Logo AND Algorithmique Numérique Distribuée

Public GIT Repository
simgrid.git
7 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Augustin Degomme [Wed, 13 Feb 2013 09:51:39 +0000 (10:51 +0100)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

7 years agoword was missing, rephrase.
suter [Wed, 13 Feb 2013 09:51:08 +0000 (10:51 +0100)]
word was missing, rephrase.

7 years agoadd another word about the trap of dynar_search with pointed elements
Martin Quinson [Wed, 13 Feb 2013 08:07:59 +0000 (09:07 +0100)]
add another word about the trap of dynar_search with pointed elements

7 years agoTypos: binded -> bound.
Arnaud Giersch [Tue, 12 Feb 2013 23:52:41 +0000 (00:52 +0100)]
Typos: binded -> bound.

7 years agodocument that it's safe to interrupt a foreach with a break or return statement
Martin Quinson [Wed, 13 Feb 2013 00:02:54 +0000 (01:02 +0100)]
document that it's safe to interrupt a foreach with a break or return statement

7 years agodocument that the search function on dynar don't work well with pointed values
Martin Quinson [Wed, 13 Feb 2013 00:00:34 +0000 (01:00 +0100)]
document that the search function on dynar don't work well with pointed values

7 years agoSet correct NATIVE folder for 32bits x86.
Arnaud Giersch [Tue, 12 Feb 2013 22:50:01 +0000 (23:50 +0100)]
Set correct NATIVE folder for 32bits x86.

7 years agoSet cmake_minimum_version for the Java bindings.
Arnaud Giersch [Tue, 12 Feb 2013 22:26:55 +0000 (23:26 +0100)]
Set cmake_minimum_version for the Java bindings.

UseJava.cmake don't exist before cmake 2.8.6.

7 years agoMove Java build rules in a separate cmake file.
Arnaud Giersch [Tue, 12 Feb 2013 21:22:04 +0000 (22:22 +0100)]
Move Java build rules in a separate cmake file.

7 years agoFix build warnings on 32bits archs.
Arnaud Giersch [Tue, 12 Feb 2013 20:53:53 +0000 (21:53 +0100)]
Fix build warnings on 32bits archs.

Use intermediate type intptr_t for conversions between pointer
types and jlong.

7 years agoTry to make the smpi-mpich-env test more robust in multitasking environments.
Arnaud Giersch [Tue, 12 Feb 2013 16:48:16 +0000 (17:48 +0100)]
Try to make the smpi-mpich-env test more robust in multitasking environments.

Only select the processes that share the same session ID.

7 years agoInitialize variable, and make gcc happy.
Arnaud Giersch [Tue, 12 Feb 2013 15:08:08 +0000 (16:08 +0100)]
Initialize variable, and make gcc happy.

7 years agoReindent.
Arnaud Giersch [Tue, 12 Feb 2013 15:06:13 +0000 (16:06 +0100)]
Reindent.

7 years agoKill unused variable.
Arnaud Giersch [Tue, 12 Feb 2013 14:58:57 +0000 (15:58 +0100)]
Kill unused variable.

7 years agoAdd missing declaration.
Arnaud Giersch [Tue, 12 Feb 2013 14:57:52 +0000 (15:57 +0100)]
Add missing declaration.

Plus whitespace cleanup.

7 years agoissend should be treated as isend, even if not detached
Augustin Degomme [Tue, 12 Feb 2013 14:27:31 +0000 (15:27 +0100)]
issend should be treated as isend, even if not detached

7 years agocorrect behavior of MPI_Send which used to values of MPI_Isend timing factors
Augustin Degomme [Tue, 12 Feb 2013 14:15:33 +0000 (15:15 +0100)]
correct behavior of MPI_Send which used to values of MPI_Isend timing factors

7 years agoUpdate .gitgnore.
Arnaud Giersch [Tue, 12 Feb 2013 13:31:14 +0000 (14:31 +0100)]
Update .gitgnore.

Match any build directory named "build_*", and add etags' tag table.

7 years agoTests msg-bittorrent-*-parallel are not broken anymore.
Arnaud Giersch [Tue, 12 Feb 2013 13:20:04 +0000 (14:20 +0100)]
Tests msg-bittorrent-*-parallel are not broken anymore.

7 years agoFix the parallel execution for the bittorrent example.
Arnaud Giersch [Tue, 12 Feb 2013 13:14:50 +0000 (14:14 +0100)]
Fix the parallel execution for the bittorrent example.

The problem was that RngStream creation is not thread safe.  Furthermore,
each created RngStream is dependent of the previously created RngStreams.

The problem is circumvented by creating the RngStreams before the launch
of the application.  Each host has its own stream, that can be retrieved
through MSG_host_get_data().

7 years agoFix double free error.
Arnaud Giersch [Tue, 12 Feb 2013 00:10:49 +0000 (01:10 +0100)]
Fix double free error.

Error reported by Borja Bergua, and patch inspired by Martin
Quinson's proposal.

7 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Jonathan Rouzaud-Cornabas [Tue, 12 Feb 2013 13:39:29 +0000 (14:39 +0100)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

7 years agoBounded receive
Jonathan Rouzaud-Cornabas [Tue, 12 Feb 2013 13:39:05 +0000 (14:39 +0100)]
Bounded receive

7 years agoadd an smpi/ois factor, to account for the fact that MPI_Send and MPI_Isend internal...
Augustin Degomme [Mon, 11 Feb 2013 17:27:33 +0000 (18:27 +0100)]
add an smpi/ois factor, to account for the fact that MPI_Send and MPI_Isend internal times may be differents

7 years agoactivate a bunch of tests using mpi_ssend, and change back those where they had been...
Augustin Degomme [Mon, 11 Feb 2013 17:22:17 +0000 (18:22 +0100)]
activate a bunch of tests using mpi_ssend, and change back those where they had been changed to mpi_send

7 years agoadd support for Ssend/Issend in SMPI
Augustin Degomme [Mon, 11 Feb 2013 16:43:44 +0000 (17:43 +0100)]
add support for Ssend/Issend in SMPI

7 years agoRevert "always have display_timing activated for smpi, as it is quite useful"
Augustin Degomme [Mon, 11 Feb 2013 15:33:26 +0000 (16:33 +0100)]
Revert "always have display_timing activated for smpi, as it is quite useful"

This reverts commit f641b68a3c807956396f8f70965ce9c4644dcfa5.

7 years agoadd option to set the threshold where smpi send stops behaving like isend.
Augustin Degomme [Mon, 11 Feb 2013 14:50:16 +0000 (15:50 +0100)]
add option to set the threshold where smpi send stops behaving like isend.
This was hardcoded to 65536, but experiments show that sometimes 327680 might be better

7 years agosmall change for smpi win
Augustin Degomme [Mon, 11 Feb 2013 14:49:08 +0000 (15:49 +0100)]
small change for smpi win

7 years agobug : smpi tracing options were replacing those the user had set
Augustin Degomme [Mon, 11 Feb 2013 14:46:59 +0000 (15:46 +0100)]
bug : smpi tracing options were replacing those the user had set

7 years agosmall fixes to repair unix build
Augustin Degomme [Tue, 5 Feb 2013 17:27:08 +0000 (18:27 +0100)]
small fixes to repair unix build

7 years agorename main function for windows
Augustin Degomme [Tue, 5 Feb 2013 17:19:47 +0000 (18:19 +0100)]
rename main function for windows

7 years agoseveral changes in the way cmake handles windows
Augustin Degomme [Tue, 5 Feb 2013 17:19:27 +0000 (18:19 +0100)]
several changes in the way cmake handles windows

7 years agoresolve cmakelists conflict
Augustin Degomme [Mon, 11 Feb 2013 15:19:13 +0000 (16:19 +0100)]
resolve cmakelists conflict

7 years agoremove a few unused things for win, but we have more bugs after ..
Augustin Degomme [Tue, 5 Feb 2013 17:16:09 +0000 (18:16 +0100)]
remove a few unused things for win, but we have more bugs after ..

7 years agovarious fixes to hopefully compile under win32
Augustin Degomme [Tue, 5 Feb 2013 17:14:38 +0000 (18:14 +0100)]
various fixes to hopefully compile under win32

7 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Augustin Degomme [Mon, 11 Feb 2013 14:50:39 +0000 (15:50 +0100)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

7 years agohandle new action trace files properly
suter [Fri, 8 Feb 2013 15:13:17 +0000 (16:13 +0100)]
handle new action trace files properly

7 years agoadd three more tests to smpi_replay : alltoall, alltoallv and waitall
suter [Fri, 8 Feb 2013 15:12:35 +0000 (16:12 +0100)]
add three more tests to smpi_replay : alltoall, alltoallv and waitall

7 years agonew traces files were added in examples/smpi/replay. treat them as the
suter [Fri, 8 Feb 2013 15:11:53 +0000 (16:11 +0100)]
new traces files were added in examples/smpi/replay. treat them as the
others

7 years agoFixing a possible bug, I should use parse_double() instead of atoi() if I want to...
George Markomanolis [Fri, 8 Feb 2013 12:02:24 +0000 (14:02 +0200)]
Fixing a possible bug, I should use parse_double() instead of atoi() if I want to handle values like 5e8. Adding examples for MPI_Alltoallv, MPI_Alltoall, MPI_Bcast/MPI_Reduce with various datatypes and MPI_Waitall.

7 years agorewriting
suter [Fri, 8 Feb 2013 09:56:07 +0000 (10:56 +0100)]
rewriting

7 years agorevalidate tesh file as the reduce action has been modified
suter [Fri, 8 Feb 2013 09:52:28 +0000 (10:52 +0100)]
revalidate tesh file as the reduce action has been modified

7 years agoMake this part automatically generated.
Arnaud Giersch [Thu, 7 Feb 2013 22:13:55 +0000 (23:13 +0100)]
Make this part automatically generated.

And avoid to give a direct link to the archive, since it's too error prone.

7 years agoTypo.
Arnaud Giersch [Thu, 7 Feb 2013 21:54:51 +0000 (22:54 +0100)]
Typo.

7 years agoFix the download link in the install documentation
Martin Quinson [Thu, 7 Feb 2013 20:15:21 +0000 (21:15 +0100)]
Fix the download link in the install documentation

7 years agoops, didn't knew how gforge downloads work, actually
Martin Quinson [Thu, 7 Feb 2013 20:10:50 +0000 (21:10 +0100)]
ops, didn't knew how gforge downloads work, actually

7 years agoa more welcoming README file
Martin Quinson [Thu, 7 Feb 2013 01:18:30 +0000 (02:18 +0100)]
a more welcoming README file

7 years agoSeed the random generators before the main()
Martin Quinson [Thu, 7 Feb 2013 01:14:02 +0000 (02:14 +0100)]
Seed the random generators before the main()

Otherwise, it is possible that the user set the seed s/he wants before
initializing simgrid, that would then override it with another seed.
That would be a *very mean* side effect of initializing simgrid :)

7 years agoUpdating the Changelog for the SMPI replay tool
George Markomanolis [Thu, 7 Feb 2013 17:12:24 +0000 (19:12 +0200)]
Updating the Changelog for the SMPI replay tool

7 years agoNow the SMPI replay tool supports the modified MPE profiling tool.
George Markomanolis [Thu, 7 Feb 2013 16:38:39 +0000 (18:38 +0200)]
Now the SMPI replay tool supports the modified MPE profiling tool.
What is new:
1) For most of the collective communications we can know exactly which rank is the root one.
2) Now we can include in the traces the real used MPI datatype (till know we were using the MPI_BYTE). Also we can have multiple datatypes in the traces.
3) The tool supports both time-independent traces from the TAU and the modified MPE tools.
4) Fix Reduce action, as there was no information about computation load.

7 years agoAdd a new simcall that modifies the rate of the first smx_action_t on smx_rdv_t
Jonathan Rouzaud-Cornabas [Thu, 7 Feb 2013 14:04:11 +0000 (15:04 +0100)]
Add a new simcall that modifies the rate of the first smx_action_t on smx_rdv_t

7 years agoTry to make simdag-test-dotload reproducible.
Arnaud Giersch [Thu, 7 Feb 2013 13:39:44 +0000 (14:39 +0100)]
Try to make simdag-test-dotload reproducible.

Comment extracted from this patch:
  /* Hack: circumvent a bug in libcgraph, where the edges are not always given
   * back in creation order.  We sort them again, according to their sequence
   * id.  The problem appears to be solved (i.e.: I did not test it) in
   * graphviz' mercurial repository by the following changeset:
   *    changeset:   8431:d5f1fb7e8103
   *    user:        Emden Gansner <erg@research.att.com>
   *    date:        Tue Oct 11 12:38:58 2011 -0400
   *    summary:     Make sure edges are stored in node creation order
   * It should be fixed in graphviz 2.30 and above.
   */

7 years agoReturn MPI_UNDEFINED for negative values too.
Arnaud Giersch [Wed, 6 Feb 2013 21:40:14 +0000 (22:40 +0100)]
Return MPI_UNDEFINED for negative values too.

7 years agoUse MPI_ANY_SOURCE instead of -1.
Arnaud Giersch [Wed, 6 Feb 2013 21:39:51 +0000 (22:39 +0100)]
Use MPI_ANY_SOURCE instead of -1.

7 years agoAvoid to modify lib while it's been iterated.
Arnaud Giersch [Wed, 6 Feb 2013 20:38:55 +0000 (21:38 +0100)]
Avoid to modify lib while it's been iterated.

7 years agoMSG_comm_get_status must be called before MSG_comm_destroy.
Arnaud Giersch [Wed, 6 Feb 2013 20:26:17 +0000 (21:26 +0100)]
MSG_comm_get_status must be called before MSG_comm_destroy.

7 years agoExclude Java tests from memcheck.
Arnaud Giersch [Wed, 6 Feb 2013 18:11:01 +0000 (19:11 +0100)]
Exclude Java tests from memcheck.

We don't want to test the JVM.

7 years agomy_valgrind.pl: don't stop loop if $arg has value 0.
Arnaud Giersch [Wed, 6 Feb 2013 17:49:43 +0000 (18:49 +0100)]
my_valgrind.pl: don't stop loop if $arg has value 0.

7 years agogenerate_memcheck_tests.pl: add support for any environment variable.
Arnaud Giersch [Wed, 6 Feb 2013 17:07:37 +0000 (18:07 +0100)]
generate_memcheck_tests.pl: add support for any environment variable.

"classpath" is an example of previously unsupported name.

7 years agoGive state a sensible value, and don't let it uninitialized.
Arnaud Giersch [Wed, 6 Feb 2013 10:10:39 +0000 (11:10 +0100)]
Give state a sensible value, and don't let it uninitialized.

7 years agoTest is not broken anymore.
Arnaud Giersch [Wed, 6 Feb 2013 09:56:04 +0000 (10:56 +0100)]
Test is not broken anymore.

7 years agoRegenerate tesh file for master_slave_virtual_machines.
Arnaud Giersch [Wed, 6 Feb 2013 09:55:33 +0000 (10:55 +0100)]
Regenerate tesh file for master_slave_virtual_machines.

7 years agoWait a while before effective shutdown.
Arnaud Giersch [Wed, 6 Feb 2013 09:52:04 +0000 (10:52 +0100)]
Wait a while before effective shutdown.

7 years agoDestroy comm action in SIMIX_process_kill.
Arnaud Giersch [Wed, 6 Feb 2013 09:48:57 +0000 (10:48 +0100)]
Destroy comm action in SIMIX_process_kill.

7 years agoCorrectly restart all processes on VM reboot.
Arnaud Giersch [Tue, 5 Feb 2013 22:07:22 +0000 (23:07 +0100)]
Correctly restart all processes on VM reboot.

vm->processes is changed by MSG_process_restart.

7 years agoFix memory leak.
Arnaud Giersch [Tue, 5 Feb 2013 20:49:36 +0000 (21:49 +0100)]
Fix memory leak.

7 years agomodel-checker : fix insertion in mc_heap_comparison_ignore
Marion Guthmuller [Wed, 6 Feb 2013 08:00:38 +0000 (09:00 +0100)]
model-checker : fix insertion in mc_heap_comparison_ignore

7 years ago[pipol] Enable Java on MC builds.
Arnaud Giersch [Tue, 5 Feb 2013 15:31:47 +0000 (16:31 +0100)]
[pipol] Enable Java on MC builds.

7 years ago[pipol] Synchronize MemCheck.sh and Nightly_memCheck.sh.
Arnaud Giersch [Tue, 5 Feb 2013 15:26:07 +0000 (16:26 +0100)]
[pipol] Synchronize MemCheck.sh and Nightly_memCheck.sh.

7 years ago[pipol] Remove tests for simgrid-java.
Arnaud Giersch [Tue, 5 Feb 2013 15:22:51 +0000 (16:22 +0100)]
[pipol] Remove tests for simgrid-java.

7 years ago[pipol] Install default version for compilers.
Arnaud Giersch [Tue, 5 Feb 2013 15:18:34 +0000 (16:18 +0100)]
[pipol] Install default version for compilers.

Particularly, default-jdk should fix the search paths for cmake.

7 years ago[pipol] Sort packages by name.
Arnaud Giersch [Tue, 5 Feb 2013 15:16:37 +0000 (16:16 +0100)]
[pipol] Sort packages by name.

7 years agoMerge branch 'v3_9_x'
Arnaud Giersch [Tue, 5 Feb 2013 15:14:07 +0000 (16:14 +0100)]
Merge branch 'v3_9_x'

7 years agoFix release date for v3.9. v3_9
Arnaud Giersch [Tue, 5 Feb 2013 10:32:10 +0000 (11:32 +0100)]
Fix release date for v3.9.

7 years agoCast value, to please C++ compilers.
Arnaud Giersch [Tue, 5 Feb 2013 10:12:03 +0000 (11:12 +0100)]
Cast value, to please C++ compilers.

7 years agoMark parameter as unused.
Arnaud Giersch [Tue, 5 Feb 2013 10:10:00 +0000 (11:10 +0100)]
Mark parameter as unused.

7 years agoRevert "Add ModelChecker build type"
Paul B├ędaride [Thu, 31 Jan 2013 10:14:00 +0000 (11:14 +0100)]
Revert "Add ModelChecker build type"

This reverts commit 07eb7317b31474d0b6702c255741b194dbfd2d6d.

Conflicts:
CMakeLists.txt

7 years agoDie if fopen() failed.
Arnaud Giersch [Mon, 4 Feb 2013 16:37:49 +0000 (17:37 +0100)]
Die if fopen() failed.

7 years agoKill spaces at eol.
Arnaud Giersch [Mon, 4 Feb 2013 16:37:19 +0000 (17:37 +0100)]
Kill spaces at eol.

7 years agodon't try to understand why the order changes when jedule is activated
suter [Mon, 4 Feb 2013 17:13:42 +0000 (18:13 +0100)]
don't try to understand why the order changes when jedule is activated
anymore. just consider that it should be off.

This test is really annoying. As valgrind indicates a lot of leaks
coming the graphviz stuff, and that the issue comes from one edge read
after or before another, I'm kind to blame this tool!

Gonna get rid of this dependency one day!

7 years agobetter to close file
suter [Mon, 4 Feb 2013 17:02:34 +0000 (18:02 +0100)]
better to close file

7 years agoAdd a new test on availability for the SimDAG API.
Arnaud Legrand [Mon, 4 Feb 2013 09:53:17 +0000 (10:53 +0100)]
Add a new test on availability for the SimDAG API.
Issue was reported by Ricardo Rodriguez on 29/12/12 and fixed in
previous commits.

7 years agoThis way of passing arguments has changed since a long time.
Arnaud Legrand [Mon, 4 Feb 2013 10:49:53 +0000 (11:49 +0100)]
This way of passing arguments has changed since a long time.
Fixing all tesh files accordingly. Yet, now that this mechanism is
effective, absolute paths are output everywhere, hence the need to
hide just like we do for contexts. I wish I had a cleaner solution but
I don't.

7 years agoBug fix in trace management.
Arnaud Legrand [Mon, 4 Feb 2013 13:04:14 +0000 (14:04 +0100)]
Bug fix in trace management.
When using periodicity, the first event indicates when events start and
has undefined value (-1) as the value of the resource is used (e.g., the
bandwidth value precised in the xml file). When looping with periodicity,
the -1 value was used, which resulted in links with bandwidth -1.0 and
could be noticed only in very specific situations.

7 years agoBug fix. The date given when updating the state of a resource was incorrect. It could...
Arnaud Legrand [Mon, 4 Feb 2013 13:01:18 +0000 (14:01 +0100)]
Bug fix. The date given when updating the state of a resource was incorrect. It could result in incoherent traces.

7 years agoAdditionnal information never hurt.
Arnaud Legrand [Mon, 4 Feb 2013 13:00:12 +0000 (14:00 +0100)]
Additionnal information never hurt.

7 years agoDocfix
Arnaud Legrand [Mon, 4 Feb 2013 09:53:33 +0000 (10:53 +0100)]
Docfix

7 years agodon't break anything this way
suter [Mon, 4 Feb 2013 16:52:28 +0000 (17:52 +0100)]
don't break anything this way

7 years agodon't break if debug is activated ...
suter [Mon, 4 Feb 2013 16:42:45 +0000 (17:42 +0100)]
don't break if debug is activated ...

7 years agomem leak --
suter [Mon, 4 Feb 2013 16:32:16 +0000 (17:32 +0100)]
mem leak --

7 years agomem leak--
suter [Mon, 4 Feb 2013 16:29:53 +0000 (17:29 +0100)]
mem leak--

7 years ago'end' is parsed as other node now, don't use a non-existing workstation
suter [Mon, 4 Feb 2013 15:52:17 +0000 (16:52 +0100)]
'end' is parsed as other node now, don't use a non-existing workstation
rank, just say nothing instead

7 years agotry again to revalidate this thing... hope it is robust now
suter [Mon, 4 Feb 2013 15:50:54 +0000 (16:50 +0100)]
try again to revalidate this thing... hope it is robust now

7 years agooups, forgot to check is graph is acyclic or not
suter [Mon, 4 Feb 2013 15:50:20 +0000 (16:50 +0100)]
oups, forgot to check is graph is acyclic or not

7 years agodeal with the predefined scheduling stuff
suter [Mon, 4 Feb 2013 15:41:31 +0000 (16:41 +0100)]
deal with the predefined scheduling stuff

7 years agoyet another attempt to solve issues with the dotload tester. This code
suter [Mon, 4 Feb 2013 14:51:38 +0000 (15:51 +0100)]
yet another attempt to solve issues with the dotload tester. This code
was very complex, more than it should have ...
Reduce it to something simple:
  - parse the compute node
  - create transfer and control dependencies by browsing the input edges
    of the compute nodes
  - add extra dependencies from or to the 'root' and 'end' nodes for the
    entry and exit tasks respectively.
The hope is that the order in some output will stay consistent across
cdash distributions.

7 years agosecurity commit before using the ax!
suter [Mon, 4 Feb 2013 14:42:30 +0000 (15:42 +0100)]
security commit before using the ax!

7 years agochange generated trace format
suter [Mon, 4 Feb 2013 14:23:36 +0000 (15:23 +0100)]
change generated trace format
cosmetics

7 years agodoesn't hurt to use types expected by some xbt_dynar functions
suter [Fri, 1 Feb 2013 10:56:53 +0000 (11:56 +0100)]
doesn't hurt to use types expected by some xbt_dynar functions