Logo AND Algorithmique Numérique Distribuée

Public GIT Repository
simgrid.git
9 years agoRemove the 'TUTORIAL: New API' chunks
Martin Quinson [Sat, 1 Nov 2014 21:25:06 +0000 (22:25 +0100)]
Remove the 'TUTORIAL: New API' chunks

This loads the code, and I'm not sure that it is of any help,
actually. Adding a new API is rather uncommon, and the existing ones
are clean enough to serve as an example, nowadays.

9 years agorename a generated file involved in the kernel popping
Martin Quinson [Sat, 1 Nov 2014 21:14:30 +0000 (22:14 +0100)]
rename a generated file involved in the kernel popping

9 years agokill dead code
Martin Quinson [Sat, 1 Nov 2014 20:52:42 +0000 (21:52 +0100)]
kill dead code

9 years ago[mc] Split config code into mc_config.c
Gabriel Corona [Fri, 31 Oct 2014 15:09:04 +0000 (16:09 +0100)]
[mc] Split config code into mc_config.c

9 years ago[mc] Make MC_resolve_subtype() and MC_resolve_subtype() static functions of mc_dwarf.c
Gabriel Corona [Fri, 31 Oct 2014 12:37:45 +0000 (13:37 +0100)]
[mc] Make MC_resolve_subtype() and MC_resolve_subtype() static functions of mc_dwarf.c

Those functions belong to the mc_dwarf.c layer and are only used there
anyway. Move them here, mark them as static in order to reduce the
number of exported symbols and reduce the cross-layers dependencies.

9 years agosmall correction
degomme [Fri, 31 Oct 2014 10:36:40 +0000 (11:36 +0100)]
small correction

9 years agoprovide user-friendly errors when replay encounters a badly formatted line.
degomme [Fri, 31 Oct 2014 10:28:09 +0000 (11:28 +0100)]
provide user-friendly errors when replay encounters a badly formatted line.
Avoids segfaults in this case

9 years agoSomehow .. we forgot to replay allgather.
degomme [Thu, 30 Oct 2014 16:58:20 +0000 (17:58 +0100)]
Somehow .. we forgot to replay allgather.

9 years agoroot should be optional for gather replay (as it is everywhere else)
degomme [Thu, 30 Oct 2014 16:58:00 +0000 (17:58 +0100)]
root should be optional for gather replay (as it is everywhere else)

9 years agoAdd tracing for RMA calls
degomme [Thu, 30 Oct 2014 15:23:10 +0000 (16:23 +0100)]
Add tracing for RMA calls

9 years agoprevious commit was a mistake. Handle the case more gracefully.
degomme [Thu, 30 Oct 2014 14:56:48 +0000 (15:56 +0100)]
previous commit was a mistake. Handle the case more gracefully.

9 years agodon't push null request back in the dynar
Augustin Degomme [Thu, 30 Oct 2014 13:48:55 +0000 (14:48 +0100)]
don't push null request back in the dynar

9 years agowe should not set error flag when wait or test is called with a null request.
Augustin Degomme [Wed, 29 Oct 2014 16:17:44 +0000 (17:17 +0100)]
we should not set error flag when wait or test is called with a null request.
This is explicitly allowed by the standard.

9 years agoavoid code duplication that lead to out-of-date fortran mpi_init_thread
Augustin Degomme [Wed, 29 Oct 2014 15:48:24 +0000 (16:48 +0100)]
avoid code duplication that lead to out-of-date fortran mpi_init_thread

9 years ago[mc] Document/simplify MC_request_is_enabled()
Gabriel Corona [Thu, 30 Oct 2014 11:30:33 +0000 (12:30 +0100)]
[mc] Document/simplify MC_request_is_enabled()

9 years ago[mc] Simplify mc_update_comm_pattern
Gabriel Corona [Thu, 30 Oct 2014 09:59:26 +0000 (10:59 +0100)]
[mc] Simplify mc_update_comm_pattern

9 years ago[mc] DRY with mc_update_comm_pattern() (broken)
Gabriel Corona [Tue, 28 Oct 2014 15:40:31 +0000 (16:40 +0100)]
[mc] DRY with mc_update_comm_pattern() (broken)

9 years ago[mc] DRY by adding get_call_type()
Gabriel Corona [Tue, 28 Oct 2014 15:30:06 +0000 (16:30 +0100)]
[mc] DRY by adding get_call_type()

9 years ago[mc] Try to DRY in MC main loops
Gabriel Corona [Tue, 28 Oct 2014 13:53:07 +0000 (14:53 +0100)]
[mc] Try to DRY in MC main loops

9 years agoadd a (unused) fortran datatype for compilation of recent bigdft
degomme [Wed, 29 Oct 2014 14:08:13 +0000 (15:08 +0100)]
add a (unused) fortran datatype for compilation of recent bigdft

9 years agosomehow we forgot MPI_REAL datatype C-fortran compatibility
degomme [Wed, 29 Oct 2014 10:17:08 +0000 (11:17 +0100)]
somehow we forgot MPI_REAL datatype C-fortran compatibility

9 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
etortilopez [Wed, 22 Oct 2014 13:46:28 +0000 (15:46 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

9 years agousing walltimer in adaptive algorithm
etortilopez [Wed, 22 Oct 2014 13:46:20 +0000 (15:46 +0200)]
using walltimer in adaptive algorithm

9 years agodoc update
Augustin Degomme [Tue, 21 Oct 2014 12:27:28 +0000 (14:27 +0200)]
doc update

9 years agoApply patch suggested by fabien Chaix. This avoids issues with reqq being deleted...
Augustin Degomme [Tue, 21 Oct 2014 12:21:15 +0000 (14:21 +0200)]
Apply patch suggested by fabien Chaix. This avoids issues with reqq being deleted in replay waitall
This also removes the MPI barrier in replay finalize, which was not needed anymore

9 years agoLoooong due Changelog update
Augustin Degomme [Fri, 17 Oct 2014 13:07:21 +0000 (15:07 +0200)]
Loooong due Changelog update

9 years agoAdd option to configure the factors used for IB model
Augustin Degomme [Fri, 17 Oct 2014 11:29:08 +0000 (13:29 +0200)]
Add option to configure the factors used for IB model

9 years ago[smpi+mc] When restoring a snapshot, always remap the SMPI privatisation segment
Gabriel Corona [Fri, 17 Oct 2014 12:50:21 +0000 (14:50 +0200)]
[smpi+mc] When restoring a snapshot, always remap the SMPI privatisation segment

After restoring the global variables in a snapshot, the global
variable containing the currently active SMPI privatization segment is
overwritten. As a consequence, the segment SMPI thinks active might be
inconsistent with the currently active segment (which the kernels
knows about).

In this case, we want to remap the segment regardless of what SMPI
thinks.

We might be more clever to avoid unecessary segment switch if the
segment which is really mapped is the same as the one we want.

9 years agoreally fix dist
Augustin Degomme [Thu, 16 Oct 2014 14:02:09 +0000 (16:02 +0200)]
really fix dist

9 years agofix dist
Augustin Degomme [Thu, 16 Oct 2014 13:55:09 +0000 (15:55 +0200)]
fix dist

9 years agoChange verbosity of debug messages
Augustin Degomme [Thu, 16 Oct 2014 13:50:09 +0000 (15:50 +0200)]
Change verbosity of debug messages

9 years agoAdd a new Infiniband network model, based on the works of Jerome Vienne.
Augustin Degomme [Thu, 16 Oct 2014 11:35:26 +0000 (13:35 +0200)]
Add a new Infiniband network model, based on the works of Jerome Vienne.
This computes penalties on communications to account for the slowdowns experimented on real systems, and modeled by jerome
check http://mescal.imag.fr/membres/jean-marc.vincent/index.html/PhD/Vienne.pdf for details

known issue: doesn't work yet with permanent receive mode, as some surf actions are not released properly

9 years agoAdd a safe version of lmm_get_var_from_cnst to avoid looping forever when iterating...
Augustin Degomme [Tue, 14 Oct 2014 12:24:22 +0000 (14:24 +0200)]
Add a safe version of lmm_get_var_from_cnst to avoid looping forever when iterating on a dynar we reorder dynamically

9 years agoRemove irrelevant API documentation
Gabriel Corona [Thu, 16 Oct 2014 12:59:46 +0000 (14:59 +0200)]
Remove irrelevant API documentation

9 years agodisable clang on travis
Martin Quinson [Wed, 15 Oct 2014 15:26:29 +0000 (17:26 +0200)]
disable clang on travis

9 years agodon't test if we cant build
Martin Quinson [Wed, 15 Oct 2014 15:16:46 +0000 (17:16 +0200)]
don't test if we cant build

9 years agobecause we need noise on IRC
Martin Quinson [Wed, 15 Oct 2014 15:13:58 +0000 (17:13 +0200)]
because we need noise on IRC

9 years agoadd a little link to travis status from the README
Martin Quinson [Wed, 15 Oct 2014 15:00:53 +0000 (17:00 +0200)]
add a little link to travis status from the README

9 years agosharing config between travis and jenkins seems non-trivial
Martin Quinson [Wed, 15 Oct 2014 14:58:40 +0000 (16:58 +0200)]
sharing config between travis and jenkins seems non-trivial

9 years agotell travis which config to test
Martin Quinson [Wed, 15 Oct 2014 14:16:20 +0000 (16:16 +0200)]
tell travis which config to test

9 years agowe need doxygen, and I fail to see who's creating the VERSION file
Martin Quinson [Wed, 15 Oct 2014 14:08:56 +0000 (16:08 +0200)]
we need doxygen, and I fail to see who's creating the VERSION file

9 years agotry to use the jenkins on travis too
Martin Quinson [Wed, 15 Oct 2014 14:00:12 +0000 (16:00 +0200)]
try to use the jenkins on travis too

9 years agoMerge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid
Martin Quinson [Wed, 15 Oct 2014 13:55:21 +0000 (15:55 +0200)]
Merge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid

9 years agoI'm not sure of why flexml generated a different flex file, but the content seems...
Martin Quinson [Wed, 15 Oct 2014 13:55:11 +0000 (15:55 +0200)]
I'm not sure of why flexml generated a different flex file, but the content seems ok too

9 years agotest if I can write a little travis config file
Martin Quinson [Wed, 15 Oct 2014 13:43:33 +0000 (15:43 +0200)]
test if I can write a little travis config file

9 years agobetter estimate of window for adaptive algorithm
etortilopez [Mon, 13 Oct 2014 14:10:22 +0000 (16:10 +0200)]
better estimate of window for adaptive algorithm

9 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Lucas Mello Schnorr [Mon, 13 Oct 2014 10:59:24 +0000 (07:59 -0300)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

9 years agoPJ_value_get assumes value exists, this is not the case here so fix it
Lucas Mello Schnorr [Mon, 13 Oct 2014 10:59:05 +0000 (07:59 -0300)]
PJ_value_get assumes value exists, this is not the case here so fix it

Hard-coded colors:
- see comments in the code

9 years ago[mmalloc] Expand the junkarea
Gabriel Corona [Mon, 13 Oct 2014 09:55:31 +0000 (11:55 +0200)]
[mmalloc] Expand the junkarea

In some cases (Fortran + Clang compilation) this is needed. We nee to
fix this more cleanly.

9 years ago[mc] Add support for DW_OP_regN locaitions from DW_AT_frame_base
Gabriel Corona [Mon, 13 Oct 2014 09:37:45 +0000 (11:37 +0200)]
[mc] Add support for DW_OP_regN locaitions from DW_AT_frame_base

Fix DWARF based introspecion support when compiling with LLVM.

9 years ago[mc] Prepare support for register location in DWARF location expression evaluation...
Gabriel Corona [Mon, 13 Oct 2014 09:13:15 +0000 (11:13 +0200)]
[mc] Prepare support for register location in DWARF location expression evaluation code

This is needed in order to support this:

  DW_AT_frame_base  : 1 byte block: 56     (DW_OP_reg6 (rbp))

9 years ago[mmalloc] Fix junkarea handling in free
Gabriel Corona [Mon, 13 Oct 2014 08:08:36 +0000 (10:08 +0200)]
[mmalloc] Fix junkarea handling in free

The call free(junkarea) was broken and was trying to delegate to
mmalloc instead of using junkarea.

Because of this libsimgrid broken when compiling with LLVM with
mmalloc support.

9 years agotry to simplify the way simcalls are generated
Martin Quinson [Sat, 11 Oct 2014 22:17:13 +0000 (00:17 +0200)]
try to simplify the way simcalls are generated

9 years agokill dead code
Martin Quinson [Sat, 11 Oct 2014 21:02:09 +0000 (23:02 +0200)]
kill dead code

9 years agoask swig to please doxygen. Tools will drive me nuts
Martin Quinson [Sat, 11 Oct 2014 20:59:04 +0000 (22:59 +0200)]
ask swig to please doxygen. Tools will drive me nuts

9 years agoignore more cruft
Martin Quinson [Sat, 11 Oct 2014 20:54:27 +0000 (22:54 +0200)]
ignore more cruft

9 years agorename SIMIX_simcall_{pre,post} to SIMIX_simcall_{enter,exit}
Martin Quinson [Sat, 11 Oct 2014 20:47:30 +0000 (22:47 +0200)]
rename SIMIX_simcall_{pre,post} to SIMIX_simcall_{enter,exit}

9 years agoensure that the generated files are autonomous and not included within another file
Martin Quinson [Sat, 11 Oct 2014 20:04:34 +0000 (22:04 +0200)]
ensure that the generated files are autonomous and not included within another file

9 years agoplease doxygen keep calm
Martin Quinson [Sat, 11 Oct 2014 20:02:34 +0000 (22:02 +0200)]
please doxygen keep calm

9 years agothat file was seriously outdated
Martin Quinson [Thu, 9 Oct 2014 23:15:32 +0000 (01:15 +0200)]
that file was seriously outdated

9 years agomake my previous commit also compile under MC (sorry)
Martin Quinson [Thu, 9 Oct 2014 23:08:53 +0000 (01:08 +0200)]
make my previous commit also compile under MC (sorry)

9 years agoour usage of doxygen is improvable
Martin Quinson [Thu, 9 Oct 2014 22:54:02 +0000 (00:54 +0200)]
our usage of doxygen is improvable

9 years agouse an automatic table of contents instead of a manual one
Martin Quinson [Thu, 9 Oct 2014 22:34:10 +0000 (00:34 +0200)]
use an automatic table of contents instead of a manual one

9 years agoMake it much easier to follow control flow through simix
Martin Quinson [Thu, 9 Oct 2014 22:30:45 +0000 (00:30 +0200)]
Make it much easier to follow control flow through simix

One of the main difficulty in navigating the source code when debuging
was to find your way from MSG to SURF, through SIMIX. The simcall
mechanism really breaks the flow.

The solution is to add a dummy call to the simcall body, such as:
    if (0) SIMIX_pre_host_off(&self->simcall, host);

With the "if (0)", it will be cut at compilation and have no impact on
the code behavior. But you can go to that function in eclipse, press
F3 and you are within the kernel now. No need to grep your way around.

9 years agook eclipse, change your config file yourself, you're big enough
Martin Quinson [Thu, 9 Oct 2014 22:27:41 +0000 (00:27 +0200)]
ok eclipse, change your config file yourself, you're big enough

9 years agoignore more cruft
Martin Quinson [Thu, 9 Oct 2014 22:27:13 +0000 (00:27 +0200)]
ignore more cruft

9 years agotry to have valid chunks in generated files to please eclipse
Martin Quinson [Thu, 9 Oct 2014 21:29:50 +0000 (23:29 +0200)]
try to have valid chunks in generated files to please eclipse

9 years agoAllow to recreate VMs in a better way (I guess)
Martin Quinson [Thu, 9 Oct 2014 21:07:29 +0000 (23:07 +0200)]
Allow to recreate VMs in a better way (I guess)

Instead of removing the VM from the host_lib (and potentially create
issues at the routing level), test whether it exists in the VM layer
before whining that we cannot redo it.

9 years agoRemove VMs from the lib of existing hosts so that they can be recreated
Martin Quinson [Thu, 9 Oct 2014 19:59:19 +0000 (21:59 +0200)]
Remove VMs from the lib of existing hosts so that they can be recreated

9 years agoadd parenthesis to shut up a useless warning
Martin Quinson [Thu, 9 Oct 2014 19:26:07 +0000 (21:26 +0200)]
add parenthesis to shut up a useless warning

9 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Adrien Lebre [Thu, 9 Oct 2014 16:31:29 +0000 (18:31 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

9 years agoone more test for the migration - adrien
Adrien Lebre [Thu, 9 Oct 2014 16:31:26 +0000 (18:31 +0200)]
one more test for the migration - adrien

9 years agoMerge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid
Martin Quinson [Thu, 9 Oct 2014 15:59:08 +0000 (17:59 +0200)]
Merge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid

Conflicts:
src/bindings/java/smx_context_java.c

9 years agofix msg_host_is_avai... in msg_host_is_on - adrien
Adrien Lebre [Thu, 9 Oct 2014 15:49:41 +0000 (17:49 +0200)]
fix msg_host_is_avai... in msg_host_is_on - adrien

9 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Adrien Lebre [Thu, 9 Oct 2014 15:45:00 +0000 (17:45 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

9 years agomake msg_vm_migrate robust (i.e. now SRC or DST can be turned off during the migratio...
Adrien Lebre [Thu, 9 Oct 2014 15:44:52 +0000 (17:44 +0200)]
make msg_vm_migrate robust (i.e. now SRC or DST can be turned off during the migration) - fix teshsuite slee_host_off in java (but did not fix the output as I don't know how to do it), discover a bug on VM destroy (it is impossible to recreate the same VM: you get /Users/alebre/DEVELOPMENTS/SIMGRID/simgrid.orig/src/msg/msg_vm.c:209: [msg_vm/ERROR] host vm0 already exits) - Adrien

9 years ago[mc] Fix segfault when a function does not have a name
Gabriel Corona [Thu, 9 Oct 2014 13:59:29 +0000 (15:59 +0200)]
[mc] Fix segfault when a function does not have a name

This happens when compiling with LLVM (clang/dragonegg).

9 years ago[mc] Give the real type of mc_heap/std_heap (xbt_mheap_t, not void*)
Gabriel Corona [Thu, 9 Oct 2014 12:21:52 +0000 (14:21 +0200)]
[mc] Give the real type of mc_heap/std_heap (xbt_mheap_t, not void*)

9 years ago[mc] Simplify tests specifications for mc-bugged1-liveness*
Gabriel Corona [Thu, 9 Oct 2014 08:54:59 +0000 (10:54 +0200)]
[mc] Simplify tests specifications for mc-bugged1-liveness*

9 years agobetter estimation of dynamic threshold
etortilopez [Wed, 8 Oct 2014 13:43:03 +0000 (15:43 +0200)]
better estimation of dynamic threshold

9 years agomore informative message when a process gets killed
Martin Quinson [Tue, 7 Oct 2014 20:06:56 +0000 (22:06 +0200)]
more informative message when a process gets killed

9 years agoplease a bit doxygen
Martin Quinson [Tue, 7 Oct 2014 19:47:50 +0000 (21:47 +0200)]
please a bit doxygen

9 years agomissing call to XBT_LOG_CONNECT
Martin Quinson [Tue, 7 Oct 2014 18:47:41 +0000 (20:47 +0200)]
missing call to XBT_LOG_CONNECT

9 years agodon't define obsolete doxygen variables that we don't use
Martin Quinson [Tue, 7 Oct 2014 18:46:02 +0000 (20:46 +0200)]
don't define obsolete doxygen variables that we don't use

9 years agorename MSG_host_is_avail() to MSG_host_is_on()
Martin Quinson [Tue, 7 Oct 2014 17:28:12 +0000 (19:28 +0200)]
rename MSG_host_is_avail() to MSG_host_is_on()

(and same in Java)

9 years agoFix bug in keyval delete
Augustin Degomme [Mon, 6 Oct 2014 12:41:37 +0000 (14:41 +0200)]
Fix bug in keyval delete

9 years agogive correct pointer when calling delete function
Augustin Degomme [Mon, 6 Oct 2014 12:28:00 +0000 (14:28 +0200)]
give correct pointer when calling delete function

9 years agoduplicated lines
Augustin Degomme [Mon, 6 Oct 2014 09:33:01 +0000 (11:33 +0200)]
duplicated lines

9 years agostore the int in a long-enough char array
Augustin Degomme [Mon, 6 Oct 2014 08:40:29 +0000 (10:40 +0200)]
store the int in a long-enough char array

9 years agocleanup, remove some useless functions
degomme [Sun, 5 Oct 2014 18:53:15 +0000 (20:53 +0200)]
cleanup, remove some useless functions

9 years agoAdd MPI_Type*keyval and MPI_Type*attr functions
degomme [Sun, 5 Oct 2014 18:17:05 +0000 (20:17 +0200)]
Add MPI_Type*keyval and MPI_Type*attr functions

9 years agoAdd MPI_Comm_*keyval and MPI_Comm*attr functions
degomme [Fri, 3 Oct 2014 23:12:39 +0000 (01:12 +0200)]
Add MPI_Comm_*keyval and MPI_Comm*attr functions
These are just aliases for MPI*keyval and MPI*attr deprecated functions

9 years agoactivate some more tests
Augustin Degomme [Fri, 3 Oct 2014 20:43:49 +0000 (22:43 +0200)]
activate some more tests

9 years agoFix compilation issue
Augustin Degomme [Fri, 3 Oct 2014 20:05:17 +0000 (22:05 +0200)]
Fix compilation issue

9 years agoImplement MPI_Keyval_create, MPI_Keyval_free, MPI_Attr_get, MPI_Attr_put, MPI_Attr_de...
Augustin Degomme [Fri, 3 Oct 2014 17:35:54 +0000 (19:35 +0200)]
Implement MPI_Keyval_create, MPI_Keyval_free, MPI_Attr_get, MPI_Attr_put, MPI_Attr_delete calls

9 years agoprovide new unimplemented signatures for RMA MPI calls
Augustin Degomme [Fri, 3 Oct 2014 08:29:34 +0000 (10:29 +0200)]
provide new unimplemented signatures for RMA MPI calls

9 years agodon't provide sync-gforge-doc* targets if doc is not enabled (cmake warning)
Augustin Degomme [Fri, 3 Oct 2014 08:29:06 +0000 (10:29 +0200)]
don't provide sync-gforge-doc* targets if doc is not enabled (cmake warning)

9 years agovarious fixes about replay and buffer usage
Augustin Degomme [Thu, 2 Oct 2014 12:57:31 +0000 (14:57 +0200)]
various fixes about replay and buffer usage

9 years agoWhen display timing is set, also display global simulation time and application times
Augustin Degomme [Thu, 2 Oct 2014 12:49:38 +0000 (14:49 +0200)]
When display timing is set, also display global simulation time and application times
This allows to check if most of the time is spent in the application, or in Simgrid
Add a hint if more than 75% of the time is spent inside the application's code (to use replay or sampling)

9 years agoChange way replay is handled, to allow cohabitation between replay and "classic"...
Augustin Degomme [Thu, 2 Oct 2014 12:18:08 +0000 (14:18 +0200)]
Change way replay is handled, to allow cohabitation between replay and "classic" SMPI