++++
>  kernel/fork.c                         |    4 +
>  kernel/futex.c                        |    4 +-
>  kernel/hrtimer.c                      |    2 +-
>  kernel/sys.c                          |    3 +
>  12 files changed, 231 insertions(+), 8 deletions(-)
>  create mode 100644 Documentation/cgroups/timer_slack.txt
>  create mode 100644 kernel/cgroup_timer_slack.c
> 
> -- 
> 1.7.4.1
> 

-- 
 Kirill A. Shutemov

Re: [PATCH, v8 0/3] *** SUBJECT HERE ***

[Kirill A. Shutemov]

On Thu, Mar 03, 2011 at 04:19:04PM +0200, Kirill A. Shutsemov wrote:
> From: Kirill A. Shutemov <kirill-oKw7cIdHH8eLwutG50LtGA@public.gmane.org>
> 
> *** BLURB HERE ***

Oops.

Changelog:

v8:
 - change hiearchy rules
 - introduce timer_slack.effective_slack_ns
 - get_task_timer_slack() -> task_get_effective_timer_slack()
 - task_get_effective_timer_slack() splited in separate patch
 - implement PR_GET_EFFECTIVE_TIMERSLACK

v7:
 - totally reworked interface and rewritten from scratch
   (See Documentation/cgroups/timer_slack.txt for more information)
v6:
 - add documentation
 - use notifier_call_chain() instead of check hook
 - fix validate_change()
 - cleanup
v5:
 - -EBUSY on writing to timer_slack.min_slack_ns/max_slack_ns if a child has
   wider min-max range
v4:
 - hierarchy support
 - drop dummy_timer_slack_check()
 - workaround lockdep false (?) positive
 - allow 0 as timer slack value
v3:
 - rework interface
 - s/EXPORT_SYMBOL/EXPORT_SYMBOL_GPL/
v2:
 - fixed with CONFIG_CGROUP_TIMER_SLACK=y
v1:
 - initial revision

> Kirill A. Shutemov (3):
>   hrtimer: introduce effective timer slack
>   hrtimer: implement PR_GET_EFFECTIVE_TIMERSLACK
>   cgroups: introduce timer slack controller
> 
>  Documentation/cgroups/timer_slack.txt |   64 +++++++++++++++++
>  fs/select.c                           |    7 +--
>  include/linux/cgroup_subsys.h         |    6 ++
>  include/linux/prctl.h                 |    6 ++
>  include/linux/sched.h                 |   10 +++
>  init/Kconfig                          |    8 ++
>  kernel/Makefile                       |    1 +
>  kernel/cgroup_timer_slack.c           |  124 +++++++++++++++++++++++++++++++++
>  kernel/fork.c                         |    4 +
>  kernel/futex.c                        |    4 +-
>  kernel/hrtimer.c                      |    2 +-
>  kernel/sys.c                          |    3 +
>  12 files changed, 231 insertions(+), 8 deletions(-)
>  create mode 100644 Documentation/cgroups/timer_slack.txt
>  create mode 100644 kernel/cgroup_timer_slack.c
> 
> -- 
> 1.7.4.1
> 

-- 
 Kirill A. Shutemov

Re: [PATCH, v8 1/3] hrtimer: introduce effective timer slack

[Arnd Bergmann]

On Thursday 03 March 2011, Kirill A. Shutsemov wrote:
> task_get_effective_timer_slack() returns timer slack value to be used
> to configure per-task timers. It can be equal or higher than task's
> timer slack value.
> 
> For now task_get_effective_timer_slack() returns timer_slack_ns of the
> task. Timer slack cgroup controller will implement a bit more
> sophisticated logic.

Some time ago, there was a discussion about a method for automatically
determining timer slack values, and I think nobody ever implemented it.

The idea was to penalize tasks that have timers expiring a lot, typically
a sign of programs that were not written with power consumption in mind.

I think that could be nicely combined with your patch. Instead of setting
the effective timer slack for the entire control group, you  could
set a target value that is applied only to tasks that have their timers
expire frequently. When a timer expires for a task, you increase the
effective slack up to the maximum, and when you set up a timer, you
decrease it again. The amount by which the effective slack gets changed
can depend on how long ago the last timer expired.

Does this make sense to you?

	Arnd

Re: [PATCH, v8 1/3] hrtimer: introduce effective timer slack

[Arnd Bergmann]

On Thursday 03 March 2011, Kirill A. Shutsemov wrote:
> task_get_effective_timer_slack() returns timer slack value to be used
> to configure per-task timers. It can be equal or higher than task's
> timer slack value.
> 
> For now task_get_effective_timer_slack() returns timer_slack_ns of the
> task. Timer slack cgroup controller will implement a bit more
> sophisticated logic.

Some time ago, there was a discussion about a method for automatically
determining timer slack values, and I think nobody ever implemented it.

The idea was to penalize tasks that have timers expiring a lot, typically
a sign of programs that were not written with power consumption in mind.

I think that could be nicely combined with your patch. Instead of setting
the effective timer slack for the entire control group, you  could
set a target value that is applied only to tasks that have their timers
expire frequently. When a timer expires for a task, you increase the
effective slack up to the maximum, and when you set up a timer, you
decrease it again. The amount by which the effective slack gets changed
can depend on how long ago the last timer expired.

Does this make sense to you?

	Arnd

Re: [PATCH, v8 1/3] hrtimer: introduce effective timer slack

[Arnd Bergmann]

On Thursday 03 March 2011, Kirill A. Shutsemov wrote:
> task_get_effective_timer_slack() returns timer slack value to be used
> to configure per-task timers. It can be equal or higher than task's
> timer slack value.
> 
> For now task_get_effective_timer_slack() returns timer_slack_ns of the
> task. Timer slack cgroup controller will implement a bit more
> sophisticated logic.

Some time ago, there was a discussion about a method for automatically
determining timer slack values, and I think nobody ever implemented it.

The idea was to penalize tasks that have timers expiring a lot, typically
a sign of programs that were not written with power consumption in mind.

I think that could be nicely combined with your patch. Instead of setting
the effective timer slack for the entire control group, you  could
set a target value that is applied only to tasks that have their timers
expire frequently. When a timer expires for a task, you increase the
effective slack up to the maximum, and when you set up a timer, you
decrease it again. The amount by which the effective slack gets changed
can depend on how long ago the last timer expired.

Does this make sense to you?

	Arnd

Re: [PATCH, v8 1/3] hrtimer: introduce effective timer slack

[Kirill A. Shutemov]

On Thu, Mar 03, 2011 at 05:32:28PM +0100, Arnd Bergmann wrote:
> On Thursday 03 March 2011, Kirill A. Shutsemov wrote:
> > task_get_effective_timer_slack() returns timer slack value to be used
> > to configure per-task timers. It can be equal or higher than task's
> > timer slack value.
> > 
> > For now task_get_effective_timer_slack() returns timer_slack_ns of the
> > task. Timer slack cgroup controller will implement a bit more
> > sophisticated logic.
> 
> Some time ago, there was a discussion about a method for automatically
> determining timer slack values, and I think nobody ever implemented it.
> 
> The idea was to penalize tasks that have timers expiring a lot, typically
> a sign of programs that were not written with power consumption in mind.
> 
> I think that could be nicely combined with your patch. Instead of setting
> the effective timer slack for the entire control group, you  could
> set a target value that is applied only to tasks that have their timers
> expire frequently. When a timer expires for a task, you increase the
> effective slack up to the maximum, and when you set up a timer, you
> decrease it again. The amount by which the effective slack gets changed
> can depend on how long ago the last timer expired.
> 
> Does this make sense to you?

Hm.. I think we can add this kind of functionality to timer slack cgroup
as a policy/stratagy later. I want to integrate basic functionality to
kernel first.

-- 
 Kirill A. Shutemov

Re: [PATCH, v8 1/3] hrtimer: introduce effective timer slack

[Kirill A. Shutemov]

On Thu, Mar 03, 2011 at 05:32:28PM +0100, Arnd Bergmann wrote:
> On Thursday 03 March 2011, Kirill A. Shutsemov wrote:
> > task_get_effective_timer_slack() returns timer slack value to be used
> > to configure per-task timers. It can be equal or higher than task's
> > timer slack value.
> > 
> > For now task_get_effective_timer_slack() returns timer_slack_ns of the
> > task. Timer slack cgroup controller will implement a bit more
> > sophisticated logic.
> 
> Some time ago, there was a discussion about a method for automatically
> determining timer slack values, and I think nobody ever implemented it.
> 
> The idea was to penalize tasks that have timers expiring a lot, typically
> a sign of programs that were not written with power consumption in mind.
> 
> I think that could be nicely combined with your patch. Instead of setting
> the effective timer slack for the entire control group, you  could
> set a target value that is applied only to tasks that have their timers
> expire frequently. When a timer expires for a task, you increase the
> effective slack up to the maximum, and when you set up a timer, you
> decrease it again. The amount by which the effective slack gets changed
> can depend on how long ago the last timer expired.
> 
> Does this make sense to you?

Hm.. I think we can add this kind of functionality to timer slack cgroup
as a policy/stratagy later. I want to integrate basic functionality to
kernel first.

-- 
 Kirill A. Shutemov

Re: [PATCH, v8 1/3] hrtimer: introduce effective timer slack

[Kirill A. Shutemov]

On Thu, Mar 03, 2011 at 05:32:28PM +0100, Arnd Bergmann wrote:
> On Thursday 03 March 2011, Kirill A. Shutsemov wrote:
> > task_get_effective_timer_slack() returns timer slack value to be used
> > to configure per-task timers. It can be equal or higher than task's
> > timer slack value.
> > 
> > For now task_get_effective_timer_slack() returns timer_slack_ns of the
> > task. Timer slack cgroup controller will implement a bit more
> > sophisticated logic.
> 
> Some time ago, there was a discussion about a method for automatically
> determining timer slack values, and I think nobody ever implemented it.
> 
> The idea was to penalize tasks that have timers expiring a lot, typically
> a sign of programs that were not written with power consumption in mind.
> 
> I think that could be nicely combined with your patch. Instead of setting
> the effective timer slack for the entire control group, you  could
> set a target value that is applied only to tasks that have their timers
> expire frequently. When a timer expires for a task, you increase the
> effective slack up to the maximum, and when you set up a timer, you
> decrease it again. The amount by which the effective slack gets changed
> can depend on how long ago the last timer expired.
> 
> Does this make sense to you?

Hm.. I think we can add this kind of functionality to timer slack cgroup
as a policy/stratagy later. I want to integrate basic functionality to
kernel first.

-- 
 Kirill A. Shutemov

Re: [PATCH, v8 1/3] hrtimer: introduce effective timer slack

[Arnd Bergmann]

On Friday 04 March 2011, Kirill A. Shutemov wrote:
> > Does this make sense to you?
> 
> Hm.. I think we can add this kind of functionality to timer slack cgroup
> as a policy/stratagy later. I want to integrate basic functionality to
> kernel first.

Yes, makes sense. I wasn't objecting the current patch set, just trying
to make sure that the other idea does not get lost, and we don't introduce
anything now that prevents us from doing it later.

	Arnd

Re: [PATCH, v8 1/3] hrtimer: introduce effective timer slack

[Arnd Bergmann]

On Friday 04 March 2011, Kirill A. Shutemov wrote:
> > Does this make sense to you?
> 
> Hm.. I think we can add this kind of functionality to timer slack cgroup
> as a policy/stratagy later. I want to integrate basic functionality to
> kernel first.

Yes, makes sense. I wasn't objecting the current patch set, just trying
to make sure that the other idea does not get lost, and we don't introduce
anything now that prevents us from doing it later.

	Arnd

Re: [PATCH, v8 1/3] hrtimer: introduce effective timer slack

[Arnd Bergmann]

On Friday 04 March 2011, Kirill A. Shutemov wrote:
> > Does this make sense to you?
> 
> Hm.. I think we can add this kind of functionality to timer slack cgroup
> as a policy/stratagy later. I want to integrate basic functionality to
> kernel first.

Yes, makes sense. I wasn't objecting the current patch set, just trying
to make sure that the other idea does not get lost, and we don't introduce
anything now that prevents us from doing it later.

	Arnd

Re: [PATCH, v8 3/3] cgroups: introduce timer slack controller

[Andrew Morton]

On Thu,  3 Mar 2011 16:19:07 +0200
"Kirill A. Shutsemov" <kirill-oKw7cIdHH8eLwutG50LtGA@public.gmane.org> wrote:

> --- /dev/null
> +++ b/Documentation/cgroups/timer_slack.txt
> @@ -0,0 +1,64 @@
> +Timer Slack Controller
> +=====================
> +
> +Overview
> +--------
> +
> +Every task_struct has timer_slack_ns value. This value uses to round up
> +poll() and select() timeout values. This feature can be useful in
> +mobile environment where combined wakeups are desired.
> +
> +cgroup subsys "timer_slack" implements timer slack controller. It
> +provides a way to set minimal timer slack value for a group of tasks.
> +If a task belongs to a cgroup with minimal timer slack value higher than
> +task's value, cgroup's value will be applied.

All I'm seeing here is a bunch of code, but no reason has been provided
for merging any of it.

Why do we need a cgroup for this as opposed to (say) inheritance over
fork(), or a system-wide knob, or a per-process/threadgroup knob, or
just leaving the existing code as-is?  Presumably you felt that a
cgroup approach is better for manageability, but you didn't tell us
about this and you didn't explore alternative ways of solving the
problem-which-you-didn't-describe.


Carefully describing the proposed feature and the overall value which
it brings does help to grease the wheels and is worth spending some
time over, please.  Don't expect the entire audience to be mind-readers!

Re: [PATCH, v8 3/3] cgroups: introduce timer slack controller

[Andrew Morton]

On Thu,  3 Mar 2011 16:19:07 +0200
"Kirill A. Shutsemov" <kirill@shutemov.name> wrote:

> --- /dev/null
> +++ b/Documentation/cgroups/timer_slack.txt
> @@ -0,0 +1,64 @@
> +Timer Slack Controller
> +=====================
> +
> +Overview
> +--------
> +
> +Every task_struct has timer_slack_ns value. This value uses to round up
> +poll() and select() timeout values. This feature can be useful in
> +mobile environment where combined wakeups are desired.
> +
> +cgroup subsys "timer_slack" implements timer slack controller. It
> +provides a way to set minimal timer slack value for a group of tasks.
> +If a task belongs to a cgroup with minimal timer slack value higher than
> +task's value, cgroup's value will be applied.

All I'm seeing here is a bunch of code, but no reason has been provided
for merging any of it.

Why do we need a cgroup for this as opposed to (say) inheritance over
fork(), or a system-wide knob, or a per-process/threadgroup knob, or
just leaving the existing code as-is?  Presumably you felt that a
cgroup approach is better for manageability, but you didn't tell us
about this and you didn't explore alternative ways of solving the
problem-which-you-didn't-describe.


Carefully describing the proposed feature and the overall value which
it brings does help to grease the wheels and is worth spending some
time over, please.  Don't expect the entire audience to be mind-readers!

Re: [PATCH, v8 3/3] cgroups: introduce timer slack controller

[Andrew Morton]

On Thu,  3 Mar 2011 16:19:07 +0200
"Kirill A. Shutsemov" <kirill-oKw7cIdHH8eLwutG50LtGA@public.gmane.org> wrote:

> --- /dev/null
> +++ b/Documentation/cgroups/timer_slack.txt
> @@ -0,0 +1,64 @@
> +Timer Slack Controller
> +=====================
> +
> +Overview
> +--------
> +
> +Every task_struct has timer_slack_ns value. This value uses to round up
> +poll() and select() timeout values. This feature can be useful in
> +mobile environment where combined wakeups are desired.
> +
> +cgroup subsys "timer_slack" implements timer slack controller. It
> +provides a way to set minimal timer slack value for a group of tasks.
> +If a task belongs to a cgroup with minimal timer slack value higher than
> +task's value, cgroup's value will be applied.

All I'm seeing here is a bunch of code, but no reason has been provided
for merging any of it.

Why do we need a cgroup for this as opposed to (say) inheritance over
fork(), or a system-wide knob, or a per-process/threadgroup knob, or
just leaving the existing code as-is?  Presumably you felt that a
cgroup approach is better for manageability, but you didn't tell us
about this and you didn't explore alternative ways of solving the
problem-which-you-didn't-describe.


Carefully describing the proposed feature and the overall value which
it brings does help to grease the wheels and is worth spending some
time over, please.  Don't expect the entire audience to be mind-readers!

[PATCH, v8 0/3] *** SUBJECT HERE ***

[Kirill A. Shutsemov]

From: Kirill A. Shutemov <kirill-oKw7cIdHH8eLwutG50LtGA@public.gmane.org>

*** BLURB HERE ***

Kirill A. Shutemov (3):
  hrtimer: introduce effective timer slack
  hrtimer: implement PR_GET_EFFECTIVE_TIMERSLACK
  cgroups: introduce timer slack controller

 Documentation/cgroups/timer_slack.txt |   64 +++++++++++++++++
 fs/select.c                           |    7 +--
 include/linux/cgroup_subsys.h         |    6 ++
 include/linux/prctl.h                 |    6 ++
 include/linux/sched.h                 |   10 +++
 init/Kconfig                          |    8 ++
 kernel/Makefile                       |    1 +
 kernel/cgroup_timer_slack.c           |  124 +++++++++++++++++++++++++++++++++
 kernel/fork.c                         |    4 +
 kernel/futex.c                        |    4 +-
 kernel/hrtimer.c                      |    2 +-
 kernel/sys.c                          |    3 +
 12 files changed, 231 insertions(+), 8 deletions(-)
 create mode 100644 Documentation/cgroups/timer_slack.txt
 create mode 100644 kernel/cgroup_timer_slack.c

-- 
1.7.4.1