* Lai Jiangshan (la...@cn.fujitsu.com) wrote:
urcu-qsbr's read site's quiescence is much longer than normal urcu ==
synchronize_rcu() is much slower ==
rcu_gp_ctr is updated much less ==
the whole urcu-qsbr will not be slowed down by false sharing of rcu_gp_ctr.
Hi Lai,
Sorry for the late
Message: 1
Date: Fri, 3 May 2013 10:42:22 -0400
There are now two tracing modes implemented in lttng-ust (user-space tracer),
each with their own advantages (+)/disadvantages(-):
1) per-pid buffer tracing,
[...]
2) per-uid (shared) buffer tracing, (buffers shared across applications
Since we are bumping the urcu soname version number to 2.0.0 for the
upcoming urcu 0.8 anyway, it's time to merge this patch.
Thanks!
Mathieu
* Lai Jiangshan (la...@cn.fujitsu.com) wrote:
@rcu_gp_ctr and @registry share the same cache line, it causes
false sharing and slowdown both of the
On 05/03/2013 08:35 PM, Mathieu Desnoyers wrote:
* Woegerer, Paul (paul_woege...@mentor.com) wrote:
Without this change the user simply cannot make sure its own
constructor gets invoked after the trace provider constructors.
If we try to support tracing constructors, I'm concerned that with
* Mohamad Gebai (mohamad.ge...@polymtl.ca) wrote:
Hi,
I would like to add some of kvm's tracepoints to lttng as only few of them are
already included. The problem is that those tracepoints are architecture
specific (in the kernel source: arch/x86/kvm/trace.h). The readme file in
* yin sun (sunyi...@gmail.com) wrote:
Hi,
I am new here. The example always need to stop tracing then view the log.
Is it possible to view it while tracing is on. I try to do that it always
fail.
How to make it work.
This will be a new feature planned around July 2013. Stay tuned,
Hello all,
I've got a question about the Java code that writes CTF traces.
Would this design provide a single trace with Java events and OS events in the
same trace?
Here is an example:
Consider an all-Java program that sends an XML requests request over HTTP.
Would like the trace detail to
I don't think so, but usually you would have a trace for your Java events
and another one for OS events that are recorded simultaneously.
Then you simply open both with Babeltrace or your favorite trace viewer and
you should see interleaving events.
You might have problems with events timing
Signed-off-by: Christian Babeux christian.bab...@efficios.com
---
tests/unit_tests | 1 +
1 file changed, 1 insertion(+)
diff --git a/tests/unit_tests b/tests/unit_tests
index d7c68b6..6bf33cc 100644
--- a/tests/unit_tests
+++ b/tests/unit_tests
@@ -2,3 +2,4 @@ unit/test_kernel_data
Let's assume I want to do a kernel-only LTTng installation. After putting
lttng-modules in place, I get lttng-tools and, at its configure step, I do:
./configure --disable-lttng-ust
However, this fails with:
checking whether cds_list_add is declared... no
configure: error: liburcu =
Yes it is. URCU is used extensively in lttng-tools regardless of UST
tracing or not.
David
Thibault, Daniel:
Let’s assume I want to do a kernel-only LTTng installation. After
putting lttng-modules in place, I get lttng-tools and, at its configure
step, I do:
./configure
Merged
Christian Babeux:
Signed-off-by: Christian Babeux christian.bab...@efficios.com
---
tests/unit_tests | 1 +
1 file changed, 1 insertion(+)
diff --git a/tests/unit_tests b/tests/unit_tests
index d7c68b6..6bf33cc 100644
--- a/tests/unit_tests
+++ b/tests/unit_tests
@@ -2,3 +2,4
Hi Erik,
The answer at this moment is no, you can't see that. That said, that is
certainly the vision of what I want to create. I am working on extending a
view so that I can see Java methods in one trace alongside state changes that
come from another trace. The idea is to have a single view
Signed-off-by: Charles Briere charlesbriere.fla...@gmail.com
---
configure.ac| 34 ++
src/bin/lttng-consumerd/Makefile.am | 6 +-
src/bin/lttng-relayd/Makefile.am| 9 -
src/bin/lttng-sessiond/Makefile.am | 6 +-
From: Pierre-Luc St-Charles pierre-luc.st-char...@polymtl.ca
Signed-off-by: Pierre-Luc St-Charles pierre-luc.st-char...@polymtl.ca
---
configure.ac | 10 ++
src/bin/lttng-relayd/cmd-2-2.c | 1 +
src/bin/lttng-relayd/main.c| 1 +
src/common/compat/endian.h | 6
Signed-off-by: Charles Briere charlesbriere.fla...@gmail.com
---
configure.ac | 1 +
src/common/Makefile.am | 5 +
src/common/compat/uuid.h | 2 +-
3 files changed, 7 insertions(+), 1 deletion(-)
diff --git a/configure.ac b/configure.ac
index 618d203..b78cc94 100644
---
Signed-off-by: Charles Briere charlesbriere.fla...@gmail.com
---
src/common/sessiond-comm/unix.h | 1 -
1 file changed, 1 deletion(-)
diff --git a/src/common/sessiond-comm/unix.h b/src/common/sessiond-comm/unix.h
index 34f156f..0252f4f 100644
--- a/src/common/sessiond-comm/unix.h
+++
Signed-off-by: Charles Briere charlesbriere.fla...@gmail.com
---
configure.ac | 23 +--
src/common/defaults.h | 2 --
2 files changed, 21 insertions(+), 4 deletions(-)
diff --git a/configure.ac b/configure.ac
index eb79fc4..b3738d2 100644
--- a/configure.ac
+++
From: Michael Poupart michael-poup...@polymtl.ca
Signed-off-by: Michael Poupart michael-poup...@polymtl.ca
---
configure.ac | 17 +
src/bin/lttng-sessiond/main.c | 7 +++
2 files changed, 24 insertions(+)
diff --git a/configure.ac b/configure.ac
index
From: Pierre-Luc St-Charles pierre-luc.st-char...@polymtl.ca
Signed-off-by: Pierre-Luc St-Charles pierre-luc.st-char...@polymtl.ca
---
src/bin/lttng-sessiond/kernel.c | 6 ++
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/src/bin/lttng-sessiond/kernel.c
From: Pierre-Luc St-Charles pierre-luc.st-char...@polymtl.ca
Signed-off-by: Pierre-Luc St-Charles pierre-luc.st-char...@polymtl.ca
---
src/bin/lttng-consumerd/lttng-consumerd.c | 6 +++
src/bin/lttng-sessiond/shm.c | 75 +++
src/bin/lttng-sessiond/shm.h
From: Pierre-Luc St-Charles pierre-luc.st-char...@polymtl.ca
Signed-off-by: Pierre-Luc St-Charles pierre-luc.st-char...@polymtl.ca
---
configure.ac | 315 ---
1 file changed, 171 insertions(+), 144 deletions(-)
diff --git a/configure.ac
From: Pierre-Luc St-Charles pierre-luc.st-char...@polymtl.ca
Signed-off-by: Pierre-Luc St-Charles pierre-luc.st-char...@polymtl.ca
---
src/bin/lttng-sessiond/consumer.c | 1 +
src/bin/lttng-sessiond/ust-metadata.c | 1 +
src/common/compat/socket.h| 9 +
3 files changed,
From: Pierre-Luc St-Charles pierre-luc.st-char...@polymtl.ca
Signed-off-by: Pierre-Luc St-Charles pierre-luc.st-char...@polymtl.ca
---
configure.ac | 18 ++
src/bin/lttng-sessiond/main.c | 8
2 files changed, 26 insertions(+)
diff --git a/configure.ac
Charles Briere:
Signed-off-by: Charles Briere charlesbriere.fla...@gmail.com
---
src/common/compat/Makefile.am | 3 ++-
src/common/compat/compat-signal.c | 14 ++
src/common/compat/signal.h| 14 ++
src/common/consumer-timer.c | 2 +-
Same, should be put in a compat layer.
Charles Briere:
From: Pierre-Luc St-Charles pierre-luc.st-char...@polymtl.ca
Signed-off-by: Pierre-Luc St-Charles pierre-luc.st-char...@polymtl.ca
---
configure.ac | 18 ++
src/bin/lttng-sessiond/main.c | 8
Why?
Thanks!
David
Charles Briere:
From: Pierre-Luc St-Charles pierre-luc.st-char...@polymtl.ca
Signed-off-by: Pierre-Luc St-Charles pierre-luc.st-char...@polymtl.ca
---
configure.ac | 315
---
1 file changed, 171 insertions(+),
Hi Charles,
These patches does not apply on git HEAD master...
Can you rebase and send me back the patches? I also just sent some
comments on most of them.
Since master is moving quite a bit these days, once rebased, send the
commit id you've been applying these on.
Thanks!
David
Charles
* David Goulet (dgou...@efficios.com) wrote:
Why?
cleaning up the configure.ac is a good thing. However, this patch should
probably be split into 3 patches.
1) Cleanup: configure.ac: replace space indents by tabs
2) Cleanup: configure.ac: regroup AC_ARG_WITH
3) Error message fix: configure.ac:
Hmm, I agree the 3+ patch split might be a better idea; as for the
'generalized coding style', it was more of a parenthesis usage
positionning cleanup to make sure the same style was applied everywhere (I
tried to pick whatever style was the most present at the time). There were
a lot of floating
On Thu, May 2, 2013 at 4:43 PM, Mathieu Desnoyers
mathieu.desnoy...@efficios.com wrote:
Jérémie, can you have a look at these questions ?
Thanks,
Mathieu
* Salman Rafiq (salman.ra...@esk.fraunhofer.de) wrote:
Hello All,
In continuation to my previous questions related to reading CTF
The calibrate function is just a rough sketch really. It could use some
more work, but it's very low priority for now.
If you feel like it, please open a feature request for this against
lttng-tools.
Thanks,
Mathieu
* Thibault, Daniel (daniel.thiba...@drdc-rddc.gc.ca) wrote:
I took note of
* Sebastian Andrzej Siewior (bige...@linutronix.de) wrote:
I started lltng to dump a few kernel events, nothing special. Once I had
the binary CTF I converted it to text output via
|babeltrace -w trace.txt kernel/
| [10:40:10.357768920] (+?.?) squsb kmalloc: { cpu_id = 3 }, {
Hi Vivek,
When reporting an issue, please provide:
- lttng-sessiond verbose logs, debug logs,
- detailed command line usage,
in text-only format. Sorry, we're kind of busy, so don't expect us to
dig this information from attachments.
The best way to do this is to file a bug on bugs.lttng.org,
* yin sun (sunyi...@gmail.com) wrote:
Hello,
Is there any example that a loadable kernel module utilize lttng
tracepoint to trace its own code. Not those ready made probes.
In this case, what minimal lttng modules do I have to load?
I guess you'll want to go by trial and error, and also
35 matches
Mail list logo