Logo AND Algorithmique Numérique Distribuée

Public GIT Repository
simgrid.git
7 years agoreduce the visibility of some functions
Martin Quinson [Wed, 16 Nov 2016 01:12:36 +0000 (02:12 +0100)]
reduce the visibility of some functions

7 years agoreduce the visibility of one field
Martin Quinson [Wed, 16 Nov 2016 01:01:35 +0000 (02:01 +0100)]
reduce the visibility of one field

7 years agoremove another now useless function from RoutingPlat
Martin Quinson [Wed, 16 Nov 2016 00:54:20 +0000 (01:54 +0100)]
remove another now useless function from RoutingPlat

7 years agoI switched to NS 3.26 locally
Martin Quinson [Wed, 16 Nov 2016 00:53:21 +0000 (01:53 +0100)]
I switched to NS 3.26 locally

7 years agocode simplification: write the recursivity properly
Martin Quinson [Wed, 16 Nov 2016 00:40:07 +0000 (01:40 +0100)]
code simplification: write the recursivity properly

7 years agounXBTize a bit
Martin Quinson [Wed, 16 Nov 2016 00:19:55 +0000 (01:19 +0100)]
unXBTize a bit

7 years agocosmetics
Martin Quinson [Tue, 15 Nov 2016 23:38:36 +0000 (00:38 +0100)]
cosmetics

7 years agolet's do standard C++ here
Martin Quinson [Tue, 15 Nov 2016 23:16:23 +0000 (00:16 +0100)]
let's do standard C++ here

7 years agocosmetics
Martin Quinson [Tue, 15 Nov 2016 23:05:48 +0000 (00:05 +0100)]
cosmetics

7 years agoreduce the amount of dynars created by getOneLinkRoutes()
Martin Quinson [Tue, 15 Nov 2016 23:02:38 +0000 (00:02 +0100)]
reduce the amount of dynars created by getOneLinkRoutes()

7 years agoless void*
Martin Quinson [Tue, 15 Nov 2016 22:54:10 +0000 (23:54 +0100)]
less void*

7 years agokill a now useless function
Martin Quinson [Tue, 15 Nov 2016 22:41:10 +0000 (23:41 +0100)]
kill a now useless function

7 years agoMerge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid
Martin Quinson [Tue, 15 Nov 2016 22:35:26 +0000 (23:35 +0100)]
Merge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid

7 years agoempty RoutingPlatf: move the loopback link to the network_model(s)
Martin Quinson [Tue, 15 Nov 2016 22:35:16 +0000 (23:35 +0100)]
empty RoutingPlatf: move the loopback link to the network_model(s)

7 years agoAdd a smpi/grow-injected-times option.
degomme [Mon, 14 Nov 2016 23:04:53 +0000 (16:04 -0700)]
Add a smpi/grow-injected-times option.
This is to allow triggering off the default behavior of injected timings growth in MPI_Iprobe and MPI_Test.
This behavior allows to simulate faster and avoid looping too much over these calls. But it could also hurt precision of the simulation.

7 years agosome more tiny optims for the smpirun generation
degomme [Mon, 14 Nov 2016 03:18:23 +0000 (20:18 -0700)]
some more tiny optims for the smpirun generation

7 years agoAdd a hint about a non trivial error.
degomme [Sun, 13 Nov 2016 22:35:54 +0000 (15:35 -0700)]
Add a hint about a non trivial error.
mmap reports no memory left, while the error is actually the number of allowed mappings per process.

7 years agocosmetics
Arnaud Legrand [Mon, 22 Aug 2016 22:54:48 +0000 (00:54 +0200)]
cosmetics

7 years agoget rid of most of the awfully slow cut commands in smpirun.
degomme [Sun, 13 Nov 2016 19:11:19 +0000 (12:11 -0700)]
get rid of most of the awfully slow cut commands in smpirun.

Those for smpi_replay are still here, though, as the set solution only works one list at a time.
Let's hope this works everywhere.

7 years agoless strdup/free
Martin Quinson [Sun, 13 Nov 2016 15:18:20 +0000 (16:18 +0100)]
less strdup/free

7 years agoalso take future releases of NS3
Martin Quinson [Sun, 13 Nov 2016 15:13:40 +0000 (16:13 +0100)]
also take future releases of NS3

7 years agoreindent, no change
Martin Quinson [Sun, 13 Nov 2016 14:27:50 +0000 (15:27 +0100)]
reindent, no change

7 years agothe property holder does not take a dict in its constructor
Martin Quinson [Sun, 13 Nov 2016 11:17:46 +0000 (12:17 +0100)]
the property holder does not take a dict in its constructor

7 years agodon't give the properties to the Link constructor either
Martin Quinson [Sun, 13 Nov 2016 10:54:57 +0000 (11:54 +0100)]
don't give the properties to the Link constructor either

7 years agodon't pass property set to the storage constructor, there is no need
Martin Quinson [Sun, 13 Nov 2016 10:42:28 +0000 (11:42 +0100)]
don't pass property set to the storage constructor, there is no need

7 years agoMove some content out of HostImpl (into VirtualMachineImpl)
Martin Quinson [Sat, 12 Nov 2016 20:28:02 +0000 (21:28 +0100)]
Move some content out of HostImpl (into VirtualMachineImpl)

7 years agothe AS can now create hosts.
Martin Quinson [Sat, 12 Nov 2016 18:15:31 +0000 (19:15 +0100)]
the AS can now create hosts.

7 years agouseless cosmetics around the host creation
Martin Quinson [Sat, 12 Nov 2016 18:09:16 +0000 (19:09 +0100)]
useless cosmetics around the host creation

7 years agodocument my last changes
Martin Quinson [Sat, 12 Nov 2016 17:51:45 +0000 (18:51 +0100)]
document my last changes

7 years agocode simplification: we don't use non-LMM resources
Martin Quinson [Sat, 12 Nov 2016 00:50:17 +0000 (01:50 +0100)]
code simplification: we don't use non-LMM resources

there was a specific constructor for non-LMM resources that was not
given the lmm constraint, which leaded to many dupplicated code.

But actually, this is not needed: NetworkConstant does not create a
link resource anyway, and NS3 can easily pass nullptr to the
constructor of its ancestor.

7 years agoless useless new and explicit mallocs
Martin Quinson [Sat, 12 Nov 2016 00:28:31 +0000 (01:28 +0100)]
less useless new and explicit mallocs

7 years agoNew function: MSG_parallel_task_execute_with_timeout
Martin Quinson [Fri, 11 Nov 2016 23:15:16 +0000 (00:15 +0100)]
New function: MSG_parallel_task_execute_with_timeout

This is the fist time that executions can finish with a timeout, and
I'm not really proud of the resulting code. Sorry, that's just a quick
(fix #115) while I was fixing the platform generation.

At some point the whole activity thingy should be reworked, too.

7 years agoMake a proper extension out of the Vivaldi coordinates
Martin Quinson [Tue, 8 Nov 2016 14:38:58 +0000 (15:38 +0100)]
Make a proper extension out of the Vivaldi coordinates

7 years agosmall cleanups in Java advised by eclipse
Martin Quinson [Tue, 8 Nov 2016 14:35:23 +0000 (15:35 +0100)]
small cleanups in Java advised by eclipse

7 years agonormalize a bit the inst callbacks
Martin Quinson [Mon, 7 Nov 2016 21:38:58 +0000 (22:38 +0100)]
normalize a bit the inst callbacks

7 years agoSpell check, again O:-)
Martin Quinson [Sun, 6 Nov 2016 22:27:28 +0000 (23:27 +0100)]
Spell check, again O:-)

7 years agothis file is not used, actually
Martin Quinson [Sat, 5 Nov 2016 12:27:28 +0000 (13:27 +0100)]
this file is not used, actually

7 years agoSet missing cmake variables to 0
degomme [Mon, 7 Nov 2016 13:47:25 +0000 (14:47 +0100)]
Set missing cmake variables to 0

7 years agoBump mmorecore buffer size to 256 bytes on FreeBSD
Matthieu Volat [Mon, 7 Nov 2016 13:21:42 +0000 (14:21 +0100)]
Bump mmorecore buffer size to 256 bytes on FreeBSD

It seems to need more memory than Linux.

7 years agoWhen mmap-ing, ensute that offset is set to 0 if anon mmap
Matthieu Volat [Mon, 7 Nov 2016 13:17:15 +0000 (14:17 +0100)]
When mmap-ing, ensute that offset is set to 0 if anon mmap

Linux tolerate non-zero offset parameter (and ignore it),
but others do not.

7 years agoCheck for a dlfunc() function to get handle if present
Matthieu Volat [Mon, 7 Nov 2016 11:25:21 +0000 (12:25 +0100)]
Check for a dlfunc() function to get handle if present

dlfunc() is a (for now) FreeBSD-only function that is to be used when
trying to retrieve function handles from code segments, rather
than dlsym(), but let's make the code generic in case somebody else
likes the idea...

7 years agoAllow to use BSD ptrace().
Matthieu Volat [Sun, 6 Nov 2016 15:36:46 +0000 (16:36 +0100)]
Allow to use BSD ptrace().

7 years agoBuild ID are somewhat gnu/linux specific.
Matthieu Volat [Sat, 5 Nov 2016 14:22:59 +0000 (15:22 +0100)]
Build ID are somewhat gnu/linux specific.

7 years agofix the handling of bypassASroutes
Martin Quinson [Fri, 4 Nov 2016 15:05:59 +0000 (16:05 +0100)]
fix the handling of bypassASroutes

Fred used to think he needs it for his work, so here is the fix. It
was wrong anyway.

Now that it works, we should make the code better (too much redundency
for now) at some point.

7 years agotesh: report the command line in messages, not the currently parsed line
Martin Quinson [Fri, 4 Nov 2016 11:35:34 +0000 (12:35 +0100)]
tesh: report the command line in messages, not the currently parsed line

This consistency is much more convenient for the user.

7 years agodon't sort the output of the flatifier, it makes debugging much harder
Martin Quinson [Fri, 4 Nov 2016 11:34:52 +0000 (12:34 +0100)]
don't sort the output of the flatifier, it makes debugging much harder

7 years agoclang complains about these seemingly unecessary std::move.
degomme [Fri, 4 Nov 2016 13:55:59 +0000 (14:55 +0100)]
clang complains about these seemingly unecessary std::move.

7 years agoMake simgrid::mc::HeapLocation instanciation C++11 compliant
Matthieu Volat [Fri, 4 Nov 2016 10:18:55 +0000 (11:18 +0100)]
Make simgrid::mc::HeapLocation instanciation C++11 compliant

simgrid::mc::HeapLocation is a typedef of std:array which require use
of double brace to declare subobjects.

7 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr/gitroot/simgrid/simgrid
degomme [Fri, 4 Nov 2016 11:28:56 +0000 (12:28 +0100)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr/gitroot/simgrid/simgrid

7 years agofix NS3
Martin Quinson [Fri, 4 Nov 2016 09:39:06 +0000 (10:39 +0100)]
fix NS3

7 years agounPERLifies a bit the routing: use the object, not its name
Martin Quinson [Thu, 3 Nov 2016 21:49:17 +0000 (22:49 +0100)]
unPERLifies a bit the routing: use the object, not its name

7 years agoless char*, more std::string
Martin Quinson [Thu, 3 Nov 2016 21:34:56 +0000 (22:34 +0100)]
less char*, more std::string

7 years agoreplace multiples allocs by one.
degomme [Thu, 3 Nov 2016 14:09:33 +0000 (15:09 +0100)]
replace multiples allocs by one.

7 years agoSMPI tracing : match links with sender/receiver + tag, as in MPI, as messages could...
degomme [Thu, 3 Nov 2016 11:01:15 +0000 (12:01 +0100)]
SMPI tracing : match links with sender/receiver + tag, as in MPI, as messages could be mixed up

7 years agooops
degomme [Wed, 2 Nov 2016 15:07:56 +0000 (16:07 +0100)]
oops

7 years agoThe sed version used on macos doesn't like the I flag..
degomme [Wed, 2 Nov 2016 14:38:53 +0000 (15:38 +0100)]
The sed version used on macos doesn't like the I flag..
So let's turn normal ugly regexpes into plainly awful ones.

7 years agoUse the libunwind from apple directly
degomme [Wed, 2 Nov 2016 14:31:09 +0000 (15:31 +0100)]
Use the libunwind from apple directly

7 years agoRevert "Fix MC builds after my fix for Mac OSX around libunwind :-("
degomme [Wed, 2 Nov 2016 13:40:00 +0000 (14:40 +0100)]
Revert "Fix MC builds after my fix for Mac OSX around libunwind :-("

This reverts commit 182a4405d85c87f52db5fcd8eaf8b04d3b27a3c8.

7 years agoRevert "cmake: better log message to get more useful information"
degomme [Wed, 2 Nov 2016 13:39:37 +0000 (14:39 +0100)]
Revert "cmake: better log message to get more useful information"

This reverts commit 438bc4767b28f0113c8f64d9d46ed4417988b6f7.

7 years agoRevert "fix MC on 32bits about libunwind"
degomme [Wed, 2 Nov 2016 13:39:34 +0000 (14:39 +0100)]
Revert "fix MC on 32bits about libunwind"

This reverts commit b1369e636e06e5ea1547c38b554fcb17ad7ca81a.

7 years agoRevert "libunwind 32bits: don't search the lib in itself but in its directory"
degomme [Wed, 2 Nov 2016 13:39:31 +0000 (14:39 +0100)]
Revert "libunwind 32bits: don't search the lib in itself but in its directory"

This reverts commit 103a2ff1188a796989e4ce99fec49f5744194b23.

7 years agolibunwind 32bits: don't search the lib in itself but in its directory
Martin Quinson [Tue, 1 Nov 2016 21:10:45 +0000 (22:10 +0100)]
libunwind 32bits: don't search the lib in itself but in its directory

7 years agofix MC on 32bits about libunwind
Martin Quinson [Tue, 1 Nov 2016 20:55:56 +0000 (21:55 +0100)]
fix MC on 32bits about libunwind

7 years agocmake: better log message to get more useful information
Martin Quinson [Tue, 1 Nov 2016 20:19:11 +0000 (21:19 +0100)]
cmake: better log message to get more useful information

7 years agoFix MC builds after my fix for Mac OSX around libunwind :-(
Martin Quinson [Tue, 1 Nov 2016 20:09:44 +0000 (21:09 +0100)]
Fix MC builds after my fix for Mac OSX around libunwind :-(

7 years agouse std:: instead of fixed size vectors. C is over.
Martin Quinson [Tue, 1 Nov 2016 19:48:26 +0000 (20:48 +0100)]
use std:: instead of fixed size vectors. C is over.

7 years agoanother try to fix mac OSX (libunwind is not the one we think there)
Martin Quinson [Tue, 1 Nov 2016 19:38:55 +0000 (20:38 +0100)]
another try to fix mac OSX (libunwind is not the one we think there)

7 years agoMerge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid
Martin Quinson [Tue, 1 Nov 2016 18:27:12 +0000 (19:27 +0100)]
Merge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid

7 years agorouting: cosmetics and doc improvement
Martin Quinson [Tue, 1 Nov 2016 18:13:36 +0000 (19:13 +0100)]
routing: cosmetics and doc improvement

7 years agoimprove the doc of the routing API
Martin Quinson [Tue, 1 Nov 2016 14:49:40 +0000 (15:49 +0100)]
improve the doc of the routing API

7 years agocosmetics in bypass routing
Martin Quinson [Tue, 1 Nov 2016 14:28:08 +0000 (15:28 +0100)]
cosmetics in bypass routing

7 years agocosmetics
Martin Quinson [Tue, 1 Nov 2016 14:05:59 +0000 (15:05 +0100)]
cosmetics

7 years agoUse BYTE_ORDER macro, not private __BYTE_ORDER
Matthieu Volat [Tue, 1 Nov 2016 07:43:22 +0000 (08:43 +0100)]
Use BYTE_ORDER macro, not private __BYTE_ORDER

7 years agoMADV_MERGEABLE is available on linux, guard it.
Matthieu Volat [Tue, 1 Nov 2016 07:24:14 +0000 (08:24 +0100)]
MADV_MERGEABLE is available on linux, guard it.

7 years agoUse MAP_PREFAULT_READ on FreeBSD as en equivalent to MAP_POPULATE.
Matthieu Volat [Mon, 31 Oct 2016 18:03:55 +0000 (19:03 +0100)]
Use MAP_PREFAULT_READ on FreeBSD as en equivalent to MAP_POPULATE.

7 years agoAdd -Wno-extern-c-compat when building with clang
Matthieu Volat [Mon, 31 Oct 2016 16:49:45 +0000 (17:49 +0100)]
Add -Wno-extern-c-compat when building with clang

Else it triggers an warning due to libunwind.h using empty C structures that
are turned into an error by -Werror.

7 years agoadd suppressions from libunwind.
degomme [Tue, 1 Nov 2016 13:32:22 +0000 (14:32 +0100)]
add suppressions from libunwind.
https://github.com/JuliaLang/julia/issues/4533 reports the same errors we have on ci as libunwind's.
I have some more locally which are more annoying, though.

7 years agoapparently, this should be in this order
degomme [Tue, 1 Nov 2016 08:28:35 +0000 (09:28 +0100)]
apparently, this should be in this order

7 years agofix graphviz tests after the host order change in sg_host_list
Martin Quinson [Tue, 1 Nov 2016 00:01:39 +0000 (01:01 +0100)]
fix graphviz tests after the host order change in sg_host_list

7 years agocmake: better error message
Martin Quinson [Mon, 31 Oct 2016 23:53:11 +0000 (00:53 +0100)]
cmake: better error message

7 years agocosmetics
Martin Quinson [Mon, 31 Oct 2016 23:50:01 +0000 (00:50 +0100)]
cosmetics

7 years agoanother try to fix Mac: don't guess the unwind component names so widely
Martin Quinson [Mon, 31 Oct 2016 23:45:22 +0000 (00:45 +0100)]
another try to fix Mac: don't guess the unwind component names so widely

7 years agotry to fix the windows build (+clang-format)
Martin Quinson [Mon, 31 Oct 2016 23:30:25 +0000 (00:30 +0100)]
try to fix the windows build (+clang-format)

7 years agofix mac build (another try)
Martin Quinson [Mon, 31 Oct 2016 23:20:03 +0000 (00:20 +0100)]
fix mac build (another try)

7 years agowoops, this code was not unused
Martin Quinson [Mon, 31 Oct 2016 23:11:26 +0000 (00:11 +0100)]
woops, this code was not unused

I must have mis-grepped :(

7 years agocosmetics
Martin Quinson [Mon, 31 Oct 2016 23:02:01 +0000 (00:02 +0100)]
cosmetics

7 years agokill an unused chunk of CMakeLists.txt
Martin Quinson [Mon, 31 Oct 2016 22:47:15 +0000 (23:47 +0100)]
kill an unused chunk of CMakeLists.txt

7 years agofix Mac OSX build
Martin Quinson [Mon, 31 Oct 2016 22:43:29 +0000 (23:43 +0100)]
fix Mac OSX build

7 years agothis is definitely a backtrace function
Martin Quinson [Mon, 31 Oct 2016 22:31:32 +0000 (23:31 +0100)]
this is definitely a backtrace function

7 years agokill empty functions
Martin Quinson [Mon, 31 Oct 2016 22:18:44 +0000 (23:18 +0100)]
kill empty functions

7 years agoMerge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid
Martin Quinson [Mon, 31 Oct 2016 22:08:42 +0000 (23:08 +0100)]
Merge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid

7 years agotest for libunwind even if not building MC
Martin Quinson [Mon, 31 Oct 2016 22:05:51 +0000 (23:05 +0100)]
test for libunwind even if not building MC

7 years agoplug a memleak
Martin Quinson [Mon, 31 Oct 2016 21:21:55 +0000 (22:21 +0100)]
plug a memleak

7 years agoAdd a FreeBSD backend for get_memory_map(), allow to enable smpi privatization.
degomme [Mon, 31 Oct 2016 13:39:09 +0000 (14:39 +0100)]
Add a FreeBSD backend for get_memory_map(), allow to enable smpi privatization.
Thanks to M. Volat !

7 years agoRework how model checking and mmap get enabled/disabled
degomme [Mon, 31 Oct 2016 13:35:33 +0000 (14:35 +0100)]
Rework how model checking and mmap get enabled/disabled

Simplify test: model checking relies on linux-only syscalls such as signalfd,
mremap, so it won't work on anything else.

But do not set HAVE_MMAP to 0 if MC cannot be built, other parts could use it
Courtesy of M. Volat

7 years agoTest for mremap function and store result in internal_config.h.
degomme [Mon, 31 Oct 2016 13:34:00 +0000 (14:34 +0100)]
Test for mremap function and store result in internal_config.h.
From M. Volat

7 years agoSetup and use a LD_LIBRARY variable in build.
degomme [Mon, 31 Oct 2016 13:33:02 +0000 (14:33 +0100)]
Setup and use a LD_LIBRARY variable in build.
libdl is linux-only, so set this variable as the result of a find_library
command here and let it empty on other systems. From M. Volat.

7 years agoFrom M. Volat : more portable way of opening shm buffers for privatization
degomme [Mon, 31 Oct 2016 09:18:20 +0000 (10:18 +0100)]
From M. Volat : more portable way of opening shm buffers for privatization

7 years agohandle MPI_IN_PLACE for this collective
degomme [Mon, 31 Oct 2016 08:31:20 +0000 (09:31 +0100)]
handle MPI_IN_PLACE for this collective

7 years agoa platform to test the AS bypass feature
Martin Quinson [Sun, 30 Oct 2016 15:55:47 +0000 (16:55 +0100)]
a platform to test the AS bypass feature