[LITMUS^RT] Question about GSN-EDF in Litmus

Luo, Zheng luozheng at wustl.edu
Wed Nov 20 20:29:47 CET 2013


Thank is great. Does that mean I have to add


CONFIG_FEATHER_TRACE=y
CONFIG_SCHED_TASK_TRACE=y


after

#

# Tracing

#

# CONFIG_SCHED_LITMUS_TRACEPOINT is not set

# CONFIG_SCHED_DEBUG_TRACE is not set



Also, Do I have to set CONFIG_SCHED_LITMUS_TRACEPOINT =y nd CONFIG_SCHED_DEBUG_TRACE=y too?


Zheng Luo


________________________________
From: litmus-dev-bounces at lists.litmus-rt.org <litmus-dev-bounces at lists.litmus-rt.org> on behalf of Glenn Elliott <gelliott at cs.unc.edu>
Sent: Wednesday, November 20, 2013 12:09 PM
To: litmus-dev at lists.litmus-rt.org
Subject: Re: [LITMUS^RT] Question about GSN-EDF in Litmus

Hi Zheng,

I see your problem.  You need to enable the following options under the LITMUS^RT > Tracing kernel configuration menu:

CONFIG_FEATHER_TRACE (“Feather-Trace Infrastructure”)
CONFIG_SCHED_TASK_TRACE (“Trace real-time tasks”)

Once you boot into a properly configured kernel, you should see trace devices in “/dev/litmus/sched_trace<CPU#>”, one for each online CPU.

-Glenn


On Nov 20, 2013, at 1:32 PM, Luo, Zheng <luozheng at wustl.edu<mailto:luozheng at wustl.edu>> wrote:

Hello, I can not run the st_trace program, I think it may be the mis-configuration in the kernel. Can anyone help me where the configuration is wrong? I send the .config file as an attachment.

Zheng Luo

________________________________
From: litmus-dev-bounces at lists.litmus-rt.org<mailto:litmus-dev-bounces at lists.litmus-rt.org> <litmus-dev-bounces at lists.litmus-rt.org<mailto:litmus-dev-bounces at lists.litmus-rt.org>> on behalf of Luo, Zheng <luozheng at wustl.edu<mailto:luozheng at wustl.edu>>
Sent: Tuesday, November 19, 2013 2:38 PM
To: litmus-dev at lists.litmus-rt.org<mailto:litmus-dev at lists.litmus-rt.org>
Subject: Re: [LITMUS^RT] Question about GSN-EDF in Litmus

Sorry about the wrong file, here is the file.

Zheng Luo

________________________________
From: litmus-dev-bounces at lists.litmus-rt.org<mailto:litmus-dev-bounces at lists.litmus-rt.org> <litmus-dev-bounces at lists.litmus-rt.org<mailto:litmus-dev-bounces at lists.litmus-rt.org>> on behalf of Glenn Elliott <gelliott at cs.unc.edu<mailto:gelliott at cs.unc.edu>>
Sent: Tuesday, November 19, 2013 1:55 PM
To: litmus-dev at lists.litmus-rt.org<mailto:litmus-dev at lists.litmus-rt.org>
Subject: Re: [LITMUS^RT] Question about GSN-EDF in Litmus

Hi Zheng,

I am actually interested in litmus-rt/.config, not these.

Thanks,
Glenn


On Nov 19, 2013, at 3:41 PM, Luo, Zheng <luozheng at wustl.edu<mailto:luozheng at wustl.edu>> wrote:

I send you both .config in ft_trace and liblitmus.

Since the .config can not be send directly, I rename the files.

Zheng Luo

________________________________
From: litmus-dev-bounces at lists.litmus-rt.org<mailto:litmus-dev-bounces at lists.litmus-rt.org> <litmus-dev-bounces at lists.litmus-rt.org<mailto:litmus-dev-bounces at lists.litmus-rt.org>> on behalf of Glenn Elliott <gelliott at cs.unc.edu<mailto:gelliott at cs.unc.edu>>
Sent: Tuesday, November 19, 2013 11:40 AM
To: litmus-dev at lists.litmus-rt.org<mailto:litmus-dev at lists.litmus-rt.org>
Subject: Re: [LITMUS^RT] Question about GSN-EDF in Litmus

Would you mind sharing your .config?

On Nov 19, 2013, at 11:56 AM, Luo, Zheng <luozheng at wustl.edu<mailto:luozheng at wustl.edu>> wrote:

Thanks Glenn,

I used it to measure the time, but I have some problems with it. I tried to started the ./st_trace, but I got some error message. All the output is in the screenshot.

Also, there is error message in the st--bin files. And the sched_trace0, sched_trace1, sched_trace2, sched_trace3 are all empty.  The simple code that I used to test is the base_mt_task.c.

I am really confused, can you help me figure that out where I am wrong? Because you mentioned that Litums can trace time in a more fine_grained way. Therefore I will not count the clock cycle from the user space.

Thank you very much. Looking forward to your reply.

Zheng Luo

________________________________
From: litmus-dev-bounces at lists.litmus-rt.org<mailto:litmus-dev-bounces at lists.litmus-rt.org> <litmus-dev-bounces at lists.litmus-rt.org<mailto:litmus-dev-bounces at lists.litmus-rt.org>> on behalf of Glenn Elliott <gelliott at cs.unc.edu<mailto:gelliott at cs.unc.edu>>
Sent: Monday, November 18, 2013 11:52 AM
To: litmus-dev at lists.litmus-rt.org<mailto:litmus-dev at lists.litmus-rt.org>
Subject: Re: [LITMUS^RT] Question about GSN-EDF in Litmus

I believe your questions may be answered by the Litmus tracing tutorial: https://wiki.litmus-rt.org/litmus/Tracing

While you should read the whole tutorial, you will be most interested in the “Recording Scheduling Traces” section.

You’ll use the feather-trace tools to capture the logs.  Then you can use Björn’s sched-trace-tools for analyzing them: https://github.com/brandenburg/sched-trace-tools

-Glenn


On Nov 18, 2013, at 10:56 AM, Luo, Zheng <luozheng at wustl.edu<mailto:luozheng at wustl.edu>> wrote:

Thank you very much for the reply. That is very helpful. In the email, you mentioned that I can also use Litmus’s sched_trace logs to get more accurate information on job release times, completion times, and many other events. I was wondering where that program is?

Is it the program in the folder ft_tools, named st_trace? It seems that I can not get the data properly from it.

Also, is there any good documentation of Litmus? I sometimes feel very hard to figure out the function of each program.

Thank you very much. Looking forward to your reply.

Zheng Luo

________________________________
From: litmus-dev-bounces at lists.litmus-rt.org<mailto:litmus-dev-bounces at lists.litmus-rt.org> <litmus-dev-bounces at lists.litmus-rt.org<mailto:litmus-dev-bounces at lists.litmus-rt.org>> on behalf of Glenn Elliott <gelliott at cs.unc.edu<mailto:gelliott at cs.unc.edu>>
Sent: Saturday, November 16, 2013 8:09 AM
To: litmus-dev at lists.litmus-rt.org<mailto:litmus-dev at lists.litmus-rt.org>
Subject: Re: [LITMUS^RT] Question about GSN-EDF in Litmus

Hi Zheng,

The general structure of a typical litmus application looks like this:

init_litmus(); /* initialize litmus (basically just pins the programs memory to avoid page faults) */
set_rt_task_param();  /* set task params, such as period, relative deadline, execution time, etc. */
task_mode(LITMUS_RT_TASK); /* become a real-time task */
wait_for_ts_release(); /* wait for synchronous task set release—i.e., until liblitmus’s release_ts program is run */
while(running) { /* keep executing jobs until task should exit */
   do_work();  /* do the actual work of a job */
   sleep_next_period();  /* sleep until next job release */
}
task_mode(BACKGROUND_TASK); /* exit real-time mode */
exit(0);

You can take a look at liblitmus/bin/rtspin.c and liblitmus/bin/base_task.c for examples.  (Note: Use of wait_for_ts_release() is optional.  However, without it, you may want to swap the order of sleep_next_period() and do_work().)

The structure of your program is incorrect:

init_litmus();
set_rt_task_param();
task_mode(LITMUS_RT_TASK);
task_mode(BACKGROUND_TASK);
job();

Problems:
1) job() is not in a loop.  (This would only be correct if you were doing real-time job shop scheduling.)
2) job() should be between task_mode(LITMUS_RT_TASK) and task_mode(BACKGROUND_TASK).  You only need to call task_mode(LITMUS_RT_TASK) once per task, not once per job.

One last comment: It looks like you are reading the time stamp counter to trace start and finish times.  This is fine in the correct context, but you can also use Litmus’s sched_trace logs to get more accurate information on job release times, completion times, and many other events.  In general, you have to be careful measuring times in userspace.  For instance, you cannot measure job release times in userspace because a job may not be immediately scheduled when it is released (there might be higher-priority work that needs to be scheduled first).  Thus, a userspace release measurement would have an error of (time the job was first scheduled - true release time).  It’s best if you use sched_trace logs to get accurate data.

-Glenn


On Nov 16, 2013, at 2:37 AM, Luo, Zheng <luozheng at wustl.edu<mailto:luozheng at wustl.edu>> wrote:

Hi All,

I am a master's student in Washington University who is doing research on realtime system. I installed Litmus because it has the global EDF scheduler. However when I do a simple experiment by using it. I simply can not get the right result. The EDF scheduler acts like a round robing scheduler. I don't know where I did wrong. The Litmus I installed is LITMUS-RT Version 2013.1.

I put my source code as a attachment, and also the screenshot of the result. Hope you can help me with. Thank you very much. Looking forward to your reply.

Zheng Luo
<Screenshot 2013-11-15 21:30:34.png><test_mt_task.c>_______________________________________________
litmus-dev mailing list
litmus-dev at lists.litmus-rt.org<mailto:litmus-dev at lists.litmus-rt.org>
https://lists.litmus-rt.org/listinfo/litmus-dev

_______________________________________________
litmus-dev mailing list
litmus-dev at lists.litmus-rt.org<mailto:litmus-dev at lists.litmus-rt.org>
https://lists.litmus-rt.org/listinfo/litmus-dev

<base_mt_task.c><Screenshot 2013-11-19 10:40:24.png><st--0.bin><st--1.bin><st--2.bin><st--3.bin>_______________________________________________
litmus-dev mailing list
litmus-dev at lists.litmus-rt.org<mailto:litmus-dev at lists.litmus-rt.org>
https://lists.litmus-rt.org/listinfo/litmus-dev

<config_ft_trace><config_liblitmus>_______________________________________________
litmus-dev mailing list
litmus-dev at lists.litmus-rt.org<mailto:litmus-dev at lists.litmus-rt.org>
https://lists.litmus-rt.org/listinfo/litmus-dev

<config_litmusrt>_______________________________________________
litmus-dev mailing list
litmus-dev at lists.litmus-rt.org<mailto:litmus-dev at lists.litmus-rt.org>
https://lists.litmus-rt.org/listinfo/litmus-dev

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.litmus-rt.org/pipermail/litmus-dev/attachments/20131120/ac9f3028/attachment.html>


More information about the litmus-dev mailing list