lkml.org 
[lkml]   [2019]   [Nov]   [7]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH v2] sched: rt: Make RT capacity aware
Hi Steve

On 10/28/19 14:01, Steven Rostedt wrote:
> On Mon, 28 Oct 2019 15:37:49 +0100
> Peter Zijlstra <peterz@infradead.org> wrote:
>
> > On Wed, Oct 09, 2019 at 11:46:11AM +0100, Qais Yousef wrote:
> > > Capacity Awareness refers to the fact that on heterogeneous systems
> > > (like Arm big.LITTLE), the capacity of the CPUs is not uniform, hence
> > > when placing tasks we need to be aware of this difference of CPU
> > > capacities.
> > >
> > > In such scenarios we want to ensure that the selected CPU has enough
> > > capacity to meet the requirement of the running task. Enough capacity
> > > means here that capacity_orig_of(cpu) >= task.requirement.
> > >
> > > The definition of task.requirement is dependent on the scheduling class.
> > >
> > > For CFS, utilization is used to select a CPU that has >= capacity value
> > > than the cfs_task.util.
> > >
> > > capacity_orig_of(cpu) >= cfs_task.util
> > >
> > > DL isn't capacity aware at the moment but can make use of the bandwidth
> > > reservation to implement that in a similar manner CFS uses utilization.
> > > The following patchset implements that:
> > >
> > > https://lore.kernel.org/lkml/20190506044836.2914-1-luca.abeni@santannapisa.it/
> > >
> > > capacity_orig_of(cpu)/SCHED_CAPACITY >= dl_deadline/dl_runtime
> > >
> > > For RT we don't have a per task utilization signal and we lack any
> > > information in general about what performance requirement the RT task
> > > needs. But with the introduction of uclamp, RT tasks can now control
> > > that by setting uclamp_min to guarantee a minimum performance point.
> > >
> > > ATM the uclamp value are only used for frequency selection; but on
> > > heterogeneous systems this is not enough and we need to ensure that the
> > > capacity of the CPU is >= uclamp_min. Which is what implemented here.
> > >
> > > capacity_orig_of(cpu) >= rt_task.uclamp_min
> > >
> > > Note that by default uclamp.min is 1024, which means that RT tasks will
> > > always be biased towards the big CPUs, which make for a better more
> > > predictable behavior for the default case.
> > >
> > > Must stress that the bias acts as a hint rather than a definite
> > > placement strategy. For example, if all big cores are busy executing
> > > other RT tasks we can't guarantee that a new RT task will be placed
> > > there.
> > >
> > > On non-heterogeneous systems the original behavior of RT should be
> > > retained. Similarly if uclamp is not selected in the config.
> > >
> > > Signed-off-by: Qais Yousef <qais.yousef@arm.com>
> >
> > Works for me; Steve you OK with this?
>
> Nothing against it, but I want to take a deeper look before we accept
> it. Are you OK in waiting a week? I'm currently at Open Source Summit
> and still have two more talks to write (giving them Thursday). I wont
> have time to look till next week.

A gentle reminder if you can spare some time to look at this. It'd be nice if
it can make it to the 5.5 merge window if there are no major concerns about it.

Thanks!

--
Qais Yousef

\
 
 \ /
  Last update: 2019-11-07 10:16    [W:0.069 / U:4.656 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site