Logo AND Algorithmique Numérique Distribuée

Public GIT Repository
simgrid.git
7 years agoMerge branch 'hypervisor' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid...
Paul Bédaride [Fri, 8 Nov 2013 12:24:16 +0000 (13:24 +0100)]
Merge branch 'hypervisor' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid into hypervisor

7 years agoMerge tag 'v3_9_90' into hypervisor
Paul Bédaride [Fri, 8 Nov 2013 10:50:47 +0000 (11:50 +0100)]
Merge tag 'v3_9_90' into hypervisor

Conflicts:
include/msg/msg.h
include/simgrid/simix.h
src/include/surf/surf.h
src/msg/msg_global.c
src/msg/msg_host.c
src/msg/msg_private.h
src/msg/msg_process.c
src/simix/smx_host.c
src/simix/smx_host_private.h
src/simix/smx_smurf_private.h
src/surf/cpu_cas01.c
src/surf/cpu_cas01_private.h
src/surf/cpu_ti.c
src/surf/surf.c
src/surf/workstation.c

7 years agoFix a segmentation fault at set_affinity
Takahiro Hirofuchi [Thu, 7 Nov 2013 15:08:08 +0000 (16:08 +0100)]
Fix a segmentation fault at set_affinity

7 years agoAdd comments and update an example.
Takahiro Hirofuchi [Thu, 7 Nov 2013 15:07:18 +0000 (16:07 +0100)]
Add comments and update an example.

7 years agoAdd comments and disable verbose outputs
Takahiro Hirofuchi [Tue, 29 Oct 2013 15:24:44 +0000 (16:24 +0100)]
Add comments and disable verbose outputs

7 years agoAdd the affinity database of each VM
Takahiro Hirofuchi [Mon, 28 Oct 2013 17:00:39 +0000 (18:00 +0100)]
Add the affinity database of each VM

7 years agoAdd the affinity database of each task
Takahiro Hirofuchi [Mon, 28 Oct 2013 16:39:22 +0000 (17:39 +0100)]
Add the affinity database of each task

The SURF layer has affinity information only related to the current host
of a task. Affinity information on other hosts (i.e., the locations
where the task may move to) is maintained in the MSG layer.

7 years agoFix lmm_shrink() to correctly free var->cnsts[i]
Takahiro Hirofuchi [Mon, 28 Oct 2013 16:32:55 +0000 (17:32 +0100)]
Fix lmm_shrink() to correctly free var->cnsts[i]

7 years agoAdd the affinity setting function for a VM
Takahiro Hirofuchi [Mon, 28 Oct 2013 11:31:29 +0000 (12:31 +0100)]
Add the affinity setting function for a VM

7 years agoFix the wrong macro usage of WITHOUT_ANSWER
Takahiro Hirofuchi [Mon, 28 Oct 2013 11:20:07 +0000 (12:20 +0100)]
Fix the wrong macro usage of WITHOUT_ANSWER

7 years agoDisallow setting an affinity to multiple cores
Takahiro Hirofuchi [Fri, 25 Oct 2013 10:55:23 +0000 (12:55 +0200)]
Disallow setting an affinity to multiple cores

7 years agoClear constraint objects before adding new ones
Takahiro Hirofuchi [Thu, 24 Oct 2013 13:48:41 +0000 (15:48 +0200)]
Clear constraint objects before adding new ones

Fix a miscalculation bug caused by the wrong use of lmm_expand().

7 years agoAdd the MSG function controlling CPU affinity
Takahiro Hirofuchi [Thu, 24 Oct 2013 10:15:55 +0000 (12:15 +0200)]
Add the MSG function controlling CPU affinity

7 years agoExtend simcall_host_execute() for CPU affinity
Takahiro Hirofuchi [Thu, 24 Oct 2013 10:13:49 +0000 (12:13 +0200)]
Extend simcall_host_execute() for CPU affinity

7 years agoAdd the simcall setting CPU affinity
Takahiro Hirofuchi [Thu, 24 Oct 2013 10:08:34 +0000 (12:08 +0200)]
Add the simcall setting CPU affinity

7 years agoAdd the set_affinity callback to the PM/VM models
Takahiro Hirofuchi [Thu, 24 Oct 2013 09:26:47 +0000 (11:26 +0200)]
Add the set_affinity callback to the PM/VM models

7 years agoAdd the affinity control function in the CPU model
Takahiro Hirofuchi [Thu, 24 Oct 2013 09:21:13 +0000 (11:21 +0200)]
Add the affinity control function in the CPU model

7 years agoadd lmm_shrink() as the opposite of lmm_expand()
Takahiro Hirofuchi [Thu, 24 Oct 2013 09:08:28 +0000 (11:08 +0200)]
add lmm_shrink() as the opposite of lmm_expand()

Note: I am not confident the code of this function is correct especially
for the lazy calculation mode.

7 years agoadd a constraint object for each CPU core
Takahiro Hirofuchi [Thu, 24 Oct 2013 09:02:25 +0000 (11:02 +0200)]
add a constraint object for each CPU core

7 years agoMerge branch 'hypervisor' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid into hypervisor
Takahiro Hirofuchi [Tue, 22 Oct 2013 11:06:47 +0000 (13:06 +0200)]
Merge branch 'hypervisor' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid into hypervisor

7 years agoAdd a test program to see multicore behaviors.
Takahiro Hirofuchi [Tue, 22 Oct 2013 10:45:30 +0000 (12:45 +0200)]
Add a test program to see multicore behaviors.

As far as tested through this test program, it looks that the current
support of multicore in SimGrid correctly works for physical and virtual
machines. The CPU share of a task or a VM never exceeds the capacity of
one of the CPU cores. The total CPU share of all tasks and VMs on a PM
never exceeds the product of the number of cores and the capacity of a core.
(But, it is not possible to pin a task to a specific core.)

TODO: use this program for regression test.

7 years agoFix miscalculation of CPU shares on a multicore PM.
Takahiro Hirofuchi [Tue, 22 Oct 2013 09:14:18 +0000 (11:14 +0200)]
Fix miscalculation of CPU shares on a multicore PM.

The recent commit adding the load capping feature broke CPU share
calculation on a multicore PM. This patch fixes the problem.

The bound value "0" means that there is no CPU bound for that task or
VM. On a single-core PM, this is true. The task can use all CPU resource
on that PM. On a multicore PM, the task can use the resource of
only a CPU core.

Even MSG_{task/vm}_set_bound() is not used in a simulation program,
simulation results will be wrong for multicore PMs. This is because
the bound value "0" is used internally.

7 years agoAdding code for benchmarking code block v3_9_90
Luka Stanisic [Tue, 22 Oct 2013 08:33:02 +0000 (10:33 +0200)]
Adding code for benchmarking code block

7 years agowhen parallel ctests are performed, using the default tracing filename may cause...
Augustin Degomme [Fri, 18 Oct 2013 09:39:16 +0000 (11:39 +0200)]
when parallel ctests are performed, using the default tracing filename may cause trouble.

7 years agotry to speed up a bit testing by using all available cores in the slaves
Augustin Degomme [Thu, 17 Oct 2013 15:54:15 +0000 (17:54 +0200)]
try to speed up a bit testing by using all available cores in the slaves

7 years agowe now only have one build mode for win, as mc is irrelevant for now
Augustin Degomme [Thu, 17 Oct 2013 15:40:46 +0000 (17:40 +0200)]
we now only have one build mode for win, as mc is irrelevant for now

7 years agonot implicit on all systems
Augustin Degomme [Thu, 17 Oct 2013 12:36:53 +0000 (14:36 +0200)]
not implicit on all systems

7 years agoadd background commands support + correct error code for output mismatch
Augustin Degomme [Wed, 16 Oct 2013 16:26:19 +0000 (18:26 +0200)]
add background commands support + correct error code for output mismatch

7 years agoUse temporary files to store output of the command in perl tesh
Augustin Degomme [Tue, 15 Oct 2013 15:33:57 +0000 (17:33 +0200)]
Use temporary files to store output of the command in perl tesh
Avoids deadlocking when large data is sent to/from pipes (see tesh test IO-bigsize)

7 years agowin is not yet ready for coverage either
Augustin Degomme [Mon, 14 Oct 2013 19:15:44 +0000 (21:15 +0200)]
win is not yet ready for coverage either

7 years agowin is not yet ready for warning removal
Augustin Degomme [Mon, 14 Oct 2013 19:02:28 +0000 (21:02 +0200)]
win is not yet ready for warning removal

7 years agoAdd error checking to the script
Augustin Degomme [Mon, 14 Oct 2013 16:13:15 +0000 (18:13 +0200)]
Add error checking to the script

7 years agoavoid failing the tar extraction and working on previous version instead
Augustin Degomme [Mon, 14 Oct 2013 15:19:45 +0000 (17:19 +0200)]
avoid failing the tar extraction and working on previous version instead

7 years agofix run script
Augustin Degomme [Mon, 14 Oct 2013 14:03:32 +0000 (16:03 +0200)]
fix run script

7 years agounify version name of executable
Augustin Degomme [Mon, 14 Oct 2013 13:54:07 +0000 (15:54 +0200)]
unify version name of executable

7 years agoLet's try to unify build rules for jenkins
Augustin Degomme [Mon, 14 Oct 2013 13:18:12 +0000 (15:18 +0200)]
Let's try to unify build rules for jenkins

7 years agoWin + cmake wants perl to be explicit here.. why not?
Augustin Degomme [Mon, 14 Oct 2013 12:29:08 +0000 (14:29 +0200)]
Win + cmake wants perl to be explicit here.. why not?

7 years agoWindows error handling some errors for you and changing them to return codes, these...
Augustin Degomme [Mon, 14 Oct 2013 11:47:02 +0000 (13:47 +0200)]
Windows error handling some errors for you and changing them to return codes, these won't work on win simply

7 years agoThis can actually be built and run in win
Augustin Degomme [Mon, 14 Oct 2013 11:44:06 +0000 (13:44 +0200)]
This can actually be built and run in win

7 years agochomp may not be enough in some cases + tell win that we want 2 digits only for exponents
Augustin Degomme [Thu, 10 Oct 2013 15:17:35 +0000 (17:17 +0200)]
chomp may not be enough in some cases + tell win that we want 2 digits only for exponents

7 years agomore windows compliancy fun
Augustin Degomme [Thu, 10 Oct 2013 14:41:42 +0000 (16:41 +0200)]
more windows compliancy fun

7 years agooops
Augustin Degomme [Thu, 10 Oct 2013 13:31:04 +0000 (15:31 +0200)]
oops

7 years agoForgotten by commit 8c9500c.
Arnaud Giersch [Thu, 10 Oct 2013 13:54:18 +0000 (15:54 +0200)]
Forgotten by commit 8c9500c.

7 years agogenerate this file at testtime, as it failed with out of source windows builds
Augustin Degomme [Thu, 10 Oct 2013 12:58:20 +0000 (14:58 +0200)]
generate this file at testtime, as it failed with out of source windows builds

7 years agoreplace signal number by its name, for better portability
Augustin Degomme [Thu, 10 Oct 2013 09:41:15 +0000 (11:41 +0200)]
replace signal number by its name, for better portability

7 years agowe wait for 255 in the tesh, so be it.
Augustin Degomme [Thu, 10 Oct 2013 09:18:10 +0000 (11:18 +0200)]
we wait for 255 in the tesh, so be it.

7 years agothis was not built on win
Augustin Degomme [Thu, 10 Oct 2013 08:56:10 +0000 (10:56 +0200)]
this was not built on win

7 years agoOnce again, Linux does not follow the real way of doing things.
Arnaud Giersch [Thu, 10 Oct 2013 12:39:30 +0000 (14:39 +0200)]
Once again, Linux does not follow the real way of doing things.

The default buffering mode for output streams seems different on
Windows (lines don't mix in the same order between stdout and stderr).
Use unbuffered mode, since line buffer mode is not supported on these
systems.

See http://msdn.microsoft.com/en-us/library/86cebhfs%28v=vs.71%29.aspx
   _IOLBF
     For some systems, this provides line buffering. However, for Win32,
     the behavior is the same as _IOFBF - Full Buffering."

Let's wait for the cdash to confirm that it works...

7 years agoat least this one works. leak--
suter [Thu, 10 Oct 2013 10:15:14 +0000 (12:15 +0200)]
at least this one works. leak--

7 years agoChasing more leaks.
Arnaud Giersch [Thu, 10 Oct 2013 10:10:52 +0000 (12:10 +0200)]
Chasing more leaks.

7 years agokill the timeout process not only for last command, but for each one
Augustin Degomme [Thu, 10 Oct 2013 08:23:52 +0000 (10:23 +0200)]
kill the timeout process not only for last command, but for each one

7 years agoLength modifier 'l' is indeed wrong in %l[efg] for printf.
Arnaud Giersch [Wed, 9 Oct 2013 20:10:33 +0000 (22:10 +0200)]
Length modifier 'l' is indeed wrong in %l[efg] for printf.

See e.g. http://c-faq.com/stdio/scanfvsprintf.html
Change it everywhere.

7 years agoturns out %le=%e and %lf=%f ... except on windows
Augustin Degomme [Wed, 9 Oct 2013 14:19:16 +0000 (16:19 +0200)]
turns out %le=%e and %lf=%f ... except on windows

7 years agoUse sg_storage_size_t in Java bindings too.
Arnaud Giersch [Wed, 9 Oct 2013 12:40:26 +0000 (14:40 +0200)]
Use sg_storage_size_t in Java bindings too.

7 years agoindent
suter [Wed, 9 Oct 2013 08:06:53 +0000 (10:06 +0200)]
indent

7 years agofree dicts
suter [Wed, 9 Oct 2013 08:06:26 +0000 (10:06 +0200)]
free dicts

7 years agomanage more cleanly the SIMIX_STORAGE_LEVEL
suter [Wed, 9 Oct 2013 07:49:07 +0000 (09:49 +0200)]
manage more cleanly the SIMIX_STORAGE_LEVEL

7 years agoRevert "Skip message if test is deactivated."
Arnaud Giersch [Wed, 9 Oct 2013 04:49:56 +0000 (06:49 +0200)]
Revert "Skip message if test is deactivated."

This reverts commit dc7b7bdc9f9d9bbb3b2a8241f762ba272779a212.

It breaks tesh test (output must not change).

7 years agoThis looks unused since 2009 (commit b036991). Remove it.
Arnaud Giersch [Tue, 8 Oct 2013 20:54:25 +0000 (22:54 +0200)]
This looks unused since 2009 (commit b036991). Remove it.

7 years agoFix error on variable name
Pierre Veyre [Tue, 8 Oct 2013 19:49:29 +0000 (21:49 +0200)]
Fix error on variable name

7 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Pierre Veyre [Tue, 8 Oct 2013 19:44:45 +0000 (21:44 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

7 years agoOups... forgot to remove this line.
Arnaud Giersch [Tue, 8 Oct 2013 19:31:37 +0000 (21:31 +0200)]
Oups... forgot to remove this line.

7 years agoAdd valgrind suppressions for the Lua interpreter.
Arnaud Giersch [Tue, 8 Oct 2013 19:23:03 +0000 (21:23 +0200)]
Add valgrind suppressions for the Lua interpreter.

7 years agoIncrease valgrind num-callers from 12 (default) to 20.
Arnaud Giersch [Tue, 8 Oct 2013 19:22:22 +0000 (21:22 +0200)]
Increase valgrind num-callers from 12 (default) to 20.

7 years agoJoin worker threads on parmap destroy.
Arnaud Giersch [Tue, 8 Oct 2013 16:12:53 +0000 (18:12 +0200)]
Join worker threads on parmap destroy.

Ensure that the allocated resources are correctly released.

7 years agoCaught another leak.
Arnaud Giersch [Tue, 8 Oct 2013 15:05:32 +0000 (17:05 +0200)]
Caught another leak.

7 years agoSkip message if test is deactivated.
Arnaud Giersch [Tue, 8 Oct 2013 14:36:35 +0000 (16:36 +0200)]
Skip message if test is deactivated.

7 years agoRemove unused fields.
Arnaud Giersch [Tue, 8 Oct 2013 13:59:34 +0000 (15:59 +0200)]
Remove unused fields.

7 years agoMake this example clean for valgrind.
Arnaud Giersch [Tue, 8 Oct 2013 13:56:03 +0000 (15:56 +0200)]
Make this example clean for valgrind.

7 years agozu to PRIu64 (again)
suter [Tue, 8 Oct 2013 13:29:15 +0000 (15:29 +0200)]
zu to PRIu64 (again)

7 years agoleak--
suter [Tue, 8 Oct 2013 13:03:49 +0000 (15:03 +0200)]
leak--

7 years agodict now contains pointers on size
suter [Tue, 8 Oct 2013 13:03:38 +0000 (15:03 +0200)]
dict now contains pointers on size

7 years agouse pointers on sg_storage_size_t in the dict instead of crappy void*
suter [Tue, 8 Oct 2013 13:03:11 +0000 (15:03 +0200)]
use pointers on sg_storage_size_t in the dict instead of crappy void*
and &size to manage contents

7 years agoFix private host variable after a migration - Adrien
alebre [Tue, 8 Oct 2013 12:50:29 +0000 (14:50 +0200)]
Fix private host variable after a migration - Adrien

7 years agomodel-checker : avoid unnecessary snapshot restore
Marion Guthmuller [Mon, 7 Oct 2013 20:38:40 +0000 (22:38 +0200)]
model-checker : avoid unnecessary snapshot restore

7 years agoArgh ... a parse error is killing me, lets clean up my mess before dying
suter [Mon, 7 Oct 2013 18:11:40 +0000 (20:11 +0200)]
Argh ... a parse error is killing me, lets clean up my mess before dying
...

Totally useless commit, unless for cdash stats

7 years agoRevert "fix windows cmake failing to detect it can actually use ucontexts"
Augustin Degomme [Mon, 7 Oct 2013 16:37:53 +0000 (18:37 +0200)]
Revert "fix windows cmake failing to detect it can actually use ucontexts"

This reverts commit f663389d95d7ac18adfc21c3478b944fefc9253a.

7 years agoUse correct type for found.
Arnaud Giersch [Mon, 7 Oct 2013 16:35:32 +0000 (18:35 +0200)]
Use correct type for found.

7 years agoRather call TRACE_end() at surf level.
Arnaud Giersch [Mon, 7 Oct 2013 15:51:13 +0000 (17:51 +0200)]
Rather call TRACE_end() at surf level.

7 years agoValue stored to 'time' is never read.
Arnaud Giersch [Mon, 7 Oct 2013 14:18:27 +0000 (16:18 +0200)]
Value stored to 'time' is never read.

7 years agoValue stored to 'bandwidth' is never read.
Arnaud Giersch [Mon, 7 Oct 2013 12:32:47 +0000 (14:32 +0200)]
Value stored to 'bandwidth' is never read.

7 years agoRemove duplicated initialization (rank).
Arnaud Giersch [Mon, 7 Oct 2013 12:31:14 +0000 (14:31 +0200)]
Remove duplicated initialization (rank).

7 years agoThere's no need to initialize p here.
Arnaud Giersch [Mon, 7 Oct 2013 12:28:46 +0000 (14:28 +0200)]
There's no need to initialize p here.

7 years agoValue is used only when MC_is_active().
Arnaud Giersch [Mon, 7 Oct 2013 12:26:41 +0000 (14:26 +0200)]
Value is used only when MC_is_active().

7 years agoValue stored to 'total_dsize' is never read.
Arnaud Giersch [Mon, 7 Oct 2013 12:24:29 +0000 (14:24 +0200)]
Value stored to 'total_dsize' is never read.

7 years agoValue stored to 'size' is never read.
Arnaud Giersch [Mon, 7 Oct 2013 12:20:18 +0000 (14:20 +0200)]
Value stored to 'size' is never read.

7 years agoVerify that request is not NULL (plus reindent).
Arnaud Giersch [Mon, 7 Oct 2013 12:10:33 +0000 (14:10 +0200)]
Verify that request is not NULL (plus reindent).

7 years agoRework test logic, and add one more case.
Arnaud Giersch [Mon, 7 Oct 2013 11:58:17 +0000 (13:58 +0200)]
Rework test logic, and add one more case.

7 years agoValue stored to 'linelen' here is never read.
Arnaud Giersch [Mon, 7 Oct 2013 09:54:25 +0000 (11:54 +0200)]
Value stored to 'linelen' here is never read.

7 years agooops
Augustin Degomme [Mon, 7 Oct 2013 16:14:25 +0000 (18:14 +0200)]
oops

7 years agofix compilation issue with windows timers
Augustin Degomme [Mon, 7 Oct 2013 15:50:36 +0000 (17:50 +0200)]
fix compilation issue with windows timers

7 years agoOn windows, try_compile may use another compiler than the one we want.
Augustin Degomme [Mon, 7 Oct 2013 14:59:36 +0000 (16:59 +0200)]
On windows, try_compile may use another compiler than the one we want.
Replace it by execute_process of the right compiler

7 years agofix windows cmake failing to detect it can actually use ucontexts
Augustin Degomme [Mon, 7 Oct 2013 14:05:00 +0000 (16:05 +0200)]
fix windows cmake failing to detect it can actually use ucontexts

7 years agofix compil error in some cases
Augustin Degomme [Mon, 7 Oct 2013 14:04:25 +0000 (16:04 +0200)]
fix compil error in some cases

7 years agoone more gloups revalidation
suter [Mon, 7 Oct 2013 14:53:14 +0000 (16:53 +0200)]
one more gloups revalidation

7 years agoGloups revalidation
suter [Mon, 7 Oct 2013 14:38:27 +0000 (16:38 +0200)]
Gloups revalidation

7 years agodestroy task when execution failed because of dead host
suter [Mon, 7 Oct 2013 14:38:06 +0000 (16:38 +0200)]
destroy task when execution failed because of dead host

7 years agoexception catching on host failure
suter [Mon, 7 Oct 2013 14:36:51 +0000 (16:36 +0200)]
exception catching on host failure

7 years agoseems that get_data can return NULL, add guards
suter [Mon, 7 Oct 2013 14:35:39 +0000 (16:35 +0200)]
seems that get_data can return NULL, add guards

7 years agoreactivate expception raising on host failure
suter [Mon, 7 Oct 2013 14:34:49 +0000 (16:34 +0200)]
reactivate expception raising on host failure