Logo AND Algorithmique Numérique Distribuée

Public GIT Repository
simgrid.git
8 years agosort my TODO list :-(
Martin Quinson [Sun, 19 Jul 2015 15:33:34 +0000 (17:33 +0200)]
sort my TODO list :-(

plus cosmetics

8 years agoKill link_lib and have C++ handle the hashmap of all links
Martin Quinson [Sun, 19 Jul 2015 15:20:33 +0000 (17:20 +0200)]
Kill link_lib and have C++ handle the hashmap of all links

I did not manage to get SD_application_reinit() working, so this
function is currently disabled. I think that it should be removed
anyway.

8 years agokill some remainings of sd_link_t
Martin Quinson [Sun, 19 Jul 2015 06:49:55 +0000 (08:49 +0200)]
kill some remainings of sd_link_t

8 years agostart refreshing and fixing the GTNetS interface (WIP)
Martin Quinson [Sun, 19 Jul 2015 00:14:49 +0000 (02:14 +0200)]
start refreshing and fixing the GTNetS interface (WIP)

8 years agoOverhaul of NS3 support in SimGrid
Martin Quinson [Sat, 18 Jul 2015 21:35:18 +0000 (23:35 +0200)]
Overhaul of NS3 support in SimGrid

- NS3 is now found if installed from the default package (eg, Debian)
- If enable_ns3 and not found, cmake will fail
- 3 log channels were a bit too much
- Don't use NS3 log channels as it fails when running in Java somehow
- Drop support for ancient version of NS3 (3.10)
- Documentation refresh/rewrite
- Revalidate the tesh files (rounding errors on timings)

8 years agofix doxygen
Martin Quinson [Sat, 18 Jul 2015 20:50:57 +0000 (22:50 +0200)]
fix doxygen

8 years agosanitize C API of sg_link
Martin Quinson [Sat, 18 Jul 2015 17:19:25 +0000 (19:19 +0200)]
sanitize C API of sg_link

8 years agothere is no need for a SimDag's link type
Martin Quinson [Sat, 18 Jul 2015 17:13:29 +0000 (19:13 +0200)]
there is no need for a SimDag's link type

8 years agokill an unused field
Martin Quinson [Sat, 18 Jul 2015 16:33:56 +0000 (18:33 +0200)]
kill an unused field

8 years agokill LinkPtr type and make Link* explicit
Martin Quinson [Sat, 18 Jul 2015 16:31:51 +0000 (18:31 +0200)]
kill LinkPtr type and make Link* explicit

8 years agogive Link a proper public interface
Martin Quinson [Sat, 18 Jul 2015 16:13:30 +0000 (18:13 +0200)]
give Link a proper public interface

8 years agoRename NetworkLink type to Link
Martin Quinson [Sat, 18 Jul 2015 14:17:26 +0000 (16:17 +0200)]
Rename NetworkLink type to Link

Yup, that's an useless cosmetics.

8 years agocosmetics in the comments
Martin Quinson [Sat, 18 Jul 2015 13:56:02 +0000 (15:56 +0200)]
cosmetics in the comments

8 years agokill unused type definitions
Martin Quinson [Sat, 18 Jul 2015 13:46:02 +0000 (15:46 +0200)]
kill unused type definitions

8 years agomake SD_HOST_LEVEL private
Martin Quinson [Sat, 18 Jul 2015 13:25:34 +0000 (15:25 +0200)]
make SD_HOST_LEVEL private

8 years agoNew function: sg_hosts_as_dynar
Martin Quinson [Sat, 18 Jul 2015 12:26:59 +0000 (14:26 +0200)]
New function: sg_hosts_as_dynar

This was implemented several times, in each layer

8 years agocosmetics: make semantic more clear
Martin Quinson [Sat, 18 Jul 2015 10:52:10 +0000 (12:52 +0200)]
cosmetics: make semantic more clear

8 years ago[SGpp] make ROUTING_HOST_LEVEL private. That was painful
Martin Quinson [Sat, 18 Jul 2015 10:42:26 +0000 (12:42 +0200)]
[SGpp] make ROUTING_HOST_LEVEL private. That was painful

8 years agowhatever, eclipse
Martin Quinson [Sat, 18 Jul 2015 10:37:42 +0000 (12:37 +0200)]
whatever, eclipse

8 years agoUse MSG_host_by_name() instead of MSG_get_host_by_name()
Martin Quinson [Wed, 15 Jul 2015 08:30:02 +0000 (10:30 +0200)]
Use MSG_host_by_name() instead of MSG_get_host_by_name()

Both work, but the first is more coherent with the rest of the
interface.

8 years agokill simcall_host_get_by_name: nobody uses it anyway
Martin Quinson [Wed, 15 Jul 2015 08:05:38 +0000 (10:05 +0200)]
kill simcall_host_get_by_name: nobody uses it anyway

8 years ago[SGpp] make SURF_CPU_LEVEL private
Martin Quinson [Wed, 15 Jul 2015 07:59:34 +0000 (09:59 +0200)]
[SGpp] make SURF_CPU_LEVEL private

8 years agokill unimplemented (braindead) prototype
Martin Quinson [Wed, 15 Jul 2015 00:59:47 +0000 (02:59 +0200)]
kill unimplemented (braindead) prototype

8 years ago[SGpp] make MSG_HOST_LEVEL private
Martin Quinson [Wed, 15 Jul 2015 00:57:44 +0000 (02:57 +0200)]
[SGpp] make MSG_HOST_LEVEL private

8 years agodamn, missing files
Martin Quinson [Tue, 14 Jul 2015 23:58:35 +0000 (01:58 +0200)]
damn, missing files

8 years agosanitize a bit the prototype of SIMIX_host_create()
Martin Quinson [Tue, 14 Jul 2015 23:58:09 +0000 (01:58 +0200)]
sanitize a bit the prototype of SIMIX_host_create()

8 years ago[SGpp] make SIMIX_HOST_LEVEL private
Martin Quinson [Tue, 14 Jul 2015 23:46:11 +0000 (01:46 +0200)]
[SGpp] make SIMIX_HOST_LEVEL private

8 years agoGive simgrid's host its own header file and datatype
Martin Quinson [Tue, 14 Jul 2015 21:25:33 +0000 (23:25 +0200)]
Give simgrid's host its own header file and datatype

This is one step further toward SGpp, the C++ version of SimGrid.

8 years ago[SURF] Cosmetics - indented assignments in surf_routing.cpp.
Christian Heinrich [Fri, 17 Jul 2015 17:10:57 +0000 (19:10 +0200)]
[SURF] Cosmetics - indented assignments in surf_routing.cpp.

8 years ago[Doc] Added Cluster description. Fixes #18
Christian Heinrich [Fri, 17 Jul 2015 17:10:21 +0000 (19:10 +0200)]
[Doc] Added Cluster description. Fixes #18

8 years ago[mc] Remove content addressable page store
Gabriel Corona [Fri, 17 Jul 2015 09:36:15 +0000 (11:36 +0200)]
[mc] Remove content addressable page store

- It did not prove useful compared fo the default option.
- It is implemented as a compile-time option instead of a runtime one.
- Let's remove compile time options!
- It makes the code more complex.

8 years ago[mc] Cleanup mc_hash
Gabriel Corona [Fri, 17 Jul 2015 09:30:40 +0000 (11:30 +0200)]
[mc] Cleanup mc_hash

8 years ago[doc] Add missing layers (MC, SIMIX, SIMDAG) in README.coding
Gabriel Corona [Fri, 17 Jul 2015 08:58:25 +0000 (10:58 +0200)]
[doc] Add missing layers (MC, SIMIX, SIMDAG) in README.coding

8 years ago[doc] Various fixes to README.git
Gabriel Corona [Fri, 17 Jul 2015 08:52:41 +0000 (10:52 +0200)]
[doc] Various fixes to README.git

- Some typographic fixes.
- Remove reference to sourceforge.
- Some other minor modifications.

8 years ago[mc] Fix another signedness conversion issue with addresses on 32 bit
Gabriel Corona [Fri, 17 Jul 2015 08:21:39 +0000 (10:21 +0200)]
[mc] Fix another signedness conversion issue with addresses on 32 bit

8 years ago[mc] Remove useless cast
Gabriel Corona [Fri, 17 Jul 2015 07:35:51 +0000 (09:35 +0200)]
[mc] Remove useless cast

8 years ago[Doc] Changed stylesheet to make headings look better
Christian Heinrich [Thu, 16 Jul 2015 19:03:56 +0000 (21:03 +0200)]
[Doc] Changed stylesheet to make headings look better

8 years ago[Doc] Significant update to the storage documentation
Christian Heinrich [Thu, 16 Jul 2015 14:25:01 +0000 (16:25 +0200)]
[Doc] Significant update to the storage documentation

8 years ago[SURF] Cosmetics in surfxml_parse.c
Christian Heinrich [Thu, 16 Jul 2015 17:17:41 +0000 (19:17 +0200)]
[SURF] Cosmetics in surfxml_parse.c

8 years ago[mc] Fix cross process memory access in 32 bit
Gabriel Corona [Thu, 16 Jul 2015 14:37:31 +0000 (16:37 +0200)]
[mc] Fix cross process memory access in 32 bit

Sign extension issue when converting offset bewteen signed and unsigned.

8 years ago[mc] SimGrid 3.11 Chanelog/NEWS
Gabriel Corona [Thu, 16 Jul 2015 11:32:04 +0000 (13:32 +0200)]
[mc] SimGrid 3.11 Chanelog/NEWS

8 years agoprotect against MPI_BOTTOM
degomme [Fri, 10 Jul 2015 14:40:10 +0000 (16:40 +0200)]
protect against MPI_BOTTOM

8 years agoFix fortran mpi_type_struct and mpi_type_create_struct functions
degomme [Fri, 10 Jul 2015 13:32:53 +0000 (15:32 +0200)]
Fix fortran mpi_type_struct and mpi_type_create_struct functions

8 years agoRevert "A candidate patch to Github issue #15. Three problems related to TRACE might...
Martin Quinson [Tue, 14 Jul 2015 22:08:57 +0000 (00:08 +0200)]
Revert "A candidate patch to Github issue #15. Three problems related to TRACE might be corrected by this patch."

This reverts commit 58a9c67822f4640964044ec485426d090bcb123f.

8 years agoRevert "rename SIMIX_process_get_maxpid() to SIMIX_process_get_nextpid() and make...
Martin Quinson [Tue, 14 Jul 2015 22:08:32 +0000 (00:08 +0200)]
Revert "rename SIMIX_process_get_maxpid() to SIMIX_process_get_nextpid() and make it public"

This reverts commit 9306ddd4b063b1934dbab43f967e380d0181e393.

8 years agokill an unused definition
Martin Quinson [Tue, 14 Jul 2015 20:04:03 +0000 (22:04 +0200)]
kill an unused definition

8 years agorename SIMIX_process_get_maxpid() to SIMIX_process_get_nextpid() and make it public
Martin Quinson [Tue, 14 Jul 2015 20:02:33 +0000 (22:02 +0200)]
rename SIMIX_process_get_maxpid() to SIMIX_process_get_nextpid() and make it public

This ends the Fix #15 after the recent commit of @mpoquet. Thanks for
that again.

8 years agoMerge branch 'master' of github.com:mquinson/simgrid
Martin Quinson [Tue, 14 Jul 2015 19:55:18 +0000 (21:55 +0200)]
Merge branch 'master' of github.com:mquinson/simgrid

8 years agoMerge pull request #17 from mpoquet/master
Martin Quinson [Tue, 14 Jul 2015 19:54:24 +0000 (21:54 +0200)]
Merge pull request #17 from mpoquet/master

Candidate patch to issue #15

8 years agokill two empty files
Martin Quinson [Sun, 12 Jul 2015 21:54:43 +0000 (23:54 +0200)]
kill two empty files

8 years agowho needs such an empty constructor?
Martin Quinson [Sun, 12 Jul 2015 21:54:27 +0000 (23:54 +0200)]
who needs such an empty constructor?

8 years agoless void*, new type: surf_host_t
Martin Quinson [Sun, 12 Jul 2015 21:30:05 +0000 (23:30 +0200)]
less void*, new type: surf_host_t

Plus some small cosmetics

8 years agoMerge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid
Martin Quinson [Fri, 10 Jul 2015 23:58:18 +0000 (01:58 +0200)]
Merge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid

8 years agodo not output a user unfriendly line
Martin Quinson [Fri, 10 Jul 2015 23:55:25 +0000 (01:55 +0200)]
do not output a user unfriendly line

"Switching host model to compound since you changed the network and/or cpu model(s)"

- Hard to understand what's going on without reading the right part of
  the source.
- I cannot think of a situation where this would do any good

- My evil plan is to change the xbt_lib of all hosts by a boost map of
  Hosts, so the host model will be gone, and hosts will always
  dispatch to their content. One this is done, objectifying everything
  will be really easy.

8 years agoignore more cruft
Martin Quinson [Fri, 10 Jul 2015 23:40:24 +0000 (01:40 +0200)]
ignore more cruft

8 years agoMASSIVE cleanup: s/workstation/host/
Martin Quinson [Fri, 10 Jul 2015 23:36:01 +0000 (01:36 +0200)]
MASSIVE cleanup: s/workstation/host/

- simdag is not affected for now (it's a user interface, it will be
  rewamped soon)
- It means that the workstation/model option is changed into host/model

That's a really intrusive change, and I'm sorry for the ones having
unmerged branches (Sorry Christian, I thought of you when I was almost
done). But I feel that this is a good move for the project, important
to the objectification of the whole.

8 years agousing trace timestamp precision when printing to trace files
Lucas Schnorr [Fri, 10 Jul 2015 17:00:21 +0000 (14:00 -0300)]
using trace timestamp precision when printing to trace files

8 years agonew option to set trace timestamp precision
Lucas Schnorr [Fri, 10 Jul 2015 16:59:09 +0000 (13:59 -0300)]
new option to set trace timestamp precision

the number must be an integer, whose value is the
desired number of digits after the decimal point
for all timestamps registered when tracing

8 years ago[mc] Cleanup the DSO ignore list and add some entries
Gabriel Corona [Thu, 9 Jul 2015 13:52:48 +0000 (15:52 +0200)]
[mc] Cleanup the DSO ignore list and add some entries

8 years ago[mc] Fix the DSO debug ignore list
Gabriel Corona [Thu, 9 Jul 2015 12:44:58 +0000 (14:44 +0200)]
[mc] Fix the DSO debug ignore list

This is nasty. We must get rid of this.

8 years agoFix the cmake for the host-on-off tests
Gabriel Corona [Thu, 9 Jul 2015 11:40:12 +0000 (13:40 +0200)]
Fix the cmake for the host-on-off tests

Fix #7

8 years agoFix the host-on-off refcount test
Gabriel Corona [Thu, 9 Jul 2015 10:53:21 +0000 (12:53 +0200)]
Fix the host-on-off refcount test

8 years agohost-on-off: add basic tests
Gabriel Corona [Mon, 6 Jul 2015 14:21:17 +0000 (16:21 +0200)]
host-on-off: add basic tests

8 years ago[jenkins] Enable debug (Ã-g) in the builds
Gabriel Corona [Fri, 3 Jul 2015 12:41:09 +0000 (14:41 +0200)]
[jenkins] Enable debug (Ã-g) in the builds

8 years agoAdd the missing breaks
Gabriel Corona [Fri, 3 Jul 2015 12:28:25 +0000 (14:28 +0200)]
Add the missing breaks

8 years agoMove the host-on-off fix above
Gabriel Corona [Fri, 3 Jul 2015 11:36:53 +0000 (13:36 +0200)]
Move the host-on-off fix above

If our host is OFF, we should always get a HOST_FAILURE.

This seems to fix issues where a host was turned off but its processes
were not woken up with HOST_FAILURE.

8 years agoClean the possibly dangling waiting_synchro pointer
Gabriel Corona [Tue, 30 Jun 2015 11:36:49 +0000 (13:36 +0200)]
Clean the possibly dangling waiting_synchro pointer

8 years agoFix host-on-off
Gabriel Corona [Mon, 29 Jun 2015 11:08:51 +0000 (13:08 +0200)]
Fix host-on-off

This is a temporary workaround. This should probably be fixed at a
lower layer instead.

The test stil has a refcount handling bug (two +1 but only one -1).

8 years agoFix the documentation
Arnaud Legrand [Wed, 1 Jul 2015 19:01:54 +0000 (21:01 +0200)]
Fix the documentation

8 years agoComment on a function whose behavior may be misleading...
Arnaud Legrand [Wed, 1 Jul 2015 07:05:09 +0000 (09:05 +0200)]
Comment on a function whose behavior may be misleading...

8 years agoDo not build html/msg-tuto-src.tg anymore
Gabriel Corona [Tue, 30 Jun 2015 07:18:59 +0000 (09:18 +0200)]
Do not build html/msg-tuto-src.tg anymore

This is not referenced anywhere. Those things are intended to go on
the website.

The tar is not reproducible by default (see
https://bugs.debian.org/789715) because it contains timestamps.  The
-n flags can be passed to gzip in order to omit the timestamps but
this option is not available in `cmake -E tar`. We would like to avoid
depending on tar+gzip because they are often not available on Windows
systems.

8 years agoAdd missing #include
Gabriel Corona [Mon, 29 Jun 2015 10:07:49 +0000 (12:07 +0200)]
Add missing #include

8 years agogenerate-dwarf-functions: add a 'Usage' comment
Gabriel Corona [Mon, 29 Jun 2015 09:21:57 +0000 (11:21 +0200)]
generate-dwarf-functions: add a 'Usage' comment

8 years agoFix reference to generate.sh (now generate-dwarf-functions)
Gabriel Corona [Mon, 29 Jun 2015 09:20:49 +0000 (11:20 +0200)]
Fix reference to generate.sh (now generate-dwarf-functions)

8 years ago[mc] Fix include guards
Gabriel Corona [Mon, 29 Jun 2015 08:53:51 +0000 (10:53 +0200)]
[mc] Fix include guards

8 years ago[mc] Remove ugly #include
Gabriel Corona [Mon, 29 Jun 2015 08:42:53 +0000 (10:42 +0200)]
[mc] Remove ugly #include

8 years agoAdd some #includes
Gabriel Corona [Mon, 29 Jun 2015 08:25:40 +0000 (10:25 +0200)]
Add some #includes

8 years agosecond attempt
degomme [Fri, 26 Jun 2015 07:36:46 +0000 (09:36 +0200)]
second attempt

8 years ago(attempt to) Disable fortran for mac platforms, for now.
degomme [Fri, 26 Jun 2015 07:32:40 +0000 (09:32 +0200)]
(attempt to) Disable fortran for mac platforms, for now.
If we ever find a user for SMPI+Fortran on apple, we will need to investigate what to do to
correctly plug the user_main function (correct underscore handling is a likely guess)

8 years agohappy now?
Frederic Suter [Thu, 25 Jun 2015 14:53:40 +0000 (16:53 +0200)]
happy now?

8 years agoplease the paranoid freak
Frederic Suter [Thu, 25 Jun 2015 14:51:17 +0000 (16:51 +0200)]
please the paranoid freak

8 years agoDon't try to change the rate of task once it's done, the new test in
Frederic Suter [Thu, 25 Jun 2015 13:56:08 +0000 (15:56 +0200)]
Don't try to change the rate of task once it's done, the new test in
SD_task_set_rate raises a justified warn.
Add a comment to warn readers that such a change must be done before the
beginning of the execution of a task.

8 years agoforgot to declare newly added actions_io.txt and
Frederic Suter [Tue, 16 Jun 2015 16:10:32 +0000 (18:10 +0200)]
forgot to declare newly added actions_io.txt and
storage_deployment.xml files.
These files are needed by the early prototype of storage action replay.

8 years agofirst prototype of storage action replay
Frederic Suter [Thu, 7 May 2015 08:30:53 +0000 (10:30 +0200)]
first prototype of storage action replay

8 years agoprepare implementation of first prototype of I/O trace replay
Frederic Suter [Thu, 7 May 2015 06:32:31 +0000 (08:32 +0200)]
prepare implementation of first prototype of I/O trace replay

8 years agoadd two declarations for fortran
degomme [Thu, 25 Jun 2015 13:47:39 +0000 (15:47 +0200)]
add two declarations for fortran

8 years agofix memory leak
degomme [Thu, 25 Jun 2015 13:47:26 +0000 (15:47 +0200)]
fix memory leak

8 years agoFix thread safety issue in process cleanup
Gabriel Corona [Fri, 19 Jun 2015 09:34:54 +0000 (11:34 +0200)]
Fix thread safety issue in process cleanup

While trying to find the root cause of the occasional failure of the
kademlia test, I found a thread-safety issue here:

When running in parallel mode all worker threads can call the
`SIMIX_process_cleanup()` concurrently which does things such as:

~~~c++
XBT_DEBUG("%p should not be run anymore",process);
xbt_swag_remove(process, simix_global->process_list);
xbt_swag_remove(process, SIMIX_host_priv(process->smx_host)->process_list);
xbt_swag_insert(process, simix_global->process_to_destroy);
~~~

The SWAG are modified concurrently by the worker threads without
synchronization. Sometimes, they go into inconsistent states (for
example, `swag->count` is no more consistent with the number of
elements really in the swag).

This fix might not be the best way to do it.

8 years agoImprove the doc and checkings of SD_task_set_rate.
Arnaud Legrand [Thu, 25 Jun 2015 06:55:09 +0000 (08:55 +0200)]
Improve the doc and checkings of SD_task_set_rate.

8 years agodo not generate the timestamps to help debian building reproducibly
Martin Quinson [Tue, 23 Jun 2015 23:49:39 +0000 (01:49 +0200)]
do not generate the timestamps to help debian building reproducibly

8 years agoFind objdump before admitting privatization is possible and compiling it.
degomme [Tue, 23 Jun 2015 07:26:35 +0000 (09:26 +0200)]
Find objdump before admitting privatization is possible and compiling it.
MacOS has mmap and no objdump, so this disables the feature on this platform for now

8 years agoremove unused var
degomme [Fri, 19 Jun 2015 10:02:37 +0000 (12:02 +0200)]
remove unused var

8 years agoMSG_process_get_data(): don't segfault if there the process has been cleaned up
Gabriel Corona [Mon, 22 Jun 2015 12:41:39 +0000 (14:41 +0200)]
MSG_process_get_data(): don't segfault if there the process has been cleaned up

8 years ago[mc] Remove some extern "C"
Gabriel Corona [Fri, 19 Jun 2015 09:01:10 +0000 (11:01 +0200)]
[mc] Remove some extern "C"

clang was complaining about C-linkage functions with non-C-linkage return/parameter types.

8 years agoAdd support for new Boost.Context API
Gabriel Corona [Thu, 18 Jun 2015 14:14:15 +0000 (16:14 +0200)]
Add support for new Boost.Context API

8 years agoParallel implementation for Boost.Context context
Gabriel Corona [Thu, 18 Jun 2015 12:23:01 +0000 (14:23 +0200)]
Parallel implementation for Boost.Context context

This is really a copy of the code of smx_context_sysv.c. (The same
logic is duplicated without mushc difference between most
implementations.)

8 years ago[cmake] Fix broken -D_DWARWIN_C_SOURCE
Gabriel Corona [Thu, 18 Jun 2015 11:23:42 +0000 (13:23 +0200)]
[cmake] Fix broken -D_DWARWIN_C_SOURCE

8 years agoDo not try to link against boost_context when there is none
Gabriel Corona [Thu, 18 Jun 2015 11:21:24 +0000 (13:21 +0200)]
Do not try to link against boost_context when there is none

8 years ago[cmake] Do not find cmake as required
Gabriel Corona [Thu, 18 Jun 2015 10:21:41 +0000 (12:21 +0200)]
[cmake] Do not find cmake as required

This is hanlded afterwards anyway and we need to succeed if Boost.Context is not found.

8 years agomerge smpi_replay_init and smpi_replay_finalize into smpi_replay_run
Martin Quinson [Thu, 18 Jun 2015 10:22:34 +0000 (12:22 +0200)]
merge smpi_replay_init and smpi_replay_finalize into smpi_replay_run