On 15 May 2013 16:48, Paolo Bonzini wrote:
> Here is an RCU implementation based on liburcu.
Doesn't compile on MacOSX/clang:
CCutil/rcu.o
In file included from util/rcu.c:35:
/Users/pm215/src/qemu/include/qemu/rcu.h:112:6: warning: implicit
declaration of function 'g_private_replace' is i
Il 15/05/2013 18:16, Peter Maydell ha scritto:
> On 15 May 2013 16:48, Paolo Bonzini wrote:
>> Giving a shot to rcutorture on a weak memory-model machine (PPC)
>> would be nice.
>
> # ./tests/rcutorture 16 rperf 2
> n_reads: 116103000 n_updates: 0 nreaders: 16 nupdaters: 0 duration: 2
> ns/rea
Il 15/05/2013 18:03, Peter Maydell ha scritto:
> On 15 May 2013 16:48, Paolo Bonzini wrote:
>> Giving a shot to rcutorture on a weak memory-model machine (PPC)
>> would be nice. It's available on my github repo as branch rcu.
>> rcutorture works on Linux-x86. My WINE setup has some problem with
On 15 May 2013 16:48, Paolo Bonzini wrote:
> Giving a shot to rcutorture on a weak memory-model machine (PPC)
> would be nice.
# ./tests/rcutorture 16 rperf 2
n_reads: 116103000 n_updates: 0 nreaders: 16 nupdaters: 0 duration: 2
ns/read: 275.617 ns/update: nan
...that "nan" isn't entirely re
On 15 May 2013 16:48, Paolo Bonzini wrote:
> Giving a shot to rcutorture on a weak memory-model machine (PPC)
> would be nice. It's available on my github repo as branch rcu.
> rcutorture works on Linux-x86. My WINE setup has some problem with glib
> right now.
Doesn't compile (ARM):
root@local
Here is an RCU implementation based on liburcu. I had posted
something like this a couple years ago, but there have been
many changes:
- more portable code
- adjusted for all the threads that we have now
- updated atomic operations for GCC 4.8
- lots of documentation
There is plenty of docume
