[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20180523031003.GA60111@joelaf.mtv.corp.google.com>
Date: Tue, 22 May 2018 20:10:03 -0700
From: Joel Fernandes <joel@...lfernandes.org>
To: Steven Rostedt <rostedt@...dmis.org>
Cc: "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>,
byungchul.park@....com, mathieu.desnoyers@...icios.com,
Josh Triplett <josh@...htriplett.org>,
Lai Jiangshan <jiangshanlai@...il.com>,
linux-kernel@...r.kernel.org, kernel-team@...roid.com
Subject: Re: Tasks RCU vs Preempt RCU
On Tue, May 22, 2018 at 08:38:32AM -0400, Steven Rostedt wrote:
> On Mon, 21 May 2018 21:54:14 -0700
> Joel Fernandes <joel@...lfernandes.org> wrote:
>
>
> > Yes, lets brain storm this if you like. One way I was thinking if we can
> > manually check every CPU and see what state its in (usermode, kernel, idle
> > etc) using an IPI mechanism. Once all CPUs have been seen to be in usermode,
> > or idle atleast once - then we are done. You have probably already thought
>
> Nope, it has nothing to do with CPUs, it really has to do with tasks.
>
> CPU0
> ----
> task 1: (pinned to CPU 0)
> call func_tracer_trampoline
> [on trampoline]
> [timer tick, schedule ]
>
> task 2: (higher priority, also pinned to CPU 0)
> goes to user space
> [ Runs for along time ]
>
> We cannot free the trampoline until task 2 releases the CPU and lets
> task 1 run again to get off the CPU.
Right. I totally missed that. Ofcourse, its not sufficient to see if a CPU is
in usermode. :(
> > about this so feel free to say why its not a good idea, but to me there are 3
> > places that a tasks quiescent state is recorded: during the timer tick,
> > during task sleep and during rcu_note_voluntary_context_switch in
> > cond_resched_rcu_qs. Of these, I feel only the cond_resched_rcu_qs case isn't
> > trackable with IPI mechanism which may make the detection a bit slower, but
> > tasks-RCU in mainline is slow right now anyway (~ 1 second delay if any task
> > was held).
>
>
> The way I was originally going to handle this was with a per task
> counter, where it can be incremented at certain points via tracepoints.
>
> Thus my synchronize tasks, would have connected to a bunch of
> tracepoints at known quiescent states that would increment the counter,
> and then check each task until they all pass a certain point, or are in
> a quiescent state (userspace or idle). But this would be doing much of
> what RCU does today, and that is why we decided to hook with the RCU
> infrastructure.
>
> I have to ask, what's your motivation for getting rid of RCU tasks?
Again, my motivation was just to see if we could use RCU-preempt. Linus was
talking about unifying RCU variants/API better. I believe Paul is well on top of
that task and I have been helping as I could with his recent series for that.
Since RCU-preempt doesn't suit this job, looks like we have keep RCU tasks
around. That said I sent you a patch to speed up RCU-tasks a bit, could you a
take a look? Paul was asking for your input: https://lkml.org/lkml/2018/5/20/263
Welcome back from your vacation, hope it was fun!
thanks,
- Joel
Powered by blists - more mailing lists