[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20160811145733.GC4214@lerouge>
Date: Thu, 11 Aug 2016 16:57:35 +0200
From: Frederic Weisbecker <fweisbec@...il.com>
To: Peter Zijlstra <peterz@...radead.org>
Cc: Wanpeng Li <kernellwp@...il.com>, linux-kernel@...r.kernel.org,
kvm@...r.kernel.org, Wanpeng Li <wanpeng.li@...mail.com>,
Ingo Molnar <mingo@...hat.com>,
Juri Lelli <juri.lelli@....com>,
Luca Abeni <luca.abeni@...tn.it>
Subject: Re: [PATCH] sched: fix the intention to re-evalute tick dependency
for offline cpu
On Thu, Aug 11, 2016 at 04:45:11PM +0200, Peter Zijlstra wrote:
> On Thu, Aug 04, 2016 at 05:51:20PM +0800, Wanpeng Li wrote:
> > From: Wanpeng Li <wanpeng.li@...mail.com>
> >
> > The dl task will be replenished after dl task timer fire and start a new
> > period. It will be enqueued and to re-evaluate its dependency on the tick
> > in order to restart it. However, if cpu is hot-unplug, irq_work_queue will
> > splash since the target cpu is offline.
> >
> > As a result:
> >
> > WARNING: CPU: 2 PID: 0 at kernel/irq_work.c:69 irq_work_queue_on+0xad/0xe0
> > Call Trace:
> > dump_stack+0x99/0xd0
> > __warn+0xd1/0xf0
> > warn_slowpath_null+0x1d/0x20
> > irq_work_queue_on+0xad/0xe0
> > tick_nohz_full_kick_cpu+0x44/0x50
> > tick_nohz_dep_set_cpu+0x74/0xb0
> > enqueue_task_dl+0x226/0x480
> > activate_task+0x5c/0xa0
> > dl_task_timer+0x19b/0x2c0
> > ? push_dl_task.part.31+0x190/0x190
>
> Hurm, so this is after hot-unplug succeeded. We get a timer (which is
> also already migrated), but we enqueue the dl task on the offline CPU,
> because we need to do replenish because start_dl_timer() -- see the
> comment in dl_task_timer() at #ifdef CONFIG_SMP.
>
> Then, once we've enqueued the task on the offline cpu, do we migrate it.
>
> Bit icky that, but I don't immediately see a better way.
>
> And I think you're right in that we don't leak the nohz state, the
> migration, which we do immediately after this, takes care of that.
Are you sure there is no way the hotplug can fail after this stage?
I see this is at the end of the CPUHP_AP callbacks. Nothing else can
fail afterward?
If so then yes we are ok as migration takes care of the tick dependency.
Thanks.
Powered by blists - more mailing lists