lkml.org 
[lkml]   [2009]   [Feb]   [10]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [ltt-dev] [RFC git tree] Userspace RCU (urcu) for Linux (repost)
On Tue, Feb 10, 2009 at 02:21:15PM -0800, Paul E. McKenney wrote:
> On Tue, Feb 10, 2009 at 04:28:33PM -0500, Mathieu Desnoyers wrote:
> > * Paul E. McKenney (paulmck@linux.vnet.ibm.com) wrote:
> > > On Tue, Feb 10, 2009 at 02:17:31PM -0500, Mathieu Desnoyers wrote:
> > > > * Paul E. McKenney (paulmck@linux.vnet.ibm.com) wrote:
> > > > > On Mon, Feb 09, 2009 at 02:03:17AM -0500, Mathieu Desnoyers wrote:
> > > > >
> > > > > [ . . . ]
> > > > >
> > > > > > I just added modified rcutorture.h and api.h from your git tree
> > > > > > specifically for an urcutorture program to the repository. Some results :
> > > > > >
> > > > > > 8-way x86_64
> > > > > > E5405 @2 GHZ
> > > > > >
> > > > > > ./urcutorture 8 perf
> > > > > > n_reads: 1937650000 n_updates: 3 nreaders: 8 nupdaters: 1 duration: 1
> > > > > > ns/read: 4.12871 ns/update: 3.33333e+08
> > > > > >
> > > > > > ./urcutorture 8 uperf
> > > > > > n_reads: 0 n_updates: 4413892 nreaders: 0 nupdaters: 8 duration: 1
> > > > > > ns/read: nan ns/update: 1812.46
> > > > > >
> > > > > > n_reads: 98844204 n_updates: 10 n_mberror: 0
> > > > > > rcu_stress_count: 98844171 33 0 0 0 0 0 0 0 0 0
> > > > > >
> > > > > > However, I've tried removing the second switch_qparity() call, and the
> > > > > > rcutorture test did not detect anything wrong. I also did a variation
> > > > > > which calls the "sched_yield" version of the urcu, "urcutorture-yield".
> > > > >
> > > > > My confusion -- I was testing my old approach where the memory barriers
> > > > > are in rcu_read_lock() and rcu_read_unlock(). To force the failures in
> > > > > your signal-handler-memory-barrier approach, I suspect that you are
> > > > > going to need a bigger hammer. In this case, one such bigger hammer
> > > > > would be:
> > > > >
> > > > > o Just before exit from the signal handler, do a
> > > > > pthread_cond_wait() under a pthread_mutex().
> > > > >
> > > > > o In force_mb_all_threads(), refrain from sending a signal to self.
> > > > >
> > > > > Then it should be safe in force_mb_all_threads() to do a
> > > > > pthread_cond_broadcast() under the same pthread_mutex().
> > > > >
> > > > > This should raise the probability of seeing the failure in the case
> > > > > where there is a single switch_qparity().
> > > > >
> > > >
> > > > I just did a mb() version of the urcu :
> > > >
> > > > (uncomment CFLAGS=+-DDEBUG_FULL_MB in the Makefile)
> > > >
> > > > Time per read : 48.4086 cycles
> > > > (about 6-7 times slower, as expected)
> > > >
> > > > This will be useful especially to increase the chance to trigger races.
> > > >
> > > > I tried removing the second parity switch from the writer. The rcu
> > > > torture test did not find the problem yet (maybe I am not using the
> > > > correct parameters ? It does not run for more than 5 seconds).
> > > >
> > > > So I added a "-n" option to test_urcu, so it can make the usleep(1)
> > > > between the writes optional. I also changed the yield for a usleep with
> > > > random delay. I also now use a circular buffer rather than malloc so we
> > > > are sure the memory is not quickly reused by the writer and stays longer
> > > > in an invalid state.
> > > >
> > > > So what really make the problem appear quickly is to add a delay between
> > > > the rcu_dereference and the assertion on the data validity in thr_reader.
> > > >
> > > > It now appears after just a few seconds when running
> > > > ./test_urcu_yield 20 -r -n
> > > > Compiled with CFLAGS=+-DDEBUG_FULL_MB
> > > >
> > > > It seem to be much harder to trigger with the signal-based version. It's
> > > > expected, because the writer takes about 50 times longer to execute than
> > > > with the -DDEBUG_FULL_MB version.
> > > >
> > > > So I'll let the ./test_urcu_yield NN -r -n run for a while on the
> > > > correct version (with DEBUG_FULL_MB) and see what it gives.
> > >
> > > Hmmm... I had worse luck this time, took three 10-second tries to
> > > see a failure:
> > >
> > > paulmck@paulmck-laptop:~/paper/perfbook/CodeSamples/defer$ ./rcu_nest32 1 stress
> > > n_reads: 44682055 n_updates: 9609503 n_mberror: 0
> > > rcu_stress_count: 44679377 2678 0 0 0 0 0 0 0 0 0
> > > paulmck@paulmck-laptop:~/paper/perfbook/CodeSamples/defer$ !!
> > > ./rcu_nest32 1 stress
> > > n_reads: 42281884 n_updates: 9870129 n_mberror: 0
> > > rcu_stress_count: 42277756 4128 0 0 0 0 0 0 0 0 0
> > > paulmck@paulmck-laptop:~/paper/perfbook/CodeSamples/defer$ !!
> > > ./rcu_nest32 1 stress
> > > n_reads: 41384304 n_updates: 10040805 n_mberror: 0
> > > rcu_stress_count: 41380075 4228 1 0 0 0 0 0 0 0 0
> > > paulmck@paulmck-laptop:~/paper/perfbook/CodeSamples/defer$
> > >
> > > This is my prototype version, with read-side memory barriers, no
> > > signals, and without your initialization-value speedup.
> > >
> >
> > It would be interesting to re-sync our trees, or if you can point me to
> > a current version of your prototype, I could review it.
>
> Look at:
>
> CodeSamples/defer/rcu_nest32.[hc]
>
> In the git archive:
>
> git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/perfbook.git

And attached is an attempted Promela-based proof, along with a script
that runs it. It currently says that this version of RCU works. Not yet
sure whether to believe it. ;-)

It notes that lines 37 and 92 are unreached. 37 is unreached because
the Promela code currently doesn't exercise nested RCU read-side
critical sections, and 92 is unreached because there is an infinite
loop processing memory-barrier requests at the end of the reader code.

Thoughts?

Thanx, Paul
bit removed = 0;
bit free = 0;

#define RCU_GP_CTR_BIT (1 << 7)
#define RCU_GP_CTR_NEST_MASK (RCU_GP_CTR_BIT - 1)

bit need_mb = 0;
byte urcu_gp_ctr = 1;
byte urcu_active_readers = 0;

bit reader_progress[4];

proctype urcu_reader()
{
bit done = 0;
byte tmp;
byte tmp_removed;
byte tmp_free;

do
:: 1 ->
if
:: need_mb == 1 ->
need_mb = 0;
:: else -> break;
fi
od;
do
:: 1 ->
if
:: reader_progress[0] == 0 ->
tmp = urcu_active_readers;
if
:: (tmp & RCU_GP_CTR_NEST_MASK) == 0 ->
urcu_active_readers = urcu_gp_ctr;
:: else ->
urcu_active_readers = tmp + 1;
fi;
reader_progress[0] = 1;
:: reader_progress[1] == 0 ->
tmp_removed = removed;
reader_progress[1] = 1;
:: reader_progress[2] == 0 ->
tmp_free = free;
reader_progress[2] = 1;
:: ((reader_progress[0] == 1) && (reader_progress[3] == 0)) ->
urcu_active_readers = urcu_active_readers - 1;
:: else -> break;
fi;
atomic {
tmp = 0;
do
:: reader_progress[tmp] == 0 ->
tmp = tmp + 1;
break;
:: reader_progress[tmp] == 1 && tmp < 4 ->
tmp = tmp + 1;
:: tmp >= 4 ->
done = 1;
break;
od;
do
:: tmp < 4 && reader_progress[tmp] == 0 ->
tmp = tmp + 1;
:: tmp < 4 && reader_progress[tmp] == 1 ->
break;
:: tmp >= 4 ->
if
:: need_mb == 1 ->
need_mb = 0;
:: else -> skip;
fi;
done = 1;
break;
od

}
if
:: done == 1 -> break;
:: else -> skip;
fi
od;
do
:: 1 ->
if
:: need_mb == 1 ->
need_mb = 0;
:: else -> skip;
fi;
assert((free == 0) || (removed == 1));
od;
}

proctype urcu_updater()
{
removed = 1;
need_mb = 1;
do
:: need_mb == 1 -> skip;
:: need_mb == 0 -> break;
od;
urcu_gp_ctr = urcu_gp_ctr + RCU_GP_CTR_BIT;
do
:: 1 ->
if
:: (urcu_active_readers & RCU_GP_CTR_NEST_MASK) != 0 &&
(urcu_active_readers & ~RCU_GP_CTR_NEST_MASK) !=
(urcu_gp_ctr & ~RCU_GP_CTR_NEST_MASK) ->
skip;
:: else -> break;
fi
od;

need_mb = 1;
do
:: need_mb == 1 -> skip;
:: need_mb == 0 -> break;
od;
urcu_gp_ctr = urcu_gp_ctr + RCU_GP_CTR_BIT;
do
:: 1 ->
if
:: (urcu_active_readers & RCU_GP_CTR_NEST_MASK) != 0 &&
(urcu_active_readers & ~RCU_GP_CTR_NEST_MASK) !=
(urcu_gp_ctr & ~RCU_GP_CTR_NEST_MASK) ->
skip;
:: else -> break;
fi;
od;

free = 1;
}

init {
atomic {
reader_progress[0] = 0;
reader_progress[1] = 0;
reader_progress[2] = 0;
reader_progress[3] = 0;
run urcu_reader();
run urcu_updater();
}
}
[unhandled content-type:application/x-sh]
\
 
 \ /
  Last update: 2009-02-11 00:01    [W:0.106 / U:0.320 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site