lkml.org 
[lkml]   [2011]   [May]   [25]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    Date
    From
    SubjectRe: [tip:core/rcu] Revert "rcu: Decrease memory-barrier usage based on semi-formal proof"
    On Wed, May 25, 2011 at 09:27:42AM +0200, Ingo Molnar wrote:
    >
    > * Paul E. McKenney <paulmck@linux.vnet.ibm.com> wrote:
    >
    > > On Tue, May 24, 2011 at 05:10:11PM -0700, Yinghai Lu wrote:
    > > > On 05/24/2011 02:23 PM, Yinghai Lu wrote:
    > > > > On 05/23/2011 06:35 PM, Paul E. McKenney wrote:
    > > > >> On Mon, May 23, 2011 at 06:26:23PM -0700, Yinghai Lu wrote:
    > > > >>> On 05/23/2011 06:18 PM, Paul E. McKenney wrote:
    > > > >>>
    > > > >>>> OK, so it looks like I need to get this out of the way in order to track
    > > > >>>> down the delays. Or does reverting PeterZ's patch get you a stable
    > > > >>>> system, but with the longish delays in memory_dev_init()? If the latter,
    > > > >>>> it might be more productive to handle the two problems separately.
    > > > >>>>
    > > > >>>> For whatever it is worth, I do see about 5% increase in grace-period
    > > > >>>> duration when switching to kthreads. This is acceptable -- your
    > > > >>>> 30x increase clearly is completely unacceptable and must be fixed.
    > > > >>>> Other than that, the main thing that affects grace period duration is
    > > > >>>> the setting of CONFIG_HZ -- the smaller the HZ value, the longer the
    > > > >>>> grace-period duration.
    > > > >>>
    > > > >>> for my 1024g system when memory hotadd is enabled in kernel config:
    > > > >>> 1. current linus tree + tip tree: memory_dev_init will take about 100s.
    > > > >>> 2. current linus tree + tip tree + your tree - Peterz patch:
    > > > >>> a. on fedora 14 gcc: will cost about 4s: like old times
    > > > >>> b. on opensuse 11.3 gcc: will cost about 10s.
    > > > >>
    > > > >> So some patch in my tree that is not yet in tip makes things better?
    > > > >>
    > > > >> If so, could you please see which one? Maybe that would give me a hint
    > > > >> that could make things better on opensuse 11.3 as well.
    > > > >
    > > > > today's tip:
    > > > >
    > > > > [ 31.795597] cpu_dev_init done
    > > > > [ 40.930202] memory_dev_init done
    > > > >
    > > >
    > > > another boot from tip got:
    > > >
    > > > [ 35.211927] cpu_dev_init done
    > > > [ 136.053698] memory_dev_init done
    > > >
    > > > wonder if you can have clean revert for
    > > >
    > > > commit a26ac2455ffcf3be5c6ef92bc6df7182700f2114
    > > > > Author: Paul E. McKenney <paul.mckenney@linaro.org>
    > > > > Date: Wed Jan 12 14:10:23 2011 -0800
    > > > >
    > > > > rcu: move TREE_RCU from softirq to kthread
    > > > >
    > > > > If RCU priority boosting is to be meaningful, callback invocation must
    > > > > be boosted in addition to preempted RCU readers. Otherwise, in presence
    > > > > of CPU real-time threads, the grace period ends, but the callbacks don't
    > > > > get invoked. If the callbacks don't get invoked, the associated memory
    > > > > doesn't get freed, so the system is still subject to OOM.
    > > > >
    > > > > But it is not reasonable to priority-boost RCU_SOFTIRQ, so this commit
    > > > > moves the callback invocations to a kthread, which can be boosted easily.
    > > > >
    > > > > Also add comments and properly synchronized all accesses to
    > > > > rcu_cpu_kthread_task, as suggested by Lai Jiangshan.
    > > > >
    > > > > Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
    > > > > Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
    > > > > Reviewed-by: Josh Triplett <josh@joshtriplett.org>
    > >
    > > There is a new branch yinghai.2011.05.24a on:
    > >
    > > git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-2.6-rcu.git
    > >
    > > Or will be as soon as kernel.org updates its mirrors.
    > >
    > > I am not sure I could call this "clean", but it does revert that commit
    > > and 11 of the subsequent commits that depend on it. It does build,
    > > and I will test it once my currently running tests complete.
    >
    > Given that this is about a 1-2 minute delays with 1 *terabyte* of RAM, the per
    > gigabyte delay is like 60-120 msecs, right?
    >
    > So it's not a regression we are absolutely forced to address via a quick
    > revert, debugging it would be nicer. There's something we don't understand and
    > that's arguably worse than having unresolved non-fatal bugs :-)

    And my attempted revert results in test failures in any case. :-(

    > We already fixed the worst problem via a revert, the semi-hang: so i don't
    > think there's pressure to do other reverts - other than for diagnostic
    > purposes, of course.

    Given that I have to debug in any case, I am happier debugging in the
    forward direction rather than in the backwards direction. ;-)

    Thanx, Paul


    \
     
     \ /
      Last update: 2011-05-25 22:49    [W:3.974 / U:0.008 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site