[tip:sched/core] sched: cpuacct: Use bigger percpu counter batch values for stats counters

[tip-bot for KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>]

Commit-ID:  50fbed3bb72cbe38a665512771a91a96d028de46
Gitweb:     http://git.kernel.org/tip/50fbed3bb72cbe38a665512771a91a96d028de46
Author:     KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
AuthorDate: Sat, 9 May 2009 19:14:58 +0900
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Mon, 11 May 2009 14:32:57 +0200

sched: cpuacct: Use bigger percpu counter batch values for stats counters

percpu counters used to accumulate statistics in cpuacct controller use
the default batch value [max(2*nr_cpus, 32)] which can be too small for
archs that define VIRT_CPU_ACCOUNTING. In such archs, a tick could result in
cputime updates in the range of thousands. As a result, cpuacct_update_stats()
would end up acquiring the percpu counter spinlock on every tick which
is not good for performance.

Let those architectures to have a bigger batch threshold so that percpu counter
spinlock isn't taken on every tick. This change doesn't affect the archs which
don't define VIRT_CPU_ACCOUNTING and they continue to have the default
percpu counter batch value.

 v5:
 - move cpuacct_batch initialization into sched_init()

 v4:
  - rewrite patch description (thanks Bharata!)
  - append read_mostly to cpuacct_batch
  - cpuacct_batch is initialized by sched_init_debug()

 v3:
  - revert using percpu_counter_sum()

 v2:
  - use percpu_counter_sum() instead percpu_counter_read()

Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Balaji Rao <balajirrao@gmail.com>
Cc: Dhaval Giani <dhaval@linux.vnet.ibm.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
LKML-Reference: <20090509191430.3AD5.A69D9226@jp.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 kernel/sched.c |    7 ++++++-
 1 files changed, 6 insertions(+), 1 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index 8908d19..873bc3b 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -872,6 +872,8 @@ static __read_mostly int scheduler_running;
  */
 int sysctl_sched_rt_runtime = 950000;
 
+static __read_mostly s32 cpuacct_batch;
+
 static inline u64 global_rt_period(void)
 {
 	return (u64)sysctl_sched_rt_period * NSEC_PER_USEC;
@@ -9171,6 +9173,8 @@ void __init sched_init(void)
 	 */
 	current->sched_class = &fair_sched_class;
 
+	cpuacct_batch = jiffies_to_cputime(percpu_counter_batch);
+
 	/* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
 	alloc_bootmem_cpumask_var(&nohz_cpu_mask);
 #ifdef CONFIG_SMP
@@ -10354,7 +10358,8 @@ static void cpuacct_update_stats(struct task_struct *tsk,
 	ca = task_ca(tsk);
 
 	do {
-		percpu_counter_add(&ca->cpustat[idx], val);
+		__percpu_counter_add(&ca->cpustat[idx], val, cpuacct_batch);
+
 		ca = ca->parent;
 	} while (ca);
 	rcu_read_unlock();