Cloud Head

While this item is way below the clouds, every so often a piece of the programmer’s art comes along that just takes your breath away.  The kernel scheduling routine has been open now for decades, with thousands of eyeballs trying to take it to the next level – and in many cases doing so!  This is some darn good code already.  Then along comes an offhand comment from Linus, and Mike Galbraith puts out with 233 lines of code that:

• • • • • • • • Drops maximum latency dropping by over ten times, and
              • average latency of the desktop by about 60 times

233 line kernel patch, that yields a 60 fold performance improvement in something as fundamental as screen latency in the Linux kernel?  Unbelievable. As of 20 October 2010, when Linux 2.6.36 was last released, it had about 13,499,457 lines of code.  We are talking a 233 line patch here!

If this little corner of the tech world has room to improve  like that, it gives me hope that we have a 100+ year run of taking the broadest interpretations of Moore’s law to places as yet undreamed of.

In honor of Mike’s work, here is the current patch code, in all its raw beauty.  Tomorrow, I go find a nice tech stock and buy 100 shares, this gives me some real joy.  Long live C.

————————————–

Signed-off-by: Mike Galbraith <efault@gmx.de>

---
 Documentation/kernel-parameters.txt |    2
 drivers/tty/tty_io.c                |    1
 include/linux/sched.h               |   19 ++++
 init/Kconfig                        |   12 +++
 kernel/fork.c                       |    5 +
 kernel/sched.c                      |   25 ++++--
 kernel/sched_autogroup.c            |  140 ++++++++++++++++++++++++++++++++++++
 kernel/sched_autogroup.h            |   18 ++++
 kernel/sysctl.c                     |   11 ++
 9 files changed, 224 insertions(+), 9 deletions(-)

Index: linux-2.6/include/linux/sched.h
===================================================================
--- linux-2.6.orig/include/linux/sched.h
+++ linux-2.6/include/linux/sched.h
@@ -509,6 +509,8 @@ struct thread_group_cputimer {
 	spinlock_t lock;
 };

+struct autogroup;
+
 /*
  * NOTE! "signal_struct" does not have it's own
  * locking, because a shared signal_struct always
@@ -576,6 +578,9 @@ struct signal_struct {

 	struct tty_struct *tty; /* NULL if no tty */

+#ifdef CONFIG_SCHED_AUTOGROUP
+	struct autogroup *autogroup;
+#endif
 	/*
 	 * Cumulative resource counters for dead threads in the group,
 	 * and for reaped dead child processes forked by this group.
@@ -1931,6 +1936,20 @@ int sched_rt_handler(struct ctl_table *t

 extern unsigned int sysctl_sched_compat_yield;

+#ifdef CONFIG_SCHED_AUTOGROUP
+extern unsigned int sysctl_sched_autogroup_enabled;
+
+extern void sched_autogroup_create_attach(struct task_struct *p);
+extern void sched_autogroup_detach(struct task_struct *p);
+extern void sched_autogroup_fork(struct signal_struct *sig);
+extern void sched_autogroup_exit(struct signal_struct *sig);
+#else
+static inline void sched_autogroup_create_attach(struct task_struct *p) { }
+static inline void sched_autogroup_detach(struct task_struct *p) { }
+static inline void sched_autogroup_fork(struct signal_struct *sig) { }
+static inline void sched_autogroup_exit(struct signal_struct *sig) { }
+#endif
+
 #ifdef CONFIG_RT_MUTEXES
 extern int rt_mutex_getprio(struct task_struct *p);
 extern void rt_mutex_setprio(struct task_struct *p, int prio);
Index: linux-2.6/kernel/sched.c
===================================================================
--- linux-2.6.orig/kernel/sched.c
+++ linux-2.6/kernel/sched.c
@@ -78,6 +78,7 @@

 #include "sched_cpupri.h"
 #include "workqueue_sched.h"
+#include "sched_autogroup.h"

 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
@@ -605,11 +606,14 @@ static inline int cpu_of(struct rq *rq)
  */
 static inline struct task_group *task_group(struct task_struct *p)
 {
+	struct task_group *tg;
 	struct cgroup_subsys_state *css;

 	css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
 			lockdep_is_held(&task_rq(p)->lock));
-	return container_of(css, struct task_group, css);
+	tg = container_of(css, struct task_group, css);
+
+	return autogroup_task_group(p, tg);
 }

 /* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
@@ -2006,6 +2010,7 @@ static void sched_irq_time_avg_update(st
 #include "sched_idletask.c"
 #include "sched_fair.c"
 #include "sched_rt.c"
+#include "sched_autogroup.c"
 #include "sched_stoptask.c"
 #ifdef CONFIG_SCHED_DEBUG
 # include "sched_debug.c"
@@ -7979,7 +7984,7 @@ void __init sched_init(void)
 #ifdef CONFIG_CGROUP_SCHED
 	list_add(&init_task_group.list, &task_groups);
 	INIT_LIST_HEAD(&init_task_group.children);
-
+	autogroup_init(&init_task);
 #endif /* CONFIG_CGROUP_SCHED */

 #if defined CONFIG_FAIR_GROUP_SCHED && defined CONFIG_SMP
@@ -8509,15 +8514,11 @@ void sched_destroy_group(struct task_gro
 /* change task's runqueue when it moves between groups.
  *	The caller of this function should have put the task in its new group
  *	by now. This function just updates tsk->se.cfs_rq and tsk->se.parent to
- *	reflect its new group.
+ *	reflect its new group.  Called with the runqueue lock held.
  */
-void sched_move_task(struct task_struct *tsk)
+void __sched_move_task(struct task_struct *tsk, struct rq *rq)
 {
 	int on_rq, running;
-	unsigned long flags;
-	struct rq *rq;
-
-	rq = task_rq_lock(tsk, &flags);

 	running = task_current(rq, tsk);
 	on_rq = tsk->se.on_rq;
@@ -8538,7 +8539,15 @@ void sched_move_task(struct task_struct
 		tsk->sched_class->set_curr_task(rq);
 	if (on_rq)
 		enqueue_task(rq, tsk, 0);
+}

+void sched_move_task(struct task_struct *tsk)
+{
+	struct rq *rq;
+	unsigned long flags;
+
+	rq = task_rq_lock(tsk, &flags);
+	__sched_move_task(tsk, rq);
 	task_rq_unlock(rq, &flags);
 }
 #endif /* CONFIG_CGROUP_SCHED */
Index: linux-2.6/kernel/fork.c
===================================================================
--- linux-2.6.orig/kernel/fork.c
+++ linux-2.6/kernel/fork.c
@@ -174,8 +174,10 @@ static inline void free_signal_struct(st

 static inline void put_signal_struct(struct signal_struct *sig)
 {
-	if (atomic_dec_and_test(&sig->sigcnt))
+	if (atomic_dec_and_test(&sig->sigcnt)) {
+		sched_autogroup_exit(sig);
 		free_signal_struct(sig);
+	}
 }

 void __put_task_struct(struct task_struct *tsk)
@@ -904,6 +906,7 @@ static int copy_signal(unsigned long clo
 	posix_cpu_timers_init_group(sig);

 	tty_audit_fork(sig);
+	sched_autogroup_fork(sig);

 	sig->oom_adj = current->signal->oom_adj;
 	sig->oom_score_adj = current->signal->oom_score_adj;
Index: linux-2.6/drivers/tty/tty_io.c
===================================================================
--- linux-2.6.orig/drivers/tty/tty_io.c
+++ linux-2.6/drivers/tty/tty_io.c
@@ -3160,6 +3160,7 @@ static void __proc_set_tty(struct task_s
 	put_pid(tsk->signal->tty_old_pgrp);
 	tsk->signal->tty = tty_kref_get(tty);
 	tsk->signal->tty_old_pgrp = NULL;
+	sched_autogroup_create_attach(tsk);
 }

 static void proc_set_tty(struct task_struct *tsk, struct tty_struct *tty)
Index: linux-2.6/kernel/sched_autogroup.h
===================================================================
--- /dev/null
+++ linux-2.6/kernel/sched_autogroup.h
@@ -0,0 +1,18 @@
+#ifdef CONFIG_SCHED_AUTOGROUP
+
+static void __sched_move_task(struct task_struct *tsk, struct rq *rq);
+
+static inline struct task_group *
+autogroup_task_group(struct task_struct *p, struct task_group *tg);
+
+#else /* !CONFIG_SCHED_AUTOGROUP */
+
+static inline void autogroup_init(struct task_struct *init_task) {  }
+
+static inline struct task_group *
+autogroup_task_group(struct task_struct *p, struct task_group *tg)
+{
+	return tg;
+}
+
+#endif /* CONFIG_SCHED_AUTOGROUP */
Index: linux-2.6/kernel/sched_autogroup.c
===================================================================
--- /dev/null
+++ linux-2.6/kernel/sched_autogroup.c
@@ -0,0 +1,140 @@
+#ifdef CONFIG_SCHED_AUTOGROUP
+
+unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1;
+
+struct autogroup {
+	struct kref		kref;
+	struct task_group	*tg;
+};
+
+static struct autogroup autogroup_default;
+
+static void autogroup_init(struct task_struct *init_task)
+{
+	autogroup_default.tg = &init_task_group;
+	kref_init(&autogroup_default.kref);
+	init_task->signal->autogroup = &autogroup_default;
+}
+
+static inline void autogroup_destroy(struct kref *kref)
+{
+	struct autogroup *ag = container_of(kref, struct autogroup, kref);
+	struct task_group *tg = ag->tg;
+
+	kfree(ag);
+	sched_destroy_group(tg);
+}
+
+static inline void autogroup_kref_put(struct autogroup *ag)
+{
+	kref_put(&ag->kref, autogroup_destroy);
+}
+
+static inline struct autogroup *autogroup_kref_get(struct autogroup *ag)
+{
+	kref_get(&ag->kref);
+	return ag;
+}
+
+static inline struct autogroup *autogroup_create(void)
+{
+	struct autogroup *ag = kmalloc(sizeof(*ag), GFP_KERNEL);
+
+	if (!ag)
+		goto out_fail;
+
+	ag->tg = sched_create_group(&init_task_group);
+	kref_init(&ag->kref);
+
+	if (!(IS_ERR(ag->tg)))
+		return ag;
+
+out_fail:
+	if (ag) {
+		kfree(ag);
+		WARN_ON(1);
+	} else
+		WARN_ON(1);
+
+	return autogroup_kref_get(&autogroup_default);
+}
+
+static inline struct task_group *
+autogroup_task_group(struct task_struct *p, struct task_group *tg)
+{
+	int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled);
+
+	enabled &= (tg == &root_task_group);
+	enabled &= (p->sched_class == &fair_sched_class);
+	enabled &= (!(p->flags & PF_EXITING));
+
+	if (enabled)
+		return p->signal->autogroup->tg;
+
+	return tg;
+}
+
+static void
+autogroup_move_group(struct task_struct *p, struct autogroup *ag)
+{
+	struct autogroup *prev;
+	struct task_struct *t;
+	struct rq *rq;
+	unsigned long flags;
+
+	rq = task_rq_lock(p, &flags);
+	prev = p->signal->autogroup;
+	if (prev == ag) {
+		task_rq_unlock(rq, &flags);
+		return;
+	}
+
+	p->signal->autogroup = autogroup_kref_get(ag);
+	__sched_move_task(p, rq);
+	task_rq_unlock(rq, &flags);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(t, &p->thread_group, thread_group) {
+		sched_move_task(t);
+	}
+	rcu_read_unlock();
+
+	autogroup_kref_put(prev);
+}
+
+void sched_autogroup_create_attach(struct task_struct *p)
+{
+	struct autogroup *ag = autogroup_create();
+
+	autogroup_move_group(p, ag);
+	/* drop extra refrence added by autogroup_create() */
+	autogroup_kref_put(ag);
+}
+EXPORT_SYMBOL(sched_autogroup_create_attach);
+
+/* currently has no users */
+void sched_autogroup_detach(struct task_struct *p)
+{
+	autogroup_move_group(p, &autogroup_default);
+}
+EXPORT_SYMBOL(sched_autogroup_detach);
+
+void sched_autogroup_fork(struct signal_struct *sig)
+{
+	sig->autogroup = autogroup_kref_get(current->signal->autogroup);
+}
+
+void sched_autogroup_exit(struct signal_struct *sig)
+{
+	autogroup_kref_put(sig->autogroup);
+}
+
+static int __init setup_autogroup(char *str)
+{
+	sysctl_sched_autogroup_enabled = 0;
+
+	return 1;
+}
+
+__setup("noautogroup", setup_autogroup);
+#endif
Index: linux-2.6/kernel/sysctl.c
===================================================================
--- linux-2.6.orig/kernel/sysctl.c
+++ linux-2.6/kernel/sysctl.c
@@ -382,6 +382,17 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+#ifdef CONFIG_SCHED_AUTOGROUP
+	{
+		.procname	= "sched_autogroup_enabled",
+		.data		= &sysctl_sched_autogroup_enabled,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+#endif
 #ifdef CONFIG_PROVE_LOCKING
 	{
 		.procname	= "prove_locking",
Index: linux-2.6/init/Kconfig
===================================================================
--- linux-2.6.orig/init/Kconfig
+++ linux-2.6/init/Kconfig
@@ -728,6 +728,18 @@ config NET_NS

 endif # NAMESPACES

+config SCHED_AUTOGROUP
+	bool "Automatic process group scheduling"
+	select CGROUPS
+	select CGROUP_SCHED
+	select FAIR_GROUP_SCHED
+	help
+	  This option optimizes the scheduler for common desktop workloads by
+	  automatically creating and populating task groups.  This separation
+	  of workloads isolates aggressive CPU burners (like build jobs) from
+	  desktop applications.  Task group autogeneration is currently based
+	  upon task tty association.
+
 config MM_OWNER
 	bool

Index: linux-2.6/Documentation/kernel-parameters.txt
===================================================================
--- linux-2.6.orig/Documentation/kernel-parameters.txt
+++ linux-2.6/Documentation/kernel-parameters.txt
@@ -1622,6 +1622,8 @@ and is between 256 and 4096 characters.
 	noapic		[SMP,APIC] Tells the kernel to not make use of any
 			IOAPICs that may be present in the system.

+	noautogroup	Disable scheduler automatic task group creation.
+
 	nobats		[PPC] Do not use BATs for mapping kernel lowmem
 			on "Classic" PPC cores.

-------------

Read more about it here.

Tags: Grollman, kernel, Linux, Mike Galbraith

This entry was posted on Thursday, November 18th, 2010 at 8:47 am and is filed under Cost Cutting, embedded, Green Computing, Linux, Mobile, Open Source, VDI. You can follow any responses to this entry through the RSS 2.0 feed. You can leave a response, or trackback from your own site.