[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <aPKSMxlGsKvxsCq8@gpd4>
Date: Fri, 17 Oct 2025 21:00:03 +0200
From: Andrea Righi <arighi@...dia.com>
To: Tejun Heo <tj@...nel.org>
Cc: Ingo Molnar <mingo@...hat.com>, Peter Zijlstra <peterz@...radead.org>,
Juri Lelli <juri.lelli@...hat.com>,
Vincent Guittot <vincent.guittot@...aro.org>,
Dietmar Eggemann <dietmar.eggemann@....com>,
Steven Rostedt <rostedt@...dmis.org>,
Ben Segall <bsegall@...gle.com>, Mel Gorman <mgorman@...e.de>,
Valentin Schneider <vschneid@...hat.com>,
Joel Fernandes <joelagnelf@...dia.com>,
David Vernet <void@...ifault.com>,
Changwoo Min <changwoo@...lia.com>, Shuah Khan <shuah@...nel.org>,
sched-ext@...ts.linux.dev, bpf@...r.kernel.org,
linux-kernel@...r.kernel.org,
Luigi De Matteis <ldematteis123@...il.com>
Subject: Re: [PATCH 06/14] sched_ext: Add a DL server for sched_ext tasks
On Fri, Oct 17, 2025 at 05:40:12AM -1000, Tejun Heo wrote:
> On Fri, Oct 17, 2025 at 11:25:53AM +0200, Andrea Righi wrote:
> > From: Joel Fernandes <joelagnelf@...dia.com>
> >
> > sched_ext currently suffers starvation due to RT. The same workload when
> > converted to EXT can get zero runtime if RT is 100% running, causing EXT
> > processes to stall. Fix it by adding a DL server for EXT.
> >
> > A kselftest is also provided later to verify:
> >
> > ./runner -t rt_stall
> > ===== START =====
> > TEST: rt_stall
> > DESCRIPTION: Verify that RT tasks cannot stall SCHED_EXT tasks
> > OUTPUT:
> > TAP version 13
> > 1..1
> > ok 1 PASS: CFS task got more than 4.00% of runtime
> >
> > [ arighi: drop ->balance() now that pick_task() has an rf argument ]
> >
> > Cc: Luigi De Matteis <ldematteis123@...il.com>
> > Co-developed-by: Andrea Righi <arighi@...dia.com>
> > Signed-off-by: Andrea Righi <arighi@...dia.com>
> > Signed-off-by: Joel Fernandes <joelagnelf@...dia.com>
>
> I don't see anything preventing this to come after patch 11 so that all
> sched_ext changes are at the end. Am I correct? That'd make applying the
> patches easier. All the debug and deadline changes can be applied to
> sched/core and I can pull that and apply sched_ext changes on top.
Oh yes, we can definitely move this one. I'll reorder the patches.
Thanks,
-Andrea
Powered by blists - more mailing lists