summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--kernel/sched.c20
1 files changed, 19 insertions, 1 deletions
diff --git a/kernel/sched.c b/kernel/sched.c
index f96be93..bae6fcf 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -8998,12 +8998,30 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime)
}
/*
+ * When CONFIG_VIRT_CPU_ACCOUNTING is enabled one jiffy can be very large
+ * in cputime_t units. As a result, cpuacct_update_stats calls
+ * percpu_counter_add with values large enough to always overflow the
+ * per cpu batch limit causing bad SMP scalability.
+ *
+ * To fix this we scale percpu_counter_batch by cputime_one_jiffy so we
+ * batch the same amount of time with CONFIG_VIRT_CPU_ACCOUNTING disabled
+ * and enabled. We cap it at INT_MAX which is the largest allowed batch value.
+ */
+#ifdef CONFIG_SMP
+#define CPUACCT_BATCH \
+ min_t(long, percpu_counter_batch * cputime_one_jiffy, INT_MAX)
+#else
+#define CPUACCT_BATCH 0
+#endif
+
+/*
* Charge the system/user time to the task's accounting group.
*/
static void cpuacct_update_stats(struct task_struct *tsk,
enum cpuacct_stat_index idx, cputime_t val)
{
struct cpuacct *ca;
+ int batch = CPUACCT_BATCH;
if (unlikely(!cpuacct_subsys.active))
return;
@@ -9012,7 +9030,7 @@ 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, batch);
ca = ca->parent;
} while (ca);
rcu_read_unlock();
OpenPOWER on IntegriCloud