Logo AND Algorithmique Numérique Distribuée

Public GIT Repository
simgrid.git
11 years agoCosmetics
suter [Fri, 21 Dec 2012 10:30:41 +0000 (11:30 +0100)]
Cosmetics

11 years agoRevert "make MSG_comm_waitany use dynar"
Paul Bédaride [Fri, 21 Dec 2012 09:21:05 +0000 (10:21 +0100)]
Revert "make MSG_comm_waitany use dynar"

This reverts commit ae811896a4746542e8de1616e8bc95a3ee6320f2.

Conflicts:
examples/msg/actions/actions.c

11 years agoAllow MSG one-side communications that rely on parallel task to work with the compoun...
Arnaud Legrand [Thu, 20 Dec 2012 22:51:26 +0000 (23:51 +0100)]
Allow MSG one-side communications that rely on parallel task to work with the compound model.

11 years agomodel-checker : fix MC_take_snapshot if malloc used for raw heap and several data...
Marion Guthmuller [Thu, 20 Dec 2012 22:18:16 +0000 (23:18 +0100)]
model-checker : fix MC_take_snapshot if malloc used for raw heap and several data segments for binary or libsimgrid

11 years agomodel-checker : fix dpor with state equality reduction
Marion Guthmuller [Thu, 20 Dec 2012 14:38:45 +0000 (15:38 +0100)]
model-checker : fix dpor with state equality reduction

11 years agomodel-checker : if frame name is empty, stop stack unwinding
Marion Guthmuller [Mon, 17 Dec 2012 10:47:21 +0000 (11:47 +0100)]
model-checker : if frame name is empty, stop stack unwinding

11 years agomodel-checker : remove restriction of DPOR if several requests for same process
Marion Guthmuller [Mon, 17 Dec 2012 09:13:29 +0000 (10:13 +0100)]
model-checker : remove restriction of DPOR if several requests for same process

11 years agochainsend: fix tesh
Maximiliano Geier [Thu, 20 Dec 2012 18:33:47 +0000 (19:33 +0100)]
chainsend: fix tesh

11 years agochainsend: change peers active wait to waitall
Maximiliano Geier [Thu, 20 Dec 2012 18:21:33 +0000 (19:21 +0100)]
chainsend: change peers active wait to waitall

11 years agochainsend: broadcaster should send synchronously
Maximiliano Geier [Thu, 20 Dec 2012 17:32:33 +0000 (18:32 +0100)]
chainsend: broadcaster should send synchronously

11 years agoNow, you have to use "cursor" instead of "i".
Arnaud Giersch [Thu, 20 Dec 2012 17:07:16 +0000 (18:07 +0100)]
Now, you have to use "cursor" instead of "i".

11 years agoReindent file before changes.
Arnaud Giersch [Thu, 20 Dec 2012 17:05:42 +0000 (18:05 +0100)]
Reindent file before changes.

11 years agoUse "debug" log level here.
Arnaud Giersch [Thu, 20 Dec 2012 16:36:46 +0000 (17:36 +0100)]
Use "debug" log level here.

11 years agoSome symbols were renamed by last flexml update.
Arnaud Giersch [Thu, 20 Dec 2012 14:42:43 +0000 (15:42 +0100)]
Some symbols were renamed by last flexml update.

11 years agoUpdate with newer flexml.
Arnaud Giersch [Thu, 20 Dec 2012 13:43:51 +0000 (14:43 +0100)]
Update with newer flexml.

11 years agomake MSG_comm_waitany use dynar
Paul Bédaride [Thu, 20 Dec 2012 16:29:45 +0000 (17:29 +0100)]
make MSG_comm_waitany use dynar

11 years agoimprove the doc to include MSG_config
Martin Quinson [Thu, 20 Dec 2012 15:17:07 +0000 (16:17 +0100)]
improve the doc to include MSG_config

11 years agomake MSG_config public, document it, and implement it properly, not through a crude...
Martin Quinson [Thu, 20 Dec 2012 15:08:57 +0000 (16:08 +0100)]
make MSG_config public, document it, and implement it properly, not through a crude hack

11 years agoMove module tracing into corresponding modules
Paul Bédaride [Thu, 20 Dec 2012 13:29:48 +0000 (14:29 +0100)]
Move module tracing into corresponding modules

11 years agoLink with -ldl when using dlsym.
Arnaud Giersch [Thu, 20 Dec 2012 10:07:31 +0000 (11:07 +0100)]
Link with -ldl when using dlsym.

11 years agoremove the create_resource entry point in resource model APIs
Martin Quinson [Thu, 20 Dec 2012 08:33:36 +0000 (09:33 +0100)]
remove the create_resource entry point in resource model APIs

That's a leftover from ancient times that is not used anymore.
Instead, these functions are registered by each model as callbacks
within the sg_platf mechanism, which is now the unique way to create
resources (we had up to 3 different ways to create resources in the
code base :)

11 years agofix a typo
Martin Quinson [Thu, 20 Dec 2012 08:21:02 +0000 (09:21 +0100)]
fix a typo

11 years agorewrite the install doc, and integrate latest feedback on Mac builds
Martin Quinson [Thu, 20 Dec 2012 08:06:02 +0000 (09:06 +0100)]
rewrite the install doc, and integrate latest feedback on Mac builds

11 years agomark as advanced some options that are useless to the users, and improve some doc
Martin Quinson [Thu, 20 Dec 2012 08:04:45 +0000 (09:04 +0100)]
mark as advanced some options that are useless to the users, and improve some doc

11 years agoremove a bit of cruft from the install doc, more remains to be cleaned
Martin Quinson [Thu, 20 Dec 2012 00:49:28 +0000 (01:49 +0100)]
remove a bit of cruft from the install doc, more remains to be cleaned

11 years agocosmetics
Martin Quinson [Wed, 19 Dec 2012 19:16:02 +0000 (20:16 +0100)]
cosmetics

11 years agoforgot the test file
Martin Quinson [Wed, 19 Dec 2012 18:41:07 +0000 (19:41 +0100)]
forgot the test file

11 years agouse system malloc for the raw heap if GNU ld is used
Martin Quinson [Wed, 19 Dec 2012 18:31:22 +0000 (19:31 +0100)]
use system malloc for the raw heap if GNU ld is used

11 years agomake this example be more valgrind compliant by increase host speed.
suter [Wed, 19 Dec 2012 11:18:52 +0000 (12:18 +0100)]
make this example be more valgrind compliant by increase host speed.
When tasks end after the "Finalize" reception, nothing is safe ...
Still has an invalid free in the end.
did some typo correction too

11 years agoUse xbt_malloc (and friends) instead of direct malloc()
Martin Quinson [Tue, 18 Dec 2012 15:17:49 +0000 (16:17 +0100)]
Use xbt_malloc (and friends) instead of direct malloc()

This is good practice as it asserts that the result is not null, and
it actually help me right now when digging in the MC.

11 years agoAdd -Wall to CMAKE_Fortran_FLAGS, unless enable_compile_warnings=OFF.
Arnaud Giersch [Tue, 18 Dec 2012 15:53:56 +0000 (16:53 +0100)]
Add -Wall to CMAKE_Fortran_FLAGS, unless enable_compile_warnings=OFF.

This triggers lots of warnings, mainly about implicit function declarations,
but I don't know how to fix them properly for now.

11 years agoLinker option is useless when '-c' is present.
Arnaud Giersch [Tue, 18 Dec 2012 12:45:56 +0000 (13:45 +0100)]
Linker option is useless when '-c' is present.

11 years agothis was fixed too
suter [Tue, 18 Dec 2012 10:43:18 +0000 (11:43 +0100)]
this was fixed too

11 years agomention bug fix in ChangeLog
suter [Tue, 18 Dec 2012 10:10:58 +0000 (11:10 +0100)]
mention bug fix in ChangeLog

11 years agoadd test_sd_avail.tesh to the list
suter [Tue, 18 Dec 2012 09:54:18 +0000 (10:54 +0100)]
add test_sd_avail.tesh to the list

11 years agoadd a tesh file for the test of availability traces
suter [Tue, 18 Dec 2012 09:50:50 +0000 (10:50 +0100)]
add a tesh file for the test of availability traces

11 years agoAvoid to compile files when they're not needed.
Arnaud Giersch [Tue, 18 Dec 2012 09:21:45 +0000 (10:21 +0100)]
Avoid to compile files when they're not needed.

11 years agoThis file does not belong to TRACING_SRC; define SIMGRID_SRC.
Arnaud Giersch [Tue, 18 Dec 2012 09:16:01 +0000 (10:16 +0100)]
This file does not belong to TRACING_SRC; define SIMGRID_SRC.

11 years agoReally remove deleted file.
Arnaud Giersch [Tue, 18 Dec 2012 09:02:45 +0000 (10:02 +0100)]
Really remove deleted file.

11 years agoLet's be honnest
Martin Quinson [Tue, 18 Dec 2012 09:20:26 +0000 (10:20 +0100)]
Let's be honnest

11 years agorefresh the README, and re-add it to the archives
Martin Quinson [Mon, 17 Dec 2012 14:41:32 +0000 (15:41 +0100)]
refresh the README, and re-add it to the archives

11 years agothat was really ancient (shame shame)
Martin Quinson [Mon, 17 Dec 2012 14:41:10 +0000 (15:41 +0100)]
that was really ancient (shame shame)

11 years agoThis prevent periodic availability/state traces to loop forever
suter [Tue, 18 Dec 2012 09:11:12 +0000 (10:11 +0100)]
This prevent periodic availability/state traces to loop forever

11 years agoFix _sg_do_model_check use with model_check=OFF
Paul Bédaride [Tue, 18 Dec 2012 09:01:10 +0000 (10:01 +0100)]
Fix _sg_do_model_check use with model_check=OFF

11 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Paul Bédaride [Tue, 18 Dec 2012 08:28:16 +0000 (09:28 +0100)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

11 years agocosmetics
suter [Mon, 17 Dec 2012 22:43:34 +0000 (23:43 +0100)]
cosmetics

11 years agoadd an example to test availability traces. Weird behavior and runs
suter [Mon, 17 Dec 2012 22:40:23 +0000 (23:40 +0100)]
add an example to test availability traces. Weird behavior and runs
forever (thus no tesh yet)

11 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Paul Bédaride [Mon, 17 Dec 2012 16:20:34 +0000 (17:20 +0100)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

11 years agoRestructure config headers
Paul Bédaride [Mon, 17 Dec 2012 16:20:27 +0000 (17:20 +0100)]
Restructure config headers

11 years agono need to explicitly tell that resources are initially up anymore.
suter [Mon, 17 Dec 2012 15:33:27 +0000 (16:33 +0100)]
no need to explicitly tell that resources are initially up anymore.

11 years agowhen the first event of a trace (availability or state) starts at a time
suter [Mon, 17 Dec 2012 15:32:20 +0000 (16:32 +0100)]
when the first event of a trace (availability or state) starts at a time
greater than 0, this means that the default value has to be used
meanwhile. Create a dummy event whose value is -1 and handle this in
surf_presolve.

11 years agowhen the value of an event is a negative one, don't update resource
suter [Mon, 17 Dec 2012 15:30:12 +0000 (16:30 +0100)]
when the value of an event is a negative one, don't update resource
state during presolve. Allows to use default status up to the time (>0)
of the "real" first event.

11 years agoadd more debugging info there. Nice to know what is the new value
suter [Mon, 17 Dec 2012 14:42:08 +0000 (15:42 +0100)]
add more debugging info there. Nice to know what is the new value
assigned to the link

11 years agochainsend: print some transfer stats, move debug prints to where they belong
Maximiliano Geier [Mon, 17 Dec 2012 14:52:20 +0000 (15:52 +0100)]
chainsend: print some transfer stats, move debug prints to where they belong

also count up bytes when transfering, so that the peer can print its "transfer speed" when it's done, and finally update tesh accordingly

11 years agoFix model checker config issue
Paul Bédaride [Mon, 17 Dec 2012 10:17:04 +0000 (11:17 +0100)]
Fix model checker config issue

11 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Paul Bédaride [Mon, 17 Dec 2012 10:04:19 +0000 (11:04 +0100)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

11 years agoMove config from surf to simgrid
Paul Bédaride [Mon, 17 Dec 2012 10:03:42 +0000 (11:03 +0100)]
Move config from surf to simgrid

11 years agoCosmetics : Remove whitespaces for mquinson :-)
Sebastien Badia [Sun, 16 Dec 2012 23:46:49 +0000 (00:46 +0100)]
Cosmetics : Remove whitespaces for mquinson :-)

11 years agomodel-checker : remove tesh bugged2 (too long with the new version of DPOR)
Marion Guthmuller [Sun, 16 Dec 2012 20:18:01 +0000 (21:18 +0100)]
model-checker : remove tesh bugged2 (too long with the new version of DPOR)

11 years agomodel-checker : update tesh bugged1 with the new version of DPOR
Marion Guthmuller [Sun, 16 Dec 2012 20:14:25 +0000 (21:14 +0100)]
model-checker : update tesh bugged1 with the new version of DPOR

11 years agomodel-checker : interleave all enabled processes for each state and apply DPOR only...
Marion Guthmuller [Sun, 16 Dec 2012 17:31:45 +0000 (18:31 +0100)]
model-checker : interleave all enabled processes for each state and apply DPOR only once per process

11 years agomodel-checker : cosmectics
Marion Guthmuller [Fri, 14 Dec 2012 15:24:09 +0000 (16:24 +0100)]
model-checker : cosmectics

11 years agoRemove comm from src_proc->comms and dst_proc->comms when finish it,
Marion Guthmuller [Fri, 14 Dec 2012 14:57:57 +0000 (15:57 +0100)]
Remove comm from src_proc->comms and dst_proc->comms when finish it,
if is detached (dsend)

Currently, with dsend action, the wait of src_proc is not necessary to
finish the communication. In this case, only dst_proc removes this
communication from its list and destroys it, if src_proc is always
running. When src_proc makes a process_cleanup after that, it
retrieves this communication in its list while it doesn't exist
anymore and thinks that this communication isn't for it. This led to a
simulation error.

11 years agoremove comm from rdv if comm destroyed before being finished
Marion Guthmuller [Fri, 14 Dec 2012 14:50:35 +0000 (15:50 +0100)]
remove comm from rdv if comm destroyed before being finished

11 years agodoc fix: AS has no 'name' attribute, but a 'id' one
Martin Quinson [Fri, 14 Dec 2012 15:02:05 +0000 (16:02 +0100)]
doc fix: AS has no 'name' attribute, but a 'id' one

11 years agoreindent, no real change
Martin Quinson [Fri, 14 Dec 2012 14:51:43 +0000 (15:51 +0100)]
reindent, no real change

11 years agoTypos.
Arnaud Giersch [Fri, 14 Dec 2012 12:39:22 +0000 (13:39 +0100)]
Typos.

11 years agoUse cat+here document, instead of non-portable echo -e.
Arnaud Giersch [Fri, 14 Dec 2012 12:39:22 +0000 (13:39 +0100)]
Use cat+here document, instead of non-portable echo -e.

11 years agomake doxygen happy
Martin Quinson [Fri, 14 Dec 2012 11:12:42 +0000 (12:12 +0100)]
make doxygen happy

11 years agoSimGrid 3.7 is ways too recent for GRAS (+cosmetics)
Martin Quinson [Thu, 13 Dec 2012 15:36:24 +0000 (16:36 +0100)]
SimGrid 3.7 is ways too recent for GRAS (+cosmetics)

11 years agodocument how to react when stuff break during the upgrade
Martin Quinson [Thu, 13 Dec 2012 15:27:01 +0000 (16:27 +0100)]
document how to react when stuff break during the upgrade

11 years agoignore that binary file
Martin Quinson [Tue, 11 Dec 2012 10:52:30 +0000 (11:52 +0100)]
ignore that binary file

11 years agochange the way we handle MPI_Request termination
Augustin Degomme [Wed, 12 Dec 2012 18:33:40 +0000 (19:33 +0100)]
change the way we handle MPI_Request termination
to avoid using smx_action too much in smpi.
Removes a few more leaks in collectives
Handling of waitany was changed, it should return sooner and avoid a few unnecessary simcalls

11 years agoSpell check...
Arnaud Legrand [Wed, 12 Dec 2012 11:00:35 +0000 (12:00 +0100)]
Spell check...

11 years agoThis is useful for those typing ./configure & make without looking at output. :)
Arnaud Legrand [Wed, 14 Nov 2012 21:55:02 +0000 (14:55 -0700)]
This is useful for those typing ./configure & make without looking at output. :)

11 years agoAdd ctest2junit.xsl for jenkins
Paul Bédaride [Wed, 12 Dec 2012 09:11:54 +0000 (10:11 +0100)]
Add ctest2junit.xsl for jenkins

11 years agoAnother missing include, needed with tracing=off.
Arnaud Giersch [Wed, 12 Dec 2012 07:19:26 +0000 (08:19 +0100)]
Another missing include, needed with tracing=off.

11 years agomodel-checker : update tesh bugged1_liveness
Marion Guthmuller [Tue, 11 Dec 2012 17:01:54 +0000 (18:01 +0100)]
model-checker : update tesh bugged1_liveness

11 years agoFile simgrid_modules.png is automatically generated.
Arnaud Giersch [Tue, 11 Dec 2012 16:46:58 +0000 (17:46 +0100)]
File simgrid_modules.png is automatically generated.

11 years agoAdd rule to generate png files from DOC_FIGS.
Arnaud Giersch [Tue, 11 Dec 2012 16:43:42 +0000 (17:43 +0100)]
Add rule to generate png files from DOC_FIGS.

11 years agoSort list, and add missing file output.goal.pdf.
Arnaud Giersch [Tue, 11 Dec 2012 16:13:46 +0000 (17:13 +0100)]
Sort list, and add missing file output.goal.pdf.

11 years agoRemove/add a few includes.
Arnaud Giersch [Tue, 11 Dec 2012 15:38:59 +0000 (16:38 +0100)]
Remove/add a few includes.

11 years agoRevert "I'm so glad that this line is useless"
Arnaud Giersch [Tue, 11 Dec 2012 15:35:15 +0000 (16:35 +0100)]
Revert "I'm so glad that this line is useless"

This reverts commit 5904252e9e4e84030ee544d5efbd832dffa696a7.

It broke builds with tracing=off.

11 years agoEnable tracing for Nightly_memCheck too.
Arnaud Giersch [Tue, 11 Dec 2012 15:30:12 +0000 (16:30 +0100)]
Enable tracing for Nightly_memCheck too.

11 years agoRemove now unused support for remote exceptions.
Arnaud Giersch [Tue, 11 Dec 2012 14:48:02 +0000 (15:48 +0100)]
Remove now unused support for remote exceptions.

Plus slight reindent in ex.h.

11 years agoDefine target before using it.
Arnaud Giersch [Tue, 11 Dec 2012 14:34:24 +0000 (15:34 +0100)]
Define target before using it.

11 years agoRename function (create->reset), and kill empty function (destroy).
Arnaud Giersch [Tue, 11 Dec 2012 14:13:41 +0000 (15:13 +0100)]
Rename function (create->reset), and kill empty function (destroy).

11 years agoUse a sinlock instead of a mutex for mallocators.
Arnaud Giersch [Tue, 11 Dec 2012 14:13:41 +0000 (15:13 +0100)]
Use a sinlock instead of a mutex for mallocators.

11 years agoFactorize code for mutex locks.
Arnaud Giersch [Tue, 11 Dec 2012 14:13:41 +0000 (15:13 +0100)]
Factorize code for mutex locks.

11 years agoProtect mallocators for concurrent acces only with parallel mode.
Arnaud Giersch [Tue, 11 Dec 2012 14:13:41 +0000 (15:13 +0100)]
Protect mallocators for concurrent acces only with parallel mode.

11 years agoEnable smpi for Nightly_memCheck.
Arnaud Giersch [Tue, 11 Dec 2012 14:13:41 +0000 (15:13 +0100)]
Enable smpi for Nightly_memCheck.

11 years agomake an error message informative
Martin Quinson [Tue, 11 Dec 2012 10:50:15 +0000 (11:50 +0100)]
make an error message informative

11 years agoI should stop coding at night -- sorry
Martin Quinson [Tue, 11 Dec 2012 10:49:31 +0000 (11:49 +0100)]
I should stop coding at night -- sorry

11 years agono need for unused variables
Martin Quinson [Tue, 11 Dec 2012 10:49:06 +0000 (11:49 +0100)]
no need for unused variables

11 years agoplug a memleak on my way
Martin Quinson [Tue, 11 Dec 2012 10:13:29 +0000 (11:13 +0100)]
plug a memleak on my way

11 years agomodel-checker : update tesh bugged1 and bugged2
Marion Guthmuller [Mon, 10 Dec 2012 16:34:50 +0000 (17:34 +0100)]
model-checker : update tesh bugged1 and bugged2

11 years agomodel-checker : forget one fix in MC_state_set_executed_request
Marion Guthmuller [Mon, 10 Dec 2012 15:53:55 +0000 (16:53 +0100)]
model-checker : forget one fix in MC_state_set_executed_request

11 years agomodel-checker : fix dpor algorithm if max depth reached
Marion Guthmuller [Mon, 10 Dec 2012 15:35:42 +0000 (16:35 +0100)]
model-checker : fix dpor algorithm if max depth reached

11 years agomodel-checker : restore previous version of MC_state_set_executed_request, fixed...
Marion Guthmuller [Mon, 10 Dec 2012 15:34:25 +0000 (16:34 +0100)]
model-checker : restore previous version of MC_state_set_executed_request, fixed with commit 87d50bb063f2937d73b984bed011fef018a761e2

11 years agoadd a bunch of new fortran bindings, to make bigdft happy
Augustin Degomme [Fri, 7 Dec 2012 15:24:32 +0000 (16:24 +0100)]
add a bunch of new fortran bindings, to make bigdft happy