summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorKen Chen <kenchen@google.com>2008-12-15 22:02:01 -0800
committerIngo Molnar <mingo@elte.hu>2008-12-16 12:15:00 +0100
commit720f54988e17b33f3f477010b3a68ee872d20d5a (patch)
treeebb475d1a7af97926c1f469a57bef47c46e9ae98
parent34f28ecd0f4bdc733c681294d02d9fab5880591b (diff)
downloadop-kernel-dev-720f54988e17b33f3f477010b3a68ee872d20d5a.zip
op-kernel-dev-720f54988e17b33f3f477010b3a68ee872d20d5a.tar.gz
sched, cpuacct: refactoring cpuusage_read / cpuusage_write
Impact: micro-optimize the code on 64-bit architectures 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 <kenchen@google.com> Cc: Paul Menage <menage@google.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
-rw-r--r--kernel/sched.c56
1 files changed, 39 insertions, 17 deletions
diff --git a/kernel/sched.c b/kernel/sched.c
index 8821506..41b7e2d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -9275,6 +9275,41 @@ cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
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)
{
@@ -9282,17 +9317,8 @@ static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft)
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;
}
@@ -9309,13 +9335,9 @@ static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype,
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;
}
OpenPOWER on IntegriCloud