In the thread regarding to 'export percpu cpuacct cgroup stats'
http://lkml.org/lkml/2008/12/7/13
akpm pointed out that current cpuacct code is inefficient. This patch
refactoring the following:
* make cpu_rq locking only on 32-bit
* change iterator to each_present_cpu instead of each_possible_cpu to
make it hotplug friendly.
It's a bit of code churn, but I was rewarded with 160 byte code size saving
on x86-64 arch and zero code size change on i386.
Signed-off-by: Ken Chen <[email protected]>
diff --git a/kernel/sched.c b/kernel/sched.c
index e4bb1dd..124bd7a 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -9302,6 +9302,41 @@ cpuacct_destroy
kfree(ca);
}
+static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
+{
+ u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+ u64 data;
+
+#ifndef CONFIG_64BIT
+ /*
+ * Take rq->lock to make 64-bit read safe on 32-bit platforms.
+ */
+ spin_lock_irq(&cpu_rq(cpu)->lock);
+ data = *cpuusage;
+ spin_unlock_irq(&cpu_rq(cpu)->lock);
+#else
+ data = *cpuusage;
+#endif
+
+ return data;
+}
+
+static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
+{
+ u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+
+#ifndef CONFIG_64BIT
+ /*
+ * Take rq->lock to make 64-bit write safe on 32-bit platforms.
+ */
+ spin_lock_irq(&cpu_rq(cpu)->lock);
+ *cpuusage = val;
+ spin_unlock_irq(&cpu_rq(cpu)->lock);
+#else
+ *cpuusage = val;
+#endif
+}
+
/* return total cpu usage (in nanoseconds) of a group */
static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft)
{
@@ -9309,17 +9344,8 @@ static u64 cpuusage_read
u64 totalcpuusage = 0;
int i;
- for_each_possible_cpu(i) {
- u64 *cpuusage = percpu_ptr(ca->cpuusage, i);
-
- /*
- * Take rq->lock to make 64-bit addition safe on 32-bit
- * platforms.
- */
- spin_lock_irq(&cpu_rq(i)->lock);
- totalcpuusage += *cpuusage;
- spin_unlock_irq(&cpu_rq(i)->lock);
- }
+ for_each_present_cpu(i)
+ totalcpuusage += cpuacct_cpuusage_read(ca, i);
return totalcpuusage;
}
@@ -9336,13 +9362,9 @@ static int cpuusage_write
goto out;
}
- for_each_possible_cpu(i) {
- u64 *cpuusage = percpu_ptr(ca->cpuusage, i);
+ for_each_present_cpu(i)
+ cpuacct_cpuusage_write(ca, i, 0);
- spin_lock_irq(&cpu_rq(i)->lock);
- *cpuusage = 0;
- spin_unlock_irq(&cpu_rq(i)->lock);
- }
out:
return err;
}
* Ken Chen <[email protected]> wrote:
> In the thread regarding to 'export percpu cpuacct cgroup stats'
> http://lkml.org/lkml/2008/12/7/13
>
> akpm pointed out that current cpuacct code is inefficient. This patch
> refactoring the following:
>
> * make cpu_rq locking only on 32-bit
> * change iterator to each_present_cpu instead of each_possible_cpu to
> make it hotplug friendly.
>
> It's a bit of code churn, but I was rewarded with 160 byte code size saving
> on x86-64 arch and zero code size change on i386.
applied to tip/sched/core, thanks Ken!
Ingo