Logo AND Algorithmique Numérique Distribuée

Public GIT Repository
simgrid.git
8 years agoFix format.
Arnaud Giersch [Tue, 10 Jan 2012 12:06:03 +0000 (13:06 +0100)]
Fix format.

8 years agoDon't use printf modifier %Z. Use %z instead.
Arnaud Giersch [Tue, 10 Jan 2012 11:04:32 +0000 (12:04 +0100)]
Don't use printf modifier %Z.  Use %z instead.

8 years agogive the localisation of parse errors more accurately
Martin Quinson [Mon, 9 Jan 2012 17:17:37 +0000 (18:17 +0100)]
give the localisation of parse errors more accurately

8 years agoMerge branches 'MC_LTL' and 'MC_LTL' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid
Martin Quinson [Mon, 9 Jan 2012 17:16:57 +0000 (18:16 +0100)]
Merge branches 'MC_LTL' and 'MC_LTL' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid

8 years agomake sure that we won't survive a parser error in the deployment file
Martin Quinson [Mon, 9 Jan 2012 15:48:39 +0000 (16:48 +0100)]
make sure that we won't survive a parser error in the deployment file

8 years agomake it compile with -Werror by forcing a type casting
Martin Quinson [Mon, 9 Jan 2012 15:18:59 +0000 (16:18 +0100)]
make it compile with -Werror by forcing a type casting

8 years agoMerge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid
Martin Quinson [Mon, 9 Jan 2012 15:11:11 +0000 (16:11 +0100)]
Merge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid

8 years agoimprove doc of multicore in FAQ
Martin Quinson [Mon, 9 Jan 2012 15:10:18 +0000 (16:10 +0100)]
improve doc of multicore in FAQ

8 years agoRemove test masterslave-cpu_ti-no-crosstraffic because it is close to simple masterslave
Navarrop [Mon, 9 Jan 2012 14:58:29 +0000 (15:58 +0100)]
Remove test masterslave-cpu_ti-no-crosstraffic because it is close to simple masterslave

8 years agoUpdate option page: Write that crosstraffic is enable by default.
Navarrop [Mon, 9 Jan 2012 13:58:46 +0000 (14:58 +0100)]
Update option page: Write that crosstraffic is enable by default.

8 years agoAdd the faq to documentation because it is under version control
Navarrop [Mon, 9 Jan 2012 13:57:57 +0000 (14:57 +0100)]
Add the faq to documentation because it is under version control

8 years agoRename old tesh with no-crosstraffic and new like old name because crosstraffic is...
Navarrop [Mon, 9 Jan 2012 11:37:11 +0000 (12:37 +0100)]
Rename old tesh with no-crosstraffic and new like old name because crosstraffic is enable by default.

8 years agocosmetics in the ChangeLog
Martin Quinson [Mon, 9 Jan 2012 10:27:20 +0000 (11:27 +0100)]
cosmetics in the ChangeLog

8 years ago[trace] valgrind's memcheck to wipe out memory leaks from the tracing system
Lucas Schnorr [Sun, 8 Jan 2012 01:19:39 +0000 (02:19 +0100)]
[trace] valgrind's memcheck to wipe out memory leaks from the tracing system

and some simplifications in tracing resource utilization

8 years agoFix the order of contraints changed by previous commits:
Arnaud Giersch [Fri, 9 Dec 2011 15:45:14 +0000 (16:45 +0100)]
Fix the order of contraints changed by previous commits:

7591b36 Reduce the number of calls to lmm_update_modified_set.
c44aefe In lmm_update_modified_set, don't visit variables twice.

8 years agoIn lmm_update_modified_set, don't visit variables twice.
Arnaud Giersch [Fri, 9 Dec 2011 15:45:13 +0000 (16:45 +0100)]
In lmm_update_modified_set, don't visit variables twice.

Note: the constraints may be ordered differently in
modified_constraint_set, and the timings may vary a bit.
If it is really important, the following patch fixes that:

--- a/src/surf/maxmin.c
+++ b/src/surf/maxmin.c
@@ -790,10 +790,8 @@ static void lmm_update_modified_set_rec(lmm_system_t sys,
     lmm_variable_t var = elem->variable;
     s_lmm_element_t *cnsts = var->cnsts;
     int i;
-    if (var->visited == sys->visited_counter)
-      continue;
-    var->visited = sys->visited_counter;
-    for (i = 0; i < var->cnsts_number; i++) {
+    for (i = 0; var->visited != sys->visited_counter
+                && i < var->cnsts_number ; i++) {
       if (cnsts[i].constraint != cnst
           && !xbt_swag_belongs(cnsts[i].constraint,
                                &sys->modified_constraint_set)) {
@@ -801,6 +799,7 @@ static void lmm_update_modified_set_rec(lmm_system_t sys,
         lmm_update_modified_set_rec(sys, cnsts[i].constraint);
       }
     }
+    var->visited = sys->visited_counter;
   }
 }

8 years agoTry hard to optimize lmm_update_modified_set.
Arnaud Giersch [Fri, 9 Dec 2011 15:45:12 +0000 (16:45 +0100)]
Try hard to optimize lmm_update_modified_set.

* move tests for final case before calling the recursive function
* try to help the compiler inliner/optimizer by putting accesses to
  modified_constraint_set together

8 years agoThe variable-constraint graph is already traversed, and there is no
Navarrop [Fri, 6 Jan 2012 15:01:33 +0000 (16:01 +0100)]
The variable-constraint graph is already traversed, and there is no
need to call lmm_update_modified_set for each constraint of a variable.

Note: the fix in lmm_update_variable_weight may change the order of the
elements in modified_constraint_set, and some timings may slightly vary.
If it is really important, the following patch fixes that:

--- a/src/surf/maxmin.c
+++ b/src/surf/maxmin.c
@@ -716,13 +716,13 @@ void lmm_update_variable_weight(lmm_system_t sys, lmm_variable_t var,
       xbt_swag_insert_at_head(elem, &(elem->constraint->element_set));
     else
       xbt_swag_insert_at_tail(elem, &(elem->constraint->element_set));
+
+    if (i == 0)
+      lmm_update_modified_set(sys, elem->constraint);
   }
   if (!weight)
     var->value = 0.0;

-  if (var->cnsts_number)
-    lmm_update_modified_set(sys, var->cnsts[0].constraint);
-
   XBT_OUT();
 }

8 years agoEnsure that all constraints are put in modified_constraint_set on lmm_expand.
Arnaud Giersch [Fri, 9 Dec 2011 15:45:10 +0000 (16:45 +0100)]
Ensure that all constraints are put in modified_constraint_set on lmm_expand.

Without this change, if cnst was previously marked as modified, the constraints
involving var were not considered.

8 years agoRemove constraint from modified_constraint_set, when made inactive.
Arnaud Giersch [Fri, 9 Dec 2011 15:45:09 +0000 (16:45 +0100)]
Remove constraint from modified_constraint_set, when made inactive.

8 years agoRewrite script for update tesh file.
Navarrop [Fri, 6 Jan 2012 14:14:07 +0000 (15:14 +0100)]
Rewrite script for update tesh file.

8 years agoKeep iwannadie set instead of lying to the context factory
Christophe Thiéry [Fri, 6 Jan 2012 14:29:17 +0000 (15:29 +0100)]
Keep iwannadie set instead of lying to the context factory

8 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot//simgrid/simgrid
Christophe Thiéry [Fri, 6 Jan 2012 14:27:35 +0000 (15:27 +0100)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot//simgrid/simgrid

8 years agoSIMIX: when a process is killed, remove its blocking comm from the list
Christophe Thiéry [Fri, 6 Jan 2012 14:27:04 +0000 (15:27 +0100)]
SIMIX: when a process is killed, remove its blocking comm from the list

8 years agoMSG: don't keep pointers to a structure freed
Christophe Thiéry [Fri, 6 Jan 2012 14:26:26 +0000 (15:26 +0100)]
MSG: don't keep pointers to a structure freed

8 years agoAdd some tests for crosstraffic = 1.
Navarrop [Fri, 6 Jan 2012 14:08:43 +0000 (15:08 +0100)]
Add some tests for crosstraffic = 1.
Set crosstraffic = 1 with default workstation model.
Update tesh.

8 years agoMerge branch 'smpi'
Christophe Thiéry [Fri, 6 Jan 2012 09:26:02 +0000 (10:26 +0100)]
Merge branch 'smpi'

8 years agoclean_fun is the function that frees the userdata of a detached send
Christophe Thiéry [Thu, 5 Jan 2012 18:30:23 +0000 (19:30 +0100)]
clean_fun is the function that frees the userdata of a detached send

8 years agoSMPI: don't finish immediately a dsend comm.
Christophe Thiéry [Thu, 5 Jan 2012 18:03:18 +0000 (19:03 +0100)]
SMPI: don't finish immediately a dsend comm.

Otherwise, the receiver would make invalid memory reads while matching
the comm. I'm not sure when the request can be freed, so for now,
dsends make a memory leaks. But smpi-reduce now works.

8 years agoSMPI: before terminating a process, wait for its asynchronous comms
Christophe Thiéry [Thu, 5 Jan 2012 17:10:46 +0000 (18:10 +0100)]
SMPI: before terminating a process, wait for its asynchronous comms

8 years agoWhen a process leaves, no one should ever finish a communication with it
Christophe Thiéry [Thu, 5 Jan 2012 17:01:13 +0000 (18:01 +0100)]
When a process leaves, no one should ever finish a communication with it

Its unstarted comms must never get matched in the future and its
started comms must be canceled, no matter if they are detached.

8 years agoExport SIMIX_rdv_remove and fix debug messages
Christophe Thiéry [Thu, 5 Jan 2012 16:59:36 +0000 (17:59 +0100)]
Export SIMIX_rdv_remove and fix debug messages

8 years ago-0.000000 is lower than 0.0. True story.
Christophe Thiéry [Thu, 5 Jan 2012 16:56:22 +0000 (17:56 +0100)]
-0.000000 is lower than 0.0. True story.

8 years agoSorry, for this stupid error
Navarrop [Thu, 5 Jan 2012 11:52:39 +0000 (12:52 +0100)]
Sorry, for this stupid error

8 years agoUse xbt_config mechanism instead of hard coding value.
Pierre [Thu, 5 Jan 2012 11:41:20 +0000 (12:41 +0100)]
Use xbt_config mechanism instead of hard coding value.

8 years agoUse of busy wait instead of futex if there is not futex.h
Pierre [Thu, 5 Jan 2012 11:40:35 +0000 (12:40 +0100)]
Use of busy wait instead of futex if there is not futex.h

8 years agoAdd a ifdef HAVE_FUTEX_H to compile on Mac
Pierre [Thu, 5 Jan 2012 09:57:45 +0000 (10:57 +0100)]
Add a ifdef HAVE_FUTEX_H to compile on Mac

8 years agoAdd a Chord test with the constant network model
Christophe Thiéry [Mon, 2 Jan 2012 15:25:06 +0000 (16:25 +0100)]
Add a Chord test with the constant network model

8 years agothis configuration option does not exist anymore (and it was useless: the AS routing...
Martin Quinson [Mon, 2 Jan 2012 15:04:29 +0000 (16:04 +0100)]
this configuration option does not exist anymore (and it was useless: the AS routing mode always superseeds it)

8 years agoFix supernovae compilation
Christophe Thiéry [Fri, 30 Dec 2011 10:10:50 +0000 (11:10 +0100)]
Fix supernovae compilation

8 years agocleanup the debug messages
Martin Quinson [Mon, 26 Dec 2011 23:30:51 +0000 (00:30 +0100)]
cleanup the debug messages

8 years agomore verbose debug messages
Martin Quinson [Mon, 26 Dec 2011 23:21:33 +0000 (00:21 +0100)]
more verbose debug messages

8 years agoWhen the process exits, don't cancel the communications it is involved into if it...
Martin Quinson [Mon, 26 Dec 2011 23:20:56 +0000 (00:20 +0100)]
When the process exits, don't cancel the communications it is involved into if it's the sender of detached sends

8 years agouse sensible process names (their rank) in SMPI, and get simix ignore that
Martin Quinson [Mon, 26 Dec 2011 23:01:56 +0000 (00:01 +0100)]
use sensible process names (their rank) in SMPI, and get simix ignore that

8 years agoFurther investigate the dsend issue, in vain so far
Martin Quinson [Mon, 26 Dec 2011 21:55:19 +0000 (22:55 +0100)]
Further investigate the dsend issue, in vain so far

- Ensure that it still compiles after the messed up merge (sorry)
- Add a simple dsend example
- Stop using the src_data to store the cleanup function since that
  field may be clear in MSG, but we store the MPI_status in there. So,
  add a cleanup_fun field down in the stacks so that both the cleanup
  function and the MPI_status can be stored
- Make that shit much more verbose (some messages should be removed
  once the bug is found, sorry for sharing my half backed changes)

8 years agomerge back the master trunk into the smpi branch
Martin Quinson [Mon, 26 Dec 2011 18:03:09 +0000 (19:03 +0100)]
merge back the master trunk into the smpi branch

8 years ago[doc] basic tracing options (and a link to the full doc) added
Lucas Schnorr [Mon, 26 Dec 2011 15:01:41 +0000 (16:01 +0100)]
[doc] basic tracing options (and a link to the full doc) added

8 years ago[doc] colors are defined through the tracing API and registered in the traces
Lucas Schnorr [Mon, 26 Dec 2011 14:17:15 +0000 (15:17 +0100)]
[doc] colors are defined through the tracing API and registered in the traces

8 years ago[doc] update the graph visualization screenshot to reflect current state of Triva
Lucas Schnorr [Mon, 26 Dec 2011 13:57:34 +0000 (14:57 +0100)]
[doc] update the graph visualization screenshot to reflect current state of Triva

8 years ago[trace] tracing needs a Full network/optim, otherwise it won't work for network
Lucas Schnorr [Mon, 26 Dec 2011 13:50:11 +0000 (14:50 +0100)]
[trace] tracing needs a Full network/optim, otherwise it won't work for network

Todo:
- find a way to trace the lazy network update method

8 years agobug fix, tracing mechanism relies on a correct set_category function
Lucas Schnorr [Mon, 26 Dec 2011 13:24:58 +0000 (14:24 +0100)]
bug fix, tracing mechanism relies on a correct set_category function

8 years agotypo
Lucas Schnorr [Mon, 26 Dec 2011 13:19:26 +0000 (14:19 +0100)]
typo

8 years ago[doc] updating the graph configuration documentation
Lucas Schnorr [Mon, 26 Dec 2011 12:52:06 +0000 (13:52 +0100)]
[doc] updating the graph configuration documentation

8 years ago[doc] fix on tracing parameter documentation
Lucas Schnorr [Mon, 26 Dec 2011 12:51:22 +0000 (13:51 +0100)]
[doc] fix on tracing parameter documentation

8 years ago[doc] triva is using git
Lucas Schnorr [Mon, 26 Dec 2011 12:25:28 +0000 (13:25 +0100)]
[doc] triva is using git

8 years ago[doc] tracing documentation was duplicated, fix it
Lucas Schnorr [Mon, 26 Dec 2011 12:23:40 +0000 (13:23 +0100)]
[doc] tracing documentation was duplicated, fix it

8 years ago[trace] better source code comments for configuration options
Lucas Schnorr [Mon, 26 Dec 2011 11:45:15 +0000 (12:45 +0100)]
[trace] better source code comments for configuration options

8 years ago[doc] documentation for three tracing options
Lucas Schnorr [Mon, 26 Dec 2011 11:44:36 +0000 (12:44 +0100)]
[doc] documentation for three tracing options

8 years ago[doc] users can also declare variable with colors for the trace
Lucas Schnorr [Mon, 26 Dec 2011 11:18:14 +0000 (12:18 +0100)]
[doc] users can also declare variable with colors for the trace

8 years ago[doc] explain how to use TRACE_declare_mark and TRACE_mark
Lucas Schnorr [Mon, 26 Dec 2011 11:14:23 +0000 (12:14 +0100)]
[doc] explain how to use TRACE_declare_mark and TRACE_mark

8 years agosend test program
Mark Stillwell [Mon, 26 Dec 2011 11:36:22 +0000 (12:36 +0100)]
send test program

8 years agomore verbose debug around detached sends
Martin Quinson [Mon, 26 Dec 2011 01:40:32 +0000 (02:40 +0100)]
more verbose debug around detached sends

8 years agodupplicate the sender buffer in eager mode, when isends are changed into dsends ...
Martin Quinson [Mon, 26 Dec 2011 01:23:21 +0000 (02:23 +0100)]
dupplicate the sender buffer in eager mode, when isends are changed into dsends (and free it once copied in position)

8 years agofix some glitches in documentation generation
Martin Quinson [Mon, 26 Dec 2011 00:43:55 +0000 (01:43 +0100)]
fix some glitches in documentation generation

8 years agoplaceholder for the configuration items related to the tracing subsystem
Martin Quinson [Mon, 26 Dec 2011 00:30:44 +0000 (01:30 +0100)]
placeholder for the configuration items related to the tracing subsystem

8 years agodocument SMPI configuration items
Martin Quinson [Mon, 26 Dec 2011 00:27:49 +0000 (01:27 +0100)]
document SMPI configuration items

8 years agocosmetics in documentation
Martin Quinson [Mon, 26 Dec 2011 00:01:48 +0000 (01:01 +0100)]
cosmetics in documentation

8 years agodocument the configuration items related to packet level simulators
Martin Quinson [Sun, 25 Dec 2011 23:54:04 +0000 (00:54 +0100)]
document the configuration items related to packet level simulators

8 years agodocument simix-related config options
Martin Quinson [Sun, 25 Dec 2011 23:36:48 +0000 (00:36 +0100)]
document simix-related config options

8 years agokill the deprecated now unused config variable 'routing'
Martin Quinson [Sun, 25 Dec 2011 20:58:32 +0000 (21:58 +0100)]
kill the deprecated now unused config variable 'routing'

8 years agofix a test broken by homogeneisation of dicts
Martin Quinson [Sun, 25 Dec 2011 20:56:04 +0000 (21:56 +0100)]
fix a test broken by homogeneisation of dicts

8 years agofix the tests that my cleanups in the config variable broke
Martin Quinson [Sun, 25 Dec 2011 20:52:39 +0000 (21:52 +0100)]
fix the tests that my cleanups in the config variable broke

8 years agorevalidate two gras tests which timings changed
Martin Quinson [Sun, 25 Dec 2011 20:40:13 +0000 (21:40 +0100)]
revalidate two gras tests which timings changed

Timings are not assessed in GRAS tests because these tests are too
complex to understand discrepencies, and the timings are already well
tested elsewere.

8 years agokill deprecated file for windows's tesh
Martin Quinson [Sun, 25 Dec 2011 20:23:30 +0000 (21:23 +0100)]
kill deprecated file for windows's tesh

8 years agodocument generic configuration variables (and fix MC one)
Martin Quinson [Sun, 25 Dec 2011 18:39:50 +0000 (19:39 +0100)]
document generic configuration variables (and fix MC one)

8 years agoRename the coordinates configuration option to network/coordinates, and document it
Martin Quinson [Sun, 25 Dec 2011 18:26:05 +0000 (19:26 +0100)]
Rename the coordinates configuration option to network/coordinates, and document it

8 years agodocument all network-related config options
Martin Quinson [Sun, 25 Dec 2011 18:16:48 +0000 (19:16 +0100)]
document all network-related config options

8 years agoRename the TCP_gamma configuration option to network/TCP_gamma, and document it
Martin Quinson [Sun, 25 Dec 2011 17:40:47 +0000 (18:40 +0100)]
Rename the TCP_gamma configuration option to network/TCP_gamma, and document it

8 years agokill the deprecated CLM03 workstation model
Martin Quinson [Sun, 25 Dec 2011 16:36:40 +0000 (17:36 +0100)]
kill the deprecated CLM03 workstation model

8 years agoalso display the existing optimizations on --help-models
Martin Quinson [Sun, 25 Dec 2011 16:34:09 +0000 (17:34 +0100)]
also display the existing optimizations on --help-models

8 years agorewrite the doc on configuring simgrid
Martin Quinson [Sun, 25 Dec 2011 16:10:40 +0000 (17:10 +0100)]
rewrite the doc on configuring simgrid

8 years agoproperly kill deprecated option that were recently added
Martin Quinson [Sun, 25 Dec 2011 16:09:01 +0000 (17:09 +0100)]
properly kill deprecated option that were recently added

8 years agocosmetics in the description of network models
Martin Quinson [Sun, 25 Dec 2011 16:05:34 +0000 (17:05 +0100)]
cosmetics in the description of network models

8 years agoMerge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid
Martin Quinson [Fri, 23 Dec 2011 18:40:46 +0000 (19:40 +0100)]
Merge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid

8 years agofix destination parameter when asking for a route in ws_get_route
Lucas Schnorr [Thu, 22 Dec 2011 08:10:01 +0000 (09:10 +0100)]
fix destination parameter when asking for a route in ws_get_route

8 years agoAdd a function SIMIX_process_get_runnable() for context factories
Christophe Thiéry [Mon, 19 Dec 2011 13:53:10 +0000 (14:53 +0100)]
Add a function SIMIX_process_get_runnable() for context factories

8 years agoRemove unstash #ifdef HAVE_SMPI from a commit.
Navarrop [Mon, 19 Dec 2011 13:26:50 +0000 (14:26 +0100)]
Remove unstash #ifdef HAVE_SMPI from a commit.

8 years agoMake simix_timers NULL so can SIMIX_init works if called again later
Christophe Thiéry [Mon, 19 Dec 2011 10:30:30 +0000 (11:30 +0100)]
Make simix_timers NULL so can SIMIX_init works if called again later

8 years agoFix vivaldi model with lazy update mechanism. :)
Navarrop [Fri, 16 Dec 2011 16:21:29 +0000 (17:21 +0100)]
Fix vivaldi model with lazy update mechanism. :)

8 years agoMerge branch 'smpi' of git+ssh://scm.gforge.inria.fr//gitroot//simgrid/simgrid into...
Stephane Genaud [Fri, 16 Dec 2011 16:16:20 +0000 (17:16 +0100)]
Merge branch 'smpi' of git+ssh://scm.gforge.inria.fr//gitroot//simgrid/simgrid into smpi

8 years agodsend used for small messages
Stephane Genaud [Fri, 16 Dec 2011 16:15:11 +0000 (17:15 +0100)]
dsend used for small messages

8 years agoFix tesh file
Navarrop [Fri, 16 Dec 2011 15:20:43 +0000 (16:20 +0100)]
Fix tesh file

8 years agoMake sure this code is thread safe.
Navarrop [Fri, 16 Dec 2011 15:56:34 +0000 (16:56 +0100)]
Make sure this code is thread safe.

8 years agoUse isend instead of send to set the simdata->comm so that get_remaining can work.
Navarrop [Fri, 16 Dec 2011 15:20:16 +0000 (16:20 +0100)]
Use isend instead of send to set the simdata->comm so that get_remaining can work.

8 years agoMove scripts to generate g5k into the right directory.
Navarrop [Thu, 15 Dec 2011 14:52:54 +0000 (15:52 +0100)]
Move scripts to generate g5k into the right directory.

8 years agoRevert an old commit (f0f66d620ef58973870652446275a55525a35944). This test was normal...
Navarrop [Wed, 14 Dec 2011 16:00:13 +0000 (17:00 +0100)]
Revert an old commit (f0f66d620ef58973870652446275a55525a35944). This test was normally broken but is now repaired.

8 years agoRemove unused file
Navarrop [Wed, 14 Dec 2011 15:56:08 +0000 (16:56 +0100)]
Remove unused file

8 years agoAdd an example for view a platform with paje
Navarrop [Wed, 14 Dec 2011 15:55:31 +0000 (16:55 +0100)]
Add an example for view a platform with paje

8 years agoCosmetics
Navarrop [Wed, 14 Dec 2011 15:54:37 +0000 (16:54 +0100)]
Cosmetics

8 years agoPort old tesh file to modernity.
Navarrop [Mon, 12 Dec 2011 17:46:44 +0000 (18:46 +0100)]
Port old tesh file to modernity.