Arnaud Giersch [Wed, 1 Jul 2020 20:52:16 +0000 (22:52 +0200)]
[sonar] Add const qualifier for reference parameter.
Arnaud Giersch [Wed, 1 Jul 2020 20:33:07 +0000 (22:33 +0200)]
[sonar] Declare function "noreturn".
Arnaud Giersch [Wed, 1 Jul 2020 20:27:56 +0000 (22:27 +0200)]
[sonar] USe a typedef for type alias.
Arnaud Giersch [Wed, 1 Jul 2020 14:41:22 +0000 (16:41 +0200)]
[sonar] Remove redundant casts.
Arnaud Giersch [Wed, 1 Jul 2020 14:28:45 +0000 (16:28 +0200)]
Ignore sonar issues about concatenatable namespaces.
Arnaud Giersch [Fri, 12 Jun 2020 15:24:26 +0000 (17:24 +0200)]
Kill unused ctor.
Augustin Degomme [Thu, 25 Jun 2020 14:47:30 +0000 (16:47 +0200)]
Merge branch 'smpi' into 'master'
Typo in SMPI gather algorithm
See merge request simgrid/simgrid!37
Julien EMMANUEL [Thu, 25 Jun 2020 13:39:03 +0000 (15:39 +0200)]
Typo in SMPI gather algorithm (comment)
Martin Quinson [Sat, 13 Jun 2020 12:55:31 +0000 (14:55 +0200)]
fix some long -> double faulty convertions reported by sonar
Arnaud Giersch [Fri, 12 Jun 2020 11:42:17 +0000 (13:42 +0200)]
Spelling fix, just like the line below.
Arnaud Giersch [Tue, 9 Jun 2020 11:40:03 +0000 (13:40 +0200)]
Use std::vector.
Arnaud Giersch [Tue, 9 Jun 2020 09:12:53 +0000 (11:12 +0200)]
Remove redundant access specifier.
Arnaud Giersch [Tue, 9 Jun 2020 09:08:32 +0000 (11:08 +0200)]
Regenerated.
Arnaud Giersch [Tue, 9 Jun 2020 08:32:46 +0000 (10:32 +0200)]
Prefer using initialization lists in ctors.
Augustin Degomme [Fri, 12 Jun 2020 10:43:00 +0000 (12:43 +0200)]
tools and contrib spelling mistakes
Augustin Degomme [Fri, 12 Jun 2020 10:37:59 +0000 (12:37 +0200)]
speeling mistakes in teshsuite (even mpich tests because why not)
Augustin Degomme [Fri, 12 Jun 2020 10:15:58 +0000 (12:15 +0200)]
spellings mistakes in doc/
Augustin Degomme [Fri, 12 Jun 2020 10:11:04 +0000 (12:11 +0200)]
spelling mistakes in docs/
Augustin Degomme [Fri, 12 Jun 2020 10:01:06 +0000 (12:01 +0200)]
spelling mistakes in include/ and examples/
still with codespell
Augustin Degomme [Fri, 12 Jun 2020 09:52:57 +0000 (11:52 +0200)]
Fix most of spelling mistakes in src/
using codespell (https://github.com/codespell-project/codespell)
exclude catch.hpp
Martin Quinson [Thu, 11 Jun 2020 00:13:29 +0000 (02:13 +0200)]
Finish converting the way we use cfg=smpi/host-speed ourselves -- Bummer
Martin Quinson [Wed, 10 Jun 2020 23:48:50 +0000 (01:48 +0200)]
Fix pip builds
Martin Quinson [Wed, 10 Jun 2020 23:43:21 +0000 (01:43 +0200)]
Align the definitions of surf_parsed_filename accross files
Martin Quinson [Wed, 10 Jun 2020 23:38:20 +0000 (01:38 +0200)]
Clarify one paragraph in the doc
Martin Quinson [Wed, 10 Jun 2020 23:24:35 +0000 (01:24 +0200)]
Accept units for 'smpi/host-speed' config element
Martin Quinson [Wed, 10 Jun 2020 21:35:42 +0000 (23:35 +0200)]
split surf_parse into a separate file to make it reusable from elsewhere
Also rename surf_parse_* functions into xbt_parse_*
Also, make the file name and line number explicit, as parameters to
functions that need it (less hidden global state is better). But I was
too lazy to clean smpi::parse_factor() tonight: the pandora box
remains closed for tonight.
Augustin Degomme [Tue, 9 Jun 2020 12:40:03 +0000 (14:40 +0200)]
leaks --
These lines were not supposed to be included in latest commit.
But as I had already written the commit message warning of memory leaks, I decided to add them anymway, in order not to lie.
Augustin Degomme [Tue, 9 Jun 2020 09:28:50 +0000 (11:28 +0200)]
don't throw in smpi_helpers when passing configure, it may confuse some checkers
petsc fails detection of getcwd and others, because we are pulling them in our header with a different signature
Augustin Degomme [Mon, 8 Jun 2020 21:24:36 +0000 (23:24 +0200)]
improve handling of persistent requests.
not great, could leak in some cases.
Augustin Degomme [Mon, 8 Jun 2020 14:05:42 +0000 (16:05 +0200)]
Finished = inactive
One is allowed to call MPI_WAIT with a null or inactive request argument. In this case the operation returns immediately with empty status.
Augustin Degomme [Mon, 8 Jun 2020 10:23:35 +0000 (12:23 +0200)]
standard says handle should be set to MPI_DATATYPE_NULL.
Augustin Degomme [Sun, 7 Jun 2020 15:39:33 +0000 (17:39 +0200)]
This call can be performed before MPI_Init, avoid bench_end/bench_start.
Augustin Degomme [Sun, 7 Jun 2020 15:08:04 +0000 (17:08 +0200)]
returning the correct value is better, weirdly.
augustin degomme [Sun, 7 Jun 2020 01:57:30 +0000 (03:57 +0200)]
fix issues with attr and cloning
Augustin Degomme [Sun, 7 Jun 2020 01:12:07 +0000 (03:12 +0200)]
please clang
Augustin Degomme [Sat, 6 Jun 2020 20:54:14 +0000 (22:54 +0200)]
even if useless, let's initialize these to avoid upsetting valgrind.
Augustin Degomme [Sat, 6 Jun 2020 20:52:23 +0000 (22:52 +0200)]
Fix MPI_Type_dup for derived datatypes.
augustin degomme [Sat, 6 Jun 2020 11:45:32 +0000 (13:45 +0200)]
please sonar
augustin degomme [Sat, 6 Jun 2020 09:38:16 +0000 (11:38 +0200)]
Tiny fixes
I was just checking than sanitizers, valgrind, and static analysis were still working.
Augustin Degomme [Fri, 5 Jun 2020 23:35:17 +0000 (01:35 +0200)]
Implement MPI_Type_get_envelope and MPI_Type_get_contents
Augustin Degomme [Fri, 5 Jun 2020 15:11:00 +0000 (17:11 +0200)]
nothing to see here.
Augustin Degomme [Fri, 5 Jun 2020 14:45:43 +0000 (16:45 +0200)]
don't fail for these probably harmless unimplemented calls
Arnaud Giersch [Thu, 4 Jun 2020 15:39:59 +0000 (17:39 +0200)]
Prefer doublequotes (codacy).
Arnaud Giersch [Thu, 4 Jun 2020 15:36:45 +0000 (17:36 +0200)]
Exclude more odr violations (seen with boost 1.71).
Augustin Degomme [Fri, 5 Jun 2020 10:19:41 +0000 (12:19 +0200)]
when SMPI_PRETEND_CC is set, don't replace program xx by subroutine xx, we want to keep an entry point
Augustin Degomme [Wed, 3 Jun 2020 20:32:12 +0000 (22:32 +0200)]
changelog
Arnaud Giersch [Wed, 3 Jun 2020 19:12:29 +0000 (21:12 +0200)]
Try to fix python tests failing with python 3.9 on fedora-rawhide.
Augustin Degomme [Wed, 3 Jun 2020 09:20:00 +0000 (11:20 +0200)]
try to fix ns3 examples. Not sure this was the way intended, but it avoids crashes for now.
Augustin Degomme [Wed, 3 Jun 2020 00:20:30 +0000 (02:20 +0200)]
requalify all SMPI tesh files with timing information due to previous change
Augustin Degomme [Wed, 3 Jun 2020 00:19:51 +0000 (02:19 +0200)]
add a 16 byte envelope to each MPI message.
This simulates the send of src/dest,tag, and communicator, as in all MPI implems.
This avoids 0-sized messages to be sent to the lower layers, and should be more realistic
This will change simulation times a little bit.
Arnaud Giersch [Sun, 31 May 2020 21:06:15 +0000 (23:06 +0200)]
Misc issues in shell scripts (codefator.io).
Arnaud Giersch [Sun, 31 May 2020 13:37:29 +0000 (15:37 +0200)]
Fix potential memory leaks.
Martin Quinson [Fri, 29 May 2020 14:37:38 +0000 (16:37 +0200)]
wifi: make room for the ns3-wifi binding
Augustin Degomme [Thu, 28 May 2020 15:30:51 +0000 (17:30 +0200)]
smpi topo : a topo can be shared between some comm (duplicates), but there was no refcounting.
Try to switch to a shared_ptr to avoid segfaults or leaks...
Augustin Degomme [Thu, 28 May 2020 15:29:14 +0000 (17:29 +0200)]
that's not a double
Augustin Degomme [Wed, 27 May 2020 16:24:06 +0000 (18:24 +0200)]
fortran : protect in case some calls return success, but with a null request.
This can be caused by sending messages to unreachable processes.
Augustin Degomme [Wed, 27 May 2020 13:42:57 +0000 (15:42 +0200)]
attempt to please fortran on ci
Augustin Degomme [Wed, 27 May 2020 12:58:51 +0000 (14:58 +0200)]
Trigger a warning when abort is called and a process exits.
Does not hurt and can help understand why there is a deadlock in simgrid, when the app forgets to print an error message.
Augustin Degomme [Wed, 27 May 2020 12:55:48 +0000 (14:55 +0200)]
dist
Augustin Degomme [Wed, 27 May 2020 12:55:33 +0000 (14:55 +0200)]
MPI IO : "support" for ./ in filename
Augustin Degomme [Wed, 27 May 2020 12:54:46 +0000 (14:54 +0200)]
MPI IO: now with more fortran bindings
Augustin Degomme [Wed, 27 May 2020 12:53:22 +0000 (14:53 +0200)]
fortran support for MPI_UB and MPI_LB
Augustin Degomme [Wed, 27 May 2020 12:53:05 +0000 (14:53 +0200)]
fortran : allow use of C names for types
Arnaud Giersch [Wed, 27 May 2020 08:10:46 +0000 (10:10 +0200)]
Remove redundant blank lines (codefactor).
Arnaud Giersch [Wed, 27 May 2020 08:07:06 +0000 (10:07 +0200)]
Make smpif90 support SMPI_NO_UNDEFINED_CHECK too.
Augustin Degomme [Tue, 26 May 2020 21:04:14 +0000 (23:04 +0200)]
SMPI : Allow to deactivate link-time definitions check with an environment var
This is breaking compilation when the code has shared libraries itself (CLAMR).
Not sure if we should keep all this, actually ...
Martin Quinson [Sun, 24 May 2020 22:13:41 +0000 (00:13 +0200)]
Don't use XBT_LOG macros within a function (thanks lgtm for noticing)
Martin Quinson [Sun, 24 May 2020 22:08:32 +0000 (00:08 +0200)]
lgtm: Add some missing header guards
Martin Quinson [Wed, 20 May 2020 10:01:12 +0000 (12:01 +0200)]
Better explanations for the parameters of the decay model
Martin Quinson [Thu, 14 May 2020 22:16:34 +0000 (00:16 +0200)]
MC: inline a function
Augustin Degomme [Fri, 15 May 2020 00:12:48 +0000 (02:12 +0200)]
bump osx version on travis
Martin Quinson [Thu, 14 May 2020 21:30:35 +0000 (23:30 +0200)]
fix ns3 builds
Martin Quinson [Thu, 14 May 2020 20:56:19 +0000 (22:56 +0200)]
remove an extraneous ';' that fools codacy
Martin Quinson [Thu, 14 May 2020 20:31:26 +0000 (22:31 +0200)]
Missing const marker
Martin Quinson [Thu, 14 May 2020 19:04:15 +0000 (21:04 +0200)]
Save the src_wifi_link and dst_wifi_link in a subclass of NetCm02Action
This way, interested parties won't have to recompute that information
and possibly miscompute it.
Martin Quinson [Thu, 14 May 2020 18:17:31 +0000 (20:17 +0200)]
fix how wifi's host_rate is used in communicate()
- Enforce that we use the first provided link for the src host,
and the last one for the dst host
- Assert that the provided links are actually associated to by the right host
- Fix the test that was missing an association
Martin Quinson [Thu, 14 May 2020 18:16:13 +0000 (20:16 +0200)]
fix save src/dst
Martin Quinson [Thu, 14 May 2020 16:29:42 +0000 (18:29 +0200)]
remove the src and dst from the Link::on_communicate callback since it's now in the action
Martin Quinson [Thu, 14 May 2020 16:23:02 +0000 (18:23 +0200)]
save the source and destination hosts in the NetworkAction
Martin Quinson [Thu, 14 May 2020 16:01:34 +0000 (18:01 +0200)]
stick to our coding standards: getters should have get_ in their name
Augustin Degomme [Wed, 13 May 2020 12:44:02 +0000 (14:44 +0200)]
third time's the charm. It was already done properly for smpicc, so just port it to smpicxx
Augustin Degomme [Wed, 13 May 2020 12:11:37 +0000 (14:11 +0200)]
disable on osx as -z is not supported there
Augustin Degomme [Wed, 13 May 2020 11:15:24 +0000 (13:15 +0200)]
add definitions check to link phase in SMPI (gh #342).. let's see how many ci workers complain
Martin Quinson [Sun, 10 May 2020 20:17:19 +0000 (22:17 +0200)]
sonar: also ignore S5271 for the examples in C++
Plus fix some other warnings reported by sonar.
Martin Quinson [Sun, 10 May 2020 13:02:46 +0000 (15:02 +0200)]
Please the checkers (sonar, codacy)
- reduce the scope of a variable
- Mark a constructor as explicit
- Blindly obey the given hints about javascript that I don't really master
Martin Quinson [Sun, 10 May 2020 12:41:20 +0000 (14:41 +0200)]
do not downcast activities to the wrong type just to get their name
- I use a protected method to keep my data private. Doing otherwise
would trigger sonar to complain.
- The code is not particularly clear this way, but I fail to see how
to do otherwise: I don't want the getter to become a virtual method.
- This was reported by UndefSan now that we have a test that deadlocks.
Martin Quinson [Sun, 10 May 2020 11:47:44 +0000 (13:47 +0200)]
Better fix for FG#50
- The previous solution was not allowing the suspended actor to be resumed properly
- Instead of going for a complex story where we create an activity on
which to suspend the actor, simply unschedule it on suspend(), and
explicitely reschedule it on resume()
- This is much easier since we don't have to save and restore the
simcall of the suspended actor, even if the price to pay is the
explicit simix_global->actors_to_run.push_back(this); in resume()
of which I'm not a big fan.
Fixes https://framagit.org/simgrid/simgrid/-/issues/50
Martin Quinson [Sun, 10 May 2020 10:28:26 +0000 (12:28 +0200)]
please codacy by not setting a variable we won't use
Martin Quinson [Sun, 10 May 2020 10:09:42 +0000 (12:09 +0200)]
sonar: ignore more useless warnings in the examples
Martin Quinson [Sun, 10 May 2020 09:22:18 +0000 (11:22 +0200)]
Fix MC on FreeBSD
Martin Quinson [Sun, 10 May 2020 08:55:18 +0000 (10:55 +0200)]
Fix pip builds
Martin Quinson [Sun, 10 May 2020 08:31:26 +0000 (10:31 +0200)]
stick to our coding standards: fields must have a trailing _
Martin Quinson [Sun, 10 May 2020 08:10:59 +0000 (10:10 +0200)]
sonar: ignore more crufty warnings about the examples
Martin Quinson [Sun, 10 May 2020 08:02:03 +0000 (10:02 +0200)]
The examples must be readable. I'll shut off sonar on these issues
Martin Quinson [Sun, 10 May 2020 07:58:45 +0000 (09:58 +0200)]
MC: obey to the rule of 5 to please sonar
Martin Quinson [Sun, 10 May 2020 07:52:22 +0000 (09:52 +0200)]
Fix MC+SMPI builds
Martin Quinson [Sat, 9 May 2020 23:56:20 +0000 (01:56 +0200)]
Ensure that suspending an actor running later in the current scheduling round actually works
Fixes https://framagit.org/simgrid/simgrid/-/issues/50
Martin Quinson [Sat, 9 May 2020 23:26:00 +0000 (01:26 +0200)]
cosmetics
Martin Quinson [Thu, 7 May 2020 17:41:21 +0000 (19:41 +0200)]
MC: Further renamings
Augustin Degomme [Thu, 7 May 2020 08:54:10 +0000 (10:54 +0200)]
try to print pointer correctly on sunos as well