Gabriel Corona [Tue, 24 Jun 2014 07:23:20 +0000 (09:23 +0200)]
[mc] Remove declaration of mc_read_pagemap() in mc_page_store.cpp
It is now in mc_page_snapshot.cpp.
Gabriel Corona [Tue, 24 Jun 2014 07:13:41 +0000 (09:13 +0200)]
[mc] Optimise more files
degomme [Mon, 23 Jun 2014 17:19:24 +0000 (19:19 +0200)]
Switch to the right version of cmakefiles for mpich3 tests.
Augustin Degomme [Mon, 23 Jun 2014 16:11:21 +0000 (18:11 +0200)]
remove warning
Augustin Degomme [Mon, 23 Jun 2014 15:56:11 +0000 (17:56 +0200)]
remove now useless functions
Augustin Degomme [Mon, 23 Jun 2014 15:50:26 +0000 (17:50 +0200)]
remove now useless comments
Augustin Degomme [Mon, 23 Jun 2014 15:39:40 +0000 (17:39 +0200)]
add MPICH3 rma tests (15 out of 88 should be passing now)
Augustin Degomme [Mon, 23 Jun 2014 15:30:01 +0000 (17:30 +0200)]
First steps for implemtation of MPI Onesided Operations :
Support for MPI_Win structures, MPI_Put, MPI_Get, MPI_Accumulate, MPI_Win_Fence
Gabriel Corona [Mon, 23 Jun 2014 10:02:49 +0000 (12:02 +0200)]
[mc] Always inline mc_page_store_get_page (C version of page_store->get_page())
Marion Guthmuller [Wed, 4 Jun 2014 15:41:09 +0000 (17:41 +0200)]
model-checker : clarify comments
Gabriel Corona [Mon, 23 Jun 2014 08:30:57 +0000 (10:30 +0200)]
[mc] Move method definition out of class declaratio and force inline
degomme [Sat, 21 Jun 2014 11:41:51 +0000 (13:41 +0200)]
Fix java tests : this dynar may be empty, don't try to iterate on it
Pierre Veyre [Fri, 20 Jun 2014 15:01:27 +0000 (17:01 +0200)]
Remove call to concurrent-rw test
Gabriel Corona [Fri, 20 Jun 2014 14:09:12 +0000 (16:09 +0200)]
[mc] Reset the softdirty bits *before* restoring the ignored bytes (not after)
We want to know what has changed since the last per-page snapshot: we
have to reset the soft dirty bits just after the per-page restoration.
Pierre Veyre [Fri, 20 Jun 2014 13:37:29 +0000 (15:37 +0200)]
Remove storage.xml example file
Gabriel Corona [Fri, 20 Jun 2014 13:31:04 +0000 (15:31 +0200)]
[mc] Try to use optimisation with some part of the MC
Pierre Veyre [Fri, 20 Jun 2014 13:30:27 +0000 (15:30 +0200)]
Initiate java bindings for MSG storage API
Pierre Veyre [Mon, 2 Jun 2014 07:34:10 +0000 (09:34 +0200)]
Add new tesh suite for msg-storage
Gabriel Corona [Fri, 20 Jun 2014 12:02:05 +0000 (14:02 +0200)]
[mc] Always inline 'inline' functions
The MC is usually compiled without optimisation as they tend to
confuse the state comparison. But we *really* want to inline functions
declared 'inline'.
suter [Fri, 20 Jun 2014 09:05:07 +0000 (11:05 +0200)]
remove documentation of non-existing date parameter
suter [Fri, 20 Jun 2014 09:04:20 +0000 (11:04 +0200)]
prevent warining for undocumented (because internal) enum members when
making doc
suter [Fri, 20 Jun 2014 08:24:59 +0000 (10:24 +0200)]
doc is whining +indent
Augustin Degomme [Fri, 20 Jun 2014 09:04:42 +0000 (11:04 +0200)]
don't do the call if an error is caught before
Augustin Degomme [Fri, 20 Jun 2014 08:58:43 +0000 (10:58 +0200)]
Remove benchmarking calls from cart_create
Stéphane Castelli [Fri, 20 Jun 2014 08:32:44 +0000 (10:32 +0200)]
Small fixes to the documentation
Stéphane Castelli [Thu, 19 Jun 2014 07:49:14 +0000 (09:49 +0200)]
Remove some unbreakable spaces breaking the pdf generation
Gabriel Corona [Fri, 20 Jun 2014 08:33:27 +0000 (10:33 +0200)]
[mc] Fix compilation warnings/errors when optimizing
Gabriel Corona [Thu, 19 Jun 2014 14:07:55 +0000 (16:07 +0200)]
[mc] Documentation of mc_page_snapshot
Gabriel Corona [Thu, 19 Jun 2014 13:49:21 +0000 (15:49 +0200)]
[mc] Config to disable soft-dirty page tracking --cfg=model-check/soft-dirty:yes
It is here mostly to test the effect on soft-dirty page tracking on
the performance of the simulator. It might be removed in the future
once we will be certain that soft-dirty page tracking does not have a
significant negative impact on some workloads.
Gabriel Corona [Thu, 19 Jun 2014 13:33:12 +0000 (15:33 +0200)]
[mc] Avoid big alloca in mc_snapshot_region_memcp and mc_snapshot_memcp
Be more stack friendly.
Gabriel Corona [Thu, 19 Jun 2014 13:17:58 +0000 (15:17 +0200)]
[mc] Poor man's TCO in compare_heap_area_with_type()
This is slightly more friendly for the stack.
Gabriel Corona [Thu, 19 Jun 2014 13:13:42 +0000 (15:13 +0200)]
[mc] Do not allocate pagemap buffer on the heap
This won't work very well with small stacks.
Gabriel Corona [Thu, 19 Jun 2014 12:47:41 +0000 (14:47 +0200)]
[mc] pread_whole must restart in cas of EINTR, not EAGAIN
This probably won't happen with this file anyway.
Gabriel Corona [Thu, 19 Jun 2014 12:46:16 +0000 (14:46 +0200)]
[mc] Documentation about per-page snapshots
Gabriel Corona [Thu, 19 Jun 2014 12:06:15 +0000 (14:06 +0200)]
[mc] Add some documentation
Gabriel Corona [Thu, 19 Jun 2014 11:09:09 +0000 (13:09 +0200)]
[mc] Avoid region lookup when we know we are in the heap
Gabriel Corona [Thu, 19 Jun 2014 10:43:22 +0000 (12:43 +0200)]
[mc] Fix bug mc_snapshot_read_fragmented
Return the correct address.
Gabriel Corona [Thu, 19 Jun 2014 10:27:31 +0000 (12:27 +0200)]
[mc] Replace test-and-die with assert
Gabriel Corona [Thu, 19 Jun 2014 10:24:09 +0000 (12:24 +0200)]
[mc] Avoid looking up region in mc_diff (we are in the heap)
Gabriel Corona [Thu, 19 Jun 2014 10:03:34 +0000 (12:03 +0200)]
[mc] Fix mc_snapshot_read_fragmented
Gabriel Corona [Thu, 19 Jun 2014 09:51:00 +0000 (11:51 +0200)]
[mc] Remove heap{base,info}{1,2} field in struct s_mc_diff (not meaningful in per-page snapashots)
Gabriel Corona [Thu, 19 Jun 2014 07:53:24 +0000 (09:53 +0200)]
[mc] Fix inverted test on page soft-dirtiness
Martin Quinson [Wed, 18 Jun 2014 16:08:32 +0000 (18:08 +0200)]
Merge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid
Paul Bédaride [Wed, 18 Jun 2014 16:02:29 +0000 (18:02 +0200)]
Merge branch 'v3_11_x'
Conflicts:
examples/msg/properties/msg_prop.c
examples/simdag/properties/sd_prop.c
Martin Quinson [Wed, 18 Jun 2014 15:29:41 +0000 (17:29 +0200)]
Merge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid
Augustin Degomme [Wed, 18 Jun 2014 15:28:28 +0000 (17:28 +0200)]
add rule to use gcc-ar and gcc-ranlib instead of ar and ranlib for gcc >=4.9
see https://gcc.gnu.org/gcc-4.9/changes.html for explanations
Augustin Degomme [Wed, 18 Jun 2014 15:26:10 +0000 (17:26 +0200)]
Revert "try to have all these mpich temporary libs sent to the right folder while building"
This reverts commit
3f8e8c0e3b6c8faab8c96a8875bff2eaebbe3e99.
Paul Bédaride [Wed, 18 Jun 2014 15:05:33 +0000 (17:05 +0200)]
Improve Packet level simulation documentation
Paul Bédaride [Wed, 18 Jun 2014 14:13:35 +0000 (16:13 +0200)]
Fix bug with const in java bindings
Augustin Degomme [Wed, 18 Jun 2014 15:00:41 +0000 (17:00 +0200)]
try to have all these mpich temporary libs sent to the right folder while building
Arnaud Giersch [Wed, 18 Jun 2014 10:30:19 +0000 (12:30 +0200)]
Update tesh files after commit
2c2afb4d73ea196ea97ca46bc89dd512451222db (untested).
Gabriel Corona [Tue, 17 Jun 2014 14:44:42 +0000 (16:44 +0200)]
[mc] Do not use offsetof() in mc_snapshot_get_heap_end
We don't need this. It's much clearer like this.
Gabriel Corona [Tue, 17 Jun 2014 14:40:25 +0000 (16:40 +0200)]
[mc] Fix mc_snapshot_get_heap_end() for per-page snapshots
Gabriel Corona [Tue, 17 Jun 2014 14:19:28 +0000 (16:19 +0200)]
[mc] Fix mc_translate_address_region() for per-page snapshots
It was completely broken :/
Gabriel Corona [Tue, 17 Jun 2014 13:52:32 +0000 (15:52 +0200)]
[mc] Remove mc_untranslate_address() and mc_member_snapshot_resolve()
Those were working in the snapshot address space so we do not use them
anymore (it is not very useful to work in the snapshot space when the
snapshot space is broken in pages).
We work in the process address space instead (mc_member_resolve).
Gabriel Corona [Tue, 17 Jun 2014 13:45:39 +0000 (15:45 +0200)]
[mc] Use mc_snapshot_read in snapshot_compare (compatibility with per-page snapshots)
Gabriel Corona [Tue, 17 Jun 2014 13:29:24 +0000 (15:29 +0200)]
[mc] mremap does not like MAP_PRIVATE|MAP_ANONYMOUS regions
Use a MAP_PRIVATE one instead.
Gabriel Corona [Tue, 17 Jun 2014 12:42:38 +0000 (14:42 +0200)]
[mc] Add option --cfg=model-check/sparse-checkpoint:yes to enable per page snapshot
Gabriel Corona [Tue, 17 Jun 2014 12:21:50 +0000 (14:21 +0200)]
[mc] Fix bugs in mc_page_snapshot
Gabriel Corona [Tue, 17 Jun 2014 12:06:04 +0000 (14:06 +0200)]
[mc] Use mc_snapshot_read in mc_diff (compatibility with per-page snapshots)
Gabriel Corona [Tue, 17 Jun 2014 10:56:32 +0000 (12:56 +0200)]
[mc] Use mc_snapshot_read in dwarf expression evaluation (compatibility with per-page snapshots)
Gabriel Corona [Tue, 17 Jun 2014 10:54:29 +0000 (12:54 +0200)]
[mc] Fix bug in mc_snapshot_read
It was broken when no snapshot was used.
Gabriel Corona [Tue, 17 Jun 2014 10:12:57 +0000 (12:12 +0200)]
[mc] Remove useless bits
Gabriel Corona [Tue, 17 Jun 2014 08:40:37 +0000 (10:40 +0200)]
Add some informations/help for the user on SIGSEGV
Martin Quinson [Tue, 17 Jun 2014 07:26:43 +0000 (09:26 +0200)]
tiny doc update
Martin Quinson [Tue, 17 Jun 2014 07:23:23 +0000 (09:23 +0200)]
cosmetics on some error messages
Stéphane Castelli [Fri, 13 Jun 2014 16:18:37 +0000 (18:18 +0200)]
This should ease the future implementation of graphes in smpi
Augustin Degomme [Mon, 16 Jun 2014 17:41:12 +0000 (19:41 +0200)]
remove simgrid_documentation target from distcheck
Augustin Degomme [Mon, 16 Jun 2014 17:40:24 +0000 (19:40 +0200)]
add missing file for distcheck
Augustin Degomme [Mon, 16 Jun 2014 14:39:28 +0000 (16:39 +0200)]
ignore sigpipes (as tesh.c used to do)
Gabriel Corona [Mon, 16 Jun 2014 14:10:26 +0000 (16:10 +0200)]
[mc] Remove useless parameters in compare_local_variables
Gabriel Corona [Mon, 16 Jun 2014 13:59:34 +0000 (15:59 +0200)]
[mc] Group MC_ignore_global_variable("mc_diff_info"); its fiends
Gabriel Corona [Mon, 16 Jun 2014 13:29:26 +0000 (15:29 +0200)]
[mc] Remove useless parts in mmalloc_compare_heap, MC_take_snapshot_stacks, snapshot_compare
Gabriel Corona [Mon, 16 Jun 2014 12:50:42 +0000 (14:50 +0200)]
[mc] Use process addresses in mc_compare
This is necessary in order to work work with per-page snapshots.
Gabriel Corona [Fri, 13 Jun 2014 14:03:58 +0000 (16:03 +0200)]
[mc] Partial integration of per-page snapshot address translation (wip)
Gabriel Corona [Mon, 16 Jun 2014 11:00:15 +0000 (13:00 +0200)]
[mc] Simplify s_mc_snapshot_stack
Some fields were not used and have been removed:
* stack_pointer (SP in the snapshot)
* real_address (address of the stack)
The first one does not make sense with page-fragmented snapshot.
Simplify the computation of snapshot->stack_sizes[cursor]. The old
computation did not make sense with page fragmented snapshots.
Stéphane Castelli [Mon, 16 Jun 2014 09:35:38 +0000 (11:35 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Stéphane Castelli [Mon, 16 Jun 2014 09:22:37 +0000 (11:22 +0200)]
Some boilerplate around IB networking
Augustin Degomme [Mon, 16 Jun 2014 09:12:44 +0000 (11:12 +0200)]
change symbol name to match one declared in mpif.h
Stéphane Castelli [Mon, 16 Jun 2014 08:54:56 +0000 (10:54 +0200)]
Uninstall recently added manpages
Fix typos in documentation
degomme [Fri, 13 Jun 2014 13:40:28 +0000 (15:40 +0200)]
Requalify one more test
degomme [Fri, 13 Jun 2014 13:05:32 +0000 (15:05 +0200)]
Revalidate tesh files
Gabriel Corona [Fri, 13 Jun 2014 09:17:52 +0000 (11:17 +0200)]
[mc] Update doc for page_store
Gabriel Corona [Tue, 27 May 2014 10:27:47 +0000 (12:27 +0200)]
[mc] Page-level sparse snapshot: work-in-progress, working page_store
Implement page_store which stores immutables/shared/refcounted copies
of memory pages.
Gabriel Corona [Fri, 13 Jun 2014 12:07:46 +0000 (14:07 +0200)]
[mc] In MC_ignore, keep the zeroed data out of the main snapshot
The previous implementation was zeroing out the snapshot data
* so that it will be automatically ignored by the state comparator;
* but not for the first snapshot in order to be able to backtrack
to the initial state;
In preparation for the per-page snapshoting code, we
1. zero out on the main memory;
2. keep the zero-ed bytes out of the main snapshot regions;
3. restore the zero-ed bytes.
This way the state comparison code and the per-page snapshoting code
do not have to worry about this. Moreover by normalizing, the
"ignored" bytes, we increase the possibility of sharing memory pages
in per-page snapshots.
Martin Quinson [Fri, 13 Jun 2014 00:21:40 +0000 (02:21 +0200)]
example simplification and cosmetics
Arnaud Giersch [Thu, 12 Jun 2014 10:55:10 +0000 (12:55 +0200)]
In tesh.pl, with "output display", print contents of array, and not a reference to it.
Arnaud Giersch [Thu, 12 Jun 2014 09:30:31 +0000 (11:30 +0200)]
Increase size of junk area to 32 KiB in mm_legacy.c.
It is apparently needed when running Fortran tests through tesh.pl.
Arnaud Giersch [Fri, 6 Jun 2014 11:42:36 +0000 (13:42 +0200)]
More updates to smpi* manpages.
Paul Bédaride [Thu, 12 Jun 2014 13:47:07 +0000 (15:47 +0200)]
Rpath active for make install on osX
Paul Bédaride [Thu, 12 Jun 2014 09:28:00 +0000 (11:28 +0200)]
Doc to install libboost on osX
degomme [Wed, 11 Jun 2014 21:10:05 +0000 (23:10 +0200)]
add option to output the right name in smpiff
it used to compile with the temporary name instead, for example with some NAS
Paul Bédaride [Wed, 11 Jun 2014 15:14:36 +0000 (17:14 +0200)]
No rpath in libsimgird-java and libsurf-java
Paul Bédaride [Wed, 11 Jun 2014 13:26:45 +0000 (15:26 +0200)]
Network::shareResourcesFull revival
degomme [Wed, 11 Jun 2014 13:09:17 +0000 (15:09 +0200)]
activate tests using resized and handle some corner cases
scastelli [Wed, 11 Jun 2014 06:56:57 +0000 (08:56 +0200)]
Implementation of MPI_Type_create_resized
degomme [Tue, 10 Jun 2014 23:13:22 +0000 (01:13 +0200)]
add missing prototype
scastelli [Tue, 10 Jun 2014 22:44:15 +0000 (00:44 +0200)]
We should'nt allow the use of uncommited datatypes in communications.
Small fix to follow more closely the specs in mpi_type_free
degomme [Tue, 10 Jun 2014 13:09:35 +0000 (15:09 +0200)]
torus should provide better results if latency is taken into account ..
scastelli [Fri, 6 Jun 2014 07:42:56 +0000 (09:42 +0200)]
Small correction in a manpage