Logo AND Algorithmique Numérique Distribuée

Public GIT Repository
simgrid.git
6 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Stéphane Castelli [Fri, 25 Apr 2014 12:15:22 +0000 (14:15 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

6 years agoAdd a man page for smpicc and smpirun
Stéphane Castelli [Fri, 25 Apr 2014 11:26:32 +0000 (13:26 +0200)]
Add a man page for smpicc and smpirun

6 years agoFix warning about undefined identifier [-Wundef].
Arnaud Giersch [Thu, 24 Apr 2014 14:38:31 +0000 (16:38 +0200)]
Fix warning about undefined identifier [-Wundef].

Thanks to Samuel Thibault for the report.

6 years ago[mc] Enable Fortran 90 code with model cheking
Gabriel Corona [Thu, 24 Apr 2014 13:54:04 +0000 (15:54 +0200)]
[mc] Enable Fortran 90 code with model cheking

6 years ago[mmalloc] Extends the junk area and use finer grained allocations
Gabriel Corona [Thu, 24 Apr 2014 13:51:54 +0000 (15:51 +0200)]
[mmalloc] Extends the junk area and use finer grained allocations

With this we are able to run Fortran 90 code at the expense of 2 more
pages per state.

6 years agoNo need to copy these files.
Arnaud Giersch [Thu, 24 Apr 2014 13:19:28 +0000 (15:19 +0200)]
No need to copy these files.

Add --setenv srcdir=... to tests when needed.

6 years agoFix surf inclusion path for test smpi-tracing-ptp.
Arnaud Giersch [Thu, 24 Apr 2014 13:08:14 +0000 (15:08 +0200)]
Fix surf inclusion path for test smpi-tracing-ptp.

6 years agoForgot to run distcheck after previous commit.
Arnaud Giersch [Thu, 24 Apr 2014 12:32:21 +0000 (14:32 +0200)]
Forgot to run distcheck after previous commit.

Register new files for dist.

6 years agoAdd missing xml file.
Arnaud Giersch [Thu, 24 Apr 2014 12:10:44 +0000 (14:10 +0200)]
Add missing xml file.

6 years ago[mc] Check error in MAP_FAILED
Gabriel Corona [Thu, 24 Apr 2014 11:31:23 +0000 (13:31 +0200)]
[mc] Check error in MAP_FAILED

6 years ago[mc] mprotect the region *after* zero-ing ignored parts:
Gabriel Corona [Thu, 24 Apr 2014 11:07:56 +0000 (13:07 +0200)]
[mc] mprotect the region *after* zero-ing ignored parts:

Doing it the other way round segfaults.

6 years ago[mc] Add basic test for lexical-block scoped variable
Gabriel Corona [Thu, 24 Apr 2014 10:17:04 +0000 (12:17 +0200)]
[mc] Add basic test for lexical-block scoped variable

6 years agoMerge "mc"
Gabriel Corona [Thu, 24 Apr 2014 09:55:50 +0000 (11:55 +0200)]
Merge "mc"

6 years ago[mc] Fix DW_AT_start_scope handling in mc_checkpoint
Gabriel Corona [Thu, 24 Apr 2014 09:48:30 +0000 (11:48 +0200)]
[mc] Fix DW_AT_start_scope handling in mc_checkpoint

6 years ago[mc] Do not use "simdata" variable (workaround for broken test)
Gabriel Corona [Thu, 24 Apr 2014 09:38:13 +0000 (11:38 +0200)]
[mc] Do not use "simdata" variable (workaround for broken test)

With DWARF4, the "simdata" variables in a nested scope seems to
prevent state equality detection and breaks a test :

  * happens with DWARF4 ;

  * does not happen it the variable is at the main scope of the
    function ;

  * the variable is found either way (DWARF2 and DWARF4) ;

  * the scope addresses seems fine in both versions of DWARF (the
    semantic of the DW_AT_high_pc is different but it is handled
    correctly).

As a temporary workaround, not using this variable fixes the test.

6 years agoFix tesh files after commit c35d96a.
Arnaud Giersch [Thu, 24 Apr 2014 09:12:44 +0000 (11:12 +0200)]
Fix tesh files after commit c35d96a.

6 years agoTest cannot work if !HAVE_RAWCTX.
Arnaud Giersch [Tue, 22 Apr 2014 15:31:13 +0000 (17:31 +0200)]
Test cannot work if !HAVE_RAWCTX.

6 years agoFix the default working set size of migration
Takahiro Hirofuchi [Thu, 24 Apr 2014 08:06:01 +0000 (17:06 +0900)]
Fix the default working set size of migration

Cherry-pick from the hypervisor branch.
Note that 90% is just an example. More cleanup and documentation should
be necessary.

Conflicts:
src/msg/msg_vm.c

6 years agoFix tracing options ignored when set in xml config file [#14853]
Paul Bédaride [Wed, 23 Apr 2014 08:50:58 +0000 (10:50 +0200)]
Fix tracing options ignored when set in xml config file [#14853]

6 years agoShould fix a build error happening on 32bits architectures, related to the size of...
Stéphane Castelli [Wed, 23 Apr 2014 08:21:38 +0000 (10:21 +0200)]
Should fix a build error happening on 32bits architectures, related to the size of an adress

6 years agoMerge branch 'smpi-topo'
Stéphane Castelli [Tue, 22 Apr 2014 14:37:30 +0000 (16:37 +0200)]
Merge branch 'smpi-topo'

Conflicts:
src/smpi/smpi_pmpi.c

6 years agoRename option multiple use of task and fix leak
Paul Bédaride [Tue, 22 Apr 2014 09:26:20 +0000 (11:26 +0200)]
Rename option multiple use of task and fix leak

6 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Stéphane Castelli [Fri, 18 Apr 2014 11:53:03 +0000 (13:53 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

6 years agoMerge with master
Stéphane Castelli [Fri, 18 Apr 2014 11:51:27 +0000 (13:51 +0200)]
Merge with master

Fat Tree routing is almost complete, except there is no routing yet

6 years agoAdd option to msg to debug multiple use of task
Paul Bédaride [Thu, 17 Apr 2014 15:40:31 +0000 (17:40 +0200)]
Add option to msg to debug multiple use of task

6 years agoDoc shareResources,updateActionsState
Paul Bédaride [Wed, 16 Apr 2014 14:22:12 +0000 (16:22 +0200)]
Doc shareResources,updateActionsState

6 years agoFat trees progress
Stéphane Castelli [Thu, 17 Apr 2014 11:39:36 +0000 (13:39 +0200)]
Fat trees progress

6 years agogenerateDotFile, to generate dot files for fat trees
Stéphane Castelli [Thu, 17 Apr 2014 09:14:44 +0000 (11:14 +0200)]
generateDotFile, to generate dot files for fat trees

6 years agoProper fix for compilation warning
Stéphane Castelli [Thu, 17 Apr 2014 08:36:37 +0000 (10:36 +0200)]
Proper fix for compilation warning

6 years agoRevert "Quick fix for warnings in compilation induced by fat trees."
Stéphane Castelli [Thu, 17 Apr 2014 07:59:00 +0000 (09:59 +0200)]
Revert "Quick fix for warnings in compilation induced by fat trees."

This reverts commit c8bcfe7ac56e69ba55d4797455a6b637baeec83e.

6 years agoQuick fix for warnings in compilation induced by fat trees.
Augustin Degomme [Wed, 16 Apr 2014 16:16:24 +0000 (18:16 +0200)]
Quick fix for warnings in compilation induced by fat trees.
This should be properly fixed quickly.

6 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Stéphane Castelli [Wed, 16 Apr 2014 15:47:12 +0000 (17:47 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

6 years ago[Bug Fix] Resolve compilation error introduced in 20984b0bb3a1e3e5e213963d9182b1c15ba...
Stéphane Castelli [Wed, 16 Apr 2014 15:44:39 +0000 (17:44 +0200)]
[Bug Fix] Resolve compilation error introduced in 20984b0bb3a1e3e5e213963d9182b1c15baba23c

Some minor progresses have been made in the implementation of fat trees

6 years agoFix inversion bug in CpuL07 constructor
Paul Bédaride [Wed, 16 Apr 2014 14:04:02 +0000 (16:04 +0200)]
Fix inversion bug in CpuL07 constructor

6 years ago[Fat Trees] Function generating dot files should be working,
Stéphane Castelli [Wed, 16 Apr 2014 07:47:06 +0000 (09:47 +0200)]
[Fat Trees] Function generating dot files should be working,
yet to be tested
FatTreeLink got its members public

6 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Stéphane Castelli [Tue, 15 Apr 2014 15:53:59 +0000 (17:53 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

6 years agoAdd doc to surf java
Paul Bédaride [Tue, 15 Apr 2014 15:59:42 +0000 (17:59 +0200)]
Add doc to surf java

6 years agoAdded some work in the creation of links in the fat trees, basically the repartion...
Stéphane Castelli [Tue, 15 Apr 2014 15:51:18 +0000 (17:51 +0200)]
Added some work in the creation of links in the fat trees, basically the repartion of nodes through the levels.

Method to generate a .dot file, almost done

Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

6 years agoFix missing java include
Paul Bédaride [Mon, 14 Apr 2014 16:01:13 +0000 (18:01 +0200)]
Fix missing java include

6 years agoSwig only in maintainer mode
Paul Bédaride [Mon, 14 Apr 2014 15:27:08 +0000 (17:27 +0200)]
Swig only in maintainer mode

6 years ago[mc] Protect snapshots against write
Gabriel Corona [Mon, 14 Apr 2014 13:06:55 +0000 (15:06 +0200)]
[mc] Protect snapshots against write

6 years ago[mc] Only enable KSM on snapshots and not on main memory
Gabriel Corona [Mon, 14 Apr 2014 11:00:27 +0000 (13:00 +0200)]
[mc] Only enable KSM on snapshots and not on main memory

Merging pages on the main memory will generate page faults on write
and we won't gain much memory.

6 years agoTalk about CFLAGS and CXXFLAGS in doc.
Arnaud Giersch [Mon, 14 Apr 2014 12:33:02 +0000 (14:33 +0200)]
Talk about CFLAGS and CXXFLAGS in doc.

6 years agoadd some MPI types definitions
Augustin Degomme [Mon, 14 Apr 2014 10:39:05 +0000 (12:39 +0200)]
add some MPI types definitions

6 years agodon't enable flto if ld version <= 2.22, as there are bugs with some version of GCC
Augustin Degomme [Mon, 14 Apr 2014 10:38:52 +0000 (12:38 +0200)]
don't enable flto if ld version <= 2.22, as there are bugs with some version of GCC
Its not clear whether bugs were actually in gcc < 4.7.2 or in the bfl ld version ...
example of related bugs : http://gcc.gnu.org/bugzilla/show_bug.cgi?id=53780 http://gcc.gnu.org/bugzilla/show_bug.cgi?id=52900
Disabling flto when ld is too old is one of the possible fixes, as ld 2.24 doesn't triggers these bugs.

6 years agotypo --
Augustin Degomme [Fri, 11 Apr 2014 09:05:10 +0000 (11:05 +0200)]
typo --

6 years agominor typo
Stéphane Castelli [Mon, 14 Apr 2014 08:40:13 +0000 (10:40 +0200)]
minor typo

6 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Stéphane Castelli [Mon, 14 Apr 2014 08:14:27 +0000 (10:14 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

6 years agoIgnore files generated by some editors (files starting with '#')
Stéphane Castelli [Mon, 14 Apr 2014 08:12:32 +0000 (10:12 +0200)]
Ignore files generated by some editors (files starting with '#')

6 years agoBeginning of the implemenation of fat tree. Parsing methods for special arguments...
Stéphane Castelli [Mon, 14 Apr 2014 08:09:06 +0000 (10:09 +0200)]
Beginning of the implemenation of fat tree. Parsing methods for special arguments related to this kind of clusters.

6 years agoDefinition of a new class to represent the routing in fat trees
Stéphane Castelli [Mon, 14 Apr 2014 07:50:13 +0000 (09:50 +0200)]
Definition of a new class to represent the routing in fat trees

6 years agoMerge branch 'mc-perf'
Gabriel Corona [Mon, 14 Apr 2014 07:10:32 +0000 (09:10 +0200)]
Merge branch 'mc-perf'

6 years ago[mc] Avoid allocation/deallocation in init_heap_information
Gabriel Corona [Thu, 10 Apr 2014 14:05:36 +0000 (16:05 +0200)]
[mc] Avoid allocation/deallocation in init_heap_information

6 years agoremove all references to the dead file_ls function
suter [Fri, 11 Apr 2014 18:46:02 +0000 (20:46 +0200)]
remove all references to the dead file_ls function

6 years agoinitialize this storage with NULL
suter [Fri, 11 Apr 2014 17:04:45 +0000 (19:04 +0200)]
initialize this storage with NULL

6 years agoupdate example according to recent modifications
suter [Fri, 11 Apr 2014 15:01:24 +0000 (17:01 +0200)]
update example according to recent modifications

6 years agoaugment example to test the semantic of the write
suter [Fri, 11 Apr 2014 14:57:32 +0000 (16:57 +0200)]
augment example to test the semantic of the write

6 years agosimplify the way free and used space are accessed
suter [Fri, 11 Apr 2014 14:51:31 +0000 (16:51 +0200)]
simplify the way free and used space are accessed

6 years agocorrect the semantic of the write
suter [Fri, 11 Apr 2014 13:24:15 +0000 (15:24 +0200)]
correct the semantic of the write

6 years agodo not use MSG stuff at SURF level
suter [Fri, 11 Apr 2014 08:28:00 +0000 (10:28 +0200)]
do not use MSG stuff at SURF level

6 years agocorrect seek's semantic
suter [Fri, 11 Apr 2014 08:10:45 +0000 (10:10 +0200)]
correct seek's semantic

6 years agomake read really depend on current position in the file
suter [Fri, 11 Apr 2014 08:10:08 +0000 (10:10 +0200)]
make read really depend on current position in the file

6 years agosurfCpuModel add execute on host
Paul Bédaride [Fri, 11 Apr 2014 14:45:25 +0000 (16:45 +0200)]
surfCpuModel add execute on host

6 years agoPrint SWIG version.
Arnaud Giersch [Fri, 11 Apr 2014 13:30:12 +0000 (15:30 +0200)]
Print SWIG version.

6 years agoFix comment, and add a runtime warning when stack overflow protection is known to...
Arnaud Giersch [Fri, 11 Apr 2014 11:37:11 +0000 (13:37 +0200)]
Fix comment, and add a runtime warning when stack overflow protection is known to be broken.

Also set default value to 0 for contexts/guard_size in this case.

6 years agoAdd comment to inform that stack protection is broken when PTH_STACKGROWTH == 1.
Arnaud Giersch [Fri, 11 Apr 2014 09:32:10 +0000 (11:32 +0200)]
Add comment to inform that stack protection is broken when PTH_STACKGROWTH == 1.

6 years agoCosmetics: XBT_PUBLIC is not needed here.
Arnaud Giersch [Fri, 11 Apr 2014 09:11:48 +0000 (11:11 +0200)]
Cosmetics: XBT_PUBLIC is not needed here.

6 years agoMake xbt_abort really silent on Windows.
Arnaud Giersch [Fri, 11 Apr 2014 08:57:45 +0000 (10:57 +0200)]
Make xbt_abort really silent on Windows.

Another option was to make a call to
    _set_abort_behavior(0, _WRITE_ABORT_MSG | _CALL_REPORTFAULT)
but it seems that it's currently not supported by mingw.

Moreover, make xbt_abort a real function.

6 years ago[mc] Avoid allocations in state->equals_to{1,2}
Gabriel Corona [Thu, 10 Apr 2014 07:18:54 +0000 (09:18 +0200)]
[mc] Avoid allocations in state->equals_to{1,2}

6 years ago[mc] Optimise memory allocation in mm_diff
Gabriel Corona [Tue, 8 Apr 2014 13:20:57 +0000 (15:20 +0200)]
[mc] Optimise memory allocation in mm_diff

Avoid a lot of allocations/deallocations by using a contiguous array
instead of array of arrays.

6 years ago[mc] Remove buggy xbt_free
Gabriel Corona [Fri, 11 Apr 2014 08:24:53 +0000 (10:24 +0200)]
[mc] Remove buggy xbt_free

6 years agomodel-checker : add commande line in comment to run the example
Marion Guthmuller [Thu, 10 Apr 2014 07:27:22 +0000 (09:27 +0200)]
model-checker : add commande line in comment to run the example

6 years agomodel-checker : worst case considered for bugged1_liveness example (bug on the last...
Marion Guthmuller [Thu, 10 Apr 2014 07:14:41 +0000 (09:14 +0200)]
model-checker : worst case considered for bugged1_liveness example (bug on the last process)

6 years agoRemove useless declaration.
Arnaud Giersch [Tue, 8 Apr 2014 14:59:11 +0000 (16:59 +0200)]
Remove useless declaration.

6 years agoAdd missing XBT_PUBLIC*.
Arnaud Giersch [Tue, 8 Apr 2014 12:57:38 +0000 (14:57 +0200)]
Add missing XBT_PUBLIC*.

6 years agoFix doc.
Arnaud Giersch [Tue, 8 Apr 2014 12:31:47 +0000 (14:31 +0200)]
Fix doc.

6 years agoNo need to have this variable global.
Arnaud Giersch [Tue, 8 Apr 2014 12:31:10 +0000 (14:31 +0200)]
No need to have this variable global.

6 years agoUpdate tesh.pl.
Arnaud Giersch [Tue, 8 Apr 2014 11:43:26 +0000 (13:43 +0200)]
Update tesh.pl.

* avoid to launch a shell for subcommands
* improve substitutions for variables

All tests pass on Linux, let's see what's happening on windows.

6 years agoRewrite command line without using find, which is not the same on windows.
Arnaud Giersch [Tue, 8 Apr 2014 09:23:28 +0000 (11:23 +0200)]
Rewrite command line without using find, which is not the same on windows.

6 years agoRemove warnings about unused parameters.
Arnaud Giersch [Tue, 8 Apr 2014 08:27:10 +0000 (10:27 +0200)]
Remove warnings about unused parameters.

6 years agoAdd example of java cpu model
Paul Bédaride [Fri, 4 Apr 2014 08:46:08 +0000 (10:46 +0200)]
Add example of java cpu model

6 years agoMerge remote-tracking branch 'origin/mc'
Gabriel Corona [Tue, 8 Apr 2014 08:08:39 +0000 (10:08 +0200)]
Merge remote-tracking branch 'origin/mc'

Conflicts:
src/mc/mc_checkpoint.c

6 years agoadd defines to windows build, to avoid breaking ucontexts examples
Augustin Degomme [Mon, 7 Apr 2014 15:33:58 +0000 (17:33 +0200)]
add defines to windows build, to avoid breaking ucontexts examples

6 years agooops
Augustin Degomme [Mon, 7 Apr 2014 14:14:51 +0000 (16:14 +0200)]
oops

6 years agoalso document torus networks
Augustin Degomme [Mon, 7 Apr 2014 14:05:04 +0000 (16:05 +0200)]
also document torus networks

6 years agodocument loopback tags for clusters
Augustin Degomme [Mon, 7 Apr 2014 13:41:41 +0000 (15:41 +0200)]
document loopback tags for clusters

6 years agoMissed by previous commit.
Arnaud Giersch [Mon, 7 Apr 2014 12:02:21 +0000 (14:02 +0200)]
Missed by previous commit.

6 years agoHope that this time win32_ucontext.h will be found.
Arnaud Giersch [Mon, 7 Apr 2014 11:51:01 +0000 (13:51 +0200)]
Hope that this time win32_ucontext.h will be found.

6 years agoPrint output when prog_AC_CHECK_MCSC.c fails to compile.
Arnaud Giersch [Mon, 7 Apr 2014 11:14:15 +0000 (13:14 +0200)]
Print output when prog_AC_CHECK_MCSC.c fails to compile.

6 years agostack-overflow tests are expected to fail on win32 too.
Arnaud Giersch [Mon, 7 Apr 2014 09:34:53 +0000 (11:34 +0200)]
stack-overflow tests are expected to fail on win32 too.

6 years agoTry to fix MCSC check.
Arnaud Giersch [Mon, 7 Apr 2014 09:28:27 +0000 (11:28 +0200)]
Try to fix MCSC check.

6 years agostartsWith doesn't expect a regexp.
Arnaud Giersch [Mon, 7 Apr 2014 08:33:16 +0000 (10:33 +0200)]
startsWith doesn't expect a regexp.

6 years agoSince SG-java is now reintegrated into the main tree, this kind of test is not needed...
Arnaud Giersch [Mon, 7 Apr 2014 08:00:19 +0000 (10:00 +0200)]
Since SG-java is now reintegrated into the main tree, this kind of test is not needed anymore.

6 years agoUpdate version strings.
Arnaud Giersch [Mon, 7 Apr 2014 07:57:17 +0000 (09:57 +0200)]
Update version strings.

6 years agoForce windows jar to bundle into x86, as we only build/support 32 bits version
Augustin Degomme [Mon, 7 Apr 2014 08:52:32 +0000 (10:52 +0200)]
Force windows jar to bundle into x86, as we only build/support 32 bits version

6 years agofix surf-java library win compilation
Augustin Degomme [Mon, 7 Apr 2014 07:54:57 +0000 (09:54 +0200)]
fix surf-java library win compilation

6 years agoAdd one more failing test.
Arnaud Giersch [Sat, 5 Apr 2014 20:30:42 +0000 (22:30 +0200)]
Add one more failing test.

An assertion is failing in lmm_print when running with --log=surf.thres:debug:

** SimGrid: UNCAUGHT EXCEPTION received on ./bug-17132(0): category: unknown error; value: 0
** Incorrect value (10000000000.000002 is not smaller than 10000000000.000000): 1.90735e-06
** Thrown by () in this process
[0.000013] [...]/src/xbt/ex.c:144: [xbt_ex/CRITICAL] Incorrect value (10000000000.000002 is not smaller than 10000000000.000000): 1.90735e-06

**   In _Z9lmm_printP10lmm_system() at [...]/src/surf/maxmin.cpp:568
**   In lmm_solve() at [...]/src/surf/maxmin.cpp:799
**   In _ZN5Model18shareResourcesLazyEd() at [...]/src/surf/surf_interface.cpp:531
**   In _ZN5Model14shareResourcesEd() at [...]/src/surf/surf_interface.cpp:512
**   In _ZN21WorkstationCLM03Model14shareResourcesEd() at [...]/src/surf/workstation_clm03.cpp:82
**   In surf_solve() at [...]/src/surf/surf_c_bindings.cpp:80
**   In SIMIX_run() at [...]/src/simix/smx_global.c:377
**   In smpi_main() at [...]/src/simgrid/sg_config.c:1001
**   In main() at [...]/src/smpi/smpi_global.c:472
Aborted

It looks like a rounding error, but I'm not sure if the problem in lmm_print
itself, or before.

6 years agoComplete tesh documentation.
Arnaud Giersch [Sat, 5 Apr 2014 20:23:24 +0000 (22:23 +0200)]
Complete tesh documentation.

6 years agoadd a flatifying test with a multicore cluster -- it's broken for now
Martin Quinson [Sat, 5 Apr 2014 20:44:13 +0000 (22:44 +0200)]
add a flatifying test with a multicore cluster -- it's broken for now

6 years agorequests the flatifier to display the amount of core if not equal to 1
Martin Quinson [Sat, 5 Apr 2014 20:28:03 +0000 (22:28 +0200)]
requests the flatifier to display the amount of core if not equal to 1

Bad news: this commit does not break the tests, meaning that we have
no flatifying test that involves multi-cores...