[PATCH 3/4] scheduler: cpuacct: Enable platform callbacks for cpuacct power tracking

From: Mike Chan
Date: Tue May 18 2010 - 21:31:00 EST


Platform must register cpu power function that return power in
milliWatt seconds.

Signed-off-by: Mike Chan <mike@xxxxxxxxxxx>
---
Documentation/cgroups/cpuacct.txt | 3 +++
include/linux/cpuacct.h | 4 +++-
kernel/sched.c | 24 ++++++++++++++++++++++--
3 files changed, 28 insertions(+), 3 deletions(-)

diff --git a/Documentation/cgroups/cpuacct.txt b/Documentation/cgroups/cpuacct.txt
index 600d2d0..84e471b 100644
--- a/Documentation/cgroups/cpuacct.txt
+++ b/Documentation/cgroups/cpuacct.txt
@@ -44,6 +44,9 @@ cpuacct.cpufreq file gives CPU time (in nanoseconds) spent at each CPU
frequency. Platform hooks must be implemented inorder to properly track
time at each CPU frequency.

+cpuacct.power file gives CPU power consumed (in milliWatt seconds). Platform
+must provide and implement power callback functions.
+
cpuacct controller uses percpu_counter interface to collect user and
system times. This has two side effects:

diff --git a/include/linux/cpuacct.h b/include/linux/cpuacct.h
index 9ff479e..effe842 100644
--- a/include/linux/cpuacct.h
+++ b/include/linux/cpuacct.h
@@ -31,7 +31,9 @@ struct cpuacct_cpufreq_calls {
*/
void (*init) (void **cpuacct_data);
void (*charge) (void *cpuacct_data, u64 cputime, unsigned int cpu);
- void (*show) (void *cpuacct_data, struct cgroup_map_cb *cb);
+ void (*cpufreq_show) (void *cpuacct_data, struct cgroup_map_cb *cb);
+ /* Returns power consumed in milliWatt seconds */
+ u64 (*power_usage) (void *cpuacct_data);
};

int cpuacct_register_cpufreq(struct cpuacct_cpufreq_calls *fn);
diff --git a/kernel/sched.c b/kernel/sched.c
index 6b6c45a..d55d8af 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -8838,12 +8838,28 @@ static int cpuacct_cpufreq_show(struct cgroup *cgrp, struct cftype *cft,
struct cgroup_map_cb *cb)
{
struct cpuacct *ca = cgroup_ca(cgrp);
- if (ca->cpufreq_fn && ca->cpufreq_fn->show)
- ca->cpufreq_fn->show(ca->cpuacct_data, cb);
+ if (ca->cpufreq_fn && ca->cpufreq_fn->cpufreq_show)
+ ca->cpufreq_fn->cpufreq_show(ca->cpuacct_data, cb);

return 0;
}

+/* return total cpu power usage (milliWatt second) of a group */
+static u64 cpuacct_powerusage_read(struct cgroup *cgrp, struct cftype *cft)
+{
+ int i;
+ struct cpuacct *ca = cgroup_ca(cgrp);
+ u64 totalpower = 0;
+
+ if (ca->cpufreq_fn && ca->cpufreq_fn->power_usage)
+ for_each_present_cpu(i) {
+ totalpower += ca->cpufreq_fn->power_usage(
+ ca->cpuacct_data);
+ }
+
+ return totalpower;
+}
+
static struct cftype files[] = {
{
.name = "usage",
@@ -8862,6 +8878,10 @@ static struct cftype files[] = {
.name = "cpufreq",
.read_map = cpuacct_cpufreq_show,
},
+ {
+ .name = "power",
+ .read_u64 = cpuacct_powerusage_read
+ },
};

static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
--
1.7.0.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/