@@ -21,6 +21,7 @@ Scheduler
sched-rt-group
sched-stats
sched-debug
+ sched-qos
text_files
new file mode 100644
@@ -0,0 +1,44 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=============
+Scheduler QoS
+=============
+
+1. Introduction
+===============
+
+Different workloads have different scheduling requirements to operate
+optimally. The same applies to tasks within the same workload.
+
+To enable smarter usage of system resources and to cater for the conflicting
+demands of various tasks, Scheduler QoS provides a mechanism to provide more
+information about those demands so that scheduler can do best-effort to
+honour them.
+
+ @sched_qos_type what QoS hint to apply
+ @sched_qos_value value of the QoS hint
+ @sched_qos_cookie magic cookie to tag a group of tasks for which the QoS
+ applies. If 0, the hint will apply globally system
+ wide. If not 0, the hint will be relative to tasks that
+ has the same cookie value only.
+
+QoS hints are set once and not inherited by children by design. The
+rationale is that each task has its individual characteristics and it is
+encouraged to describe each of these separately. Also since system resources
+are finite, there's a limit to what can be done to honour these requests
+before reaching a tipping point where there are too many requests for
+a particular QoS that is impossible to service for all of them at once and
+some will start to lose out. For example if 10 tasks require better wake
+up latencies on a 4 CPUs SMP system, then if they all wake up at once, only
+4 can perceive the hint honoured and the rest will have to wait. Inheritance
+can lead these 10 to become a 100 or a 1000 more easily, and then the QoS
+hint will lose its meaning and effectiveness rapidly. The chances of 10
+tasks waking up at the same time is lower than a 100 and lower than a 1000.
+
+To set multiple QoS hints, a syscall is required for each. This is a
+trade-off to reduce the churn on extending the interface as the hope for
+this to evolve as workloads and hardware get more sophisticated and the
+need for extension will arise; and when this happen the task should be
+simpler to add the kernel extension and allow userspace to use readily by
+setting the newly added flag without having to update the whole of
+sched_attr.
@@ -102,6 +102,9 @@ struct clone_args {
__aligned_u64 set_tid_size;
__aligned_u64 cgroup;
};
+
+enum sched_qos_type {
+};
#endif
#define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */
@@ -132,6 +135,7 @@ struct clone_args {
#define SCHED_FLAG_KEEP_PARAMS 0x10
#define SCHED_FLAG_UTIL_CLAMP_MIN 0x20
#define SCHED_FLAG_UTIL_CLAMP_MAX 0x40
+#define SCHED_FLAG_QOS 0x80
#define SCHED_FLAG_KEEP_ALL (SCHED_FLAG_KEEP_POLICY | \
SCHED_FLAG_KEEP_PARAMS)
@@ -94,6 +94,48 @@
* scheduled on a CPU with no more capacity than the specified value.
*
* A task utilization boundary can be reset by setting the attribute to -1.
+ *
+ * Scheduler QoS
+ * =============
+ *
+ * Different workloads have different scheduling requirements to operate
+ * optimally. The same applies to tasks within the same workload.
+ *
+ * To enable smarter usage of system resources and to cater for the conflicting
+ * demands of various tasks, Scheduler QoS provides a mechanism to provide more
+ * information about those demands so that scheduler can do best-effort to
+ * honour them.
+ *
+ * @sched_qos_type what QoS hint to apply
+ * @sched_qos_value value of the QoS hint
+ * @sched_qos_cookie magic cookie to tag a group of tasks for which the QoS
+ * applies. If 0, the hint will apply globally system
+ * wide. If not 0, the hint will be relative to tasks that
+ * has the same cookie value only.
+ *
+ * QoS hints are set once and not inherited by children by design. The
+ * rationale is that each task has its individual characteristics and it is
+ * encouraged to describe each of these separately. Also since system resources
+ * are finite, there's a limit to what can be done to honour these requests
+ * before reaching a tipping point where there are too many requests for
+ * a particular QoS that is impossible to service for all of them at once and
+ * some will start to lose out. For example if 10 tasks require better wake
+ * up latencies on a 4 CPUs SMP system, then if they all wake up at once, only
+ * 4 can perceive the hint honoured and the rest will have to wait. Inheritance
+ * can lead these 10 to become a 100 or a 1000 more easily, and then the QoS
+ * hint will lose its meaning and effectiveness rapidly. The chances of 10
+ * tasks waking up at the same time is lower than a 100 and lower than a 1000.
+ *
+ * To set multiple QoS hints, a syscall is required for each. This is a
+ * trade-off to reduce the churn on extending the interface as the hope for
+ * this to evolve as workloads and hardware get more sophisticated and the
+ * need for extension will arise; and when this happen the task should be
+ * simpler to add the kernel extension and allow userspace to use readily by
+ * setting the newly added flag without having to update the whole of
+ * sched_attr.
+ *
+ * Details about the available QoS hints can be found in:
+ * Documentation/scheduler/sched-qos.rst
*/
struct sched_attr {
__u32 size;
@@ -116,6 +158,10 @@ struct sched_attr {
__u32 sched_util_min;
__u32 sched_util_max;
+ __u32 sched_qos_type;
+ __s64 sched_qos_value;
+ __u32 sched_qos_cookie;
+
};
#endif /* _UAPI_LINUX_SCHED_TYPES_H */
@@ -668,6 +668,9 @@ int __sched_setscheduler(struct task_struct *p,
return retval;
}
+ if (attr->sched_flags & SCHED_FLAG_QOS)
+ return -EOPNOTSUPP;
+
/*
* SCHED_DEADLINE bandwidth accounting relies on stable cpusets
* information.
@@ -102,6 +102,9 @@ struct clone_args {
__aligned_u64 set_tid_size;
__aligned_u64 cgroup;
};
+
+enum sched_qos_type {
+};
#endif
#define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */
@@ -132,6 +135,7 @@ struct clone_args {
#define SCHED_FLAG_KEEP_PARAMS 0x10
#define SCHED_FLAG_UTIL_CLAMP_MIN 0x20
#define SCHED_FLAG_UTIL_CLAMP_MAX 0x40
+#define SCHED_FLAG_QOS 0x80
#define SCHED_FLAG_KEEP_ALL (SCHED_FLAG_KEEP_POLICY | \
SCHED_FLAG_KEEP_PARAMS)
The need to describe the conflicting demand of various workloads hasn't been higher. Both hardware and software have moved rapidly in the past decade and system usage is more diverse and the number of workloads expected to run on the same machine whether on Mobile or Server markets has created a big dilemma on how to better manage those requirements. The problem is that we lack mechanisms to allow these workloads to describe what they need, and then allow kernel to do best efforts to manage those demands based on the hardware it is running on transparently and current system state. Example of conflicting requirements that come across frequently: 1. Improve wake up latency for SCHED_OTHER. Many tasks end up using SCHED_FIFO/SCHED_RR to compensate for this shortcoming. RT tasks lack power management and fairness and can be hard and error prone to use correctly and portably. 2. Prefer spreading vs prefer packing on wake up for a group of tasks. Geekbench-like workloads would benefit from parallelising on different CPUs. hackbench type of workloads can benefit from waking on up same CPUs or a CPU that is closer in the cache hierarchy. 3. Nice values for SCHED_OTHER are system wide and require privileges. Many workloads would like a way to set relative nice value so they can preempt each others, but not be impact or be impacted by other tasks belong to different workloads on the system. 4. Provide a way to tag some tasks as 'background' to keep them out of the way. SCHED_IDLE is too strong for some of these tasks but yet they can be computationally heavy. Example tasks are garbage collectors. Their work is both important and not important. 5. Provide a way to improve DVFS/upmigration rampup time for specific tasks that are bursty in nature and highly interactive. Whether any of these use cases warrants an additional QoS hint is something to be discussed individually. But the main point is to introduce an interface that can be extendable to cater for potentially those requirements and more. rampup_multiplier to improve DVFS/upmigration for bursty tasks will be the first user in later patch. It is desired to have apps (and benchmarks!) directly use this interface for optimal perf/watt. But in the absence of such support, it should be possible to write a userspace daemon to monitor workloads and apply these QoS hints on apps behalf based on analysis done by anyone interested in improving the performance of those workloads. Signed-off-by: Qais Yousef <qyousef@layalina.io> --- Documentation/scheduler/index.rst | 1 + Documentation/scheduler/sched-qos.rst | 44 ++++++++++++++++++ include/uapi/linux/sched.h | 4 ++ include/uapi/linux/sched/types.h | 46 +++++++++++++++++++ kernel/sched/syscalls.c | 3 ++ .../trace/beauty/include/uapi/linux/sched.h | 4 ++ 6 files changed, 102 insertions(+) create mode 100644 Documentation/scheduler/sched-qos.rst