From fe7de49f9d4e53f24ec9ef762a503f70b562341c Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Wed, 20 Oct 2010 16:01:12 -0700 Subject: sched: Make sched_param argument static in sched_setscheduler() callers Andrew Morton pointed out almost all sched_setscheduler() callers are using fixed parameters and can be converted to static. It reduces runtime memory use a little. Signed-off-by: KOSAKI Motohiro Reported-by: Andrew Morton Acked-by: James Morris Cc: Ingo Molnar Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/sched.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 0383601a927c..849c8670583d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1942,9 +1942,10 @@ extern int task_nice(const struct task_struct *p); extern int can_nice(const struct task_struct *p, const int nice); extern int task_curr(const struct task_struct *p); extern int idle_cpu(int cpu); -extern int sched_setscheduler(struct task_struct *, int, struct sched_param *); +extern int sched_setscheduler(struct task_struct *, int, + const struct sched_param *); extern int sched_setscheduler_nocheck(struct task_struct *, int, - struct sched_param *); + const struct sched_param *); extern struct task_struct *idle_task(int cpu); extern struct task_struct *curr_task(int cpu); extern void set_curr_task(int cpu, struct task_struct *p); -- cgit v1.2.2 From aae6d3ddd8b90f5b2c8d79a2b914d1706d124193 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Fri, 17 Sep 2010 15:02:32 -0700 Subject: sched: Use group weight, idle cpu metrics to fix imbalances during idle Currently we consider a sched domain to be well balanced when the imbalance is less than the domain's imablance_pct. As the number of cores and threads are increasing, current values of imbalance_pct (for example 25% for a NUMA domain) are not enough to detect imbalances like: a) On a WSM-EP system (two sockets, each having 6 cores and 12 logical threads), 24 cpu-hogging tasks get scheduled as 13 on one socket and 11 on another socket. Leading to an idle HT cpu. b) On a hypothetial 2 socket NHM-EX system (each socket having 8 cores and 16 logical threads), 16 cpu-hogging tasks can get scheduled as 9 on one socket and 7 on another socket. Leaving one core in a socket idle whereas in another socket we have a core having both its HT siblings busy. While this issue can be fixed by decreasing the domain's imbalance_pct (by making it a function of number of logical cpus in the domain), it can potentially cause more task migrations across sched groups in an overloaded case. Fix this by using imbalance_pct only during newly_idle and busy load balancing. And during idle load balancing, check if there is an imbalance in number of idle cpu's across the busiest and this sched_group or if the busiest group has more tasks than its weight that the idle cpu in this_group can pull. Reported-by: Nikhil Rao Signed-off-by: Suresh Siddha Signed-off-by: Peter Zijlstra LKML-Reference: <1284760952.2676.11.camel@sbsiddha-MOBL3.sc.intel.com> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index d0036e52a24a..2c79e921a68b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -862,6 +862,7 @@ struct sched_group { * single CPU. */ unsigned int cpu_power, cpu_power_orig; + unsigned int group_weight; /* * The CPUs this group covers. -- cgit v1.2.2 From 48c5ccae88dcd989d9de507e8510313c6cbd352b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sat, 13 Nov 2010 19:32:29 +0100 Subject: sched: Simplify cpu-hot-unplug task migration While discussing the need for sched_idle_next(), Oleg remarked that since try_to_wake_up() ensures sleeping tasks will end up running on a sane cpu, we can do away with migrate_live_tasks(). If we then extend the existing hack of migrating current from CPU_DYING to migrating the full rq worth of tasks from CPU_DYING, the need for the sched_idle_next() abomination disappears as well, since idle will be the only possible thread left after the migration thread stops. This greatly simplifies the hot-unplug task migration path, as can be seen from the resulting code reduction (and about half the new lines are comments). Suggested-by: Oleg Nesterov Signed-off-by: Peter Zijlstra LKML-Reference: <1289851597.2109.547.camel@laptop> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 3cd70cf91fde..29d953abb5ad 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1871,14 +1871,11 @@ extern void sched_clock_idle_sleep_event(void); extern void sched_clock_idle_wakeup_event(u64 delta_ns); #ifdef CONFIG_HOTPLUG_CPU -extern void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p); extern void idle_task_exit(void); #else static inline void idle_task_exit(void) {} #endif -extern void sched_idle_next(void); - #if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP) extern void wake_up_idle_cpu(int cpu); #else -- cgit v1.2.2 From 2069dd75c7d0f49355939e5586daf5a9ab216db7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 15 Nov 2010 15:47:00 -0800 Subject: sched: Rewrite tg_shares_up) By tracking a per-cpu load-avg for each cfs_rq and folding it into a global task_group load on each tick we can rework tg_shares_up to be strictly per-cpu. This should improve cpu-cgroup performance for smp systems significantly. [ Paul: changed to use queueing cfs_rq + bug fixes ] Signed-off-by: Paul Turner Signed-off-by: Peter Zijlstra LKML-Reference: <20101115234937.580480400@google.com> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 29d953abb5ad..8abb8aa59664 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1885,8 +1885,6 @@ static inline void wake_up_idle_cpu(int cpu) { } extern unsigned int sysctl_sched_latency; extern unsigned int sysctl_sched_min_granularity; extern unsigned int sysctl_sched_wakeup_granularity; -extern unsigned int sysctl_sched_shares_ratelimit; -extern unsigned int sysctl_sched_shares_thresh; extern unsigned int sysctl_sched_child_runs_first; enum sched_tunable_scaling { -- cgit v1.2.2 From a7a4f8a752ec734b2eab904fc863d5dc873de338 Mon Sep 17 00:00:00 2001 From: Paul Turner Date: Mon, 15 Nov 2010 15:47:06 -0800 Subject: sched: Add sysctl_sched_shares_window Introduce a new sysctl for the shares window and disambiguate it from sched_time_avg. A 10ms window appears to be a good compromise between accuracy and performance. Signed-off-by: Paul Turner Signed-off-by: Peter Zijlstra LKML-Reference: <20101115234938.112173964@google.com> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 8abb8aa59664..840f1277492f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1900,6 +1900,7 @@ extern unsigned int sysctl_sched_migration_cost; extern unsigned int sysctl_sched_nr_migrate; extern unsigned int sysctl_sched_time_avg; extern unsigned int sysctl_timer_migration; +extern unsigned int sysctl_sched_shares_window; int sched_proc_update_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, -- cgit v1.2.2 From 004417a6d468e24399e383645c068b498eed84ad Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 25 Nov 2010 18:38:29 +0100 Subject: perf, arch: Cleanup perf-pmu init vs lockup-detector The perf hardware pmu got initialized at various points in the boot, some before early_initcall() some after (notably arch_initcall). The problem is that the NMI lockup detector is ran from early_initcall() and expects the hardware pmu to be present. Sanitize this by moving all architecture hardware pmu implementations to initialize at early_initcall() and move the lockup detector to an explicit initcall right after that. Cc: paulus Cc: davem Cc: Michael Cree Cc: Deng-Cheng Zhu Acked-by: Paul Mundt Acked-by: Will Deacon Signed-off-by: Peter Zijlstra LKML-Reference: <1290707759.2145.119.camel@laptop> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2c79e921a68b..d2e63d1e725c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -316,6 +316,7 @@ extern int proc_dowatchdog_thresh(struct ctl_table *table, int write, size_t *lenp, loff_t *ppos); extern unsigned int softlockup_panic; extern int softlockup_thresh; +void lockup_detector_init(void); #else static inline void touch_softlockup_watchdog(void) { @@ -326,6 +327,9 @@ static inline void touch_softlockup_watchdog_sync(void) static inline void touch_all_softlockup_watchdogs(void) { } +static inline void lockup_detector_init(void) +{ +} #endif #ifdef CONFIG_DETECT_HUNG_TASK -- cgit v1.2.2 From 24278d148316d2180be6df40e06db013d8b232b8 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 27 Sep 2010 17:25:23 -0700 Subject: rcu: priority boosting for TINY_PREEMPT_RCU Add priority boosting, but only for TINY_PREEMPT_RCU. This is enabled by the default-off RCU_BOOST kernel parameter. The priority to which to boost preempted RCU readers is controlled by the RCU_BOOST_PRIO kernel parameter (defaulting to real-time priority 1) and the time to wait before boosting the readers blocking a given grace period is controlled by the RCU_BOOST_DELAY kernel parameter (defaulting to 500 milliseconds). Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- include/linux/sched.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index e18473f0eb78..ed1a9bc52b2f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1210,6 +1210,9 @@ struct task_struct { #ifdef CONFIG_TREE_PREEMPT_RCU struct rcu_node *rcu_blocked_node; #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ +#ifdef CONFIG_RCU_BOOST + struct rt_mutex *rcu_boost_mutex; +#endif /* #ifdef CONFIG_RCU_BOOST */ #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) struct sched_info sched_info; @@ -1745,7 +1748,8 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * #ifdef CONFIG_PREEMPT_RCU #define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */ -#define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */ +#define RCU_READ_UNLOCK_BOOSTED (1 << 1) /* boosted while in RCU read-side. */ +#define RCU_READ_UNLOCK_NEED_QS (1 << 2) /* RCU core needs CPU response. */ static inline void rcu_copy_process(struct task_struct *p) { @@ -1753,7 +1757,10 @@ static inline void rcu_copy_process(struct task_struct *p) p->rcu_read_unlock_special = 0; #ifdef CONFIG_TREE_PREEMPT_RCU p->rcu_blocked_node = NULL; -#endif +#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ +#ifdef CONFIG_RCU_BOOST + p->rcu_boost_mutex = NULL; +#endif /* #ifdef CONFIG_RCU_BOOST */ INIT_LIST_HEAD(&p->rcu_node_entry); } -- cgit v1.2.2 From 5091faa449ee0b7d73bc296a93bca9540fc51d0a Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Tue, 30 Nov 2010 14:18:03 +0100 Subject: sched: Add 'autogroup' scheduling feature: automated per session task groups A recurring complaint from CFS users is that parallel kbuild has a negative impact on desktop interactivity. This patch implements an idea from Linus, to automatically create task groups. Currently, only per session autogroups are implemented, but the patch leaves the way open for enhancement. Implementation: each task's signal struct contains an inherited pointer to a refcounted autogroup struct containing a task group pointer, the default for all tasks pointing to the init_task_group. When a task calls setsid(), a new task group is created, the process is moved into the new task group, and a reference to the preveious task group is dropped. Child processes inherit this task group thereafter, and increase it's refcount. When the last thread of a process exits, the process's reference is dropped, such that when the last process referencing an autogroup exits, the autogroup is destroyed. At runqueue selection time, IFF a task has no cgroup assignment, its current autogroup is used. Autogroup bandwidth is controllable via setting it's nice level through the proc filesystem: cat /proc//autogroup Displays the task's group and the group's nice level. echo > /proc//autogroup Sets the task group's shares to the weight of nice task. Setting nice level is rate limited for !admin users due to the abuse risk of task group locking. The feature is enabled from boot by default if CONFIG_SCHED_AUTOGROUP=y is selected, but can be disabled via the boot option noautogroup, and can also be turned on/off on the fly via: echo [01] > /proc/sys/kernel/sched_autogroup_enabled ... which will automatically move tasks to/from the root task group. Signed-off-by: Mike Galbraith Acked-by: Linus Torvalds Acked-by: Peter Zijlstra Cc: Markus Trippelsdorf Cc: Mathieu Desnoyers Cc: Paul Turner Cc: Oleg Nesterov [ Removed the task_group_path() debug code, and fixed !EVENTFD build failure. ] Signed-off-by: Ingo Molnar LKML-Reference: <1290281700.28711.9.camel@maggy.simson.net> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index a5b92c70c737..9c2d46da486e 100644 --- a/include/linux/sched.h +++ b/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. @@ -1927,6 +1932,24 @@ int sched_rt_handler(struct ctl_table *table, int write, 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); +#ifdef CONFIG_PROC_FS +extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m); +extern int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice); +#endif +#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); -- cgit v1.2.2 From 0f004f5a696a9434b7214d0d3cbd0525ee77d428 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 30 Nov 2010 19:48:45 +0100 Subject: sched: Cure more NO_HZ load average woes There's a long-running regression that proved difficult to fix and which is hitting certain people and is rather annoying in its effects. Damien reported that after 74f5187ac8 (sched: Cure load average vs NO_HZ woes) his load average is unnaturally high, he also noted that even with that patch reverted the load avgerage numbers are not correct. The problem is that the previous patch only solved half the NO_HZ problem, it addressed the part of going into NO_HZ mode, not of comming out of NO_HZ mode. This patch implements that missing half. When comming out of NO_HZ mode there are two important things to take care of: - Folding the pending idle delta into the global active count. - Correctly aging the averages for the idle-duration. So with this patch the NO_HZ interaction should be complete and behaviour between CONFIG_NO_HZ=[yn] should be equivalent. Furthermore, this patch slightly changes the load average computation by adding a rounding term to the fixed point multiplication. Reported-by: Damien Wyart Reported-by: Tim McGrath Tested-by: Damien Wyart Tested-by: Orion Poplawski Tested-by: Kyle McMartin Signed-off-by: Peter Zijlstra Cc: stable@kernel.org Cc: Chase Douglas LKML-Reference: <1291129145.32004.874.camel@laptop> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2c79e921a68b..223874538b33 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -143,7 +143,7 @@ extern unsigned long nr_iowait_cpu(int cpu); extern unsigned long this_cpu_load(void); -extern void calc_global_load(void); +extern void calc_global_load(unsigned long ticks); extern unsigned long get_parent_ip(unsigned long addr); -- cgit v1.2.2 From 806c09a7db457be3758e14b1f152761135d89af5 Mon Sep 17 00:00:00 2001 From: Dario Faggioli Date: Tue, 30 Nov 2010 19:51:33 +0100 Subject: sched: Make pushable_tasks CONFIG_SMP dependant As noted by Peter Zijlstra at https://lkml.org/lkml/2010/11/10/391 (while reviewing other stuff, though), tracking pushable tasks only makes sense on SMP systems. Signed-off-by: Dario Faggioli Acked-by: Steven Rostedt Acked-by: Gregory Haskins Signed-off-by: Peter Zijlstra LKML-Reference: <1291143093.2697.298.camel@Palantir> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 9c2d46da486e..4f92a239c14d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1240,7 +1240,9 @@ struct task_struct { #endif struct list_head tasks; +#ifdef CONFIG_SMP struct plist_node pushable_tasks; +#endif struct mm_struct *mm, *active_mm; #if defined(SPLIT_RSS_COUNTING) -- cgit v1.2.2 From 07e06b011db2b3300f6c975ebf293fc4c8c59942 Mon Sep 17 00:00:00 2001 From: Yong Zhang Date: Fri, 7 Jan 2011 15:17:36 +0800 Subject: sched: Consolidate the name of root_task_group and init_task_group root_task_group is the leftover of USER_SCHED, now it's always same to init_task_group. But as Mike suggested, root_task_group is maybe the suitable name to keep for a tree. So in this patch: init_task_group --> root_task_group init_task_group_load --> root_task_group_load INIT_TASK_GROUP_LOAD --> ROOT_TASK_GROUP_LOAD Suggested-by: Mike Galbraith Signed-off-by: Yong Zhang Signed-off-by: Peter Zijlstra LKML-Reference: <20110107071736.GA32635@windriver.com> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 777cd01e240e..341acbbc434a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2511,7 +2511,7 @@ extern void normalize_rt_tasks(void); #ifdef CONFIG_CGROUP_SCHED -extern struct task_group init_task_group; +extern struct task_group root_task_group; extern struct task_group *sched_create_group(struct task_group *parent); extern void sched_destroy_group(struct task_group *tg); -- cgit v1.2.2