Re: iowait boost is broken

[Qais Yousef]

On 06/09/21 09:50, Quentin Perret wrote:
> On Tuesday 08 Jun 2021 at 19:46:54 (+0200), Peter Zijlstra wrote:
> > On Mon, Jun 07, 2021 at 08:10:32PM +0100, Beata Michalska wrote:
> > > So back to the expectations.
> > > The main problem, as I see it, is what do we actually want to achieve with
> > > the I/O boosting? Is it supposed to compensate the time lost while waiting
> > > for the I/O request to be completed or is is supposed to optimize the rate
> > > at which I/O requests are being made. 
> > 
> > The latter, you want to increase the race of submission.
> > 
> > > Do we want to boost I/O bound tasks by
> > > default, no limits applied  or should we care about balancing performance
> > > vs power ? And unless those expectations are clearly stated, we might not
> > > get too far with any changes, really.
> > 
> > You want to not increase power beyond what is needed to match the rate
> > of processing I suppose.
> 
> Note that in some cases we also don't care about throughput, and would
> prefer to keep the frequency for some unimportant IO bound tasks (e.g.
> background logging deamons and such). Uclamp.max indicates this to some
> extent.

In theory, one can have a user space daemon that monitors IO (via BPF?) and
auto boost via uclamp. You can have allow/disallow list per-app too to setup
the limits.

So I say rm -rf iowait_boost and let's make it a user space problem :)

/me runs

--
Qais Yousef