Re: regression: unregister_netdev() unusably slow
From: Damien Wyart
Date: Mon May 25 2009 - 04:20:20 EST
* Eric Dumazet <dada1@xxxxxxxxxxxxx> [2009-05-25 07:22]:
> Time to include Paul and lkml in the discussion, and find a better
> solution than one provided in February.
> > bf51935f3e988e0ed6f34b55593e5912f990750a is first bad commit
> > commit bf51935f3e988e0ed6f34b55593e5912f990750a
> > Author: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
> > Date: Tue Feb 17 06:01:30 2009 -0800
> > x86, rcu: fix strange load average and ksoftirqd behavior
> > Damien Wyart reported high ksoftirqd CPU usage (20%) on an
> > otherwise idle system.
> > The function-graph trace Damien provided:
> > ...
> > diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
> > index a546f55..bd4da2a 100644
> > --- a/arch/x86/kernel/process_32.c
> > +++ b/arch/x86/kernel/process_32.c
> > @@ -104,9 +104,6 @@ void cpu_idle(void)
> > check_pgt_cache();
> > rmb();
> > - if (rcu_pending(cpu))
> > - rcu_check_callbacks(cpu, 0);
> > -
> > if (cpu_is_offline(cpu))
> > play_dead();
> I wonder if the real root of the problem was not discovered in the meantime,
> by commit 64ca5ab913f1594ef316556e65f5eae63ff50cee
> rcu: increment quiescent state counter in ksoftirqd()
> Maybe this commit solved Damien Wyart problem as well, and we can revert
> commit bf51935f3e988e0ed6f34b55593e5912f990750a ?
Ran some tests on 2.6.30-rc7 with bf51935f reverted, and I am still
seeing the problems I originally reported back in February, so I guess
64ca5ab9 is not enough to fully solve all the issues... Note that I am
using CONFIG_TREE_RCU=y (was already true in my February reports).
Feel free to ask if more testing is needed.
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/