Cristian Rosa [Mon, 10 Sep 2012 12:55:59 +0000 (09:55 -0300)]
Kill unused macro.
Cristian Rosa [Mon, 10 Sep 2012 12:24:14 +0000 (09:24 -0300)]
Move Hosts related simcalls to the new API.
Cristian Rosa [Fri, 7 Sep 2012 18:12:34 +0000 (15:12 -0300)]
Add new type of scalar value 'STRING' for const char*
Cristian Rosa [Fri, 7 Sep 2012 15:33:18 +0000 (12:33 -0300)]
Extend definition of simcalls to include a pointer to the simcall handler functions.
Use these pointers to initialize a simcall dispatch table.
Cristian Rosa [Fri, 7 Sep 2012 13:59:04 +0000 (10:59 -0300)]
Move SIMCALL_HOST_EXECUTE to the new simcall architecture for initial testing.
Cristian Rosa [Thu, 6 Sep 2012 14:25:07 +0000 (11:25 -0300)]
Add new simcall interface definitions.
Cristian Rosa [Fri, 7 Sep 2012 15:33:18 +0000 (12:33 -0300)]
Extend definition of simcalls to include a pointer to the simcall handler functions.
Use these pointers to initialize a simcall dispatch table.
Cristian Rosa [Fri, 7 Sep 2012 13:59:04 +0000 (10:59 -0300)]
Move SIMCALL_HOST_EXECUTE to the new simcall architecture for initial testing.
Cristian Rosa [Thu, 6 Sep 2012 14:25:07 +0000 (11:25 -0300)]
Add new simcall interface definitions.
schnorr [Wed, 22 Aug 2012 21:39:39 +0000 (23:39 +0200)]
[trace] avoiding key clashes on paje links
Augustin Degomme [Tue, 21 Aug 2012 16:10:50 +0000 (18:10 +0200)]
forgot to add color for computing in previous commit
Augustin Degomme [Tue, 21 Aug 2012 13:26:57 +0000 (15:26 +0200)]
add option to generate states for code outside smpi to allow computation timing (not completely accurate as some smpi calls are not traced yet)
jean-noel quintin [Tue, 21 Aug 2012 10:46:15 +0000 (11:46 +0100)]
[smpi,simix-network] remove a useless function
schnorr [Mon, 20 Aug 2012 15:41:53 +0000 (17:41 +0200)]
[trace] for some reason, simulated time changed in smpi -> fix tesh then
schnorr [Mon, 20 Aug 2012 15:39:26 +0000 (17:39 +0200)]
[trace] updating tesh'es according to header changes
details:
- albeit recent modifications on the header, only a white
space after the events number identification was removed
schnorr [Mon, 20 Aug 2012 15:33:25 +0000 (17:33 +0200)]
[trace] header re-organization (now with a basic version)
details:
you can generate a basic version of the header by passing
--cfg=tracing/basic:1 when launching your simulator (considering
you are using other arguments to enable the tracing)
schnorr [Mon, 20 Aug 2012 13:30:14 +0000 (15:30 +0200)]
[trace] fix color for MPI operations to correctly follow color specification
details:
http://paje.sourceforge.net/download/publication/lang-paje.pdf
schnorr [Mon, 20 Aug 2012 13:25:20 +0000 (15:25 +0200)]
[trace] new option tracing/basic (used to generate impoverished trace files)
details:
- this option should be used with visualization tools that are
incapable to read the complete Paje file format specification, as
detailed in this file:
http://paje.sourceforge.net/download/publication/lang-paje.pdf
Marion Guthmuller [Sat, 18 Aug 2012 16:48:28 +0000 (18:48 +0200)]
model-checker : init result of simcalls for snapshot comparison done during simcall
Marion Guthmuller [Fri, 17 Aug 2012 07:55:59 +0000 (09:55 +0200)]
model-checker : try first to associate each block or fragment with the same positiion in the other heap
Marion Guthmuller [Thu, 16 Aug 2012 22:32:52 +0000 (00:32 +0200)]
model-checker : remove unnecessary step
Marion Guthmuller [Thu, 16 Aug 2012 22:24:49 +0000 (00:24 +0200)]
model-checker : equal_to field of blocks/fragments updated twice with match_equals
Marion Guthmuller [Thu, 16 Aug 2012 22:19:08 +0000 (00:19 +0200)]
modelc-checker : reset list of blocks/fragments pairs associated
Marion Guthmuller [Thu, 16 Aug 2012 22:13:52 +0000 (00:13 +0200)]
model-checker : init equal_to field to -1 for each allocated block/fragment at the beginning of the heap comparison
Marion Guthmuller [Wed, 8 Aug 2012 10:06:33 +0000 (12:06 +0200)]
model-checker : set size used to 0 when free fragment
Jean-Baptiste Hervé [Fri, 10 Aug 2012 15:52:53 +0000 (17:52 +0200)]
Add a master/slave example using a generated platform, and using generated event traces
This example fails at the end for the moment, apparently because of autorestart.
Jean-Baptiste Hervé [Fri, 10 Aug 2012 13:38:46 +0000 (15:38 +0200)]
Platform generation: add a bittorent example using a generated platform
Jean-Baptiste Hervé [Thu, 9 Aug 2012 15:36:23 +0000 (17:36 +0200)]
Platform generation: add a master/slave example using a generated platform
Arnaud Giersch [Tue, 27 Nov 2012 14:32:03 +0000 (15:32 +0100)]
Call xbt_log_postexit() at the end.
Arnaud Giersch [Tue, 27 Nov 2012 12:45:58 +0000 (13:45 +0100)]
gras_os_time() has vanished.
Arnaud Giersch [Tue, 27 Nov 2012 12:41:25 +0000 (13:41 +0100)]
Arnaud Giersch [Mon, 26 Nov 2012 16:45:43 +0000 (17:45 +0100)]
Remove unused test program.
It was used to define SIZEOF_MAX for Gras.
Arnaud Giersch [Mon, 26 Nov 2012 16:45:43 +0000 (17:45 +0100)]
Remove needless volatile qualifier.
Arnaud Giersch [Mon, 26 Nov 2012 16:45:43 +0000 (17:45 +0100)]
Remove unused variable.
Arnaud Giersch [Mon, 26 Nov 2012 16:45:43 +0000 (17:45 +0100)]
s/diffrent/different/
Arnaud Giersch [Mon, 26 Nov 2012 16:45:43 +0000 (17:45 +0100)]
Typos.
Arnaud Giersch [Mon, 26 Nov 2012 16:45:43 +0000 (17:45 +0100)]
Revalidate tesh outputs for msg/cloud, and lua tests.
suter [Mon, 26 Nov 2012 15:26:31 +0000 (16:26 +0100)]
mention the modification of TCP_gamma default value, its impact and
workaround
suter [Mon, 26 Nov 2012 15:21:29 +0000 (16:21 +0100)]
revalidate tesh output for tracing ms and simdag
suter [Mon, 26 Nov 2012 15:15:10 +0000 (16:15 +0100)]
revalidate tesh output for token ring
suter [Mon, 26 Nov 2012 15:10:02 +0000 (16:10 +0100)]
revalidate tesh outputs for masterslave
suter [Mon, 26 Nov 2012 15:00:31 +0000 (16:00 +0100)]
revalidate tesh output for bittorrent
suter [Mon, 26 Nov 2012 14:44:24 +0000 (15:44 +0100)]
revalidate tesh output for actions
suter [Mon, 26 Nov 2012 14:30:24 +0000 (15:30 +0100)]
revalidate tesh outputs for chord
suter [Mon, 26 Nov 2012 13:15:21 +0000 (14:15 +0100)]
revalidate tesh outputs for icomms, pmm, sendrecv
suter [Mon, 26 Nov 2012 12:46:06 +0000 (13:46 +0100)]
revalidate tesh outputs for simdag tests
suter [Mon, 26 Nov 2012 12:45:16 +0000 (13:45 +0100)]
revalidate (ans simplify) tesh outputs
suter [Mon, 26 Nov 2012 12:44:27 +0000 (13:44 +0100)]
change default value of tcp_gamma to use something more realistic than
20K. Use 4MiB now
suter [Mon, 26 Nov 2012 11:18:06 +0000 (12:18 +0100)]
better description of the basic simdag tests + cosmetics
suter [Mon, 26 Nov 2012 11:17:17 +0000 (12:17 +0100)]
oops removed the AS
suter [Mon, 26 Nov 2012 11:03:49 +0000 (12:03 +0100)]
get rid of useless spaces and tabs
suter [Mon, 26 Nov 2012 10:31:14 +0000 (11:31 +0100)]
add a description of the scenario
suter [Mon, 26 Nov 2012 10:28:50 +0000 (11:28 +0100)]
Add a description of the scenario
suter [Mon, 26 Nov 2012 09:04:41 +0000 (10:04 +0100)]
add a description of the scenario and expected result
Martin Quinson [Mon, 26 Nov 2012 13:15:26 +0000 (14:15 +0100)]
doxygen is sooooo roten, it drives me crazy
Martin Quinson [Mon, 26 Nov 2012 13:08:25 +0000 (14:08 +0100)]
add xbt_fifo_search(), to search an item with a user-provided comparison function
Martin Quinson [Sun, 25 Nov 2012 14:15:52 +0000 (15:15 +0100)]
move sg_cmdline to xbt/virtu.h module, and rename it to xbt_cmdline
Martin Quinson [Sun, 25 Nov 2012 14:07:45 +0000 (15:07 +0100)]
xbt_os_procname and xbt_binary_name are the same -- keep only one of them
Martin Quinson [Sun, 25 Nov 2012 13:29:43 +0000 (14:29 +0100)]
Apparently, I'm not allowed to free the memory here
I'm not sure of why I MUST free it in the other path, 10 lines above,
if I don't want to leak and why I MUST NOT free it here, but anyway.
All test pass this way, let's be pragmatic and move forward.
Martin Quinson [Sun, 25 Nov 2012 13:21:06 +0000 (14:21 +0100)]
plug a (damn) memleak. Gosh, this one was hard to get, too
Martin Quinson [Sun, 25 Nov 2012 11:37:58 +0000 (12:37 +0100)]
plug a memleak in that example
Martin Quinson [Sun, 25 Nov 2012 11:09:00 +0000 (12:09 +0100)]
Remove all traces of chord_before_dsend
This was an attempt at working around bugs in the model-checker, but
it turned out that the bugs were not due to dsend, making the work
around useless.
Martin Quinson [Sun, 25 Nov 2012 11:02:33 +0000 (12:02 +0100)]
further eradicate all traces of GRAS existance
Martin Quinson [Sun, 25 Nov 2012 10:38:20 +0000 (11:38 +0100)]
don't polute my disk with your crappy test files
Martin Quinson [Sat, 24 Nov 2012 17:57:39 +0000 (18:57 +0100)]
document one of the major change of the upcoming release
Arnaud Giersch [Fri, 23 Nov 2012 15:45:59 +0000 (16:45 +0100)]
Remove doc items about gras.
Arnaud Giersch [Fri, 23 Nov 2012 15:44:53 +0000 (16:44 +0100)]
These files are automatically regenerated at another place.
Remove them.
Arnaud Giersch [Fri, 23 Nov 2012 15:20:42 +0000 (16:20 +0100)]
Remove deprecated figures.
Arnaud Giersch [Fri, 23 Nov 2012 15:17:22 +0000 (16:17 +0100)]
Remove old pictures.
The files seem to be corrupted anyway.
Arnaud Giersch [Fri, 23 Nov 2012 15:11:56 +0000 (16:11 +0100)]
Remove binary file!
Arnaud Giersch [Fri, 23 Nov 2012 14:18:30 +0000 (15:18 +0100)]
Remove fixme comment.
We cannot use an assert here, since test simdag_reinit_costs tries
to call xbt_init twice.
Arnaud Giersch [Fri, 23 Nov 2012 14:17:27 +0000 (15:17 +0100)]
Log priorities were renamed a long time ago.
Arnaud Giersch [Fri, 23 Nov 2012 14:15:45 +0000 (15:15 +0100)]
Eradicate gras further.
Arnaud Giersch [Fri, 23 Nov 2012 11:43:21 +0000 (12:43 +0100)]
Merge XBT_SG_SRC with XBT_SRC, and fix make dist.
Arnaud Giersch [Fri, 23 Nov 2012 11:35:33 +0000 (12:35 +0100)]
Re-add file (wrongly removed).
Augustin Degomme [Fri, 23 Nov 2012 10:58:55 +0000 (11:58 +0100)]
fix distcheck to handle mpich-test
Arnaud Giersch [Fri, 23 Nov 2012 10:24:55 +0000 (11:24 +0100)]
Merge branch 'killgraskill'
Arnaud Giersch [Fri, 23 Nov 2012 10:19:05 +0000 (11:19 +0100)]
Update ChangeLog.
Arnaud Giersch [Fri, 23 Nov 2012 10:04:17 +0000 (11:04 +0100)]
Fix make dist.
make distcheck is still broken, though.
Arnaud Giersch [Tue, 20 Nov 2012 10:20:29 +0000 (11:20 +0100)]
Finalize coverage for swag.c.
Arnaud Giersch [Fri, 23 Nov 2012 09:41:53 +0000 (10:41 +0100)]
Kill more references to GRAS.
Arnaud Giersch [Fri, 23 Nov 2012 09:36:26 +0000 (10:36 +0100)]
This hack is not needed since gras is killed.
Arnaud Giersch [Fri, 23 Nov 2012 09:20:12 +0000 (10:20 +0100)]
Rename gras_config to internal_config.
Arnaud Giersch [Fri, 23 Nov 2012 09:15:46 +0000 (10:15 +0100)]
Kill xbt_dynar_dopar().
Keep it as a separated commit, to make a potential revert easier.
Arnaud Giersch [Fri, 23 Nov 2012 08:57:35 +0000 (09:57 +0100)]
Use real threads for xbt_dynar_dopar.
Arnaud Giersch [Fri, 23 Nov 2012 08:40:34 +0000 (09:40 +0100)]
Revert "use MSG_init instead of xbt_init since someone wrongly create mutexes"
This reverts commit
becf2ff78c488808dcb55883271ca759ac0ca492
since it's not needed anymore.
Arnaud Giersch [Fri, 23 Nov 2012 08:34:07 +0000 (09:34 +0100)]
Move check at another place where it doesn't break the log machinery.
Martin Quinson [Fri, 23 Nov 2012 00:03:17 +0000 (01:03 +0100)]
try to fix 'make dist' after GRAS murder (SMPI test still break it)
Martin Quinson [Thu, 22 Nov 2012 23:52:31 +0000 (00:52 +0100)]
adapt the links of this figure to the fact that the doc is splited in 3 parts (fixes #15069)
Martin Quinson [Thu, 22 Nov 2012 23:49:06 +0000 (00:49 +0100)]
remove GRAS and AMOK from the module picture
Martin Quinson [Thu, 22 Nov 2012 23:42:28 +0000 (00:42 +0100)]
further remove GRAS and friends (from the doxygen config files)
Martin Quinson [Thu, 22 Nov 2012 23:15:48 +0000 (00:15 +0100)]
useless cosmetic
Martin Quinson [Thu, 22 Nov 2012 23:04:19 +0000 (00:04 +0100)]
comments, debugs and other minor glitches
Martin Quinson [Thu, 22 Nov 2012 23:01:05 +0000 (00:01 +0100)]
use OS threads and not simix ones to run the test in parallel
Martin Quinson [Thu, 22 Nov 2012 22:50:35 +0000 (23:50 +0100)]
a public xbt header wasnt included from xbt.h
Martin Quinson [Thu, 22 Nov 2012 22:49:52 +0000 (23:49 +0100)]
ignore some of the recently added generated files
Martin Quinson [Thu, 22 Nov 2012 22:41:11 +0000 (23:41 +0100)]
these examples were moved as tesh tests
Martin Quinson [Thu, 22 Nov 2012 22:03:52 +0000 (23:03 +0100)]
kill synchronized dynars: we don't need them and they are a mess to keep (sorry, users)
Martin Quinson [Thu, 22 Nov 2012 22:01:36 +0000 (23:01 +0100)]
use MSG_init instead of xbt_init since someone wrongly create mutexes
There should not be necessary to call MSG_init to create xbt_mutexes,
but since this creation induces a simcall, we'd better initialize
simix.
This is not sufficient though, as maestro_context does not seem to be
initialized this way, leading to a try to dereference the host of the
current process, that was never set.
Martin Quinson [Thu, 22 Nov 2012 21:39:04 +0000 (22:39 +0100)]
how did that cruft manage to live that long?