Logo AND Algorithmique Numérique Distribuée

Public GIT Repository
simgrid.git
11 years agoadd tracing for the trace replay tool. produces a trace, have to
suter [Tue, 11 Sep 2012 16:21:10 +0000 (18:21 +0200)]
add tracing for the trace replay tool. produces a trace, have to
visualize it now.

11 years agoUpdate file example for ls command
navarro [Tue, 11 Sep 2012 12:14:12 +0000 (14:14 +0200)]
Update file example for ls command

11 years agoAdd a function ls to storage
navarro [Tue, 11 Sep 2012 12:03:31 +0000 (14:03 +0200)]
Add a function ls to storage

11 years agodon't need to synchronize processes anymore
suter [Mon, 10 Sep 2012 12:27:06 +0000 (14:27 +0200)]
don't need to synchronize processes anymore

11 years agoslight change in the example that lauchs everything
suter [Mon, 10 Sep 2012 09:02:16 +0000 (11:02 +0200)]
slight change in the example that lauchs everything

11 years agofunctional implementation of trace replay on top of SMPI.
suter [Mon, 10 Sep 2012 09:01:04 +0000 (11:01 +0200)]
functional implementation of trace replay on top of SMPI.
Major modifications required in the input traces:
* get rid off the "p" before the rank of the process (it was useless
BTW)
* add the message size to the recv actions (simplify a lot of thing, and
we can get it easily from the TAU traces)

11 years agoadd some test to not perform some memcpy. Mandatory for trace replay on
suter [Mon, 10 Sep 2012 08:58:13 +0000 (10:58 +0200)]
add some test to not perform some memcpy. Mandatory for trace replay on
top of SMPI. We don't care about data, so the send and recv buffers are
always NULL. memcpy doesn't like that at all.

11 years agoadd a getter to user data attached to a smpi_process
suter [Mon, 10 Sep 2012 08:56:33 +0000 (10:56 +0200)]
add a getter to user data attached to a smpi_process

11 years agoadd a getter on user data attached to a smpi_process
suter [Mon, 10 Sep 2012 08:55:50 +0000 (10:55 +0200)]
add a getter on user data attached to a smpi_process

11 years agoattach time-independent traces to processes when the executable is
suter [Thu, 6 Sep 2012 14:16:14 +0000 (16:16 +0200)]
attach time-independent traces to processes when the executable is
called replay. It takes only one argument that is a file listing the
traces to attach. If there is only one trace in this file, all the
processes try to find their own actions in it. Otherwise, they have
their own trace to read.

11 years agodoxygen correction: SD_READY state doesn't exist anymore, replaced by
suter [Thu, 23 Aug 2012 14:04:45 +0000 (16:04 +0200)]
doxygen correction: SD_READY state doesn't exist anymore, replaced by
SD_SCHEDULABLE.

11 years agoadd a field to attach user data to a smpi process and the associate set
suter [Thu, 12 Jul 2012 15:17:16 +0000 (17:17 +0200)]
add a field to attach user data to a smpi process and the associate set
function

11 years agoAdd a simcall for as and router property
navarro [Thu, 6 Sep 2012 14:06:51 +0000 (16:06 +0200)]
Add a simcall for as and router property

11 years agoAdd 3 msg functions to get and modify property of an AS or router
navarro [Thu, 6 Sep 2012 13:43:39 +0000 (15:43 +0200)]
Add 3 msg functions to get and modify property of an AS or router

11 years agoCosmetics. (Forgot from a previous renaming)
navarro [Thu, 6 Sep 2012 13:29:37 +0000 (15:29 +0200)]
Cosmetics. (Forgot from a previous renaming)

11 years agoFinalize properties on AS.
navarro [Thu, 6 Sep 2012 13:28:40 +0000 (15:28 +0200)]
Finalize properties on AS.

11 years agoAdd properties to AS structure (Not work for now) and use SG_PLATF_AS_INITIALIZER
navarro [Mon, 3 Sep 2012 11:29:29 +0000 (13:29 +0200)]
Add properties to AS structure (Not work for now) and use SG_PLATF_AS_INITIALIZER

11 years agoOups, take the information in the argument structure.
navarro [Wed, 29 Aug 2012 10:11:56 +0000 (12:11 +0200)]
Oups, take the information in the argument structure.

11 years agoRewrite the init of bypass mecanism (tks Martin;)
navarro [Wed, 29 Aug 2012 10:10:43 +0000 (12:10 +0200)]
Rewrite the init of bypass mecanism (tks Martin;)

11 years agoCompletely remove route_t and replace by sg_platf_route_cbarg_t.
navarro [Tue, 28 Aug 2012 12:51:46 +0000 (14:51 +0200)]
Completely remove route_t and replace by sg_platf_route_cbarg_t.

11 years ago[trace] avoiding key clashes on paje links
schnorr [Wed, 22 Aug 2012 21:39:39 +0000 (23:39 +0200)]
[trace] avoiding key clashes on paje links

11 years ago[trace] only fixing some tesh'es, paje header has changed
schnorr [Wed, 22 Aug 2012 21:32:10 +0000 (23:32 +0200)]
[trace] only fixing some tesh'es, paje header has changed

11 years agoadd a little sed script to convert a paje trace (generated with basic smpi flag)...
Augustin Degomme [Tue, 21 Aug 2012 16:11:43 +0000 (18:11 +0200)]
add a little sed script to convert a paje trace (generated with basic smpi flag) into a vite-readable paje trace

11 years agoforgot to add color for computing in previous commit
Augustin Degomme [Tue, 21 Aug 2012 16:10:50 +0000 (18:10 +0200)]
forgot to add color for computing in previous commit

11 years ago[trace] color fields must have type 'color'
schnorr [Tue, 21 Aug 2012 13:37:37 +0000 (15:37 +0200)]
[trace] color fields must have type 'color'

11 years agoadd option to generate states for code outside smpi to allow computation timing ...
Augustin Degomme [Tue, 21 Aug 2012 13:26:57 +0000 (15:26 +0200)]
add option to generate states for code outside smpi to allow computation timing (not completely accurate as some smpi calls are not traced yet)

11 years agoMerge remote-tracking branch 'origin/master'
jean-noel quintin [Tue, 21 Aug 2012 10:51:04 +0000 (11:51 +0100)]
Merge remote-tracking branch 'origin/master'

11 years ago[smpi,simix-network] remove a useless function
jean-noel quintin [Tue, 21 Aug 2012 10:46:15 +0000 (11:46 +0100)]
[smpi,simix-network] remove a useless function

11 years ago[trace] for some reason, simulated time changed in smpi -> fix tesh then
schnorr [Mon, 20 Aug 2012 15:41:53 +0000 (17:41 +0200)]
[trace] for some reason, simulated time changed in smpi -> fix tesh then

11 years ago[trace] updating tesh'es according to header changes
schnorr [Mon, 20 Aug 2012 15:39:26 +0000 (17:39 +0200)]
[trace] updating tesh'es according to header changes

details:
- albeit recent modifications on the header, only a white
space after the events number identification was removed

11 years ago[trace] header re-organization (now with a basic version)
schnorr [Mon, 20 Aug 2012 15:33:25 +0000 (17:33 +0200)]
[trace] header re-organization (now with a basic version)

details:
you can generate a basic version of the header by passing
--cfg=tracing/basic:1 when launching your simulator (considering
you are using other arguments to enable the tracing)

11 years ago[trace] fix color for MPI operations to correctly follow color specification
schnorr [Mon, 20 Aug 2012 13:30:14 +0000 (15:30 +0200)]
[trace] fix color for MPI operations to correctly follow color specification

details:
http://paje.sourceforge.net/download/publication/lang-paje.pdf

11 years ago[trace] new option tracing/basic (used to generate impoverished trace files)
schnorr [Mon, 20 Aug 2012 13:25:20 +0000 (15:25 +0200)]
[trace] new option tracing/basic (used to generate impoverished trace files)

details:
- this option should be used with visualization tools that are
incapable to read the complete Paje file format specification, as
detailed in this file:
http://paje.sourceforge.net/download/publication/lang-paje.pdf

11 years agomodel-checker : init result of simcalls for snapshot comparison done during simcall
Marion Guthmuller [Sat, 18 Aug 2012 16:48:28 +0000 (18:48 +0200)]
model-checker : init result of simcalls for snapshot comparison done during simcall

11 years agomodel-checker : try first to associate each block or fragment with the same positiion...
Marion Guthmuller [Fri, 17 Aug 2012 07:55:59 +0000 (09:55 +0200)]
model-checker : try first to associate each block or fragment with the same positiion in the other heap

11 years agomodel-checker : remove unnecessary step
Marion Guthmuller [Thu, 16 Aug 2012 22:32:52 +0000 (00:32 +0200)]
model-checker : remove unnecessary step

11 years agomodel-checker : equal_to field of blocks/fragments updated twice with match_equals
Marion Guthmuller [Thu, 16 Aug 2012 22:24:49 +0000 (00:24 +0200)]
model-checker : equal_to field of blocks/fragments updated twice with match_equals

11 years agomodelc-checker : reset list of blocks/fragments pairs associated
Marion Guthmuller [Thu, 16 Aug 2012 22:19:08 +0000 (00:19 +0200)]
modelc-checker : reset list of blocks/fragments pairs associated

11 years agomodel-checker : init equal_to field to -1 for each allocated block/fragment at the...
Marion Guthmuller [Thu, 16 Aug 2012 22:13:52 +0000 (00:13 +0200)]
model-checker : init equal_to field to -1 for each allocated block/fragment at the beginning of the heap comparison

11 years agomodel-checker : set size used to 0 when free fragment
Marion Guthmuller [Wed, 8 Aug 2012 10:06:33 +0000 (12:06 +0200)]
model-checker : set size used to 0 when free fragment

11 years agomake it clear that this platform only documents the NREN, not the whole computational...
Martin Quinson [Thu, 16 Aug 2012 12:14:26 +0000 (14:14 +0200)]
make it clear that this platform only documents the NREN, not the whole computational platform

11 years agodafuk did I just see?
Martin Quinson [Wed, 15 Aug 2012 22:54:51 +0000 (00:54 +0200)]
dafuk did I just see?

11 years agoif this line induce a bug (see commit 05cd623), then kill it
Martin Quinson [Wed, 15 Aug 2012 22:37:53 +0000 (00:37 +0200)]
if this line induce a bug (see commit 05cd623), then kill it

11 years agoAdd a master/slave example using a generated platform, and using generated event...
Jean-Baptiste Hervé [Fri, 10 Aug 2012 15:52:53 +0000 (17:52 +0200)]
Add a master/slave example using a generated platform, and using generated event traces

This example fails at the end for the moment, apparently because of autorestart.

11 years agoEvent trace generation: Change interface of constructors
Jean-Baptiste Hervé [Fri, 10 Aug 2012 15:48:42 +0000 (17:48 +0200)]
Event trace generation: Change interface of constructors

The previous interface was not intuitive, even for me. I hope this one is better.
Replace 1 function by 3, and add the choice of the first value for state trace.

11 years agoPlatform generation: add a bittorent example using a generated platform
Jean-Baptiste Hervé [Fri, 10 Aug 2012 13:38:46 +0000 (15:38 +0200)]
Platform generation: add a bittorent example using a generated platform

11 years agoPlatform generation: fex modification of the master/slave example
Jean-Baptiste Hervé [Fri, 10 Aug 2012 12:31:48 +0000 (14:31 +0200)]
Platform generation: fex modification of the master/slave example

Change the topology generation parameter, so the program will have to retry the topology generation, as the first produced graph is not connected.
Correct a typo mistake.

11 years agoPlatform generation: fix the remove links function
Jean-Baptiste Hervé [Fri, 10 Aug 2012 12:29:24 +0000 (14:29 +0200)]
Platform generation: fix the remove links function

11 years agoPlatform generation: record the router id
Jean-Baptiste Hervé [Fri, 10 Aug 2012 12:12:42 +0000 (14:12 +0200)]
Platform generation: record the router id

11 years agodeactivate change induced by re7d52b71aae7 in logging for smpi which caused problems...
Augustin Degomme [Fri, 10 Aug 2012 08:55:18 +0000 (10:55 +0200)]
deactivate change induced by re7d52b71aae7 in logging for smpi which caused problems, waiting for a better idea

11 years agonow that the simcall has been created, use it
Augustin Degomme [Fri, 10 Aug 2012 08:53:24 +0000 (10:53 +0200)]
now that the simcall has been created, use it

11 years agoPlatform generation: add a master/slave example using a generated platform
Jean-Baptiste Hervé [Thu, 9 Aug 2012 15:36:23 +0000 (17:36 +0200)]
Platform generation: add a master/slave example using a generated platform

11 years agoAdd a new simcall to get/set the receiver of a rendez-vous point.
Cristian Rosa [Thu, 9 Aug 2012 13:17:14 +0000 (10:17 -0300)]
Add a new simcall to get/set the receiver of a rendez-vous point.

11 years agoPlatform generation: little modifications to the connectedness check function
Jean-Baptiste Hervé [Thu, 9 Aug 2012 11:56:44 +0000 (13:56 +0200)]
Platform generation: little modifications to the connectedness check function

"Speed improvement" is not strong enough to describe the difference...

11 years agoPlatform generation: "clique" topology does not need to duplicate links
Jean-Baptiste Hervé [Thu, 9 Aug 2012 09:56:56 +0000 (11:56 +0200)]
Platform generation: "clique" topology does not need to duplicate links

11 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Jean-Baptiste Hervé [Thu, 9 Aug 2012 09:15:16 +0000 (11:15 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

11 years agoPlatform generation: generate routes
Jean-Baptiste Hervé [Thu, 9 Aug 2012 09:14:42 +0000 (11:14 +0200)]
Platform generation: generate routes

11 years agoPlatform generation: record the router id given while generation
Jean-Baptiste Hervé [Thu, 9 Aug 2012 09:13:56 +0000 (11:13 +0200)]
Platform generation: record the router id given while generation

11 years agoVarious hacks to unbench the logging to disk when run in SMPI
Martin Quinson [Thu, 9 Aug 2012 07:59:35 +0000 (09:59 +0200)]
Various hacks to unbench the logging to disk when run in SMPI

- First use of weak symbols aliases in our source tree :-/
  I hope it won't induce portability issues
- Only very partially tested, sorry.
  Read: it compiles, that's all I know

11 years agoadd getter/setter functions in simix to access more cleanly the process associated...
Augustin Degomme [Wed, 8 Aug 2012 15:58:02 +0000 (17:58 +0200)]
add getter/setter functions in simix to access more cleanly the process associated to the mailbox for permanent receive mode

11 years agoPlatform generation: Make link labeling work
Jean-Baptiste Hervé [Wed, 8 Aug 2012 14:49:00 +0000 (16:49 +0200)]
Platform generation: Make link labeling work

Also check if the link is labeled when the callbacks have been called.

11 years agoadd missing includes
Augustin Degomme [Wed, 8 Aug 2012 13:37:17 +0000 (15:37 +0200)]
add missing includes

11 years agoPlatform generation: add some documentation
Jean-Baptiste Hervé [Wed, 8 Aug 2012 12:57:22 +0000 (14:57 +0200)]
Platform generation: add some documentation

11 years agoTrace generation: add some documentation
Jean-Baptiste Hervé [Wed, 8 Aug 2012 12:56:42 +0000 (14:56 +0200)]
Trace generation: add some documentation

11 years agoFactorize route ASroute bypassRoute and bypassASroute from sg_platf.
navarro [Wed, 8 Aug 2012 12:41:22 +0000 (14:41 +0200)]
Factorize route ASroute bypassRoute and bypassASroute from sg_platf.
Replace char* gw_src/dst for edge.

11 years agoFirst example for bypass platform wit sg_platf_new* functions.
navarro [Wed, 8 Aug 2012 12:08:58 +0000 (14:08 +0200)]
First example for bypass platform wit sg_platf_new* functions.

11 years agoAdd a MSG_mailbox_set_async function to allow to set a mailbox to eagerly receive...
Augustin Degomme [Wed, 8 Aug 2012 09:18:40 +0000 (11:18 +0200)]
Add a MSG_mailbox_set_async function to allow to set a mailbox to eagerly receive messages (the message is sent without waiting for the receive)

11 years agoRemove link_list from surf_routing.c and add it into the structure of *route and...
navarro [Wed, 8 Aug 2012 08:33:54 +0000 (10:33 +0200)]
Remove link_list from surf_routing.c and add it into the structure of *route and *bypassRoute

11 years agomodel-checker : MC_ignore_init in MSG for ucontext
Marion Guthmuller [Wed, 8 Aug 2012 07:50:52 +0000 (09:50 +0200)]
model-checker : MC_ignore_init in MSG for ucontext

11 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Augustin Degomme [Tue, 7 Aug 2012 16:07:59 +0000 (18:07 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

11 years agoadd an "smpi/async_small_thres" configure option to smpi, to allow to toy with the...
Augustin Degomme [Tue, 7 Aug 2012 15:56:58 +0000 (17:56 +0200)]
add an "smpi/async_small_thres" configure option to smpi, to allow to toy with the threshold used to determine whether a message has to be sent eagerly (without waiting for the receiver) or not. The default value is 0, to deactivate this behavior for now. (note: this is independent from the "detached" state that is for now used for messages < 64*1024 bytes, which should become a new config option also)

11 years agoadd an immediate asynchronous send possibility for messages. This can be set by addin...
Augustin Degomme [Tue, 7 Aug 2012 15:53:48 +0000 (17:53 +0200)]
add an immediate asynchronous send possibility for messages. This can be set by adding a permanent receiver to a mailbox. This will be used by default in smpi (commit to come), and proposed for msg

Conflicts:
src/simix/smx_network.c

11 years agoRemove unused structure and function
navarro [Tue, 7 Aug 2012 15:45:13 +0000 (17:45 +0200)]
Remove unused structure and function

11 years agofix a bug causing surf to sometimes loop forever
Augustin Degomme [Tue, 7 Aug 2012 12:08:21 +0000 (14:08 +0200)]
fix a bug causing surf to sometimes loop forever

11 years agoCompletely remove surfxml_callback.
navarro [Tue, 7 Aug 2012 14:32:00 +0000 (16:32 +0200)]
Completely remove surfxml_callback.
Clean the way to create arg for the process.

11 years agoPlatform generation : REALLY check if the graph is connected
Jean-Baptiste Hervé [Tue, 7 Aug 2012 09:44:39 +0000 (11:44 +0200)]
Platform generation : REALLY check if the graph is connected

11 years agoMore cleaning for surfxml callback (property and trace*)
navarro [Mon, 6 Aug 2012 16:28:01 +0000 (18:28 +0200)]
More cleaning for surfxml callback (property and trace*)

11 years agoCleanUp unused xbt_dynar_t from callback
navarro [Mon, 6 Aug 2012 14:35:49 +0000 (16:35 +0200)]
CleanUp unused xbt_dynar_t from callback

11 years agoMore condensed debug...
Jean-Baptiste Hervé [Mon, 6 Aug 2012 16:00:39 +0000 (18:00 +0200)]
More condensed debug...

11 years agoEvent generator: Correct a mistake and add tiny debug
Jean-Baptiste Hervé [Mon, 6 Aug 2012 15:32:08 +0000 (17:32 +0200)]
Event generator: Correct a mistake and add tiny debug

11 years agoAdd function sg_platf_new_* for *route and bypass*route.
navarro [Mon, 6 Aug 2012 09:38:35 +0000 (11:38 +0200)]
Add function sg_platf_new_* for *route and bypass*route.

11 years agoPlatform generation : Add a function to remove links in the graph
Jean-Baptiste Hervé [Mon, 6 Aug 2012 09:23:00 +0000 (11:23 +0200)]
Platform generation : Add a function to remove links in the graph

11 years agoPlatform generation : add a function to check if the graph is connected
Jean-Baptiste Hervé [Mon, 6 Aug 2012 07:33:08 +0000 (09:33 +0200)]
Platform generation : add a function to check if the graph is connected

11 years agoand now, get the execution sampling macros work also when the user gives a maximal...
Martin Quinson [Sat, 4 Aug 2012 15:41:13 +0000 (17:41 +0200)]
and now, get the execution sampling macros work also when the user gives a maximal stderr AND a minimal execution count (hopefully)

11 years agodafuk? don't mix seconds and flops!
Martin Quinson [Sat, 4 Aug 2012 15:15:42 +0000 (17:15 +0200)]
dafuk? don't mix seconds and flops!

SMPI_SAMPLE_DELAY parameter were an amount of flops. Consider it as a
  delay instead.
Introduce SMPI_SAMPLE_FLOPS to report an amount of flops into the
  simulo (and use it in the replay part of SMPI)

11 years agorewrite the MPI execution sampling facility (previous implem was deeply bugged)
Martin Quinson [Sat, 4 Aug 2012 15:00:46 +0000 (17:00 +0200)]
rewrite the MPI execution sampling facility (previous implem was deeply bugged)

11 years agorewrite this example to betterly demo SMPI_SAMPLE_LOCAL and SMPI_SAMPLE_GLOBAL
Martin Quinson [Sat, 4 Aug 2012 14:58:27 +0000 (16:58 +0200)]
rewrite this example to betterly demo SMPI_SAMPLE_LOCAL and SMPI_SAMPLE_GLOBAL

11 years agostop being protective against things we cannot deal with. Let the segfault happen
Martin Quinson [Sat, 4 Aug 2012 13:04:45 +0000 (15:04 +0200)]
stop being protective against things we cannot deal with. Let the segfault happen

11 years agovariable renaming to try to understand this code
Martin Quinson [Sat, 4 Aug 2012 08:22:09 +0000 (10:22 +0200)]
variable renaming to try to understand this code

11 years agomake an error message marginally more understandable to the users
Martin Quinson [Sat, 4 Aug 2012 08:12:23 +0000 (10:12 +0200)]
make an error message marginally more understandable to the users

11 years agoUse the function sg_platf_new_linkctn when parsing platform
navarro [Fri, 3 Aug 2012 14:44:09 +0000 (16:44 +0200)]
Use the function sg_platf_new_linkctn when parsing platform

11 years agoPlatform generation: Cluster generation should work
Jean-Baptiste Hervé [Fri, 3 Aug 2012 14:28:14 +0000 (16:28 +0200)]
Platform generation: Cluster generation should work

11 years agoCheck if string is NULL before a strcmp
Jean-Baptiste Hervé [Fri, 3 Aug 2012 14:25:40 +0000 (16:25 +0200)]
Check if string is NULL before a strcmp

11 years agoFirst platform step for tag random
navarro [Fri, 3 Aug 2012 13:58:15 +0000 (15:58 +0200)]
First platform step for tag random

11 years agoPlatform generation can now be used with MSG
Jean-Baptiste Hervé [Fri, 3 Aug 2012 12:00:49 +0000 (14:00 +0200)]
Platform generation can now be used with MSG

Some stuff had to be done by SIMIX and MSG right after the XML platform parsing. It is now done by callbacks, registered in SURF at initialization. So that stuff is also done when you create a random platform with the generator.
Add some ugly code to avoid the deletion of these registered callbacks before the parsing.

11 years agoRevert "[trace] something might have failed during process creation, reflect that...
Martin Quinson [Thu, 2 Aug 2012 23:03:17 +0000 (01:03 +0200)]
Revert "[trace] something might have failed during process creation, reflect that in traces"

This reverts commit 75d4e75aa8b07c422a88923449e5aa635912a8a5.

Rational: I see the motivation to add this call here, but it breaks 6
tests here. I hope that LucasS will fix it properly when possible.

11 years agomore verbose error messages
Martin Quinson [Thu, 2 Aug 2012 23:00:45 +0000 (01:00 +0200)]
more verbose error messages

11 years agocleanups
Martin Quinson [Thu, 2 Aug 2012 22:59:40 +0000 (00:59 +0200)]
cleanups

- Add some newly create test files
- somehow sort the content of the file alphabetically within sections

11 years agouseless cosmetic in this code that is full of surprises
Martin Quinson [Thu, 2 Aug 2012 22:01:43 +0000 (00:01 +0200)]
useless cosmetic in this code that is full of surprises

11 years agotypo--
Martin Quinson [Thu, 2 Aug 2012 21:59:27 +0000 (23:59 +0200)]
typo--