Gustavo Bittencourt | 30 Mar 15:49 2015
Picon

Re: Tracing within functions.

I think you can use FTRACE (http://lwn.net/Articles/365835/) and set
function_graph as the tracer. To filter the output, you must enable
CONFIG_DYNAMIC_FTRACE and set which function should be traced.

On Sun, Mar 29, 2015 at 5:16 PM, Andy Ng <andreas2025 <at> gmail.com> wrote:
> Hello,
>
> I am using an RT kernel and in my  driver there is  an atomic code
> path that just makes some critical I/O operations. I would like to
> trigger a system function trace when kernel enters into a specific
> function in my driver and stop the system trace at the end of the
> function. I would like to identify time execution latencies for a
> specific code path. I am using Cortex A9 and I have perf and PMU up
> and running, but still it is not clear to me how to retrieve the
> traces with those latencies in my code path.
>
> Any ideas how to trace/measure that  will be very much appreciated.
>
> Best regards,
> Andy
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in
> the body of a message to majordomo <at> vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in
the body of a message to majordomo <at> vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

(Continue reading)

Andy Ng | 29 Mar 22:16 2015
Picon

Tracing within functions.

Hello,

I am using an RT kernel and in my  driver there is  an atomic code
path that just makes some critical I/O operations. I would like to
trigger a system function trace when kernel enters into a specific
function in my driver and stop the system trace at the end of the
function. I would like to identify time execution latencies for a
specific code path. I am using Cortex A9 and I have perf and PMU up
and running, but still it is not clear to me how to retrieve the
traces with those latencies in my code path.

Any ideas how to trace/measure that  will be very much appreciated.

Best regards,
Andy
--
To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in
the body of a message to majordomo <at> vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Daniel Kasak | 29 Mar 00:55 2015
Picon

Re: btrfs and linux-rt

I've tested with 3.18.9-rt5, and I'm happy to report that this kernel
works fine for me :)

Dan

On Sat, Mar 14, 2015 at 5:51 PM, Daniel Kasak <d.j.kasak.dk <at> gmail.com> wrote:
> Interesting.
>
> Nah I wasn't doing anything special with btrfs. I'll try again with a 3.18
> kernel and see if it's magically resolved :)
>
> Dan
>
> On Sat, Mar 14, 2015 at 8:14 AM, Sebastian Andrzej Siewior
> <bigeasy <at> linutronix.de> wrote:
>>
>> * Sebastian Andrzej Siewior | 2015-03-13 12:38:32 [+0100]:
>>
>> >I remember some people complained about btrfs. I then bootet a kvm
>> >machine with btrfs as rootfs and it worked fineā€¦ Are you using some
>> >"special" btrfs features or is this just a plain install?
>>
>> Okay. Among other things I manged to install fc21 on btrfs and it
>> booted (well systemd complain about missing things and did not want to
>> continue but I got a shell and could login which means btrfs got
>> mounted).
>>
>> >>Thanks :)
>> >>
>> >>Dan
(Continue reading)

Steven Rostedt | 20 Mar 16:30 2015

[ANNOUNCE] 3.4.106-rt132


Dear RT Folks,

I'm pleased to announce the 3.4.106-rt132 stable release.


You can get this release via the git tree at:

  git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-stable-rt.git

  branch: v3.4-rt
  Head SHA1: f375b23874f95d56e5fcc24c07504f626bd6aee6


Or to build 3.4.106-rt132 directly, the following patches should be applied:

  http://www.kernel.org/pub/linux/kernel/v3.x/linux-3.4.tar.xz

  http://www.kernel.org/pub/linux/kernel/v3.x/patch-3.4.106.xz

  http://www.kernel.org/pub/linux/kernel/projects/rt/3.4/patch-3.4.106-rt132.patch.xz



You can also build from 3.4.106-rt131 by applying the incremental patch:

  http://www.kernel.org/pub/linux/kernel/projects/rt/3.4/incr/patch-3.4.106-rt131-rt132.patch.xz



(Continue reading)

Steven Rostedt | 18 Mar 19:49 2015

[PATCH v5] sched/rt: Use IPI to trigger RT task push migration instead of pulling


When debugging the latencies on a 40 core box, where we hit 300 to
500 microsecond latencies, I found there was a huge contention on the
runqueue locks.

Investigating it further, running ftrace, I found that it was due to
the pulling of RT tasks.

The test that was run was the following:

 cyclictest --numa -p95 -m -d0 -i100

This created a thread on each CPU, that would set its wakeup in iterations
of 100 microseconds. The -d0 means that all the threads had the same
interval (100us). Each thread sleeps for 100us and wakes up and measures
its latencies.

cyclictest is maintained at:
 git://git.kernel.org/pub/scm/linux/kernel/git/clrkwllms/rt-tests.git

What happened was another RT task would be scheduled on one of the CPUs
that was running our test, when the other CPU tests went to sleep and
scheduled idle. This caused the "pull" operation to execute on all
these CPUs. Each one of these saw the RT task that was overloaded on
the CPU of the test that was still running, and each one tried
to grab that task in a thundering herd way.

To grab the task, each thread would do a double rq lock grab, grabbing
its own lock as well as the rq of the overloaded CPU. As the sched
domains on this box was rather flat for its size, I saw up to 12 CPUs
(Continue reading)

Steven Rostedt | 18 Mar 15:02 2015

[PATCH] Linux 3.4.106-rt132-rc4


Dear RT Folks,

This is the RT stable review cycle of patch 3.4.106-rt132-rc4.

Please scream at me if I messed something up. Please test the patches too.

The -rc release will be uploaded to kernel.org and will be deleted when
the final release is out. This is just a review release (or release candidate).

The pre-releases will not be pushed to the git repository, only the
final release is.

If all goes well, this patch will be converted to the next main release
on 3/20/2015.

Enjoy,

-- Steve

To build 3.4.106-rt132-rc4 directly, the following patches should be applied:

  http://www.kernel.org/pub/linux/kernel/v3.x/linux-3.4.tar.xz

  http://www.kernel.org/pub/linux/kernel/v3.x/patch-3.4.106.xz

  http://www.kernel.org/pub/linux/kernel/projects/rt/3.4/patch-3.4.106-rt132-rc4.patch.xz

You can also build from 3.4.106-rt131 by applying the incremental patch:

(Continue reading)

Steven Rostedt | 18 Mar 14:43 2015

[PATCH] Linux 3.14.34-rt32-rc4


Dear RT Folks,

This is the RT stable review cycle of patch 3.14.34-rt32-rc4.

Please scream at me if I messed something up. Please test the patches too.

The -rc release will be uploaded to kernel.org and will be deleted when
the final release is out. This is just a review release (or release candidate).

The pre-releases will not be pushed to the git repository, only the
final release is.

If all goes well, this patch will be converted to the next main release
on 3/20/2015.

Enjoy,

-- Steve

To build 3.14.34-rt32-rc4 directly, the following patches should be applied:

  http://www.kernel.org/pub/linux/kernel/v3.x/linux-3.14.tar.xz

  http://www.kernel.org/pub/linux/kernel/v3.x/patch-3.14.34.xz

  http://www.kernel.org/pub/linux/kernel/projects/rt/3.14/patch-3.14.34-rt32-rc4.patch.xz

You can also build from 3.14.34-rt31 by applying the incremental patch:

(Continue reading)

Steven Rostedt | 17 Mar 23:27 2015

[PATCH] Linux 3.2.68-rt99-rc3


Dear RT Folks,

This is the RT stable review cycle of patch 3.2.68-rt99-rc3.

Please scream at me if I messed something up. Please test the patches too.

The -rc release will be uploaded to kernel.org and will be deleted when
the final release is out. This is just a review release (or release candidate).

The pre-releases will not be pushed to the git repository, only the
final release is.

If all goes well, this patch will be converted to the next main release
on 3/20/2015.

Enjoy,

-- Steve

To build 3.2.68-rt99-rc3 directly, the following patches should be applied:

  http://www.kernel.org/pub/linux/kernel/v3.x/linux-3.2.tar.xz

  http://www.kernel.org/pub/linux/kernel/v3.x/patch-3.2.68.xz

  http://www.kernel.org/pub/linux/kernel/projects/rt/3.2/patch-3.2.68-rt99-rc3.patch.xz

You can also build from 3.2.68-rt98 by applying the incremental patch:

(Continue reading)

Steven Rostedt | 17 Mar 23:23 2015

[PATCH] Linux 3.10.70-rt75-rc3


Dear RT Folks,

This is the RT stable review cycle of patch 3.10.70-rt75-rc3.

Please scream at me if I messed something up. Please test the patches too.

The -rc release will be uploaded to kernel.org and will be deleted when
the final release is out. This is just a review release (or release candidate).

The pre-releases will not be pushed to the git repository, only the
final release is.

If all goes well, this patch will be converted to the next main release
on 3/20/2015.

Enjoy,

-- Steve

To build 3.10.70-rt75-rc3 directly, the following patches should be applied:

  http://www.kernel.org/pub/linux/kernel/v3.x/linux-3.10.tar.xz

  http://www.kernel.org/pub/linux/kernel/v3.x/patch-3.10.70.xz

  http://www.kernel.org/pub/linux/kernel/projects/rt/3.10/patch-3.10.70-rt75-rc3.patch.xz

You can also build from 3.10.70-rt74 by applying the incremental patch:

(Continue reading)

Steven Rostedt | 17 Mar 23:21 2015

[PATCH] Linux 3.12.38-rt53-rc3


Dear RT Folks,

This is the RT stable review cycle of patch 3.12.38-rt53-rc3.

Please scream at me if I messed something up. Please test the patches too.

The -rc release will be uploaded to kernel.org and will be deleted when
the final release is out. This is just a review release (or release candidate).

The pre-releases will not be pushed to the git repository, only the
final release is.

If all goes well, this patch will be converted to the next main release
on 3/20/2015.

Enjoy,

-- Steve

To build 3.12.38-rt53-rc3 directly, the following patches should be applied:

  http://www.kernel.org/pub/linux/kernel/v3.x/linux-3.12.tar.xz

  http://www.kernel.org/pub/linux/kernel/v3.x/patch-3.12.38.xz

  http://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patch-3.12.38-rt53-rc3.patch.xz

You can also build from 3.12.38-rt52 by applying the incremental patch:

(Continue reading)

Steven Rostedt | 17 Mar 17:38 2015

[PATCH RT 1/2] fs,btrfs: fix rt deadlock on extent_buffer->lock

3.4.106-rt132-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Mike Galbraith <mgalbraith <at> suse.de>

Sat Jul 14 12:30:41 CEST 2012

Trivially repeatable deadlock is cured by enabling lockdep code in
btrfs_clear_path_blocking() as suggested by Chris Mason.  He also
suggested restricting blocking reader count to one, and not allowing
a spinning reader while blocking reader exists.  This has proven to
be unnecessary, the strict lock order enforcement is enough.. or
rather that's my box's opinion after long hours of hard pounding.

Note: extent-tree.c bit is additional recommendation from Chris
      Mason, split into a separate patch after discussion.

Link: http://lkml.kernel.org/r/1414913478.5380.114.camel <at> marge.simpson.net

Cc: linux-rt-users <linux-rt-users <at> vger.kernel.org>
Cc: Thomas Gleixner <tglx <at> linutronix.de>
Cc: Carsten Emde <C.Emde <at> osadl.org>
Cc: John Kacur <jkacur <at> redhat.com>
Cc: Sebastian Andrzej Siewior <bigeasy <at> linutronix.de>
Cc: Clark Williams <williams <at> redhat.com>
Cc: Chris Mason <chris.mason <at> fusionio.com>
Signed-off-by: Mike Galbraith <efault <at> gmx.de>
Signed-off-by: Steven Rostedt <rostedt <at> goodmis.org>
(Continue reading)


Gmane