sched/tune: add sysctl interface to define a boost value

The current (CFS) scheduler implementation does not allow "to boost"
tasks performance by running them at a higher OPP compared to the
minimum required to meet their workload demands.

To support tasks performance boosting the scheduler should provide a
"knob" which allows to tune how much the system is going to be optimised
for energy efficiency vs performance.

This patch is the first of a series which provides a simple interface to
define a tuning knob. One system-wide "boost" tunable is exposed via:
  /proc/sys/kernel/sched_cfs_boost
which can be configured in the range [0..100], to define a percentage
where:
  - 0%   boost requires to operate in "standard" mode by scheduling
         tasks at the minimum capacities required by the workload demand
  - 100% boost requires to push at maximum the task performances,
         "regardless" of the incurred energy consumption

A boost value in between these two boundaries is used to bias the
power/performance trade-off, the higher the boost value the more the
scheduler is biased toward performance boosting instead of energy
efficiency.

cc: Ingo Molnar <mingo@redhat.com>
cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>

diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index c9e4731cf10b8e97956b160c503e447490991931..4479e48c7712f384493bc0fe15de8207519575b0 100644 (file)
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -77,6 +77,22 @@ extern int sysctl_sched_rt_runtime;
 extern unsigned int sysctl_sched_cfs_bandwidth_slice;
 #endif
 
+#ifdef CONFIG_SCHED_TUNE
+extern unsigned int sysctl_sched_cfs_boost;
+int sysctl_sched_cfs_boost_handler(struct ctl_table *table, int write,
+                                  void __user *buffer, size_t *length,
+                                  loff_t *ppos);
+static inline unsigned int get_sysctl_sched_cfs_boost(void)
+{
+       return sysctl_sched_cfs_boost;
+}
+#else
+static inline unsigned int get_sysctl_sched_cfs_boost(void)
+{
+       return 0;
+}
+#endif
+
 #ifdef CONFIG_SCHED_AUTOGROUP
 extern unsigned int sysctl_sched_autogroup_enabled;
 #endif

diff --git a/init/Kconfig b/init/Kconfig
index 235c7a2c0d2004f1121b7d98f4140683ab45ef53..83d8c02e7a5798bd2f363f6a022b3d22ca4d2d33 100644 (file)
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1237,6 +1237,32 @@ config SCHED_AUTOGROUP
          desktop applications.  Task group autogeneration is currently based
          upon task session.
 
+config SCHED_TUNE
+       bool "Boosting for CFS tasks (EXPERIMENTAL)"
+       help
+         This option enables the system-wide support for task boosting.
+         When this support is enabled a new sysctl interface is exposed to
+         userspace via:
+            /proc/sys/kernel/sched_cfs_boost
+         which allows to set a system-wide boost value in range [0..100].
+
+         The currently boosting strategy is implemented in such a way that:
+         - a 0% boost value requires to operate in "standard" mode by
+           scheduling all tasks at the minimum capacities required by their
+           workload demand
+         - a 100% boost value requires to push at maximum the task
+           performances, "regardless" of the incurred energy consumption
+
+         A boost value in between these two boundaries is used to bias the
+         power/performance trade-off, the higher the boost value the more the
+         scheduler is biased toward performance boosting instead of energy
+         efficiency.
+
+         Since this support exposes a single system-wide knob, the specified
+         boost value is applied to all (CFS) tasks in the system.
+
+         If unsure, say N.
+
 config SYSFS_DEPRECATED
        bool "Enable deprecated sysfs features to support old userspace tools"
        depends on SYSFS

diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 0eabc9db4c3d567a708d95f0a150d8850943e3a8..c6a85f813dfda2798a0ceadfd8066b082afae1c9 100644 (file)
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -18,5 +18,6 @@ obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
+obj-$(CONFIG_SCHED_TUNE) += tune.o
 obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
 obj-$(CONFIG_CPU_FREQ_GOV_SCHED) += cpufreq_sched.o

diff --git a/kernel/sched/tune.c b/kernel/sched/tune.c
new file mode 100644 (file)
index 0000000..4c44b1a
--- /dev/null
+++ b/kernel/sched/tune.c
@@ -0,0 +1,17 @@
+#include "sched.h"
+
+unsigned int sysctl_sched_cfs_boost __read_mostly;
+
+int
+sysctl_sched_cfs_boost_handler(struct ctl_table *table, int write,
+                              void __user *buffer, size_t *lenp,
+                              loff_t *ppos)
+{
+       int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+
+       if (ret || !write)
+               return ret;
+
+       return 0;
+}
+

diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index dc6858d6639ed022d65129bdbb869ff7bcc05789..827ba256fdad9335470a8cc85fe271f5f92fa1db 100644 (file)
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -434,6 +434,17 @@ static struct ctl_table kern_table[] = {
                .extra1         = &one,
        },
 #endif
+#ifdef CONFIG_SCHED_TUNE
+       {
+               .procname       = "sched_cfs_boost",
+               .data           = &sysctl_sched_cfs_boost,
+               .maxlen         = sizeof(sysctl_sched_cfs_boost),
+               .mode           = 0644,
+               .proc_handler   = &sysctl_sched_cfs_boost_handler,
+               .extra1         = &zero,
+               .extra2         = &one_hundred,
+       },
+#endif
 #ifdef CONFIG_PROVE_LOCKING
        {
                .procname       = "prove_locking",