[Starpu-devel] StarPU: subgraph_repeat_regenerate.c

[Olivier Aumage <olivier.aumage@inria.fr>]

Hi,

I am frequently experiencing crashes with the 'subgraph_repeat_regenerate' 
test of the StarPU test suite.
The crashes frequency is about 1 crash out of 5 runs with '--enable-debug' 
enabled. Frequency is slightly higher without --enable-debug 

The machine used is a regular node from the PlaFRIM machine without GPU (e.g. 
a 'fourmi' node).

Module list:
------------
  1) tools/svn/1.6.11        6) compiler/gcc/4.6.0
  2) lib/gmp/5.0.1           7) tools/autoconf/2.68
  3) lib/mpfr/3.0.0          8) tools/automake/1.11.1
  4) lib/mpc/0.8.2           9) tools/libtool/2.4
  5) lib/libelf/0.8.13

Configure settings:
-------------------
../trunk/configure --prefix=/home/aumage/SVN/StarPU/install 
--with-fxt=/home/aumage/local/src/FxT/install --enable-gcc-extensions 
--disable-cuda --enable-debug

Program output:
---------------
./subgraph_repeat_regenerate
pthread_mutex_lock : Invalid argument
Abandon (core dumped)

GDB output:
-----------
Core was generated by `./subgraph_repeat_regenerate'.
Program terminated with signal 6, Aborted.
#0  0x00007f445a2f7645 in raise () from /lib64/libc.so.6
(gdb) bt
#0  0x00007f445a2f7645 in raise () from /lib64/libc.so.6
#1  0x00007f445a2f8c33 in abort () from /lib64/libc.so.6
#2  0x00007f445a630764 in _starpu_submit_job (j=0x7f444c001350, 
do_not_increment_nsubmitted=1) at ../../trunk/src/core/task.c:209
#3  0x00007f445a62fd0c in _starpu_handle_job_termination (j=0x7f444c001350, 
job_is_already_locked=0) at ../../trunk/src/core/jobs.c:229
#4  0x00007f445a65e7cb in _starpu_cpu_worker (arg=0x7f445a874a40) at 
../../trunk/src/drivers/cpu/driver_cpu.c:197
#5  0x00007f4459829070 in start_thread () from /lib64/libpthread.so.0
#6  0x00007f445a39810d in clone () from /lib64/libc.so.6
#7  0x0000000000000000 in ?? ()

Note: every coredump I got shows the same backtrace with the location of the 
bug at task.c:209
-- 
Olivier