|| ||"Paul E. McKenney" <paulmck-AT-linux.vnet.ibm.com> |
|| ||Peter Zijlstra <peterz-AT-infradead.org> |
|| ||Re: [PATCH RFC tip/core/rcu 4/6] rcu: Clarify help text for
|| ||Thu, 26 Apr 2012 10:28:59 -0700|
|| ||linux-kernel-AT-vger.kernel.org, mingo-AT-elte.hu, laijs-AT-cn.fujitsu.com,
niv-AT-us.ibm.com, tglx-AT-linutronix.de, rostedt-AT-goodmis.org,
eric.dumazet-AT-gmail.com, darren-AT-dvhart.com, fweisbec-AT-gmail.com,
patches-AT-linaro.org, "Paul E. McKenney" <paul.mckenney-AT-linaro.org>|
|| ||Article, Thread
On Thu, Apr 26, 2012 at 02:46:31PM +0200, Peter Zijlstra wrote:
> On Mon, 2012-04-23 at 09:42 -0700, Paul E. McKenney wrote:
> > + This option specifies the real-time priority to which long-term
> > + preempted RCU readers are to be boosted. If you are working
> > + with a real-time application that has one or more CPU-bound
> > + threads running at a real-time priority level,
> Then your application is broken ;-) the kernel is known to mis-behave
> under these circumstances since it doesn't get to run house-keeping
> tasks. RCU is just one of these and elevating it doesn't make it work.
As you say, CPU-bound RT tasks have a number of problems, and RCU is but
one of them. That said, an RCU-induced memory-exhaustion system hang
is an extremely unfriendly diagnostic message, and use of RCU priority
boosting allows them a better debugging environment.
> > you should set
> > + RCU_BOOST_PRIO to a priority higher then the highest-priority
> > + real-time CPU-bound thread. The default RCU_BOOST_PRIO value
> > + of 1 is appropriate in the common case, which is real-time
> > + applications that do not have any CPU-bound threads.
> Alternatively, 1 is the worst possible choice forcing people to consider
> the issue.
You say that as if forcing people to consider the issue was a
bad thing. ;-)
> > + Some real-time applications might not have a single real-time
> > + thread that saturates a given CPU, but instead might have
> > + multiple real-time threads that, taken together, fully utilize
> > + that CPU. In this case, you should set RCU_BOOST_PRIO to
> > + a priority higher than the lowest-priority thread that is
> > + conspiring to prevent the CPU from running any non-real-time
> > + tasks. For example, if one thread at priority 10 and another
> > + thread at priority 5 are between themselves fully consuming
> > + the CPU time on a given CPU, then RCU_BOOST_PRIO should be
> > + set to priority 6 or higher.
> I'd call this misleading, who's to say that preempting the 5 would yield
> enough time to complete the RCU work?
Yep, hence the "or higher".
> This all gets us back to the fun question of RCU delayed bandwidth
> budgeting.. ideally every 'task' that does call_rcu() should donate some
> of its budget towards the thread running the callback.
There was an academic interested in that topic a few years ago, but
I don't believe anything came of it. An interesting approach would
be to do EDF scheduling on the callbacks themselves, but having a
separate thread for each callback sounds like overkill.
> Anyway, I'd argue both the old and new description are bonkers.
Indeed, my goal was "less bonkers" rather than "not bonkers". A
"not bonkers" description remains a long-term aspiration rather than
a short-term goal for the moment. I can only hope that the timeframe
is shorter than it was for RCU back in the early 1990s. ;-)
to post comments)