From 9430d58e34ec3861e1ca72f8e49105b227aad327 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Wed, 22 Mar 2006 00:07:33 -0800 Subject: [PATCH] sched: remove sleep_avg multiplier Remove the sleep_avg multiplier. This multiplier was necessary back when we had 10 seconds of dynamic range in sleep_avg, but now that we only have one second, it causes that one second to be compressed down to 100ms in some cases. This is particularly noticeable when compiling a kernel in a slow NFS mount, and I believe it to be a very likely candidate for other recently reported network related interactivity problems. In testing, I can detect no negative impact of this removal. Signed-off-by: Mike Galbraith Acked-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sched.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 4d46e90f59c..6b6e0d70eb3 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -706,12 +706,6 @@ static int recalc_task_prio(task_t *p, unsigned long long now) p->sleep_avg = JIFFIES_TO_NS(MAX_SLEEP_AVG - DEF_TIMESLICE); } else { - /* - * The lower the sleep avg a task has the more - * rapidly it will rise with sleep time. - */ - sleep_time *= (MAX_BONUS - CURRENT_BONUS(p)) ? : 1; - /* * Tasks waking from uninterruptible sleep are * limited in their sleep_avg rise as they -- cgit v1.2.3-70-g09d2 From e9028b0ff2bad1954568604dc17725692c8524d6 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Thu, 23 Mar 2006 02:59:20 -0800 Subject: [PATCH] fix scheduler deadlock We have noticed lockups during boot when stress testing kexec on ppc64. Two cpus would deadlock in scheduler code trying to grab already taken spinlocks. The double_rq_lock code uses the address of the runqueue to order the taking of multiple locks. This address is a per cpu variable: if (rq1 < rq2) { spin_lock(&rq1->lock); spin_lock(&rq2->lock); } else { spin_lock(&rq2->lock); spin_lock(&rq1->lock); } On the other hand, the code in wake_sleeping_dependent uses the cpu id order to grab locks: for_each_cpu_mask(i, sibling_map) spin_lock(&cpu_rq(i)->lock); This means we rely on the address of per cpu data increasing as cpu ids increase. While this will be true for the generic percpu implementation it may not be true for arch specific implementations. One way to solve this is to always take runqueues in cpu id order. To do this we add a cpu variable to the runqueue and check it in the double runqueue locking functions. Signed-off-by: Anton Blanchard Acked-by: Ingo Molnar Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sched.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 6b6e0d70eb3..a5bd60453ea 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -237,6 +237,7 @@ struct runqueue { task_t *migration_thread; struct list_head migration_queue; + int cpu; #endif #ifdef CONFIG_SCHEDSTATS @@ -1654,6 +1655,9 @@ unsigned long nr_iowait(void) /* * double_rq_lock - safely lock two runqueues * + * We must take them in cpu order to match code in + * dependent_sleeper and wake_dependent_sleeper. + * * Note this does not disable interrupts like task_rq_lock, * you need to do so manually before calling. */ @@ -1665,7 +1669,7 @@ static void double_rq_lock(runqueue_t *rq1, runqueue_t *rq2) spin_lock(&rq1->lock); __acquire(rq2->lock); /* Fake it out ;) */ } else { - if (rq1 < rq2) { + if (rq1->cpu < rq2->cpu) { spin_lock(&rq1->lock); spin_lock(&rq2->lock); } else { @@ -1701,7 +1705,7 @@ static void double_lock_balance(runqueue_t *this_rq, runqueue_t *busiest) __acquires(this_rq->lock) { if (unlikely(!spin_trylock(&busiest->lock))) { - if (busiest < this_rq) { + if (busiest->cpu < this_rq->cpu) { spin_unlock(&this_rq->lock); spin_lock(&busiest->lock); spin_lock(&this_rq->lock); @@ -6029,6 +6033,7 @@ void __init sched_init(void) rq->push_cpu = 0; rq->migration_thread = NULL; INIT_LIST_HEAD(&rq->migration_queue); + rq->cpu = i; #endif atomic_set(&rq->nr_iowait, 0); -- cgit v1.2.3-70-g09d2 From 91368d73e4b60d577ad171e5bd315b564265fcdb Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 23 Mar 2006 03:00:54 -0800 Subject: [PATCH] make bug messages more consistent Consolidate all kernel bug printouts to begin with the "BUG: " string. Makes it easier to find them in large bootup logs. Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/kernel/nmi.c | 2 +- arch/i386/mm/fault.c | 4 ++-- include/asm-generic/bug.h | 4 ++-- kernel/sched.c | 4 ++-- 4 files changed, 7 insertions(+), 7 deletions(-) (limited to 'kernel/sched.c') diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c index be87c5e2ee9..1db34effdd8 100644 --- a/arch/i386/kernel/nmi.c +++ b/arch/i386/kernel/nmi.c @@ -543,7 +543,7 @@ void nmi_watchdog_tick (struct pt_regs * regs) /* * die_nmi will return ONLY if NOTIFY_STOP happens.. */ - die_nmi(regs, "NMI Watchdog detected LOCKUP"); + die_nmi(regs, "BUG: NMI Watchdog detected LOCKUP"); } else { last_irq_sums[cpu] = sum; alert_counter[cpu] = 0; diff --git a/arch/i386/mm/fault.c b/arch/i386/mm/fault.c index bbb24af5d86..47a3b72ec7b 100644 --- a/arch/i386/mm/fault.c +++ b/arch/i386/mm/fault.c @@ -518,9 +518,9 @@ no_context: } #endif if (address < PAGE_SIZE) - printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference"); + printk(KERN_ALERT "BUG: unable to handle kernel NULL pointer dereference"); else - printk(KERN_ALERT "Unable to handle kernel paging request"); + printk(KERN_ALERT "BUG: unable to handle kernel paging request"); printk(" at virtual address %08lx\n",address); printk(KERN_ALERT " printing eip:\n"); printk("%08lx\n", regs->eip); diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index 400c2b41896..1a565a9d2fa 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -7,7 +7,7 @@ #ifdef CONFIG_BUG #ifndef HAVE_ARCH_BUG #define BUG() do { \ - printk("kernel BUG at %s:%d!\n", __FILE__, __LINE__); \ + printk("BUG: failure at %s:%d/%s()!\n", __FILE__, __LINE__, __FUNCTION__); \ panic("BUG!"); \ } while (0) #endif @@ -19,7 +19,7 @@ #ifndef HAVE_ARCH_WARN_ON #define WARN_ON(condition) do { \ if (unlikely((condition)!=0)) { \ - printk("Badness in %s at %s:%d\n", __FUNCTION__, __FILE__, __LINE__); \ + printk("BUG: warning at %s:%d/%s()\n", __FILE__, __LINE__, __FUNCTION__); \ dump_stack(); \ } \ } while (0) diff --git a/kernel/sched.c b/kernel/sched.c index a5bd60453ea..7ffaabd64f8 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2873,7 +2873,7 @@ asmlinkage void __sched schedule(void) */ if (likely(!current->exit_state)) { if (unlikely(in_atomic())) { - printk(KERN_ERR "scheduling while atomic: " + printk(KERN_ERR "BUG: scheduling while atomic: " "%s/0x%08x/%d\n", current->comm, preempt_count(), current->pid); dump_stack(); @@ -6074,7 +6074,7 @@ void __might_sleep(char *file, int line) if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) return; prev_jiffy = jiffies; - printk(KERN_ERR "Debug: sleeping function called from invalid" + printk(KERN_ERR "BUG: sleeping function called from invalid" " context at %s:%d\n", file, line); printk("in_atomic():%d, irqs_disabled():%d\n", in_atomic(), irqs_disabled()); -- cgit v1.2.3-70-g09d2