From f5dc37530ba8a35aae0f7f4f13781d1904f71e94 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Fri, 9 Oct 2009 08:35:03 +0200 Subject: [PATCH 1/3] sched: Update the clock of runqueue select_task_rq() selected In try_to_wake_up(), we update the runqueue clock, but select_task_rq() may select a different runqueue than the one we updated, leaving the new runqueue's clock stale for a bit. This patch cures occasional huge latencies reported by latencytop when coming out of idle on a mostly idle NO_HZ box. Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra LKML-Reference: <1255070103.7639.30.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- kernel/sched.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index 76c0e9691fc0..e3f8f4f61c8e 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2311,7 +2311,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, { int cpu, orig_cpu, this_cpu, success = 0; unsigned long flags; - struct rq *rq; + struct rq *rq, *orig_rq; if (!sched_feat(SYNC_WAKEUPS)) wake_flags &= ~WF_SYNC; @@ -2319,7 +2319,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, this_cpu = get_cpu(); smp_wmb(); - rq = task_rq_lock(p, &flags); + rq = orig_rq = task_rq_lock(p, &flags); update_rq_clock(rq); if (!(p->state & state)) goto out; @@ -2350,6 +2350,10 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, set_task_cpu(p, cpu); rq = task_rq_lock(p, &flags); + + if (rq != orig_rq) + update_rq_clock(rq); + WARN_ON(p->state != TASK_WAKING); cpu = task_cpu(p); From e7ab0f7b50bc4688fb5cf65de5d42e3b882fb8d1 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 9 Oct 2009 15:58:20 +0200 Subject: [PATCH 2/3] Revert "x86, timers: Check for pending timers after (device) interrupts" This reverts commit 9bcbdd9c58617f1301dd4f17c738bb9bc73aca70. The real bug producing LatencyTop latencies has been fixed in: f5dc375: sched: Update the clock of runqueue select_task_rq() selected And the commit being reverted here triggers local timer processing from every device IRQ. If device IRQs come in at a high frequency, this could cause a performance regression. The commit being reverted here purely 'fixed' the reported latency as a side effect, because CPUs were being moved out of idle more often. Acked-by: Peter Zijlstra Cc: Arjan van de Ven Cc: Frans Pop Cc: Linus Torvalds Cc: Mike Galbraith Cc: Thomas Gleixner LKML-Reference: <20091008064041.67219b13@infradead.org> Signed-off-by: Ingo Molnar --- arch/x86/kernel/irq.c | 2 -- arch/x86/kernel/smp.c | 1 - 2 files changed, 3 deletions(-) diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 391206199515..74656d1d4e30 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -244,7 +244,6 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs) __func__, smp_processor_id(), vector, irq); } - run_local_timers(); irq_exit(); set_irq_regs(old_regs); @@ -269,7 +268,6 @@ void smp_generic_interrupt(struct pt_regs *regs) if (generic_interrupt_extension) generic_interrupt_extension(); - run_local_timers(); irq_exit(); set_irq_regs(old_regs); diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index d915d956e66d..ec1de97600e7 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -198,7 +198,6 @@ void smp_reschedule_interrupt(struct pt_regs *regs) { ack_APIC_irq(); inc_irq_stat(irq_resched_count); - run_local_timers(); /* * KVM uses this interrupt to force a cpu out of guest mode */ From e17b38bf9e70d74f3739a600db75240078ac1407 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 11 Oct 2009 19:12:00 -0700 Subject: [PATCH 3/3] sched: Fix missing kernel-doc notation The following htmldocs warnings: Warning(kernel/sched.c:685): No description found for parameter 'cpu' Warning(kernel/sched.c:3676): No description found for parameter 'sd' Trigger because new parameters were added to update_rq_clock() and update_group_power() without updating the kernel-doc notation. Signed-off-by: Jaswinder Singh Rajput Signed-off-by: Randy Dunlap Cc: Andrew Morton Cc: Steven Rostedt Cc: Peter Zijlstra LKML-Reference: <4AD29070.7070002@oracle.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/sched.c b/kernel/sched.c index e3f8f4f61c8e..789001da0a94 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -676,6 +676,7 @@ inline void update_rq_clock(struct rq *rq) /** * runqueue_is_locked + * @cpu: the processor in question. * * Returns true if the current cpu runqueue is locked. * This interface allows printk to be called with the runqueue lock @@ -3660,6 +3661,7 @@ static void update_group_power(struct sched_domain *sd, int cpu) /** * update_sg_lb_stats - Update sched_group's statistics for load balancing. + * @sd: The sched_domain whose statistics are to be updated. * @group: sched_group whose statistics are to be updated. * @this_cpu: Cpu for which load balance is currently performed. * @idle: Idle status of this_cpu