sched: cpu accounting controller (V2)
Commit cfb5285660aad4931b2ebbfa902ea48a37dfffa1 removed a useful feature for
us, which provided a cpu accounting resource controller. This feature would be
useful if someone wants to group tasks only for accounting purpose and doesnt
really want to exercise any control over their cpu consumption.
The patch below reintroduces the feature. It is based on Paul Menage's
original patch (Commit 62d0df64065e7c135d0002f069444fbdfc64768f), with
these differences:
- Removed load average information. I felt it needs more thought (esp
to deal with SMP and virtualized platforms) and can be added for
2.6.25 after more discussions.
- Convert group cpu usage to be nanosecond accurate (as rest of the cfs
stats are) and invoke cpuacct_charge() from the respective scheduler
classes
- Make accounting scalable on SMP systems by splitting the usage
counter to be per-cpu
- Move the code from kernel/cpu_acct.c to kernel/sched.c (since the
code is not big enough to warrant a new file and also this rightly
needs to live inside the scheduler. Also things like accessing
rq->lock while reading cpu usage becomes easier if the code lived in
kernel/sched.c)
The patch also modifies the cpu controller not to provide the same accounting
information.
Tested-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Tested the patches on top of 2.6.24-rc3. The patches work fine. Ran
some simple tests like cpuspin (spin on the cpu), ran several tasks in
the same group and timed them. Compared their time stamps with
cpuacct.usage.
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/kernel/sched.c b/kernel/sched.c
index 98dcdf2..59ff6b1 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -854,6 +854,12 @@
struct rq_iterator *iterator);
#endif
+#ifdef CONFIG_CGROUP_CPUACCT
+static void cpuacct_charge(struct task_struct *tsk, u64 cputime);
+#else
+static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
+#endif
+
#include "sched_stats.h"
#include "sched_idletask.c"
#include "sched_fair.c"
@@ -7221,38 +7227,12 @@
return (u64) tg->shares;
}
-static u64 cpu_usage_read(struct cgroup *cgrp, struct cftype *cft)
-{
- struct task_group *tg = cgroup_tg(cgrp);
- unsigned long flags;
- u64 res = 0;
- int i;
-
- for_each_possible_cpu(i) {
- /*
- * Lock to prevent races with updating 64-bit counters
- * on 32-bit arches.
- */
- spin_lock_irqsave(&cpu_rq(i)->lock, flags);
- res += tg->se[i]->sum_exec_runtime;
- spin_unlock_irqrestore(&cpu_rq(i)->lock, flags);
- }
- /* Convert from ns to ms */
- do_div(res, NSEC_PER_MSEC);
-
- return res;
-}
-
static struct cftype cpu_files[] = {
{
.name = "shares",
.read_uint = cpu_shares_read_uint,
.write_uint = cpu_shares_write_uint,
},
- {
- .name = "usage",
- .read_uint = cpu_usage_read,
- },
};
static int cpu_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cont)
@@ -7272,3 +7252,126 @@
};
#endif /* CONFIG_FAIR_CGROUP_SCHED */
+
+#ifdef CONFIG_CGROUP_CPUACCT
+
+/*
+ * CPU accounting code for task groups.
+ *
+ * Based on the work by Paul Menage (menage@google.com) and Balbir Singh
+ * (balbir@in.ibm.com).
+ */
+
+/* track cpu usage of a group of tasks */
+struct cpuacct {
+ struct cgroup_subsys_state css;
+ /* cpuusage holds pointer to a u64-type object on every cpu */
+ u64 *cpuusage;
+};
+
+struct cgroup_subsys cpuacct_subsys;
+
+/* return cpu accounting group corresponding to this container */
+static inline struct cpuacct *cgroup_ca(struct cgroup *cont)
+{
+ return container_of(cgroup_subsys_state(cont, cpuacct_subsys_id),
+ struct cpuacct, css);
+}
+
+/* return cpu accounting group to which this task belongs */
+static inline struct cpuacct *task_ca(struct task_struct *tsk)
+{
+ return container_of(task_subsys_state(tsk, cpuacct_subsys_id),
+ struct cpuacct, css);
+}
+
+/* create a new cpu accounting group */
+static struct cgroup_subsys_state *cpuacct_create(
+ struct cgroup_subsys *ss, struct cgroup *cont)
+{
+ struct cpuacct *ca = kzalloc(sizeof(*ca), GFP_KERNEL);
+
+ if (!ca)
+ return ERR_PTR(-ENOMEM);
+
+ ca->cpuusage = alloc_percpu(u64);
+ if (!ca->cpuusage) {
+ kfree(ca);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ return &ca->css;
+}
+
+/* destroy an existing cpu accounting group */
+static void cpuacct_destroy(struct cgroup_subsys *ss,
+ struct cgroup *cont)
+{
+ struct cpuacct *ca = cgroup_ca(cont);
+
+ free_percpu(ca->cpuusage);
+ kfree(ca);
+}
+
+/* return total cpu usage (in nanoseconds) of a group */
+static u64 cpuusage_read(struct cgroup *cont, struct cftype *cft)
+{
+ struct cpuacct *ca = cgroup_ca(cont);
+ 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);
+ }
+
+ return totalcpuusage;
+}
+
+static struct cftype files[] = {
+ {
+ .name = "usage",
+ .read_uint = cpuusage_read,
+ },
+};
+
+static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cont)
+{
+ return cgroup_add_files(cont, ss, files, ARRAY_SIZE(files));
+}
+
+/*
+ * charge this task's execution time to its accounting group.
+ *
+ * called with rq->lock held.
+ */
+static void cpuacct_charge(struct task_struct *tsk, u64 cputime)
+{
+ struct cpuacct *ca;
+
+ if (!cpuacct_subsys.active)
+ return;
+
+ ca = task_ca(tsk);
+ if (ca) {
+ u64 *cpuusage = percpu_ptr(ca->cpuusage, task_cpu(tsk));
+
+ *cpuusage += cputime;
+ }
+}
+
+struct cgroup_subsys cpuacct_subsys = {
+ .name = "cpuacct",
+ .create = cpuacct_create,
+ .destroy = cpuacct_destroy,
+ .populate = cpuacct_populate,
+ .subsys_id = cpuacct_subsys_id,
+};
+#endif /* CONFIG_CGROUP_CPUACCT */
