

Real-Time group scheduling.

The problem space:

In order to schedule multiple groups of realtime tasks each group must
be assigned a fixed portion of the CPU time available. Without a minimum
guarantee a realtime group can obviously fall short. A fuzzy upper limit
is of no use since it cannot be relied upon. Which leaves us with just
the single fixed portion.

CPU time is divided by means of specifying how much time can be spent
running in a given period. Say a frame fixed realtime renderer must
deliver 25 frames a second, which yields a period of 0.04s. Now say
it will also have to play some music and respond to input, leaving it
with around 80% for the graphics. We can then give this group a runtime
of 0.8 * 0.04s = 0.032s.

This way the graphics group will have a 0.04s period with a 0.032s runtime
limit.

Now if the audio thread needs to refill the DMA buffer every 0.005s, but
needs only about 3% CPU time to do so, it can do with a 0.03 * 0.005s
= 0.00015s.


The Interface:

system wide:

/proc/sys/kernel/sched_rt_period_ms
/proc/sys/kernel/sched_rt_runtime_us

CONFIG_FAIR_USER_SCHED

/sys/kernel/uids/<uid>/cpu_rt_runtime_us

or

CONFIG_FAIR_CGROUP_SCHED

/cgroup/<cgroup>/cpu.rt_runtime_us

[ time is specified in us because the interface is s32; this gives an
  operating range of ~35m to 1us ]

The period takes values in [ 1, INT_MAX ], runtime in [ -1, INT_MAX - 1 ].

A runtime of -1 specifies runtime == period, ie. no limit.

New groups get the period from /proc/sys/kernel/sched_rt_period_us and
a runtime of 0.

Settings are constrained to:

   \Sum_{i} runtime_{i} / global_period <= global_runtime / global_period

in order to keep the configuration schedulable.