Add hierarchical accounting to cpu accounting controller

Add hierarchical accounting to cpu accounting controller

Currently, while charging the task's cputime to its accounting group,
the accounting group hierarchy isn't updated. This patch charges the cputime
of a task to its accounting group and all its parent accounting groups.

Reported-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com>
CC: Peter Zijlstra <a.p.zijlstra@chello.nl>
CC: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched.c |   30 ++++++++++++++++++++++++------
 1 file changed, 24 insertions(+), 6 deletions(-)

--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -9131,10 +9131,15 @@ struct cpuacct {
 	struct cgroup_subsys_state css;
 	/* cpuusage holds pointer to a u64-type object on every cpu */
 	u64 *cpuusage;
+	struct cpuacct *parent;
 };
 
+static struct cpuacct init_cpuacct_group;
 struct cgroup_subsys cpuacct_subsys;
 
+#define for_each_cpuacct_group(ca) \
+		for (; ca; ca = ca->parent)
+
 /* return cpu accounting group corresponding to this container */
 static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp)
 {
@@ -9153,17 +9158,28 @@ static inline struct cpuacct *task_ca(st
 static struct cgroup_subsys_state *cpuacct_create(
 	struct cgroup_subsys *ss, struct cgroup *cgrp)
 {
-	struct cpuacct *ca = kzalloc(sizeof(*ca), GFP_KERNEL);
+	struct cpuacct *ca;
 
-	if (!ca)
-		return ERR_PTR(-ENOMEM);
+	if (!cgrp->parent) {
+		/* This is early initialization for the top cgroup */
+		ca = &init_cpuacct_group;
+	} else {
+		ca = kzalloc(sizeof(*ca), GFP_KERNEL);
+		if (!ca)
+			return ERR_PTR(-ENOMEM);
+	}
 
 	ca->cpuusage = alloc_percpu(u64);
 	if (!ca->cpuusage) {
-		kfree(ca);
+		if (cgrp->parent)
+			kfree(ca);
 		return ERR_PTR(-ENOMEM);
 	}
 
+	if (cgrp->parent) {
+		ca->css.cgroup = cgrp;
+		ca->parent = cgroup_ca(cgrp->parent);
+	}
 	return &ca->css;
 }
 
@@ -9243,14 +9259,16 @@ static int cpuacct_populate(struct cgrou
 static void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 {
 	struct cpuacct *ca;
+	int cpu;
 
 	if (!cpuacct_subsys.active)
 		return;
 
+	cpu = task_cpu(tsk);
 	ca = task_ca(tsk);
-	if (ca) {
-		u64 *cpuusage = percpu_ptr(ca->cpuusage, task_cpu(tsk));
 
+	for_each_cpuacct_group(ca) {
+		u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
 		*cpuusage += cputime;
 	}
 }
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/