gt; return new_fd;
> -
> -error:
> - return -1;
> }
>
> /*
> --
> 1.7.9.5
>
>
> ___
> lttng-dev mailing list
> lttng-dev@lists.lttng.org
> http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
--
Mathieu Desnoyers
Operating
ment when running the program, this will
> +indicate how many threads to use. For example
> +
> +./hello 10
> +
> +will run the test with 10 threads. If no argument is passed, the default of
> +1 thread is used, in which case the behaviour should be similar to the
> original
g-ust
No ETA at the moment for this feature. It's a "wishlist" feature, but
it is not planned for any specific point in time.
Thanks,
Mathieu
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
___
/probes/Makefile
> +++ b/probes/Makefile
> @@ -14,6 +14,8 @@ obj-m += lttng-probe-sched.o
> obj-m += lttng-probe-irq.o
> obj-m += lttng-probe-signal.o
> obj-m += lttng-probe-timer.o
> +obj-m += lttng-probe-uevent.o
> +obj-m += lttng-uevent.o
>
> obj-m += lttng-probe-
* Alexandre Montplaisir (alexmon...@voxpopuli.im) wrote:
> On 12-06-26 02:03 AM, Mathieu Desnoyers wrote:
> > * Alexandre Montplaisir (alexmon...@voxpopuli.im) wrote:
> >> [...]
> >> diff --git a/tests/hello-mt/README b/tests/hello-mt/README
> >> new file mod
* Brosseau, Yannick (yannick.bross...@gmail.com) wrote:
> On Tue, Jun 26, 2012 at 8:02 AM, Mathieu Desnoyers
> wrote:
> > * Alexandre Montplaisir (alexmon...@voxpopuli.im) wrote:
> >> On 12-06-26 02:03 AM, Mathieu Desnoyers wrote:
> >> > * Alexandre Montplaisi
ld, MA 01880-2400
>
> ___
> lttng-dev mailing list
> lttng-dev@lists.lttng.org
> http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.e
* Francis Giraldeau (francis.girald...@gmail.com) wrote:
> Le 2012-06-26 08:40, Mathieu Desnoyers a écrit :
> >> +/*
> >> + * lttng_uevent_set_handler - set handler functions for uevent
> >> + *
> >> + * Access to handler code is protected with rwlock in
link: http://lttng.org/download
(please refer to the README files for installation instructions and
lttng-tools doc/quickstart.txt for usage information)
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios
ve this commit
already:
commit e51500edbd9919cee53bc85cbb4b22cd4786fc42
Author: Mathieu Desnoyers
Date: Tue Jun 12 11:24:31 2012 -0400
Fix c99 compatibility: use __asm__ and __volatile__ in public headers
Signed-off-by: Mathieu Desnoyers
Does it fix it for you ?
Thanks,
Mathieu
&g
ian''s 6.7.2 rather than the newer version.
>
> Gerhard
>
>
> On Wed, 27 Jun 2012, Mathieu Desnoyers wrote:
>
> > Date: Wed, 27 Jun 2012 09:35:24 -0400
> > From: Mathieu Desnoyers
> > To: Gerhard Mack
> > Cc: Alexandre Montplais
struct ltt_event *event;
> int ret = 0;
>
> + if (strlen(event_param->name) > 0 && event_param->name[0] == '!')
> + {
> + struct session_wildcard *sw = NULL;
> + ltt_wildcard_create(chan, event_param, &sw );
>
catch. I guess we did not test enough on 32-bit. It's fixed on the
lttng-tools master branch by commit:
commit c72b7d965eb65a9f49a5615cac731cec3082aa7f
Author: Mathieu Desnoyers
Date: Fri Jun 29 12:40:30 2012 +0200
Fix: support large files on 32-bit systems
Signed-off-by: Mathieu Desnoyers
it sh
f Google Inc. Use of this trademark is subject to
> Google Permissions.
> Linux is the registered trademark of Linus Torvalds in the U.S. and other
> countries.
>
>
> ___
> lttng-dev mailing list
> lttng-dev@lists.lttng.org
> http
Hi Yannick,
The babeltrace commit:
commit 6cba487f031260536d6a77acde888c8b1a876fcf
Author: Mathieu Desnoyers
Date: Fri Feb 10 12:01:01 2012 -0500
babeltrace lib cleanup, folded with open/remove trace functions
Folded patch from Yannick Brosseau , along
with various updates
sched.o
> obj-m += lttng-probe-irq.o
> obj-m += lttng-probe-signal.o
> obj-m += lttng-probe-timer.o
> +obj-m += lttng-probe-uevent.o
> +obj-m += lttng-uevent.o
>
> obj-m += lttng-probe-statedump.o
>
> diff --git a/probes/lttng-probe-uevent.c b/probes/lttng-probe-uevent.c
>
Thanks,
Mathieu
>
>
> I am using.
> Lttng modules 2.0.2
> Lttng tools:2.0.1
> Kernel:2.6.33.7 with RT-29 patch.
>
> Thanks In Advance,
> Pavan
>
> -Original Message-
> From: Pavan Anumula
> Sent: Thursday, June 21, 2012 8:54 PM
> To: 'Da
* Francis Giraldeau (francis.girald...@gmail.com) wrote:
> Le 2012-07-02 16:13, Mathieu Desnoyers a écrit :
> > * Francis Giraldeau (francis.girald...@gmail.com) wrote:
> >> By writing to the file /proc/lttng, a user-space application creates a
> >> kernel event. The ev
j-m += lttng-probe-sched.o
> obj-m += lttng-probe-irq.o
> obj-m += lttng-probe-signal.o
> obj-m += lttng-probe-timer.o
> +obj-m += lttng-uevent.o
>
> obj-m += lttng-probe-statedump.o
>
> diff --git a/probes/lttng-uevent.c b/probes/lttng-uevent.c
> new file mode 1006
* Francis Giraldeau (francis.girald...@gmail.com) wrote:
> Le 2012-07-03 00:23, Mathieu Desnoyers a écrit :
> > * Francis Giraldeau (francis.girald...@gmail.com) wrote:
> >> By writing to the file /proc/lttng_uevent, a user-space application
> >> creates a
> >&g
* Francis Giraldeau (francis.girald...@gmail.com) wrote:
> Le 2012-07-03 13:39, Mathieu Desnoyers a écrit :
> > * Francis Giraldeau (francis.girald...@gmail.com) wrote:
> >> Le 2012-07-03 00:23, Mathieu Desnoyers a écrit :
> >>> * Francis Giraldeau (francis.girald.
. Feedback is welcome.
Signed-off-by: Mathieu Desnoyers
---
diff --git a/src/common/kernel-consumer/kernel-consumer.c
b/src/common/kernel-consumer/kernel-consumer.c
index bbc31f8..eca710d 100644
--- a/src/common/kernel-consumer/kernel-consumer.c
+++ b/src/common/kernel-consumer/kernel-consumer.c
t in CC, which I'm doing here.
Thanks,
Mathieu
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
___
lttng-dev mailing list
lttng-dev@lists.lttng.org
http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
* David Goulet (dgou...@efficios.com) wrote:
> -BEGIN PGP SIGNED MESSAGE-
> Hash: SHA1
>
> Comments below.
>
> On 04/07/12 12:10 PM, Mathieu Desnoyers wrote:
> > With large subbuffer (packet) size, if write() returns before copying the
> > entire packet f
return ret;
+ return written;
}
/*
@@ -384,7 +394,7 @@ int lttng_ustconsumer_read_subbuffer(struct
lttng_consumer_stream *stream,
assert(err == 0);
/* write the subbuffer to the tracefile */
ret = lttng_consumer_on_read_subbuffer_mmap(ctx, stream, len);
- if (ret < 0) {
+
struct
lttng_consumer_stream *stream,
assert(err == 0);
/* write the subbuffer to the tracefile */
ret = lttng_consumer_on_read_subbuffer_mmap(ctx, stream, len);
- if (ret < 0) {
+ if (ret != len) {
currently
encountered.
Testing is welcome.
Signed-off-by: Mathieu Desnoyers
---
diff --git a/src/common/kernel-consumer/kernel-consumer.c
b/src/common/kernel-consumer/kernel-consumer.c
index bbc31f8..cc16f9f 100644
--- a/src/common/kernel-consumer/kernel-consumer.c
+++ b/src/common/kernel-consumer
nding, it decides the output
> format of each argument.
> Why does the argument anint need three cft_integer with different types?
>
> Best Regards
> Zheng
>
> ___
> lttng-dev mailing list
> lttng-dev@lists.lttng.org
> http://lists.lttng.org/cgi-b
gt; lttng-dev@lists.lttng.org
> http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
___
lttng-dev mailing list
lttng-dev@lists.lttng.org
http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
[ Edit by Mathieu Desnoyers: add explanations about supported
MIPS architectures, extracted from conversation with Ralf Baechle:
* Supported architectures
Ralf Baechle (edited by Mathieu Desnoyers):
This code works on all MIPS architecture variants. The memor
you very much.
>
> Regards,
> Rui
> ___
> lttng-dev mailing list
> lttng-dev@lists.lttng.org
> http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
__
* Jon Bernard (jbern...@debian.org) wrote:
> * Jon Bernard wrote:
> > * Mathieu Desnoyers wrote:
> > > Hi Jon,
> > >
> > > I wanted to get in touch with you regarding LTTng 2.0 Debian packages.
> > > Is there anything we can do to help you getting
\
> struct ltt_event *__event = __tp_data; \
> @@ -547,6 +554,8 @@ static struct lttng_probe_desc
> _TP_COMBINE_TOKENS(__probe_desc___, TRACEPOINT_PR
> /* Reset all macros within TRACEPOINT_EVENT */
> #include
> static void __attribute__((
ffer snapshot.
Hoping this helps,
Thanks,
Mathieu
>
> Cheers
>
> -- Sebastian
>
> ___
> lttng-dev mailing list
> lttng-dev@lists.lttng.org
> http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
--
Mathieu Des
* Woegerer, Paul (paul_woege...@mentor.com) wrote:
> On 07/17/2012 04:13 PM, Mathieu Desnoyers wrote:
>
>> I think we want to make the notrace always active. I don't see the point
>> in letting UST lib be compiled with those tracing stubs in place.
>
> OK, I'
I ended up pushing your work as:
commit a8909ba54718ed54cefb1b839a5d41a065df09f9
Author: Paul Woegerer
Date: Wed Jul 18 15:28:44 2012 -0400
Make lttng-ust robust against -finstrument-functions.
[ Edit by Mathieu Desnoyers:
We need to declare the no_instrument_function
___
> lttng-dev mailing list
> lttng-dev@lists.lttng.org
> http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
___
lttng-dev mailing list
lttng-dev@lists.lttng.org
http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
logging.
>
> Thanks,
>
> Luay Alawneh
> Nuance Communications
>
> ___
> lttng-dev mailing list
> lttng-dev@lists.lttng.org
> http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
--
Mathi
ffer is very modular, it should be
straightforward to implement.
Thanks!
Mathieu
>
> Thank you,
> - Bingfeng
>
> ___
> lttng-dev mailing list
> lttng-dev@lists.lttng.org
> http://lists.lttng.org/cgi
ly he will make progress on
this issue within the next week. Adding a bug entry would be helpful to
track this issue, yes.
Thanks,
Mathieu
>
>
> Cheers,
>
> Fredrik Östman
>
>
> ___
> lttng-dev mailing list
> lttng-dev
; Best Regards,
> Lars Ekman
>
>
>
> ___________
> lttng-dev mailing list
> lttng-dev@lists.lttng.org
> http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
HYRc3aKk1+X5u
> RMnIuqx4ZdkakeGkTtZMr3ujmy/vOj9NOMuZsigV9z7g/jL5uXzfL0eJcW9kJLQ3
> cNEtdO519q9hInoxpRBkRQtJya1LHoT66oc5AK8TWMBCLjHzvTvvqWNSEBEOfQqH
> b7CulD3x6//DvnlVImA3zFNB2YXLvY6bL3XnU9I/DIEENjG1uAP+9/h+IzWRMNcS
> F0bttSrK9faUqBedMB81hadx0uLjpQxnIB9oFR2NEW/W1J3HAwwVN5YntZFo+lw=
> =BfP8
> -END PGP SIGNATURE-
>
> ___
> lttng-dev mailing list
> lttng-dev@lists.lttng.org
> http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
___
lttng-dev mailing list
lttng-dev@lists.lttng.org
http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
_
> lttng-dev mailing list
> lttng-dev@lists.lttng.org
> http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
__
ot;The Good You Do, The Best You GET"
>
> Regards
> Srikanth Krishnakar
> **
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
___
lttng-dev mailing list
lttng-dev@lists.lttng.org
http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
* bingfeng.z...@emc.com (bingfeng.z...@emc.com) wrote:
>
>
> > -Original Message-
> > From: Mathieu Desnoyers [mailto:mathieu.desnoy...@efficios.com]
> > Sent: Saturday, July 21, 2012 1:26 AM
> > To: Zhao, Bingfeng; t...@linutronix.de
> > Cc: lttng
ror, not on "normal" teardown condition (thread quit pipe
being closed). Flagging threads as being in error condition upon all
exit paths would lead to false "errors" sent to the client, which we
want to avoid, since the client could then think it needs to kill a
sessiond wh
the "last" snapshot, so
we can do a time delta between the current and last snapshot to figure
out if we need to report the thread as stalled or not.
Signed-off-by: Mathieu Desnoyers
CC: David Goulet
---
diff --git a/src/bin/lttng-sessiond/health.c b/src/bin/lttng-sessiond/health.c
in
the following fix ?
Fix: set health to bad state for good when error state detected
Signed-off-by: Mathieu Desnoyers
---
diff --git a/src/bin/lttng-sessiond/health.c b/src/bin/lttng-sessiond/health.c
index 7bf41c8..3637225 100644
--- a/src/bin/lttng-sessiond/health.c
+++ b/src/bin/lttng-sess
Having those showing
up in strace tells me that you kernel might be quite old, or use use an
architecture that implements those as standard system calls rather than
vDSO.
Thanks,
Mathieu
>
> BR
> Zheng
> ___
> lttng-dev mailing list
>
ng that script.
So typically it will require no interaction from users, except when they
"know what they are doing" and want to explicitely disable our
work-around.
Thoughts ?
Mathieu
>
> Other components of LTTng might be affected be the same issue.
>
> Any thoughts or add
tp://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
___
lttng-dev mailing list
lttng-dev@lists.lttng.org
http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
am be able to do it or not within
> time constrain.
>
> Regards,
> Rui
>
> On Tue, Jul 31, 2012 at 12:29 PM, Mathieu Desnoyers <
> mathieu.desnoy...@efficios.com> wrote:
>
> > * Rui Han (r@umiami.edu) wrote:
> > > Hi,
> > >
> > > In the
H_LIBDL
> --
> 1.7.0.4
>
>
> ___
> lttng-dev mailing list
> lttng-dev@lists.lttng.org
> http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
___
lttng-dev mailing list
lttng-dev@lists.lttng.org
http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
t; + AC_MSG_WARN([the detected libtool will not link all
> dependencies, forcing link_all_deplibs = unknown])
> + sed -i "s/\($libtool_flag_pattern\)=no/\1=unknown/g"
> $libtool_m4
Could you modify your patch to tabs and spaces around "=" wo
n conjunction with an Android build (or NDK?)
> area. Would you view one of these (or something else), a "preferred"
> way?
>
> Thanks,
> Kent
>
> -Original Message-
> From: Mathieu Desnoyers [mailto:mathieu.desnoy...@efficios.com]
> Sent: Tues
attern_count])
> + AC_MSG_WARN([the detected libtool will not link all
> dependencies, forcing link_all_deplibs = unknown])
> + sed -i "s/\($libtool_flag_pattern\)\s*=\s*no/\1=unknown/g"
> $libtool_m4
> + ],
> + [
>
_
> lttng-dev mailing list
> lttng-dev@lists.lttng.org
> http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
nect macros to enable the logging of the
> connected IP/port from the socket. Is this method right? what are other
> possible solutions in order to logging the details of the socket
> information?
>
> Thank you very much.
>
> Regards,
> Rui
--
Mathieu Desnoyers
Operati
ced by
> > "bt_ctf_get_real_timestamp"
> > - the function "bt_ctf_get_cycles_timestamp" is added
> >
> Why not simply calling them
> bt_ctf_get_timestamp and bt_ctf_get_cycles ?
Yes, it makes sense. Julien, any thoughts on this ?
Thanks,
Mathieu
>
>
ve on the wake up site too ?
>
> Thanks,
> Lai.
>
> (today I found a old patchset in my private tree, tried to rebase it
> and suddenly notice this urcu/futex.h but the patchset has nothing
> related with urcu/futex.h).
I look forward to see that work!
Thanks!
Mathieu
--
lddir)/include -include config.h"),
but let's remove this misleading line of code.
Signed-off-by: Mathieu Desnoyers
---
diff --git a/src/common/hashtable/rculfhash.c b/src/common/hashtable/rculfhash.c
index 776f9f3..423d186 100644
--- a/src/common/hashtable/rculfhash.c
+++ b/src/common/hashta
event offsetted
> * with the system clock source (in ns) or -1ULL on error
> */
> -uint64_t bt_ctf_get_real_timestamp(const struct bt_ctf_event *event);
> +uint64_t bt_ctf_get_timestamp(const struct bt_ctf_event *event);
>
> /*
> * bt_ctf_get_field_list: set list point
UK/94MEPjeWd2cSNJxsaidYj9mD07ST9UWfputU=
> =GYy5
> -END PGP SIGNATURE-
> RFC - LTTng address API proposal
>
> Author: David Goulet
>
> Contributors:
> * Mathieu Desnoyers
> * Yannick Brosseau
>
> Version:
> - v0.1: 31/07/2012
>
ikqWyRt/4wwiufaZNtlC85/w
> C0pGJL/9TBTY4rFmyZ/e19lJRUoNEygrFRRoJb5qxKWH5nHvfRXdFGw78xjDgim7
> g9AvrWZ7g73KZaS7LEpmAcofgRicWafIMd0+jUXv0MMrj3NeT/xD66UbtcUusl8=
> =jRvr
> -END PGP SIGNATURE-
> RFC - LTTng address API proposal
>
> Author: David Goulet
>
> Contributors:
> * Mathieu De
ct definition *field)
> {
> - int ret = 0;
> + int64_t ret = 0;
>
> if (field && bt_ctf_field_type(field) == CTF_TYPE_INTEGER)
> ret = get_signed_int(field);
> --
> 1.7.10.4
>
--
Mathieu Desnoyers
Operating System Efficiency R&D Consu
};
> };
> stream {
> packet.context := struct {
> uint32_t content_size;
> uint32_t packet_size;
> };
> typealias integer { size = 64; align = 64; signed = false; } :=
> uint64_t;
> event.header := st
gt; lttng-dev mailing list
> lttng-dev@lists.lttng.org
> http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
___
lttng-dev mailing list
lttng-de
_deplibs = no in
>./config/libtool.m4... 3
> configure: WARNING: the detected libtool will not link all
> dependencies, forcing link_all_deplibs = unknown
>
> Signed-off-by: Christian Babeux
Acked-by: Mathieu Desnoyers
> ---
> configure.ac | 25 +++
> # check for dlopen
> --
> 1.7.11.3
>
>
> ___
> lttng-dev mailing list
> lttng-dev@lists.lttng.org
> http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
___
lttng-dev mailing list
lttng-dev@lists.lttng.org
http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
the header. Could
> you give me some hint that I can understand lttng and debug the code to get
> what I wanted?
>
> Thank you very much.
>
> Regards,
> Rui
>
> On Sun, Aug 5, 2012 at 1:03 PM, Mathieu Desnoyers <
> mathieu.desnoy...@efficios.com> wrot
breaking the
code dump.
Thoughts ?
Thanks,
Mathieu
>
>
>
> BR
>
> Zheng
>
> ___
> lttng-dev mailing list
> lttng-dev@lists.lttng.org
> http://lists.lttng.org/cgi-bin/mailman/listinfo/l
LS(my_int_array_type, var_name);
> + *
> + * Another exmaple:
> + * typedef void (*call_rcu_flavor)(struct rcu_head *, );
> + * DECLARE_URCU_TLS(call_rcu_flavor, p_call_rcu);
> + */
> +
> # define DECLARE_URCU_TLS(type, name)\
> CONFIG_RCU_TLS type name
&
id) (in tls-compat.h) and make sure it is async-signal-safe I
guess ? I would prefer that solution: it would make the code more robust
for a rarely taken performance hit.
Thoughts ?
Thanks,
Mathieu
> + */
> +
> # include
>
> struct urcu_tls {
> --
> 1.7
c(int32_t *uaddr, int op, int32_t
> val,
> pthread_cond_wait(&compat_futex_cond, &compat_futex_lock);
> break;
> case FUTEX_WAKE:
> - for (i = 0; i < val; i++)
> - pthread_cond_signal(&compat_futex_cond);
> +
().
Signed-off-by: Lai Jiangshan
Signed-off-by: Mathieu Desnoyers
Thanks!
Mathieu
>
> Signed-off-by: Lai Jiangshan
> ---
> urcu/static/wfqueue.h | 36 +---
> 1 files changed, 25 insertions(+), 11 deletions(-)
>
> diff --g
ONDITIONAL([HAVE_LIBLTTNG_UST_CTL], [test "x$lttng_ust_ctl_found" =
> >> xyes])
> >
> > why are you changing this line ?
> >
>
> I only changed the test flag to lttng_ust_ctl_found for clarity sake.
> It might not be obvious to everyone th
e value otherwise.
> */
> --
> 1.7.9.5
>
>
> ___
> lttng-dev mailing list
> lttng-dev@lists.lttng.org
> http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
___
lttng-dev mailing list
lttng-dev@lists.lttng.org
http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
gt;
> On Thu, Aug 9, 2012 at 10:14 PM, Mathieu Desnoyers
> wrote:
> > * Lai Jiangshan (la...@cn.fujitsu.com) wrote:
> >> Signed-off-by: Lai Jiangshan
> >> ---
> >> urcu/tls-compat.h | 14 ++
> >> 1 files changed, 14 insertions(+), 0
b/lib/iterator.c
> index bcb77d8..5125afb 100644
> --- a/lib/iterator.c
> +++ b/lib/iterator.c
> @@ -3,7 +3,7 @@
> *
> * Babeltrace Library
> *
> - * Copyright 2010-2011 EfficiOS Inc. and Linux Foundation
> +/ * Copyright 2010-2011 EfficiOS Inc. and Linux Foundatio
-signal-safety of pthread_key_* and TLS.
The code we refer to is:
http://git.lttng.org/?p=userspace-rcu.git;a=blob;f=urcu/tls-compat.h;h=192a53609fb5f6bc445f98fdd6bc26918126687e;hb=HEAD)
* Lai Jiangshan (la...@cn.fujitsu.com) wrote:
> On 08/10/2012 04:02 AM, Mathieu Desnoyers wrote:
> > L
_wfq_dequeue_all_blocking(&crdp->cbs, &tail);
> + assert(head);
> +
> /* Create default call rcu data if need be */
> (void) get_default_call_rcu_data();
> - cbs_endprev = (struct cds_wfq_node **)
> -
> babeltrace/types.h \
> babeltrace/ctf-ir/metadata.h \
> babeltrace/ctf/events-internal.h \
> --
> 1.7.9.5
>
>
> ___
> lttng-dev mailing list
> lttng-dev@lists.lttng.org
> http://lists.lttng.org/cgi-bin/mailman/list
- strncpy(handle->path, path, PATH_MAX);
> - handle->path[PATH_MAX - 1] = '\0';
> + if (path) {
> + strncpy(handle->path, path, PATH_MAX);
> + handle->path[PATH_MAX - 1] = '\0';
> + }
>
> if (fmt->set_h
tc = iter->ctx->tc;
> +
> + ret = seek_last_ctf_file_stream(tc, &cfs);
> + if (ret < 0)
> + goto error;
> + /* remove all stream from the heap*/
> + heap_free(iter->stream_heap);
> +
lt call rcu data if need be */
> (void) get_default_call_rcu_data();
> - cbs_endprev = (struct cds_wfq_node **)
> - uatomic_xchg(&default_call_rcu_data, cbs_tail);
> - *cbs_endprev = cbs;
> +
> + __cds_w
* Mathieu Desnoyers (mathieu.desnoy...@efficios.com) wrote:
> * Lai Jiangshan (la...@cn.fujitsu.com) wrote:
> > Some guys would be surprised by this fact:
> > There are already TWO implementations of wfqueue in urcu.
> >
> > The first one is in urcu/static/wfqueue.h:
&
enqueue, 2% (performance improvement) for
dequeue. Overall number of operations (dequeue+enqueue) increased with
the patch.
We can verify that:
successful enqueues - successful dequeues = end_dequeues
For all runs (ensures correctness: no lost node).
CC: Lai Jiangshan
CC: Paul McKenney
Signed-of
are set [in set_permissions() at main.c:5310]
> DEBUG1: epoll set max size is 180337 [in compat_epoll_set_max_size()
> at compat-epoll.c:224]
> Illegal instruction
>
> What to do? :P
>
> --
> Henrik Hautakoski
> hen...@fiktivkod.org
--
Mathieu Desnoyers
Operati
Hi Lai,
* Lai Jiangshan (eag0...@gmail.com) wrote:
> On Sun, Aug 12, 2012 at 10:50 PM, Mathieu Desnoyers
> wrote:
> > This work is derived from the patch from Lai Jiangshan submitted as
> > "urcu: new wfqueue implementation"
> > (http://lists.lttng.org/pipermail
=
pthread_sigmask(SIG_SETMASK, &old_set, NULL);
+ assert(!ret);
+ }
}
}
-
}
}
}
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
Eff
* Lai Jiangshan (eag0...@gmail.com) wrote:
> On Tue, Aug 14, 2012 at 4:12 AM, Mathieu Desnoyers
> wrote:
[...]
> >> > /*
> >> > + * ___cds_wfq_first_blocking: get first node of a queue, without
> >> > dequeuing.
> >> > + *
> >> >
* Mathieu Desnoyers (mathieu.desnoy...@efficios.com) wrote:
> * Lai Jiangshan (eag0...@gmail.com) wrote:
> > On Tue, Aug 14, 2012 at 4:12 AM, Mathieu Desnoyers
> > wrote:
> [...]
> > >> > /*
> > >> > + * ___cds_wfq_first_blocking: get fi
* Mathieu Desnoyers (mathieu.desnoy...@efficios.com) wrote:
[...]
> One more thing: I think we need to add cmm_smp_read_barrier_depends()
> before returning the node pointers in dequeue, first, and next
> operations. This memory barrier would match the implicit barrier in the
> enqu
* Lai Jiangshan (eag0...@gmail.com) wrote:
> On Wed, Aug 15, 2012 at 6:27 AM, Mathieu Desnoyers
> wrote:
> > * Lai Jiangshan (eag0...@gmail.com) wrote:
> >> On Tue, Aug 14, 2012 at 4:12 AM, Mathieu Desnoyers
> >> wrote:
> > [...]
> >> >> >
Introduce wfqueue v0 ABI compatibility
Preparing for v1 ABI.
CC: Lai Jiangshan
CC: Paul McKenney
Signed-off-by: Mathieu Desnoyers
---
diff --git a/wfqueue0.c b/wfqueue0.c
new file mode 100644
index 000..e928c0a
--- /dev/null
+++ b/wfqueue0.c
@@ -0,0 +1,191 @@
+/*
+ * wfqueue0.c
only way to run into this corner-case would be to
combine objects compiled with different versions of the urcu/wfqueue.h
header.
CC: Lai Jiangshan
CC: Paul McKenney
Signed-off-by: Mathieu Desnoyers
---
diff --git a/Makefile.am b/Makefile.am
index 2396fcf..31052ef 100644
--- a/Makefile.am
s gracefully.
>
> Signed-off-by: Christian Babeux
Acked-by: Mathieu Desnoyers
> ---
> src/bin/lttng/commands/destroy.c | 27 ---
> 1 file changed, 16 insertions(+), 11 deletions(-)
>
> diff --git a/src/bin/lttng/commands/destroy.c
> b/src/bin/lttn
* Christian Babeux (christian.bab...@efficios.com) wrote:
>
> Signed-off-by: Christian Babeux
Acked-by: Mathieu Desnoyers
> ---
> src/bin/lttng/commands/destroy.c | 15 ---
> 1 file changed, 15 deletions(-)
>
> diff --git a/src/bin/lttng/commands/destroy
n wfqueue without having to
have legacy code in our way: I plan to move all the legacy ABI to
wfqueue0.c, and have a fresh start in terms of ABI for the new wfqueue.
That way, we can eventually remove the wfqueue v0 ABI when we decide to
bump the library version number (and break compatibi
ze, which would break API compatibility. Any idea on how to
> >> best do this without causing incompatibility would be welcome.
> >>
> >
> > choice 1) two set of APIs?(cache-line-opt and none-cache-line-opt),
> > many users don't need the cache-line-opt
601 - 700 of 3784 matches
Mail list logo