Re: [PATCH v2] sched/core: Don't mix isolcpus and housekeeping CPUs

From: Mel Gorman
Date: Wed Oct 24 2018 - 07:21:59 EST


On Wed, Oct 24, 2018 at 04:11:24PM +0530, Srikar Dronamraju wrote:
> * Peter Zijlstra <peterz@xxxxxxxxxxxxx> [2018-10-24 12:15:08]:
>
> > On Wed, Oct 24, 2018 at 03:16:46PM +0530, Srikar Dronamraju wrote:
> > > * Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx> [2018-10-24 09:56:36]:
> > >
> > > > On Wed, Oct 24, 2018 at 08:32:49AM +0530, Srikar Dronamraju wrote:
> > > > It would certainly be a bit odd because the
> > > > application is asking for some protection but no guarantees are given
> > > > and the application is not made aware via an error code that there is a
> > > > problem. Asking the application to parse dmesg hoping to find the right
> > > > error message is going to be fragile.
> > >
> > > Its a actually a good question.
> > > What should we be doing if a mix of isolcpus and housekeeping (aka
> > > non-isolcpus) is given in the mask.
> > >
> > > Right now as you pointed, there is no easy way for the application to know
> > > which are the non-isolcpus to set its affinity. cpusets effective_cpus and
> > > cpus_allowed both will contain isolcpus too.
> >
> > The easy option is to not use isolcpus :-) It is a horrifically bad
> > interface.
>
> Agree, but thats something thats been exposed long time back.
> Do we have an option to remove that? Hopefully nobody is using it.
>

I occasionally see bugs asking questions about interference from the kernel
when isolcpus are in use. The last one was related to a timer interrupt
every HZ (not a mainline kernel) but still, it's some evidence that it
has users :(

--
Mel Gorman
SUSE Labs