<div dir="ltr"><br><div class="gmail_extra"><br><br><div class="gmail_quote">On Thu, Jul 18, 2013 at 6:11 PM, Björn Brandenburg <span dir="ltr"><<a href="mailto:bbb@mpi-sws.org" target="_blank">bbb@mpi-sws.org</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div style="word-wrap:break-word"><div><div class="h5"><br><div><div>On Jul 18, 2013, at 10:51 PM, Daniel Bristot de Oliveira <<a href="mailto:danielbristot@gmail.com" target="_blank">danielbristot@gmail.com</a>> wrote:</div>
<br><blockquote type="cite"><div style="font-family:Helvetica;font-size:medium;font-style:normal;font-variant:normal;font-weight:normal;letter-spacing:normal;line-height:normal;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px">
I'm on a Ms in automation engineering at UFSC - Brazil, working with real time Linux, but, my works fits better on PREEMPT_RT, then I'm using it. I already have made tests with Litmus RT, but I'm not a Litmus RT expert. I'm interested to help.<span> </span><br>
<br>At my work (I work on a company too, where I use the PREEMPT_RT too) I have a Xeon E5620 @ 2.40GHz at my desk, where I compile the rebased-3.8.13.<br><br>I used the make localmodconfig, the config file is here:<span> </span><a href="http://www.bristot.eti.br/files/litmus/3_8_13/config" target="_blank">http://www.bristot.eti.br/files/litmus/3_8_13/config</a>, and I build the kernel as is on the git.<br>
<br>I got just one compilation problem:<br><br> CC kernel/sched/core.o<br>kernel/sched/core.c: In function ‘ttwu_queue’:<br>kernel/sched/core.c:1417:2: error: implicit declaration of function ‘is_realtime’ [-Werror=implicit-function-declaration]<br>
kernel/sched/core.c: In function ‘finish_task_switch’:<br>kernel/sched/core.c:1871:32: error: ‘NO_CPU’ undeclared (first use in this function)<br>kernel/sched/core.c:1871:32: note: each undeclared identifier is reported only once for each function it appears in<br>
kernel/sched/core.c: In function ‘__schedule’:<br>kernel/sched/core.c:3051:2: error: implicit declaration of function ‘srp_ceiling_block’ [-Werror=implicit-function-declaration]<br>kernel/sched/core.c: In function ‘__sched_setscheduler’:<br>
kernel/sched/core.c:3952:3: error: implicit declaration of function ‘litmus_admit_task’ [-Werror=implicit-function-declaration]<br>kernel/sched/core.c:4014:3: error: implicit declaration of function ‘litmus_exit_task’ [-Werror=implicit-function-declaration]<br>
kernel/sched/core.c:4021:50: error: ‘NO_CPU’ undeclared (first use in this function)<br>cc1: some warnings being treated as errors<br>make[2]: *** [kernel/sched/core.o] Error 1<br>make[1]: *** [kernel/sched] Error 2<br>make: *** [kernel] Error 2<br>
[root@localhost litmus-rt-preempt_rt]#<span> </span><br><br><br>that I fixed with this:<br><br>diff --git a/kernel/sched/core.c b/kernel/sched/core.c<br>index 2a6de74..c36d86d 100644<br>--- a/kernel/sched/core.c<br>+++ b/kernel/sched/core.c<br>
@@ -89,6 +89,7 @@<br> #include <litmus/trace.h><br> #include <litmus/sched_trace.h><br> #include <litmus/sched_plugin.h><br>+#include <litmus/litmus.h><br> <br> void litmus_tick(struct rq*, struct task_struct*);<br>
<br>the system is running, what's the next step? compile with PREEMPT_RT?</div></blockquote><br></div></div></div><div>Hi Daniel,</div><div><br></div><div>welcome! Thanks for joining the effort. With the running system, the next step would be to compile liblitmus (from the port-3.10 branch), pick a plugin with setsched, and run 'runtests', which runs the liblitmus test suite.</div>
</div></blockquote><div><br></div><div>Thanks :)<br><br></div><div>I'm in a meeting, away from my desk, and from Xeon too. But I build the LITMUS rebased-3.8.13 on a VM (KVM) on my notebook and run the test:<br><br>[root@localhost liblitmus]# ./setsched GSN-EDF<br>
[root@localhost liblitmus]# ./runtests <br>** LITMUS^RT test suite.<br>** Running tests for GSN-EDF.<br>** Testing: reject invalid rt_task pointers... ok.<br>** Testing: reject invalid rt_task values... ok.<br>** Testing: reject job control for non-rt tasks... ok.<br>
** Testing: children of RT tasks are not automatically RT tasks... ok.<br>** Testing: tasks have write access to /dev/litmus/ctrl mappings... ok.<br>** Testing: admission control handles suspended tasks correctly... ok.<br>
** Testing: admission control handles running tasks correctly... ok.<br>** Testing: FMLP no nesting allowed... <br>!! TEST FAILURE od = open_fmlp_sem(fd, 0) -> -1, Invalid argument<br> at tests/nesting.c:18 (test_lock_fmlp_nesting)<br>
in task PID=729<br>** Testing: reject invalid object descriptors... <br>!! TEST FAILURE litmus_lock(3) -> -1, Function not implemented (expected: EINVAL)<br> at tests/fdso.c:34 (test_invalid_od)<br> in task PID=730<br>
** Testing: reject invalid object types... ok.<br>** Testing: don't inherit FDSO handles across fork... <br>!! TEST FAILURE od = open_fmlp_sem(fd, 0) -> -1, Invalid argument<br> at tests/fdso.c:62 (test_not_inherit_od)<br>
in task PID=732<br>** Testing: don't let best-effort tasks lock FMLP semaphores... <br>!! TEST FAILURE od = open_fmlp_sem(fd, 0) -> -1, Invalid argument<br> at tests/locks.c:16 (test_not_lock_fmlp_be)<br> in task PID=733<br>
** Testing: FMLP acquisition and release... <br>!! TEST FAILURE od = open_fmlp_sem(fd, 0) -> -1, Invalid argument<br> at tests/locks.c:91 (test_lock_fmlp)<br> in task PID=734<br>** Result: 8 ok, 5 failed.<br><br></div>
<div>Dmesg:<br></div><div><br>[ 220.569011] Switching to LITMUS^RT plugin GSN-EDF.<br>[ 226.070144] Setting up rt task parameters for process 719.<br>[ 226.070149] Setting up rt task parameters for process 719.<br>[ 226.072635] Setting up rt task parameters for process 720.<br>
[ 226.072638] litmus: real-time task 720 rejected because task density > 1.0<br>[ 226.072640] Setting up rt task parameters for process 720.<br>[ 226.072641] Setting up rt task parameters for process 720.<br>[ 226.072642] litmus: real-time task 720 rejected because task density > 1.0<br>
[ 226.072643] Setting up rt task parameters for process -1.<br>[ 226.072644] Setting up rt task parameters for process 720.<br>[ 226.076256] Setting up rt task parameters for process 722.<br>[ 226.381512] Setting up rt task parameters for process 726.<br>
[ 226.597153] Setting up rt task parameters for process 728.<br>[ 226.700791] Setting up rt task parameters for process 729.<br>[ 226.700810] get_inode_obj(ffff88003b7d3f28, 0, 0): couldn't find object<br>[ 226.708555] get_inode_obj(ffff88003b7d3f28, 0, 0): couldn't find object<br>
[ 226.710410] get_inode_obj(ffff88003b7d3f28, 0, 0): couldn't find object<br>[ 226.712909] Setting up rt task parameters for process 734.<br>[ 226.712924] get_inode_obj(ffff88003b7d3f28, 0, 0): couldn't find object<br>
<br></div><div>I'll try it on xeon too.<br></div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div style="word-wrap:break-word"><div>
<br></div><div>If everything works, the second step would be to build the branch that includes PREEMPT_RT:</div><br><div><span style="white-space:pre-wrap"> </span><a href="https://github.com/LITMUS-RT/litmus-rt/commits/rebased-3.8.13-rt14" target="_blank">https://github.com/LITMUS-RT/litmus-rt/commits/rebased-3.8.13-rt14</a> <br>
</div></div></blockquote><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div style="word-wrap:break-word"><div><br></div><div>And then debug it… I assume we are breaking some PREEMPT_RT assumptions that will need fixing. If you have experience with PREEMPT_RT, you could help us out by suggesting fixes for bugs in LITMUS^RT.</div>
<div><br></div></div></blockquote><div><br></div><div>I use the PREEMPT RT it at work, I work in a R&D lab, developing telecommunication devices. On my Ms, I'm developing a new ftrace tracer plugin, and I'm using and analyzing the kernel with PREEMPT RT. I know how it works, the difference between the vanilla and the Preempt RT and some implementations, like the rt\_spinlocks.<br>
<br>I'm sorry, in advance, if I'm a little late in the answers, I work 44 hours/week and I'm finishing my ms degree, then, I'm a little busy... But I really want to find time to help.<br><br></div><div> </div>
<blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div style="word-wrap:break-word"><div></div><div>For example, rt_domain.c calls hrtimer_cancel() while (indirectly) holding a run queue lock. This works fine in mainline, but causes a recursive locking problem in PREEMPT_RT. Once that is fixed, I'm sure there will be more that breaks.</div>
<div><br></div></div></blockquote><div><br></div>If I can reproduce this on some machine here, I would like to debug, on this kind of bugs is where the fun lives :-)<br> <br><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
<div style="word-wrap:break-word"><div></div><div>Thanks,</div><div>Björn</div><div><br></div></div><br>_______________________________________________<br>
litmus-dev mailing list<br>
<a href="mailto:litmus-dev@lists.litmus-rt.org">litmus-dev@lists.litmus-rt.org</a><br>
<a href="https://lists.litmus-rt.org/listinfo/litmus-dev" target="_blank">https://lists.litmus-rt.org/listinfo/litmus-dev</a><br>
<br></blockquote></div><br><br clear="all"><br>-- <br>Daniel Bristot de Oliveira
</div></div>