On Mon, Aug 21, 2023 at 11:43:32AM -0400, Mathieu Desnoyers wrote:
> On 8/15/23 08:38, Mathieu Desnoyers via lttng-dev wrote:
> > On 8/14/23 17:05, Olivier Dion via lttng-dev wrote:
> > >
> > > After discussing it with Mathieu, we agree on the following 3 phases for
> > > deprecating the signal
On Wed, Jul 05, 2023 at 03:03:21PM -0400, Olivier Dion wrote:
> On Wed, 05 Jul 2023, "Paul E. McKenney" wrote:
> > On Tue, Jul 04, 2023 at 10:43:21AM -0400, Olivier Dion wrote:
> >> On Wed, 21 Jun 2023, "Paul E. McKenney" wrote:
> >> > On Wed, Ju
On Tue, Jul 04, 2023 at 10:43:21AM -0400, Olivier Dion wrote:
> On Wed, 21 Jun 2023, "Paul E. McKenney" wrote:
> > On Wed, Jun 07, 2023 at 02:53:51PM -0400, Olivier Dion wrote:
> >
> > Same question here on loss of volatile semantics.
>
> This apply to all r
On Thu, Jun 29, 2023 at 12:49:00PM -0400, Olivier Dion wrote:
> On Wed, 21 Jun 2023, "Paul E. McKenney" wrote:
> > On Wed, Jun 07, 2023 at 02:53:52PM -0400, Olivier Dion wrote:
> >> -#ifdef __URCU_DEREFERENCE_USE_ATOMIC_CONSUME
> >> -# def
On Thu, Jun 22, 2023 at 03:53:33PM -0400, Olivier Dion wrote:
> On Thu, 22 Jun 2023, "Paul E. McKenney" wrote:
>
> > I suggest C11 volatile atomic load/store. Load/store fusing is permitted
> > for non-volatile atomic loads and stores, and such fusing can rui
On Thu, Jun 22, 2023 at 11:55:55AM -0400, Mathieu Desnoyers wrote:
> On 6/21/23 19:19, Paul E. McKenney wrote:
> [...]
> > > diff --git a/include/urcu/uatomic/builtins-generic.h
> > > b/include/urcu/uatomic/builtins-generic.h
> > > new file mode 100644
> >
On Wed, Jun 21, 2023 at 09:48:10PM -0400, Mathieu Desnoyers wrote:
> On 6/21/23 20:53, Olivier Dion wrote:
> > On Wed, 21 Jun 2023, "Paul E. McKenney" wrote:
> > > On Mon, May 15, 2023 at 04:17:11PM -0400, Olivier Dion wrote:
> > > >
On Wed, Jun 07, 2023 at 02:53:55PM -0400, Olivier Dion wrote:
> Global states accesses were protected via memory barriers. Use the
> uatomic API with the CMM memory model so that TSAN can understand the
> ordering imposed by the synchronization flags.
>
> Change-Id:
On Wed, Jun 07, 2023 at 02:53:54PM -0400, Olivier Dion wrote:
> Global states accesses were protected via memory barriers. Use the
> uatomic API with the CMM memory model so that TSAN does not warns about
"does not warn", for whatever that is worth.
> none atomic concurrent accesses.
>
> Also,
On Mon, May 15, 2023 at 04:17:09PM -0400, Olivier Dion wrote:
> Implement uatomic in term of atomic builtins if configured to do so.
>
> Change-Id: I5814494c62ee507fd5d381c3ba4ccd0a80c4f4e3
> Co-authored-by: Mathieu Desnoyers
> Signed-off-by: Olivier Dion
> ---
> include/Makefile.am
On Wed, Jun 07, 2023 at 02:53:52PM -0400, Olivier Dion wrote:
> Introducing the CMM memory model with the following new primitives:
>
> - uatomic_load(addr, memory_order)
>
> - uatomic_store(addr, value, memory_order)
> - uatomic_and_mo(addr, mask, memory_order)
> - uatomic_or_mo(addr,
On Wed, Jun 07, 2023 at 02:53:51PM -0400, Olivier Dion wrote:
> If configured to use atomic builtins, use them for implementing the
> CMM_LOAD_SHARED and CMM_STORE_SHARED macros.
>
> Change-Id: I3ef0d26c47aced6e94b40fd59c7b8baa6272
> Co-authored-by: Mathieu Desnoyers
> Signed-off-by: Olivier
On Mon, May 15, 2023 at 04:17:11PM -0400, Olivier Dion wrote:
> If configured to use atomic builtins, implement SMP memory barriers in
> term of atomic builtins if the architecture does not implement its own
> version.
>
> Change-Id: Iddc4283606e0fce572e104d2d3f03b5c0d9926fb
> Co-authored-by:
On Wed, May 10, 2023 at 05:10:27PM -0400, Olivier Dion wrote:
> Hi all,
>
> We have the intention of deprecating the urcu-signal flavor in the
> future. We are asking users of URCU for _feedback_ on this before
> going any further.
>
> Part of this decision is that we are adding support for
On Wed, Mar 22, 2023 at 09:57:25AM -0400, Mathieu Desnoyers wrote:
> On 2023-03-22 07:08, Ondřej Surý via lttng-dev wrote:
> > Hi,
> >
> > the documentation is pretty silent on this, and asking here is probably
> > going to be faster
> > than me trying to use the source to figure this out.
> >
On Wed, Feb 16, 2022 at 03:53:20PM -0500, Mathieu Desnoyers wrote:
> - On Feb 16, 2022, at 2:35 AM, lttng-dev lttng-dev@lists.lttng.org wrote:
>
> > It is enough to have three values of rcu_gp.ctr, 00 for INACTIVE,
> > 01 or 11 for ACTIVE. So it is possible to replace add operation
> > with
On Wed, May 05, 2021 at 10:46:58AM -0400, Mathieu Desnoyers wrote:
> - On May 5, 2021, at 3:54 AM, Martin Wilck mwi...@suse.com wrote:
>
> > On Fri, 2021-04-30 at 14:41 -0400, Mathieu Desnoyers wrote:
> >> - On Apr 29, 2021, at 9:49 AM, lttng-dev
> >> lttng-dev@lists.lttng.org wrote:
> >>
On Fri, Apr 16, 2021 at 03:30:53PM -0400, Mathieu Desnoyers wrote:
> - On Apr 16, 2021, at 3:02 PM, paulmck paul...@kernel.org wrote:
> [...]
> >
> > If it can be done reasonably, I suggest also having some way for the
> > person building userspace RCU to say "I know what I am doing, so do
>
On Fri, Apr 16, 2021 at 02:40:08PM -0400, Mathieu Desnoyers wrote:
> - On Apr 16, 2021, at 12:01 PM, paulmck paul...@kernel.org wrote:
>
> > On Fri, Apr 16, 2021 at 05:17:11PM +0200, Peter Zijlstra wrote:
> >> On Fri, Apr 16, 2021 at 10:52:16AM -0400, Mathieu Desnoyers wrote:
> >> > Hi Paul,
On Fri, Apr 16, 2021 at 05:17:11PM +0200, Peter Zijlstra wrote:
> On Fri, Apr 16, 2021 at 10:52:16AM -0400, Mathieu Desnoyers wrote:
> > Hi Paul, Will, Peter,
> >
> > I noticed in this discussion https://lkml.org/lkml/2021/4/16/118 that LTO
> > is able to break rcu_dereference. This seems to be
has undoubtedly
changed over time, so...
> Signed-off-by: Michael Jeanson
> Cc: Paul E. McKenney
Acked-by: Paul E. McKenney
> Change-Id: I1d1bb5cc0fa0be8f8b1d6a9ad7bf063809be1aef
> ---
> configure.ac | 4
> 1 file changed, 4 deletions(-)
>
> diff --git a/conf
el system where this was reported.
> >
> > Signed-off-by: Michael Jeanson
> > Cc: Paul E. McKenney
> > Change-Id: Ib3cb5d8cb4515e6f626be33c2685fa38cb081782
> > ---
> > tests/common/api.h | 2 +-
> > 1 file changed, 1 insertion(+), 1 deletion(-)
> >
>
eated and exit repeatedly,
and make a per-thread call_rcu() worker in the meantime..
Thoughts?
Thanx, Paul
[1] git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/perfbook.git
> Thanks,
>
> Mathieu
>
> [1] https://ci.lttn
-by: Paul E. McKenney
Cc: Mathieu Desnoyers
Cc: Stephen Hemminger
Cc: Alan Stern
Cc: Lai Jiangshan
Cc:
Cc:
---
urcu-call-rcu-impl.h |7 +--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/src/urcu-call-rcu-impl.h b/src/urcu-call-rcu-impl.h
index b6ec6ba..18fd65a 100644
On Mon, Jan 27, 2020 at 10:38:05AM -0500, Mathieu Desnoyers wrote:
> - On Jan 23, 2020, at 7:19 PM, lttng-dev lttng-dev@lists.lttng.org wrote:
>
> > Hi,
> >
> > I recently installed knot dns for a very small FreeBSD server. I noticed
> > that it uses a surprising amount of CPU, even when
On Sun, Dec 15, 2019 at 05:10:11PM -0500, Yuxin Ren wrote:
> On Sun, Dec 15, 2019 at 3:30 PM Paul E. McKenney wrote:
>
> > On Sat, Dec 14, 2019 at 01:31:31AM -0500, Yuxin Ren wrote:
> > > Hi Paul
> > >
> > > On Sat, Dec 7, 2019 at 5:42 PM Paul E. McKenney
On Sat, Dec 14, 2019 at 01:31:31AM -0500, Yuxin Ren wrote:
> Hi Paul
>
> On Sat, Dec 7, 2019 at 5:42 PM Paul E. McKenney wrote:
>
> > On Sat, Dec 07, 2019 at 03:04:42PM -0500, Yuxin Ren wrote:
> > > Thanks a lot for your help. I have some questions below.
> > &g
On Sat, Dec 07, 2019 at 03:04:42PM -0500, Yuxin Ren wrote:
> Thanks a lot for your help. I have some questions below.
>
> On Sat, Dec 7, 2019 at 1:37 AM Paul E. McKenney wrote:
>
> > On Fri, Dec 06, 2019 at 07:00:13PM -0500, Yuxin Ren wrote:
> > > Thanks so much f
consistency, which opens the door to things like RCU.
Thanx, Paul
> Thanks
> Yuxin
>
> On Fri, Dec 6, 2019 at 11:30 AM Paul E. McKenney wrote:
>
> > On Fri, Dec 06, 2019 at 10:59:05AM -0500, Mathieu Desnoyers wrote:
&g
not designed for
> > linearizability, and it is totally acceptable that RCU is not linearizable.
> > However, I am curious how to accurately/formally Characterize RCU
> > consistency
> > model/guarantees
>
> Adding Paul E. McKenney in CC.
>
> I am referring to the
BTW, your expedited commit hit mainline earlier this week. Here is
hoping! ;-)
Thanx, Paul
On Wed, Sep 06, 2017 at 08:23:40PM +, Mathieu Desnoyers wrote:
> - On Sep 6, 2017, at 3:57 PM, Mathieu Desnoyers
>
On Tue, May 30, 2017 at 05:10:18PM -0400, Mathieu Desnoyers wrote:
> The RCU lock-free hash table currently requires that the destroy
> function should not be called from within RCU read-side critical
> sections. This is caused by the lazy resize, which uses the call_rcu
> worker thread, even
stion could be stupid.
> Many thanks for your time
> Yuxin
>
> On Thu, May 11, 2017 at 4:23 PM, Paul E. McKenney
> <paul...@linux.vnet.ibm.com> wrote:
> > On Thu, May 11, 2017 at 04:05:45PM -0400, Yuxin Ren wrote:
> >> Hi,
> >>
> >> I
On Thu, May 11, 2017 at 04:05:45PM -0400, Yuxin Ren wrote:
> Hi,
>
> I am learning U-RCU now.
> And I read paper Concurrent Updates with RCU: Search Tree as an Example
> (
> https://pdfs.semanticscholar.org/73e4/cd29273cf9d98d35bc184330e694ba798987.pdf
> )
>
> In this paper, the authors present
On Mon, Dec 05, 2016 at 11:01:10PM +, Mathieu Desnoyers wrote:
> - On Dec 5, 2016, at 5:35 PM, Paul E. McKenney paul...@linux.vnet.ibm.com
> wrote:
>
> > On Mon, Dec 05, 2016 at 02:14:47PM +, Mathieu Desnoyers wrote:
> >> Hi Paul,
> >>
> >
On Mon, Dec 05, 2016 at 02:14:47PM +, Mathieu Desnoyers wrote:
> Hi Paul,
>
> So about the liburcu rcu_xchg_pointer() barriers, here is the current
> situation:
>
> rcu_xchg_pointer is implemented as:
>
> #define _rcu_xchg_pointer(p, v) \
> __extension__
On Sat, Sep 24, 2016 at 03:34:47PM +, Mathieu Desnoyers wrote:
> - On Sep 24, 2016, at 11:22 AM, Paul E. McKenney
> paul...@linux.vnet.ibm.com wrote:
>
> > On Sat, Sep 24, 2016 at 10:42:24AM +0300, Evgeniy Ivanov wrote:
> >> Hi Mathieu,
> >>
>
On Sat, Sep 24, 2016 at 10:42:24AM +0300, Evgeniy Ivanov wrote:
> Hi Mathieu,
>
> On Sat, Sep 24, 2016 at 12:59 AM, Mathieu Desnoyers
> wrote:
> > - On Sep 22, 2016, at 3:14 PM, Evgeniy Ivanov lolkaanti...@gmail.com
> > wrote:
> >
> >> Hi all,
> >>
> >> I'm
e?
> > Not only RCU, any other synchronization technique on top of
> > non-cache-coherent multi-core
> > is also helpful.
>
> CCing Paul E. McKenney, who might know more on this topic.
>
> Back in 2009 when I started the liburcu.org project, I
> planned to eventu
Hello!
On the off chance that this is new news of interest...
https://arxiv.org/pdf/1606.01400v1.pdf
"Operational Aspects of C/C++ Concurrency", Anton Podkopaev, Ilya Sergey,
Aleksandar Nanevski.
At first glance, they seem to be using a combination of formal
verification and testing, using a
On Wed, May 18, 2016 at 06:40:03PM +, Mathieu Desnoyers wrote:
> - On May 18, 2016, at 5:44 AM, songxin wrote:
>
> > Hi,
> > Now I get a crash because receiving signal SIGSEGV as below.
>
> > #0 arena_alloc (arena=) at
> >
> > Thanks again!!
> > Yuxin
> >
> > On Thu, Apr 28, 2016 at 8:44 AM, Boqun Feng <boqun.f...@gmail.com> wrote:
> >> Hi Paul and Yuxin,
> >>
> >> On Wed, Apr 27, 2016 at 09:23:27PM -0700, Paul E. McKenney wrote:
> >>> Try building wi
u, Apr 28, 2016 at 8:44 AM, Boqun Feng <boqun.f...@gmail.com> wrote:
> > Hi Paul and Yuxin,
> >
> > On Wed, Apr 27, 2016 at 09:23:27PM -0700, Paul E. McKenney wrote:
> >> Try building without it and see what happens when you run the tests.
> >>
> &g
On Thu, Apr 28, 2016 at 08:44:01PM +0800, Boqun Feng wrote:
> Hi Paul and Yuxin,
>
> On Wed, Apr 27, 2016 at 09:23:27PM -0700, Paul E. McKenney wrote:
> > Try building without it and see what happens when you run the tests.
> >
>
> I've run a 'regtest' with the
n't currently perform grace period, why do we use the rcu_gp_lock?
>
> Thank you.
> Yuxin
>
> On Wed, Apr 27, 2016 at 10:08 PM, Paul E. McKenney
> <paul...@linux.vnet.ibm.com> wrote:
> > On Wed, Apr 27, 2016 at 09:34:16PM -0400, Yuxin Ren wrote:
> >>
On Wed, Apr 27, 2016 at 09:34:16PM -0400, Yuxin Ren wrote:
> Hi,
>
> I am learning the URCU code.
>
> Why do we need rcu_gp_lock in synchronize_rcu?
> https://github.com/urcu/userspace-rcu/blob/master/urcu.c#L401
>
> In the comment, it says this lock ensures mutual exclusion between
> threads
work on -rt Linux.
Thanx, Paul
> Thanks again.
>
> On Fri, Mar 11, 2016 at 10:00 PM, Mathieu Desnoyers
> <mathieu.desnoy...@efficios.com> wrote:
> > - On Mar 11, 2016, at 6:45 AM, Paul E. McKenney
> > paul...@linux.vnet.ibm.com wrote:
> >
I know real time system focus on predictability on both timing and
> > memory consumption.
> > So how does real time urcu support predictability?
> > Could you provide me some papers, documents or any materials about any
> > aspect of real time urcu?
>
> Adding Paul E. McKen
On Thu, Jan 21, 2016 at 05:06:09PM +, Mathieu Desnoyers wrote:
> - On Jan 21, 2016, at 11:59 AM, Josh Triplett j...@joshtriplett.org wrote:
>
> > On Thu, Jan 21, 2016 at 04:45:20PM +, Mathieu Desnoyers wrote:
> >> - On Jan 19, 2016, at 3:57 PM, Mathieu Desnoyers
> >>
asonable approach to me.
Acked-by: Paul E. McKenney <paul...@linux.vnet.ibm.com>
> Signed-off-by: Mathieu Desnoyers <mathieu.desnoy...@efficios.com>
> CC: Paul E. McKenney <paul...@linux.vnet.ibm.com>
> CC: Michael Jeanson <mjean...@efficios.com>
> CC: Jon Be
mjean...@efficios.com
Suggested-by: Paul E. McKenney paul...@linux.vnet.ibm.com
Signed-off-by: Mathieu Desnoyers mathieu.desnoy...@efficios.com
A couple of issues, but otherwise good. (They might even be issues
with your code rather than my eyes, you never know
On Mon, Jun 29, 2015 at 11:06:15PM +, Mathieu Desnoyers wrote:
- On Jun 29, 2015, at 7:01 PM, Paul E. McKenney
paul...@linux.vnet.ibm.com wrote:
On Mon, Jun 29, 2015 at 06:56:34PM -0400, Mathieu Desnoyers wrote:
Make call_rcu_thread() affine itself more persistently
Currently
read-side critical sections to complete.
Changes since v1:
- Hold both rcu_gp_lock and rcu_registry_lock across fork in urcu-bp.
Signed-off-by: Mathieu Desnoyers mathieu.desnoy...@efficios.com
Reviewed-by: Paul E. McKenney paul...@linux.vnet.ibm.com
CC: Eugene Ivanov eugene.iva...@orc
On Fri, Apr 17, 2015 at 12:23:46PM +0300, Eugene Ivanov wrote:
Hi Mathieu,
On 04/10/2015 11:26 PM, Mathieu Desnoyers wrote:
- Original Message -
Hi,
I use rcu-bp (0.8.6) and get deadlock between call_rcu thread and
threads willing to do rcu_read_lock():
1. Some thread is in
On Fri, Apr 17, 2015 at 07:18:18AM -0700, Paul E. McKenney wrote:
On Fri, Apr 17, 2015 at 12:23:46PM +0300, Eugene Ivanov wrote:
Hi Mathieu,
On 04/10/2015 11:26 PM, Mathieu Desnoyers wrote:
- Original Message -
Hi,
I use rcu-bp (0.8.6) and get deadlock between call_rcu
...@msully.net, lttng-dev@lists.lttng.org,
LKML linux-ker...@vger.kernel.org, Paul E.
McKenney paul...@linux.vnet.ibm.com, Peter Zijlstra
pet...@infradead.org, Ingo Molnar mi...@kernel.org,
Thomas Gleixner t...@linutronix.de, Steven Rostedt
rost...@goodmis.org
Sent: Thursday, March 12
On Thu, Mar 12, 2015 at 08:56:00PM +, Mathieu Desnoyers wrote:
(sorry for re-send, my mail client tricked me into posting HTML
to lkml)
Hi,
Michael Sullivan proposed a clever hack abusing mprotect() to
perform the same effect as sys_membarrier() I submitted a few
years ago (
,
While reading this reply, please keep in mind that I'm in a
mindset where I've been in a full week of meeting, and it's late on
Friday evening here. So YMMV ;-) I'm CCing Paul E. McKenney, so he can
debunk my answer :)
liburcu does not build on the Intel Xeon Phi, because the chip
On Sun, Nov 03, 2013 at 02:13:52PM +, Mathieu Desnoyers wrote:
- Original Message -
From: Paul E. McKenney paul...@linux.vnet.ibm.com
To: Mathieu Desnoyers mathieu.desnoy...@efficios.com
Cc: Vladimir Nikulichev n...@tbricks.com, lttng-dev@lists.lttng.org
Sent: Sunday, November
On Fri, Nov 01, 2013 at 08:18:59PM +, Mathieu Desnoyers wrote:
- Original Message -
From: Mathieu Desnoyers mathieu.desnoy...@efficios.com
To: Vladimir Nikulichev n...@tbricks.com
Cc: lttng-dev@lists.lttng.org, Paul E. McKenney
paul...@linux.vnet.ibm.com
Sent: Friday
On Wed, Sep 11, 2013 at 02:54:41PM -0400, Mathieu Desnoyers wrote:
* John Stultz (john.stu...@linaro.org) wrote:
On 09/11/2013 08:08 AM, Mathieu Desnoyers wrote:
[...]
Now focusing on features (the fix discussion is in a separate
sub-thread):
LTTng uses ktime to have the same
On Sun, Sep 01, 2013 at 01:42:10PM -0700, Josh Triplett wrote:
On Sat, Aug 31, 2013 at 02:32:28PM -0700, Paul E. McKenney wrote:
On Thu, Aug 29, 2013 at 07:16:37PM -0700, Josh Triplett wrote:
On Thu, Aug 29, 2013 at 05:57:33PM -0700, Paul E. McKenney wrote:
On Fri, Aug 23, 2013 at 02:08
On Sun, Sep 01, 2013 at 04:42:52PM -0700, Josh Triplett wrote:
rcu_assign_pointer needs to use ACCESS_ONCE to make the assignment to
the destination pointer volatile, to protect against compilers too
clever for their own good.
In addition, since rcu_assign_pointer force-casts the source
On Thu, Aug 29, 2013 at 07:16:37PM -0700, Josh Triplett wrote:
On Thu, Aug 29, 2013 at 05:57:33PM -0700, Paul E. McKenney wrote:
On Fri, Aug 23, 2013 at 02:08:22PM -0700, Paul E. McKenney wrote:
On Fri, Aug 23, 2013 at 01:16:53PM -0400, Mathieu Desnoyers wrote:
#define
On Fri, Aug 23, 2013 at 02:08:22PM -0700, Paul E. McKenney wrote:
On Fri, Aug 23, 2013 at 01:16:53PM -0400, Mathieu Desnoyers wrote:
* Paul E. McKenney (paul...@linux.vnet.ibm.com) wrote:
On Thu, Aug 22, 2013 at 09:33:18PM -0700, Stephen Hemminger wrote
rcu_assign_pointer() is that list_splice_init_rcu() is updating the
pointers to reference something that is already visible to readers, so
that there is no problem with pre-initialized values.
Signed-off-by: Paul E. McKenney paul...@linux.vnet.ibm.com
diff --git a/include/linux/rculist.h b/include/linux
On Fri, Aug 23, 2013 at 12:09:56PM -0700, Stephen Hemminger wrote:
On Fri, 23 Aug 2013 13:16:53 -0400
Mathieu Desnoyers mathieu.desnoy...@efficios.com wrote:
* Paul E. McKenney (paul...@linux.vnet.ibm.com) wrote:
On Thu, Aug 22, 2013 at 09:33:18PM -0700, Stephen Hemminger wrote:
I
On Fri, Aug 23, 2013 at 01:16:53PM -0400, Mathieu Desnoyers wrote:
* Paul E. McKenney (paul...@linux.vnet.ibm.com) wrote:
On Thu, Aug 22, 2013 at 09:33:18PM -0700, Stephen Hemminger wrote:
I needed to add into the middle of an RCU list, does this make sense.
From
On Fri, May 31, 2013 at 11:35:17AM -0400, Mathieu Desnoyers wrote:
Awaits for all in-flight call_rcu handlers to complete execution before
returning.
Signed-off-by: Mathieu Desnoyers mathieu.desnoy...@efficios.com
One suggestion below, looks good in general.
On Tue, May 07, 2013 at 07:59:14AM -0400, Mathieu Desnoyers wrote:
Hi Richard,
* Richard Braun (rbr...@sceen.net) wrote:
Hello,
I'm currently studying RCU/URCU, and I have a few questions that I wasn't
sure where to ask.
1/ Why use poll instead of sched_yield in e.g.
On Thu, Feb 14, 2013 at 11:19:33AM -0500, Mathieu Desnoyers wrote:
I've had a report of someone running into issues with the RCU lock-free
hash table by embedding the struct cds_lfht_node into a packed structure
by mistake, thus not respecting alignment requirements stated in
urcu/rculfhash.h.
On Wed, Jan 16, 2013 at 07:50:54AM -0500, Mathieu Desnoyers wrote:
* Mathieu Desnoyers (mathieu.desnoy...@efficios.com) wrote:
* Paul E. McKenney (paul...@linux.vnet.ibm.com) wrote:
As noted by Konstantin Khlebnikov, gcc can split assignment of
constants to long variables (https
[Sorry for the delay, finally getting back to this.]
On Mon, Dec 17, 2012 at 09:40:09AM -0500, Mathieu Desnoyers wrote:
* Paul E. McKenney (paul...@linux.vnet.ibm.com) wrote:
On Thu, Dec 13, 2012 at 06:44:56AM -0500, Mathieu Desnoyers wrote:
I noticed that in addition to having
On Thu, Dec 13, 2012 at 06:44:56AM -0500, Mathieu Desnoyers wrote:
I noticed that in addition to having:
- push/enqueue returning whether the stack/queue was empty prior to the
operation,
- pop_all/splice, by nature, emptying the stack/queue,
it can be interesting to make pop/dequeue
On Fri, Dec 07, 2012 at 12:22:52PM -0500, Mathieu Desnoyers wrote:
* Lai Jiangshan (eag0...@gmail.com) wrote:
On Saturday, December 8, 2012, Mathieu Desnoyers wrote:
* Lai Jiangshan (eag0...@gmail.com javascript:;) wrote:
we can define rcu_gp_ctr and registry with aligned attribute,
testdur 20 nr_readers 4
rdur 0 wdur 0 nr_writers 1 wdelay 0
nr_reads 19160162768 nr_writes 2253068 nr_ops 1916241583
2253068 vs 2137036 - a couple of runs show that this difference lost in
the noise for single updater.
CC: Paul E. McKenney paul
The current implementation of cds_wfcq_dequeue_lock() and
cds_wfcq_dequeue_unlock() entails mutually assured recursion.
Redirect to _cds_wfcq_dequeue_lock() and _cds_wfcq_dequeue_unlock(),
respectively.
Signed-off-by: Paul E. McKenney paul...@linux.vnet.ibm.com
diff --git a/wfcqueue.c b
FYI, userspace RCU proposed to solve an issue with epoll.
Thanx, Paul
- Forwarded message from Matt Helsley matth...@linux.vnet.ibm.com -
Date: Fri, 26 Oct 2012 14:52:42 -0700
From: Matt Helsley matth...@linux.vnet.ibm.com
To:
On Wed, Oct 17, 2012 at 11:19:46AM -0400, Mathieu Desnoyers wrote:
* Paul E. McKenney (paul...@linux.vnet.ibm.com) wrote:
On Sun, Oct 14, 2012 at 01:53:32PM -0400, Mathieu Desnoyers wrote:
Hi Paul!
I know you are currently looking at documentation of urcu data
structures. I did
On Sun, Oct 14, 2012 at 01:53:32PM -0400, Mathieu Desnoyers wrote:
Hi Paul!
I know you are currently looking at documentation of urcu data
structures. I did quite a bit of work in that area these past days. Here
is my plan:
Actually, I diverted to the atomic operations, given that the
) and worker threads
on the queue head and tail.
Acked-by: Paul E. McKenney paul...@linux.vnet.ibm.com
Signed-off-by: Mathieu Desnoyers mathieu.desnoy...@efficios.com
Could have managed to fix the issue, or change the timing enough that it
does not reproduces. I'll continue
On Wed, Oct 10, 2012 at 03:52:08PM +0800, Lai Jiangshan wrote:
rculfstack is not really require RCU-only.
1) cds_lfs_push_rcu() don't need any lock, don't need RCU nor other locks.
2) cds_lfs_pop_rcu() don't only one of the following synchronization(not only
RCU):
A) use
On Wed, Oct 10, 2012 at 01:53:04PM -0400, Mathieu Desnoyers wrote:
* Mathieu Desnoyers (mathieu.desnoy...@efficios.com) wrote:
* Paul E. McKenney (paul...@linux.vnet.ibm.com) wrote:
On Wed, Oct 10, 2012 at 07:42:15AM -0400, Mathieu Desnoyers wrote:
* Lai Jiangshan (la...@cn.fujitsu.com
On Thu, Oct 11, 2012 at 09:31:01AM +0800, Lai Jiangshan wrote:
On 10/11/2012 03:50 AM, Paul E. McKenney wrote:
On Wed, Oct 10, 2012 at 01:53:04PM -0400, Mathieu Desnoyers wrote:
* Mathieu Desnoyers (mathieu.desnoy...@efficios.com) wrote:
* Paul E. McKenney (paul...@linux.vnet.ibm.com) wrote
On Mon, Oct 08, 2012 at 10:49:16AM -0400, Mathieu Desnoyers wrote:
* Lai Jiangshan (la...@cn.fujitsu.com) wrote:
On 10/02/2012 10:16 PM, Mathieu Desnoyers wrote:
Eliminate false-sharing between call_rcu (enqueuer) and worker threads
on the queue head and tail.
Signed-off-by:
On Wed, Oct 03, 2012 at 05:04:36PM -0400, Mathieu Desnoyers wrote:
* Paul E. McKenney (paul...@linux.vnet.ibm.com) wrote:
On Tue, Oct 02, 2012 at 10:13:07AM -0400, Mathieu Desnoyers wrote:
Implement wait-free concurrent queues, with a new API different from
wfqueue.h, which is already
On Tue, Oct 02, 2012 at 10:13:07AM -0400, Mathieu Desnoyers wrote:
Implement wait-free concurrent queues, with a new API different from
wfqueue.h, which is already provided by Userspace RCU. The advantage of
splitting the head and tail objects of the queue into different
arguments is to allow
On Mon, Sep 03, 2012 at 02:03:00PM -0400, Mathieu Desnoyers wrote:
* Paul E. McKenney (paul...@linux.vnet.ibm.com) wrote:
This commit ensures that all read-side functions meet the 10-line LGPL
criterion that permits them to be expanded directly into non-LGPL code,
without function-call
On Sat, Sep 01, 2012 at 10:13:55PM -0700, Josh Triplett wrote:
On Sat, Sep 01, 2012 at 05:59:11PM -0700, Paul E. McKenney wrote:
This commit ensures that all read-side functions meet the 10-line LGPL
criterion that permits them to be expanded directly into non-LGPL code,
without function
This commit ensures that all read-side functions meet the 10-line LGPL
criterion that permits them to be expanded directly into non-LGPL code,
without function-call instructions. It also documents this as the intent.
Signed-off-by: Paul E. McKenney paul...@linux.vnet.ibm.com
diff --git a/urcu
{
/*
* Queue with wait-free enqueue/blocking dequeue.
- * This implementation adds a dummy head node when the queue is empty to
ensure
- * we can always update the queue locklessly.
*
* Inspired from half-wait-free/half-blocking queue implementation done by
* Paul E. McKenney.
@@ -57,31
On Thu, Jun 21, 2012 at 12:41:13PM -0400, Mathieu Desnoyers wrote:
Hi,
Currently, liburcu calls exit(-1) upon internal consistency error.
This is not pretty, and usually frowned upon in libraries.
One example of failure path where we use this is if pthread_mutex_lock()
would happen to
On Thu, May 17, 2012 at 06:04:13PM -0400, Mathieu Desnoyers wrote:
* Paul E. McKenney (paul...@linux.vnet.ibm.com) wrote:
On Thu, May 17, 2012 at 01:59:43PM -0400, Mathieu Desnoyers wrote:
* Paul E. McKenney (paul...@linux.vnet.ibm.com) wrote:
On Wed, May 16, 2012 at 11:45:39AM -0700
On Tue, May 15, 2012 at 08:10:03AM -0400, Mathieu Desnoyers wrote:
* Paul E. McKenney (paul...@linux.vnet.ibm.com) wrote:
On Mon, May 14, 2012 at 10:39:01PM -0400, Mathieu Desnoyers wrote:
Document each atomic operation provided by urcu/uatomic.h, along with
their memory barrier
On Wed, May 16, 2012 at 09:56:58AM -0400, Mathieu Desnoyers wrote:
Suggested-by: Marek Vavruša marek.vavr...@nic.cz
Signed-off-by: Mathieu Desnoyers mathieu.desnoy...@efficios.com
Interesting! Jeffrey Yasskin of Google was suggesting use of
pthread_get_specific() over __thread even where
On Wed, May 16, 2012 at 02:17:42PM -0400, Mathieu Desnoyers wrote:
* Paul E. McKenney (paul...@linux.vnet.ibm.com) wrote:
On Tue, May 15, 2012 at 08:10:03AM -0400, Mathieu Desnoyers wrote:
* Paul E. McKenney (paul...@linux.vnet.ibm.com) wrote:
On Mon, May 14, 2012 at 10:39:01PM -0400
On Wed, May 16, 2012 at 11:45:39AM -0700, Josh Triplett wrote:
On Wed, May 16, 2012 at 11:32:38AM -0700, Paul E. McKenney wrote:
On Wed, May 16, 2012 at 02:17:42PM -0400, Mathieu Desnoyers wrote:
* Paul E. McKenney (paul...@linux.vnet.ibm.com) wrote:
On Tue, May 15, 2012 at 08:10:03AM
On Mon, May 14, 2012 at 11:36:04PM -0400, Mathieu Desnoyers wrote:
Document the concurrent data structures provided by the userspace RCU
library.
Looks good to me!
Reviewed-by: Paul E. McKenney paul...@linux.vnet.ibm.com
Signed-off-by: Mathieu Desnoyers mathieu.desnoy...@efficios.com
On Mon, May 07, 2012 at 12:10:55PM -0400, Mathieu Desnoyers wrote:
* Paul E. McKenney (paul...@linux.vnet.ibm.com) wrote:
On Fri, May 04, 2012 at 12:53:12PM -0400, Mathieu Desnoyers wrote:
[...]
Just to make sure I understand -- the reason that the del functions
say no memory barrier
On Tue, May 08, 2012 at 02:48:27PM -0400, Mathieu Desnoyers wrote:
* Paul E. McKenney (paul...@linux.vnet.ibm.com) wrote:
On Mon, May 07, 2012 at 12:10:55PM -0400, Mathieu Desnoyers wrote:
* Paul E. McKenney (paul...@linux.vnet.ibm.com) wrote:
On Fri, May 04, 2012 at 12:53:12PM -0400
1 - 100 of 112 matches
Mail list logo