Re: [RFC PATCH 1/9] sched,cgroup: Add interface for latency-nice

[Valentin Schneider <valentin.schneider@arm.com>]

On 05/09/2019 12:18, Patrick Bellasi wrote:
>> There's a few things wrong there; I really feel that if we call it nice,
>> it should be like nice. Otherwise we should call it latency-bias and not
>> have the association with nice to confuse people.
>>
>> Secondly; the default should be in the middle of the range. Naturally
>> this would be a signed range like nice [-(x+1),x] for some x. but if you
>> want [0,1024], then the default really should be 512, but personally I
>> like 0 better as a default, in which case we need negative numbers.
>>
>> This is important because we want to be able to bias towards less
>> importance to (tail) latency as well as more importantance to (tail)
>> latency.
>>
>> Specifically, Oracle wants to sacrifice (some) latency for throughput.
>> Facebook OTOH seems to want to sacrifice (some) throughput for latency.
> 
> Right, we have this dualism to deal with and current mainline behaviour
> is somehow in the middle.
> 
> BTW, the FB requirement is the same we have in Android.
> We want some CFS tasks to have very small latency and a low chance
> to be preempted by the wake-up of less-important "background" tasks.
> 
> I'm not totally against the usage of a signed range, but I'm thinking
> that since we are introducing a new (non POSIX) concept we can get the
> chance to make it more human friendly.
> 
> Give the two extremes above, would not be much simpler and intuitive to
> have 0 implementing the FB/Android (no latency) case and 1024 the
> (max latency) Oracle case?
> 

For something like latency-<whatever>, I don't see the point of having
such a wide range. The nice range is probably more than enough - and before
even bothering about the range, we should probably agree on what the range
should represent.

If it's niceness, I read it as: positive latency-nice value means we're
nice to latency, means we reduce it. So the further up you go, the more you
restrict your wakeup scan. I think it's quite easy to map that into the
code: current behaviour at 0, with a decreasing scan mask size as we go
towards +19. I don't think anyone needs 512 steps to tune this.

I don't know what logic we'd follow for negative values though. Maybe
latency-nice -20 means always going through the slowpath, but what of the
intermediate values?

AFAICT this RFC only looks at wakeups, but I guess latency-nice can be
applied elsewhere (e.g. load-balance, something like task_hot() and its
use of sysctl_sched_migration_cost).

> Moreover, we will never match completely the nice semantic, give that
> a 1 nice unit has a proper math meaning, isn't something like 10% CPU
> usage change for each step?
> 
> For latency-nice instead we will likely base our biasing strategies on
> some predefined (maybe system-wide configurable) const thresholds.
> 
> Could changing the name to "latency-tolerance" break the tie by marking
> its difference wrt prior/nice levels? AFAIR, that was also the original
> proposal [1] by PaulT during the OSPM discussion.
> 
> Best,
> Patrick
> 
> [1] https://youtu.be/oz43thSFqmk?t=1302
>