Logo AND Algorithmique Numérique Distribuée

Public GIT Repository
simgrid.git
2 years agoadapt these tests to the fact that the hosts are now multicores
Martin Quinson [Mon, 19 Jun 2017 20:10:32 +0000 (22:10 +0200)]
adapt these tests to the fact that the hosts are now multicores

2 years agoadapt the platform examples to the new energy model checks
Martin Quinson [Mon, 19 Jun 2017 20:09:38 +0000 (22:09 +0200)]
adapt the platform examples to the new energy model checks

2 years agoenergy: improve the documentation, and have a sensible assert when cores=1
Martin Quinson [Mon, 19 Jun 2017 18:41:33 +0000 (20:41 +0200)]
energy: improve the documentation, and have a sensible assert when cores=1

2 years agoRevert "platform change impacts java too"
Martin Quinson [Mon, 19 Jun 2017 14:10:40 +0000 (16:10 +0200)]
Revert "platform change impacts java too"

This reverts commit db53dd2fb0c95b25eebb7da2bccab7a4359c3441.

2 years agoRevert "[ENERGY] Assert that 1-core systems are correctly configured."
Martin Quinson [Mon, 19 Jun 2017 14:10:34 +0000 (16:10 +0200)]
Revert "[ENERGY] Assert that 1-core systems are correctly configured."

This reverts commit 7cb96467cddc465b7b0f8f819755bc9c850198c5.

2 years agoplatform change impacts java too
Frederic Suter [Mon, 19 Jun 2017 13:03:12 +0000 (15:03 +0200)]
platform change impacts java too

2 years agodict/32-bit combo from hell!
Frederic Suter [Mon, 19 Jun 2017 13:00:00 +0000 (15:00 +0200)]
dict/32-bit combo from hell!

2 years agoMerge branch 'master' of github.com:simgrid/simgrid
Martin Quinson [Mon, 19 Jun 2017 12:20:49 +0000 (14:20 +0200)]
Merge branch 'master' of github.com:simgrid/simgrid

2 years agocosmetics
Martin Quinson [Mon, 19 Jun 2017 12:20:29 +0000 (14:20 +0200)]
cosmetics

2 years agoplug a memleak
Martin Quinson [Mon, 19 Jun 2017 12:13:22 +0000 (14:13 +0200)]
plug a memleak

2 years agoMerge pull request #190 from Takishipp/clean_events
Martin Quinson [Mon, 19 Jun 2017 12:20:00 +0000 (14:20 +0200)]
Merge pull request #190 from Takishipp/clean_events

fix leak of memory caused by DefineEventTypeEvent call

2 years agobummer
Frederic Suter [Mon, 19 Jun 2017 11:44:14 +0000 (13:44 +0200)]
bummer

2 years agofix test (hate dict) and please sonar
Frederic Suter [Mon, 19 Jun 2017 11:12:19 +0000 (13:12 +0200)]
fix test (hate dict) and please sonar

2 years agofix leak of memory caused by DefineEventTypeEvent call
Takishipp [Mon, 19 Jun 2017 09:59:25 +0000 (11:59 +0200)]
fix leak of memory caused by DefineEventTypeEvent call

2 years agofix clang (try #2)
Frederic Suter [Mon, 19 Jun 2017 09:11:30 +0000 (11:11 +0200)]
fix clang (try #2)

2 years agotry to please clang
Frederic Suter [Mon, 19 Jun 2017 09:05:53 +0000 (11:05 +0200)]
try to please clang

2 years agotry to fix build by adding back some includes
Frederic Suter [Mon, 19 Jun 2017 08:40:47 +0000 (10:40 +0200)]
try to fix build by adding back some includes

2 years agomassive cleanups in the storage world.
Frederic Suter [Mon, 19 Jun 2017 08:26:18 +0000 (10:26 +0200)]
massive cleanups in the storage world.
Next step will be to improve the file management

2 years agoActivityImplPtr are not part of any C struct, only C++ classes
Martin Quinson [Mon, 19 Jun 2017 07:16:42 +0000 (09:16 +0200)]
ActivityImplPtr are not part of any C struct, only C++ classes

the refcounting fails on malloc/free. We need new/delete for that.

2 years agomove the C++ data of MSG into a namespace
Martin Quinson [Mon, 19 Jun 2017 07:01:24 +0000 (09:01 +0200)]
move the C++ data of MSG into a namespace

2 years agotypo
Martin Quinson [Mon, 19 Jun 2017 06:26:48 +0000 (08:26 +0200)]
typo

2 years agoand now, a correct implementation of this_actor::isMaestro()
Martin Quinson [Sun, 18 Jun 2017 20:42:52 +0000 (22:42 +0200)]
and now, a correct implementation of this_actor::isMaestro()

2 years agoNew: this_actor::isMaestro() returns whether we are in kernel mode
Martin Quinson [Sun, 18 Jun 2017 20:14:08 +0000 (22:14 +0200)]
New: this_actor::isMaestro() returns whether we are in kernel mode

2 years agomake it possible to run this test with any platform
Martin Quinson [Sat, 17 Jun 2017 22:27:10 +0000 (00:27 +0200)]
make it possible to run this test with any platform

2 years agoprivate headers should not be loaded from public ones
Martin Quinson [Sat, 17 Jun 2017 22:26:55 +0000 (00:26 +0200)]
private headers should not be loaded from public ones

2 years agoplease sonar a bit
Martin Quinson [Sat, 17 Jun 2017 18:57:45 +0000 (20:57 +0200)]
please sonar a bit

2 years agofix windows build
Martin Quinson [Sat, 17 Jun 2017 12:14:21 +0000 (14:14 +0200)]
fix windows build

We should change the XBT_PUBLIC(type) macro into a XBT_PUBLIC just as
XBT_PRIVATE. But that's a big change and I have other ongoing things.

2 years agochange my settings to build out of tree
Martin Quinson [Sat, 17 Jun 2017 06:49:26 +0000 (08:49 +0200)]
change my settings to build out of tree

My settings should still be useable for in-tree builds, provided that
you don't have a default/ subdirectory

2 years agoclang-format broke gcc builds, damnit
Martin Quinson [Sat, 17 Jun 2017 06:48:55 +0000 (08:48 +0200)]
clang-format broke gcc builds, damnit

2 years agomake this error message reproducible
Martin Quinson [Sat, 17 Jun 2017 00:59:24 +0000 (02:59 +0200)]
make this error message reproducible

2 years agogive the full path to the files (to ease copy/paste)
Martin Quinson [Sat, 17 Jun 2017 00:57:50 +0000 (02:57 +0200)]
give the full path to the files (to ease copy/paste)

2 years agoforgot the copyright header
Martin Quinson [Sat, 17 Jun 2017 00:41:29 +0000 (02:41 +0200)]
forgot the copyright header

2 years agokill all horizontal tabs
Martin Quinson [Sat, 17 Jun 2017 00:39:01 +0000 (02:39 +0200)]
kill all horizontal tabs

2 years agoMerge pull request #188 from Takishipp/clean_events
Martin Quinson [Sat, 17 Jun 2017 00:34:54 +0000 (02:34 +0200)]
Merge pull request #188 from Takishipp/clean_events

Remove the events that have the below criteria

2 years agore-activate the liveness tests: they are not melting cores anymore
Martin Quinson [Sat, 17 Jun 2017 00:23:22 +0000 (02:23 +0200)]
re-activate the liveness tests: they are not melting cores anymore

2 years agogcc dont' like zero-length fmt strings
Martin Quinson [Sat, 17 Jun 2017 00:20:21 +0000 (02:20 +0200)]
gcc dont' like zero-length fmt strings

2 years agofix gcc builds: missing prototype
Martin Quinson [Sat, 17 Jun 2017 00:09:02 +0000 (02:09 +0200)]
fix gcc builds: missing prototype

2 years agocosmetics
Martin Quinson [Sat, 17 Jun 2017 00:04:15 +0000 (02:04 +0200)]
cosmetics

2 years agokill a useless platform file
Martin Quinson [Fri, 16 Jun 2017 23:30:16 +0000 (01:30 +0200)]
kill a useless platform file

2 years agocosmetics around the cloud-sharing test
Martin Quinson [Fri, 16 Jun 2017 23:28:59 +0000 (01:28 +0200)]
cosmetics around the cloud-sharing test

2 years agonew platform file, serving as a documentation to clusters
Martin Quinson [Fri, 16 Jun 2017 23:13:52 +0000 (01:13 +0200)]
new platform file, serving as a documentation to clusters

2 years agoswitch the platform used by these examples
Martin Quinson [Fri, 16 Jun 2017 23:03:55 +0000 (01:03 +0200)]
switch the platform used by these examples

I will rework the two_clusters.xml platform file

2 years agogreatly improve an error message
Martin Quinson [Fri, 16 Jun 2017 22:48:52 +0000 (00:48 +0200)]
greatly improve an error message

2 years agoacknowledge that #120 can be seen here
Martin Quinson [Fri, 16 Jun 2017 21:39:18 +0000 (23:39 +0200)]
acknowledge that #120 can be seen here

we will fix it at some point, but not today...

2 years agoimprove an error message
Martin Quinson [Fri, 16 Jun 2017 21:22:50 +0000 (23:22 +0200)]
improve an error message

2 years agoThis test was broken because a bug was solved :)
Martin Quinson [Fri, 16 Jun 2017 20:43:13 +0000 (22:43 +0200)]
This test was broken because a bug was solved :)

2 years agofix most of the MC tests. Liveness and CommPattern remain broken
Martin Quinson [Fri, 16 Jun 2017 16:03:20 +0000 (18:03 +0200)]
fix most of the MC tests. Liveness and CommPattern remain broken

2 years ago[ENERGY] Add API call for querying current consumption
Christian Heinrich [Fri, 16 Jun 2017 11:52:18 +0000 (13:52 +0200)]
[ENERGY] Add API call for querying current consumption

2 years ago[ENERGY] Assert that 1-core systems are correctly configured.
Christian Heinrich [Fri, 16 Jun 2017 09:30:46 +0000 (11:30 +0200)]
[ENERGY] Assert that 1-core systems are correctly configured.

The values for 1-core and max-core load must be the same. If not, the
assert() will fail and the user will be warned.

2 years agoRevert "[ENERGY] Fixed wrong calculation for 1-core systems"
Christian Heinrich [Fri, 16 Jun 2017 08:14:27 +0000 (10:14 +0200)]
Revert "[ENERGY] Fixed wrong calculation for 1-core systems"

This reverts commit e96681fb89b328389ad0d4aecfe7addbda714da4.

We decided to add an assert() instead, as the error was not really
in the energy plugin but in the user-supplied platform.

2 years agoRemove a debug message, sorry
Martin Quinson [Fri, 16 Jun 2017 06:31:33 +0000 (08:31 +0200)]
Remove a debug message, sorry

2 years agocommit some harmless changes
Frederic Suter [Thu, 15 Jun 2017 16:51:27 +0000 (18:51 +0200)]
commit some harmless changes

2 years agoMerge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid
Martin Quinson [Thu, 15 Jun 2017 15:37:29 +0000 (17:37 +0200)]
Merge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid

2 years agomake this test easier to maintain and work with
Martin Quinson [Thu, 15 Jun 2017 15:37:11 +0000 (17:37 +0200)]
make this test easier to maintain and work with

2 years agotry to fix the impact of a big full VM on its PM
Martin Quinson [Thu, 15 Jun 2017 15:36:21 +0000 (17:36 +0200)]
try to fix the impact of a big full VM on its PM

2 years agoLMM: add a function to see how many variables are active on a constraint
Martin Quinson [Thu, 15 Jun 2017 15:30:59 +0000 (17:30 +0200)]
LMM: add a function to see how many variables are active on a constraint

2 years ago[ENERGY] Fixed wrong calculation for 1-core systems
Christian Heinrich [Thu, 15 Jun 2017 13:54:53 +0000 (15:54 +0200)]
[ENERGY] Fixed wrong calculation for 1-core systems

2 years agoFixed spelling: zoneZoute -> zoneRoute
Christian Heinrich [Mon, 29 May 2017 09:14:25 +0000 (11:14 +0200)]
Fixed spelling: zoneZoute -> zoneRoute

2 years agoMerge pull request #181 from bcamus/master
Martin Quinson [Thu, 15 Jun 2017 08:43:11 +0000 (10:43 +0200)]
Merge pull request #181 from bcamus/master

Add tests for multi-core VM

2 years agofix the linkage declaration of a function
Martin Quinson [Thu, 15 Jun 2017 05:42:42 +0000 (07:42 +0200)]
fix the linkage declaration of a function

2 years agofix clang build
Martin Quinson [Thu, 15 Jun 2017 01:58:51 +0000 (03:58 +0200)]
fix clang build

2 years agoDon't use the C linkage when we use C++ datatypes
Martin Quinson [Thu, 15 Jun 2017 01:36:57 +0000 (03:36 +0200)]
Don't use the C linkage when we use C++ datatypes

2 years agoMerge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid
Martin Quinson [Thu, 15 Jun 2017 01:14:16 +0000 (03:14 +0200)]
Merge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid

2 years agocorrectly use clumsy xbt_dynar interface
Martin Quinson [Thu, 15 Jun 2017 01:13:35 +0000 (03:13 +0200)]
correctly use clumsy xbt_dynar interface

How can I be so stupid?

2 years agowe manipulate CommPtr and not Comm* nowadays
Martin Quinson [Thu, 15 Jun 2017 00:42:54 +0000 (02:42 +0200)]
we manipulate CommPtr and not Comm* nowadays

don't trust the automatic conversions

2 years agoNow this test may pass
Martin Quinson [Thu, 15 Jun 2017 00:41:07 +0000 (02:41 +0200)]
Now this test may pass

2 years agothese static casts are useless
Martin Quinson [Thu, 15 Jun 2017 00:31:21 +0000 (02:31 +0200)]
these static casts are useless

2 years agoMerge branch 'ActivityPtr' of github.com:simgrid/simgrid into ActivityPtr
Martin Quinson [Wed, 14 Jun 2017 21:46:30 +0000 (23:46 +0200)]
Merge branch 'ActivityPtr' of github.com:simgrid/simgrid into ActivityPtr

2 years agosimplify this test for the ongoing debugging
Martin Quinson [Wed, 14 Jun 2017 21:31:21 +0000 (23:31 +0200)]
simplify this test for the ongoing debugging

2 years agoFox broken CMakeLists.txt
Gabriel Corona [Wed, 14 Jun 2017 21:07:27 +0000 (23:07 +0200)]
Fox broken CMakeLists.txt

2 years agosimple test on waitany
Martin Quinson [Wed, 14 Jun 2017 20:44:14 +0000 (22:44 +0200)]
simple test on waitany

This is the MWE of #170. Thanks, Henri.

2 years agobummer
Martin Quinson [Wed, 14 Jun 2017 20:08:42 +0000 (22:08 +0200)]
bummer

2 years agotry to get the refcounting right on waitany simcalls
Martin Quinson [Wed, 14 Jun 2017 19:35:03 +0000 (21:35 +0200)]
try to get the refcounting right on waitany simcalls

2 years agoMerge branch 'clean_events' of github.com:Takishipp/simgrid into clean_events
Takishipp [Wed, 14 Jun 2017 07:40:20 +0000 (09:40 +0200)]
Merge branch 'clean_events' of github.com:Takishipp/simgrid into clean_events

2 years agoremove useless XBT_DEBUG
Takishipp [Wed, 14 Jun 2017 07:38:52 +0000 (09:38 +0200)]
remove useless XBT_DEBUG

2 years agoMC doesn'y like some of the explicit
Frederic Suter [Wed, 14 Jun 2017 07:33:18 +0000 (09:33 +0200)]
MC doesn'y like some of the explicit

2 years agofix the actor name; improve doc
Martin Quinson [Wed, 14 Jun 2017 07:30:53 +0000 (09:30 +0200)]
fix the actor name; improve doc

2 years agoMerge branch 'master' into clean_events
Toufik Boubehziz [Wed, 14 Jun 2017 07:17:16 +0000 (09:17 +0200)]
Merge branch 'master' into clean_events

2 years agoplease both sonar and codacy
Frederic Suter [Wed, 14 Jun 2017 06:57:05 +0000 (08:57 +0200)]
please both sonar and codacy

2 years agoeradicate all remaining manual refcounting on ActivityImpl
Martin Quinson [Thu, 8 Jun 2017 05:08:24 +0000 (07:08 +0200)]
eradicate all remaining manual refcounting on ActivityImpl

2 years agorefcount should be automatic now, and initialized to 0
Martin Quinson [Thu, 8 Jun 2017 04:56:24 +0000 (06:56 +0200)]
refcount should be automatic now, and initialized to 0

2 years agoAH! there was a remaining manual refcount stain
Martin Quinson [Thu, 8 Jun 2017 00:22:52 +0000 (02:22 +0200)]
AH! there was a remaining manual refcount stain

2 years agocosmetics (+ sleep at the end of test to avoid problems)
Martin Quinson [Thu, 8 Jun 2017 00:06:54 +0000 (02:06 +0200)]
cosmetics (+ sleep at the end of test to avoid problems)

2 years agoimprove the debug messages of smx_network
Martin Quinson [Thu, 8 Jun 2017 00:00:38 +0000 (02:00 +0200)]
improve the debug messages of smx_network

2 years agoCorrectly deal with simcall returning a intrusive_ptr of nullptr
Martin Quinson [Wed, 7 Jun 2017 23:59:46 +0000 (01:59 +0200)]
Correctly deal with simcall returning a intrusive_ptr of nullptr

2 years agoMake sure that the user don't try a detached receive
Martin Quinson [Wed, 7 Jun 2017 23:54:44 +0000 (01:54 +0200)]
Make sure that the user don't try a detached receive

2 years agocorrect refcounting of ActorPtr
Martin Quinson [Wed, 7 Jun 2017 23:54:16 +0000 (01:54 +0200)]
correct refcounting of ActorPtr

2 years agoAdd an exhaustive test for point to point communications
Martin Quinson [Wed, 7 Jun 2017 22:29:34 +0000 (00:29 +0200)]
Add an exhaustive test for point to point communications

2 years agofurther WIP on the ActivityImplPtr feature. Now it compiles (but fails)
Martin Quinson [Wed, 7 Jun 2017 09:17:05 +0000 (11:17 +0200)]
further WIP on the ActivityImplPtr feature. Now it compiles (but fails)

ActivityImplPtr are all over the place, and the manual refcounting is
dead. Most tests still fail, for some reason that I don't understand
yet. That's a WIP...

Notable point:
MC wants to retrieve the pointers to the ActivityImpl in a remote
process, even if their type is ActivityImplPtr (that is,
intrusive_ptr<ActivityImpl>).

The good thing is that in this case, the raw pointer is stored in the
simcall parameters, and the *Ptr type is reconstructed by the marshal
function.

So I just have to generate the <simcall>__getraw__<param/res>()
functions that return the raw pointer without building a *Ptr type. It
compiles, but the MC is broken ATM so maybe it's not sufficient.

I'm committing anyway because I want to add simpler tests for the
communications that would make the debug of this feature easier to
achieve.

2 years agoDeclare and use ActorImplPtr
Martin Quinson [Wed, 7 Jun 2017 09:13:26 +0000 (11:13 +0200)]
Declare and use ActorImplPtr

2 years agoReduce the displayed backtrace
Martin Quinson [Wed, 7 Jun 2017 07:20:13 +0000 (09:20 +0200)]
Reduce the displayed backtrace

2 years agofirst attempt (ongoing WIP)
Martin Quinson [Tue, 6 Jun 2017 06:16:34 +0000 (08:16 +0200)]
first attempt (ongoing WIP)

2 years agokill all trailling whitespaces
Martin Quinson [Tue, 13 Jun 2017 20:15:05 +0000 (22:15 +0200)]
kill all trailling whitespaces

This commit could have been called "VI VI VI, the editor of the beast"
:)

2 years agoplease codacy
Martin Quinson [Tue, 13 Jun 2017 20:06:10 +0000 (22:06 +0200)]
please codacy

2 years agoplease vera++: don't pass vectors by copy
Martin Quinson [Tue, 13 Jun 2017 19:58:34 +0000 (21:58 +0200)]
please vera++: don't pass vectors by copy

2 years agoUpdate changelog for SMPI before release, this time.
degomme [Tue, 13 Jun 2017 16:24:35 +0000 (18:24 +0200)]
Update changelog for SMPI before release, this time.

2 years agoplease sonar, damnit
Martin Quinson [Tue, 13 Jun 2017 16:03:57 +0000 (18:03 +0200)]
please sonar, damnit

2 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Frederic Suter [Tue, 13 Jun 2017 15:50:54 +0000 (17:50 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

2 years agoplug leak
Frederic Suter [Tue, 13 Jun 2017 15:50:44 +0000 (17:50 +0200)]
plug leak

2 years agoEnergy: New function to update the consumption of all hosts at once
Martin Quinson [Tue, 13 Jun 2017 15:20:49 +0000 (17:20 +0200)]
Energy: New function to update the consumption of all hosts at once