sched/core updates for v2.6.31
Subsystems (7)
Linus,
Please pull the latest sched-core-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git sched-core-for-linus
Thanks,
Ingo
------------------>
David Rientjes (1):
sched: emit thread info flags with stack trace
Gautham R Shenoy (3):
sched: Nominate idle load balancer from a semi-idle package.
sched: Nominate a power-efficient ilb in select_nohz_balancer()
sched: Replace first_cpu() with cpumask_first() in ILB nomination code
GeunSik Lim (2):
ftrace: fix typo about map of kernel priority in ftrace.txt file.
sched: fix typo in sched-rt-group.txt file
Ingo Molnar (1):
sched: properly define the sched_group::cpumask and sched_domain::span fields
Johannes Weiner (1):
wait: don't use __wake_up_common()
Miao Xie (1):
sched: use group_first_cpu() instead of cpumask_first(sched_group_cpus())
Paul Turner (1):
sched: remove redundant hierarchy walk in check_preempt_wakeup
Peter Zijlstra (2):
sched: remove extra call overhead for schedule()
sched: rt: document the risk of small values in the bandwidth settings
Thomas Gleixner (2):
sched, timers: move calc_load() to scheduler sched, timers: cleanup avenrun users
Vaidyanathan Srinivasan (1):
sched: Don't export sched_mc_power_savings on multi-socket single core system
Documentation/scheduler/sched-rt-group.txt | 20 ++- Documentation/trace/ftrace.txt | 15 ++- arch/x86/include/asm/topology.h | 3 +- fs/proc/loadavg.c | 18 +-- include/linux/sched.h | 28 +++- include/linux/wait.h | 2 - kernel/mutex.c | 4 +- kernel/sched.c | 279 ++++++++++++++++++++++++---- kernel/sched_fair.c | 13 +- kernel/sched_idletask.c | 3 +- kernel/time/timekeeping.c | 2 +- kernel/timer.c | 86 +-------- kernel/wait.c | 2 +- 13 files changed, 325 insertions(+), 150 deletions(-)
Documentation/scheduler/sched-rt-group.txt +19 -1
@@ -4,6 +4,7 @@ CONTENTS ======== +0. WARNING 1. Overview 1.1 The problem 1.2 The solution
@@ -14,6 +15,23 @@ CONTENTS 3. Future plans +0. WARNING +========== + + Fiddling with these settings can result in an unstable system, the knobs are + root only and assumes root knows what he is doing. + +Most notable: + + * very small values in sched_rt_period_us can result in an unstable + system when the period is smaller than either the available hrtimer + resolution, or the time it takes to handle the budget refresh itself. + + * very small values in sched_rt_runtime_us can result in an unstable + system when the runtime is so small the system has difficulty making + forward progress (NOTE: the migration thread and kstopmachine both + are real-time processes). + 1. Overview ===========
@@ -169,7 +187,7 @@ get their allocated time. Implementing SCHED_EDF might take a while to complete. Priority Inheritance is the biggest challenge as the current linux PI infrastructure is geared towards -the limited static priority levels 0-139. With deadline scheduling you need to +the limited static priority levels 0-99. With deadline scheduling you need to do deadline inheritance (since priority is inversely proportional to the deadline delta (deadline - now).
Documentation/trace/ftrace.txt +12 -3
@@ -518,9 +518,18 @@ priority with zero (0) being the highest priority and the nice values starting at 100 (nice -20). Below is a quick chart to map the kernel priority to user land priorities. - Kernel priority: 0 to 99 ==> user RT priority 99 to 0 - Kernel priority: 100 to 139 ==> user nice -20 to 19 - Kernel priority: 140 ==> idle task priority + Kernel Space User Space + =============================================================== + 0(high) to 98(low) user RT priority 99(high) to 1(low) + with SCHED_RR or SCHED_FIFO + --------------------------------------------------------------- + 99 sched_priority is not used in scheduling + decisions(it must be specified as 0) + --------------------------------------------------------------- + 100(high) to 139(low) user nice -20(high) to 19(low) + --------------------------------------------------------------- + 140 idle task priority + --------------------------------------------------------------- The task states are:
arch/x86/include/asm/topology.h +2 -1
@@ -203,7 +203,8 @@ struct pci_bus;void x86_pci_root_bus_res_quirks (struct pci_bus *b);#ifdef CONFIG_SMP -#define mc_capable () (cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids) +#define mc_capable () ((boot_cpu_data.x86_max_cores > 1) && \ + (cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids))#define smt_capable () (smp_num_siblings > 1)#endif
fs/proc/loadavg.c +6 -12
@@ -12,20 +12,14 @@static int loadavg_proc_show (struct seq_file *m,void *v) { -int a, b, c; -unsigned long seq; +unsigned long avnrun[3 ]; -do { - seq =read_seqbegin (&xtime_lock); - a = avenrun[0 ] + (FIXED_1 /200 ); - b = avenrun[1 ] + (FIXED_1 /200 ); - c = avenrun[2 ] + (FIXED_1 /200 ); - }while (read_seqretry (&xtime_lock, seq)); +get_avenrun (avnrun,FIXED_1 /200 ,0 ); -seq_printf (m,"%d.%02d %d.%02d %d.%02d %ld/%d %d\n" , -LOAD_INT (a),LOAD_FRAC (a), -LOAD_INT (b),LOAD_FRAC (b), -LOAD_INT (c),LOAD_FRAC (c), +seq_printf (m,"%lu.%02lu %lu.%02lu %lu.%02lu %ld/%d %d\n" , +LOAD_INT (avnrun[0 ]),LOAD_FRAC (avnrun[0 ]), +LOAD_INT (avnrun[1 ]),LOAD_FRAC (avnrun[1 ]), +LOAD_INT (avnrun[2 ]),LOAD_FRAC (avnrun[2 ]),nr_running (), nr_threads,task_active_pid_ns (current)->last_pid);return 0 ;
include/linux/sched.h +24 -4
@@ -116,6 +116,7 @@ struct fs_struct;* 11 bit fractions. */ extern unsigned long avenrun[];/* Load averages */ +extern void get_avenrun (unsigned long *loads,unsigned long offset,int shift);#define FSHIFT 11/* nr of bits of precision */ #define FIXED_1 (1<<FSHIFT)/* 1.0 as fixed-point */
@@ -135,8 +136,8 @@ DECLARE_PER_CPU(unsigned long, process_counts);extern int nr_processes (void );extern unsigned long nr_running (void );extern unsigned long nr_uninterruptible (void ); -extern unsigned long nr_active (void );extern unsigned long nr_iowait (void ); +extern void calc_global_load (void );extern unsigned long get_parent_ip (unsigned long addr);
@@ -838,7 +839,17 @@ struct sched_group {*/ u32 reciprocal_cpu_power; -unsigned long cpumask[]; +/* +* The CPUs this group covers. +* +* NOTE: this field is variable length. (Allocated dynamically +* by attaching extra space to the end of the structure, +* depending on how many CPUs the kernel has booted up with) +* +* It is also be embedded into static data structures at build +* time. (See 'struct static_sched_group' in kernel/sched.c) +*/ +unsigned long cpumask[0 ]; };static inline struct cpumask *sched_group_cpus (struct sched_group *sg)
@@ -924,8 +935,17 @@ struct sched_domain {char *name;#endif -/* span of all CPUs in this domain */ -unsigned long span[]; +/* +* Span of all CPUs in this domain. +* +* NOTE: this field is variable length. (Allocated dynamically +* by attaching extra space to the end of the structure, +* depending on how many CPUs the kernel has booted up with) +* +* It is also be embedded into static data structures at build +* time. (See 'struct static_sched_domain' in kernel/sched.c) +*/ +unsigned long span[0 ]; };static inline struct cpumask *sched_domain_span (struct sched_domain *sd)
include/linux/wait.h +0 -2
@@ -132,8 +132,6 @@ static inline void __remove_wait_queue(wait_queue_head_t *head,list_del (&old->task_list); } -void __wake_up_common (wait_queue_head_t *q,unsigned int mode, -int nr_exclusive,int sync,void *key);void __wake_up (wait_queue_head_t *q,unsigned int mode,int nr,void *key);void __wake_up_locked_key (wait_queue_head_t *q,unsigned int mode,void *key); void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr,
kernel/mutex.c +3 -1
@@ -249,7 +249,9 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,/* didnt get the lock, go to sleep: */ spin_unlock_mutex (&lock->wait_lock, flags); -__schedule (); +preempt_enable_no_resched (); +schedule (); +preempt_disable ();spin_lock_mutex (&lock->wait_lock, flags); }
kernel/sched.c +244 -35
422 lines not on this page · raw message
kernel/sched_fair.c +3 -10
@@ -1487,17 +1487,10 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)find_matching_se (&se, &pse); -while (se) { -BUG_ON (!pse); +BUG_ON (!pse); -if (wakeup_preempt_entity (se, pse) ==1 ) { -resched_task (curr); -break ; - } - - se =parent_entity (se); - pse =parent_entity (pse); - } +if (wakeup_preempt_entity (se, pse) ==1 ) +resched_task (curr); }static struct task_struct *pick_next_task_fair (struct rq *rq)
kernel/sched_idletask.c +2 -1
@@ -22,7 +22,8 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int systatic struct task_struct *pick_next_task_idle (struct rq *rq) {schedstat_inc (rq, sched_goidle); - +/* adjust the active tasks as we might go into a long sleep */ +calc_load_account_active (rq);return rq->idle; }
kernel/time/timekeeping.c +1 -1
@@ -22,7 +22,7 @@/* * This read-write spinlock protects us from races in SMP while -* playing with xtime and avenrun. +* playing with xtime. */ __cacheline_aligned_in_smp DEFINE_SEQLOCK (xtime_lock );
kernel/timer.c +8 -78
115 lines not on this page · raw message
kernel/wait.c +1 -1
@@ -154,7 +154,7 @@ void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,if (!list_empty (&wait->task_list))list_del_init (&wait->task_list);else if (waitqueue_active (q)) -__wake_up_common (q, mode,1 ,0 , key); +__wake_up_locked_key (q, mode, key);spin_unlock_irqrestore (&q->lock, flags); }EXPORT_SYMBOL (abort_exclusive_wait);