1 /*! \page faq Frequently Asked Questions
3 \htmlinclude .FAQ.doc.toc
5 \section faq_simgrid I'm new to SimGrid. I have some questions. Where should I start?
7 You are at the right place... Having a look to these
8 <a href="http://www.loria.fr/~quinson/articles/simgrid-tutorial.pdf">the tutorial slides</a>
9 (or to these <a href="http://graal.ens-lyon.fr/~alegrand/articles/slides_g5k_simul.pdf">old slides</a>,
11 <a href="http://graal.ens-lyon.fr/~alegrand/articles/Simgrid-Introduction.pdf">"obsolete" slides</a>)
12 may give you some insights on what SimGrid can help you to do and what
13 are its limitations. Then you definitely should read the \ref
14 MSG_examples. The \ref GRAS_tut can also help you.
16 If you are stuck at any point and if this FAQ cannot help you, please drop us a
17 mail to the user mailing list: <simgrid-user@lists.gforge.inria.fr>.
19 \subsection faq_interfaces What is the difference between MSG, SimDag, and GRAS? Do they serve the same purpose?
21 It depend on how you define "purpose", I guess ;)
23 They all allow you to build a prototype of application which you can run
24 within the simulator afterward. They all share the same simulation kernel,
25 which is the core of the SimGrid project. They differ by the way you express
28 With SimDag, you express your code as a collection of interdependent
29 parallel tasks. So, in this model, applications can be seen as a DAG of
30 tasks. This is the interface of choice for people wanting to port old
31 code designed for SimGrid v1 or v2 to the framework current version.
33 With both GRAS and MSG, your application is seen as a set of communicating
34 processes, exchanging data by the way of messages and performing computation
37 The difference between both is that MSG is somehow easier to use, but GRAS
38 is not limited to the simulator. Once you're done writing your GRAS code,
39 you can run your code both in the simulator or on a real platform. For this,
40 there is two implementations of the GRAS interface, one for simulation, one
41 for real execution. So, you just have to relink your code to chose one of
44 \subsection faq_generic First steps with SimGrid
46 If you decide to go for the MSG interface, please read carefully the
47 \ref MSG_examples. You'll find in \ref MSG_ex_master_slave a very
48 simple consisting of a master (that owns a bunch of tasks and
49 distributes them) , some slaves (that process tasks whenever they
50 receive one) and some forwarder agents (that simply pass the tasks
51 they receive to some slaves).
53 If you decide to go for the GRAS interface, you should definitively
54 read the \ref GRAS_tut. The first section constitutes an introduction
55 to the tool and presents the model we use. The second section
56 constitutes a complete step-by-step tutorial building a distributed
57 application from the beginning and exemplifying most of the GRAS
58 features in the process. The last section groups some HOWTOS
59 highlighting a given feature of the framework in a more concise way.
61 If you decide to go for another interface, I'm afraid your only sources
62 of information will be the source code and the mailing lists...
64 \subsection faq_visualization Visualizing and analyzing the results
66 It is sometime convenient to "see" how the agents are behaving. If you
67 like colors, you can use <tt>tools/MSG_visualization/colorize.pl </tt>
68 as a filter to your MSG outputs. It works directly with INFO. Beware,
69 INFO() prints on stderr. Do not forget to redirect if you want to
70 filter (e.g. with bash):
72 ./msg_test small_platform.xml small_deployment.xml 2>&1 | ../../tools/MSG_visualization/colorize.pl
75 We also have a more graphical output. Have a look at MSG_paje_output(). It
76 generates an input to <a href="http://www-id.imag.fr/Logiciels/paje/">Paje</a>.
79 <a href="Paje_MSG_screenshot.jpg"><img src="Paje_MSG_screenshot_thn.jpg"></a>
83 Visualization with Paje can be seen as a kind of postmortem
84 analysis. However, as soon as you start playing with big simulations,
85 you'll realize that processing such output is kind of tricky. There is
86 so much generic information that it is hard to find the information
89 As a matter of fact, logging really depends on simulations (e.g. what
90 kind of events is important...). That is why we do not propose a big
91 dump of your whole simulation (it would slow everything down) but give
92 you neat tools to structure you logs. Have a look at \ref XBT_log. In
93 fact, rather than a post-mortem analysis, you may want to do it on the
94 fly. The process you are running can do whatever you want. Have you
95 thought about adding a global structure where you directly compute the
96 information that are really important rather than writing everything
97 down and then processing huge files?
99 \subsection faq_C Argh! Do I really have to code in C?
101 Up until now, there is no binding for other languages. If you use C++,
102 you should be able to use the SimGrid library as a standard C library
103 and everything should work fine (simply <i>link</i> against this
104 library; recompiling SimGrid with a C++ compiler won't work and it
105 wouldn't help if you could).
107 In fact, we are currently working on Java bindings of MSG to allow
108 all the undergrad students of the world to use this tool. This is a
109 little more tricky than I would have expected, but the work is moving
110 fast forward [2006/05/13]. More languages are evaluated, but for now,
111 we do not feel a real demand for any other language. Please speak up!
113 \section faq_installation Installing the SimGrid library
115 Many people have been asking me questions on how to use SimGrid. Quite
116 often, the questions were not really about SimGrid but on the
117 installation process. This section is intended to help people that are
118 not familiar with compiling C files under UNIX. If you follow these
119 instructions and still have some troubles, drop an e-mail to
120 <simgrid-user@lists.gforge.inria.fr>.
122 \subsection faq_compiling Compiling SimGrid from a stable archive
124 First of all, you need to download the latest version of SimGrid from
125 <a href="http://gforge.inria.fr/frs/?group_id=12">here</a>.
126 Suppose you have uncompressed SimGrid in some temporary location of
127 your home directory (say <tt>/home/joe/tmp/simgrid-3.0.1 </tt>). The
128 simplest way to use SimGrid is to install it in your home
129 directory. Change your directory to
130 <tt>/home/joe/tmp/simgrid-3.0.1</tt> and type
133 ./configure --prefix=$HOME
138 If at some point, something fails, check the section \ref faq_trouble_compil .
139 If it does not help, you can report this problem to the
140 list but, please, avoid sending a laconic mail like "There is a problem. Is it
141 okay?". Send the config.log file which is automatically generated by
142 configure. Try to capture both the standard output and the error output of the
143 <tt>make</tt> command with <tt>script</tt>. There is no way for us to help you
144 without the relevant bits of information.
146 Now, the following directory should have been created :
148 \li <tt>/home/joe/doc/simgrid/html/</tt>
149 \li <tt>/home/joe/lib/</tt>
150 \li <tt>/home/joe/include/</tt>
152 SimGrid is not a binary, it is a library. Both a static and a dynamic
153 version are available. Here is what you can find if you try a <tt>ls
156 \verbatim libsimgrid.a libsimgrid.la libsimgrid.so libsimgrid.so.0 libsimgrid.so.0.0.1
159 Thus, there is two ways to link your program with SimGrid:
160 \li Either you use the static version, e.g
161 \verbatim gcc libsimgrid.a -o MainProgram MainProgram.c
163 In this case, all the SimGrid functions are directly
164 included in <tt>MainProgram</tt> (hence a bigger binary).
165 \li Either you use the dynamic version (the preferred method)
166 \verbatim gcc -lsimgrid -o MainProgram MainProgram.c
168 In this case, the SimGrid functions are not included in
169 <tt>MainProgram</tt> and you need to set your environment
170 variable in such a way that <tt>libsimgrid.so</tt> will be
171 found at runtime. This can be done by adding the following
172 line in your .bashrc (if you use bash and if you have
173 installed the SimGrid libraries in your home directory):
174 \verbatim export LD_LIBRARY_PATH=$HOME/lib/:$LD_LIBRARY_PATH
177 \subsection faq_compiling_java Java bindings don't get compiled
179 The configure script detects automatically whether you have the
180 softwares needed to use the Java bindings or not. At the end of the
181 configure, you can see the configuration picked by the script, which
182 should look similar to
183 \verbatim Configuration of package simgrid' (version 3.3.4-svn) on
186 Compiler: gcc (version: )
188 CFlags: -O3 -finline-functions -funroll-loops -fno-strict-aliasing -Wall -Wunused -Wmissing-prototypes -Wmissing-declarations -Wpointer-arith -Wchar-subscripts -Wcomment -Wformat -Wwrite-strings -Wno-unused-function -Wno-unused-parameter -Wno-strict-aliasing -Wno-format-nonliteral -Werror -g3
192 Context backend: ucontext
199 In this example, Java backends won't be compiled.
201 On Debian-like systems (which includes ubuntu), you need the following
202 packages: sun-java6-jdk libgcj10-dev. If you cannot find the
203 libgcj10-dev, try another version, like libgcj9-dev (on Ubuntu before
204 9.10) or libgcj11-dev (not released yet, but certainly one day).
205 Please note that you need to activate the contrib and non-free
206 repositories in Debian, and the universe ones in Ubuntu. Java comes at
209 \subsection faq_compiling_snapshoot SimGrid development snapshots
211 We have very high standards on software quality, and we are reluctant releasing
212 a stable release as long as there is still some known bug in the code base. In
213 addition, we added quite an extensive test base, making sure that we correctly
214 test the most important parts of the tool.
216 As an unfortunate conclusion, there may be some time between the stable
217 releases. If you want to benefit from the most recent features we introduced,
218 but don't want to take the risk of an untested version from the SVN, then
219 development snapshots are done for you.
221 These are pre-releases of SimGrid that still fail some tests about features
222 that almost nobody use, or on platforms not being in our core target (which is
223 Linux, Mac, other Unixes and Windows, from the most important to the less
224 one). That means that using this development releases should be safe for most
227 These archives can be found on
228 <a href="http://www.loria.fr/~quinson/simgrid.html">this web page</a>. Once you
229 got the lastest archive, you can compile it just like any archive (see above).
231 \subsection faq_compiling_svn Compiling SimGrid from the SVN
233 The project development takes place in the SVN, where all changes are
234 committed when they happen. Then every once in a while, we make sure that the
235 code quality meets our standard and release an archive from the code in the
236 SVN. We afterward go back to the development in the SVN. So, if you need a
237 recently added feature and can afford some little problem with the stability
238 of the lastest features, you may want to use the SVN version instead of a
241 For that, you first need to get the "simgrid" module from
242 <a href="http://gforge.inria.fr/scm/?group_id=12">here</a>.
244 You won't find any <tt>configure</tt> and a few other things
245 (<tt>Makefile.in</tt>'s, documentation, ...) will be missing as well. The
246 reason for that is that all these files have to be regenerated using the
247 latest versions of <tt>autoconf</tt>, <tt>libtool</tt>, <tt>automake</tt>
248 (>1.9) and <tt>doxygen</tt> (>1.4). To generate the <tt>configure</tt> and
249 the <tt>Makefile.in</tt>'s, you just have to launch the <tt>bootstrap</tt>
250 command that resides in the top of the source tree. Then just follow the
251 instructions of Section \ref faq_compiling.
253 We insist on the fact that you really need the latest versions of
254 autoconf, automake and libtool. Doing this step on exotic architectures/systems
255 (i.e. anything different from a recent linux distribution) may be
256 ... uncertain. If you need to compile the SVN version on a machine where all these
257 dependencies are not met, the easiest is to do <tt>make dist</tt> in the SVN
258 directory of another machine where all dependencies are met. It will create an
259 archive you may deploy on other sites just as a regular stable release.
261 In summary, the following commands will checkout the SVN, regenerate the
262 configure script and friends, configure SimGrid and build it.
264 \verbatim svn checkout svn://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk simgrid
267 ./configure --enable-maintainer-mode --prefix=<where to install SimGrid>
270 Then, if you want to install SimGrid on the current box, just do:
271 \verbatim make install \endverbatim
273 If you want to build an snapshot of the SVN to deploy it on another box (for
274 example because the other machine don't have the autotools), do:
275 \verbatim make dist \endverbatim
277 Moreover, you should never call the autotools manually since you must run
278 them in a specific order with specific arguments. Most of the times, the
279 makefiles will automatically call the tools for you. When it's not possible
280 (such as the first time you checkout the SVN), use the ./bootstrap command
281 to call them explicitly.
284 \subsection faq_setting_MSG Setting up your own MSG code
286 Do not build your simulator by modifying the SimGrid examples. Go
287 outside the SimGrid source tree and create your own working directory
288 (say <tt>/home/joe/SimGrid/MyFirstScheduler/</tt>).
290 Suppose your simulation has the following structure (remember it is
291 just an example to illustrate a possible way to compile everything;
292 feel free to organize it as you want).
294 \li <tt>sched.h</tt>: a description of the core of the
295 scheduler (i.e. which functions are can be used by the
296 agents). For example we could find the following functions
297 (master, forwarder, slave).
299 \li <tt>sched.c</tt>: a C file including <tt>sched.h</tt> and
300 implementing the core of the scheduler. Most of these
301 functions use the MSG functions defined in section \ref
304 \li <tt>masterslave.c</tt>: a C file with the main function, i.e.
305 the MSG initialization (MSG_global_init()), the platform
306 creation (e.g. with MSG_create_environment()), the
307 deployment phase (e.g. with MSG_function_register() and
308 MSG_launch_application()) and the call to
311 To compile such a program, we suggest to use the following
312 Makefile. It is a generic Makefile that we have used many times with
313 our students when we teach the C language.
317 masterslave: masterslave.o sched.o
319 INSTALL_PATH = $$HOME
321 PEDANTIC_PARANOID_FREAK = -O0 -Wshadow -Wcast-align \
322 -Waggregate-return -Wmissing-prototypes -Wmissing-declarations \
323 -Wstrict-prototypes -Wmissing-prototypes -Wmissing-declarations \
324 -Wmissing-noreturn -Wredundant-decls -Wnested-externs \
325 -Wpointer-arith -Wwrite-strings -finline-functions
326 REASONABLY_CAREFUL_DUDE = -Wall
327 NO_PRAYER_FOR_THE_WICKED = -w -O2
328 WARNINGS = $(REASONABLY_CAREFUL_DUDE)
329 CFLAGS = -g $(WARNINGS)
331 INCLUDES = -I$(INSTALL_PATH)/include
332 DEFS = -L$(INSTALL_PATH)/lib/
333 LDADD = -lm -lsimgrid
337 $(CC) $(INCLUDES) $(DEFS) $(CFLAGS) $^ $(LIBS) $(LDADD) -o $@
340 $(CC) $(INCLUDES) $(DEFS) $(CFLAGS) -c -o $@ $<
343 rm -f $(BIN_FILES) *.o *~
349 The first two lines indicates what should be build when typing make
350 (<tt>masterslave</tt>) and of which files it is to be made of
351 (<tt>masterslave.o</tt> and <tt>sched.o</tt>). This makefile assumes
352 that you have set up correctly your <tt>LD_LIBRARY_PATH</tt> variable
353 (look, there is a <tt>LDADD = -lm -lsimgrid</tt>). If you prefer using
354 the static version, remove the <tt>-lsimgrid</tt> and add a
355 <tt>$(INSTALL_PATH)/lib/libsimgrid.a</tt> on the next line, right
356 after the <tt>LIBS = </tt>.
358 More generally, if you have never written a Makefile by yourself, type
359 in a terminal : <tt>info make</tt> and read the introduction. The
360 previous example should be enough for a first try but you may want to
361 perform some more complex compilations...
363 \subsection faq_setting_GRAS Setting up your own GRAS code
365 If you use the GRAS interface instead of the MSG one, then previous section
366 is not the better source of information. Instead, you should check the GRAS
367 tutorial in general, and the \ref GRAS_tut_tour_setup in particular.
369 \section faq_cmake CMAKE
371 \subsection faq_intro Some generalitty
373 \subsubsection faq_intro1 What is Cmake?
375 CMake is a family of tools designed to build, test and package software. CMake is used to control the software compilation process using simple platform and compiler independent configuration files. CMake generates native makefiles and workspaces that can be used in the compiler environment of your choice. For more information see official web site <a href="http://www.cmake.org/">here</a>.
377 \subsubsection faq_intro2 Why cmake?
379 CMake permits to developers to compil projects on different plateform. Then many tools are embedded like ctest for making test, a link to cdash for vizualise results but also test coverage and bug reports.
381 \subsubsection faq_intro3 What cmake need?
383 CMake needs some prerequists like :
385 \li c, c++ and java compiler regards to developers
386 \li ccmake for graphical used of CMake
387 \li cmake <a href="http://www.cmake.org/cmake/resources/software.html">(download page)</a>
389 \subsubsection faq_intro4 Cmake vs Autotools...
393 \subsection faq_cmakeoption Cmake options
395 \subsubsection faq_cmakeoption1 Liste of options
398 "cmake -D[name]=[value] ... ./"
400 [name] disable_gtnets [value] ON/OFF or TRUE/FALSE or 1/0
401 disable_java ON/OFF or TRUE/FALSE or 1/0
402 disable_lua ON/OFF or TRUE/FALSE or 1/0
403 disable_ruby ON/OFF or TRUE/FALSE or 1/0
405 enable_compile_optimizations ON/OFF or TRUE/FALSE or 1/0
406 enable_compile_warnings ON/OFF or TRUE/FALSE or 1/0
407 enable_maintainer_mode ON/OFF or TRUE/FALSE or 1/0
409 supernovae ON/OFF or TRUE/FALSE or 1/0
411 gtnets_path <path_to_gtnets_directory>
412 prefix <path_to_install_directory>
413 with_context auto/ucontext/pthread/window
416 \subsubsection faq_cmakeoption2 Options explaination
418 \li disable_gtnets : set to true implie that user doesn't want to use gtnets.
420 \li disable_java : set to true implie that user doesn't want to add java langage into simgrid compilation.
422 \li disable_lua : set to true implie that user doesn't want to add lua langage into simgrid compilation.
424 \li disable_ruby : set to true implie that user doesn't want to add ruby langage into simgrid compilation.
426 \li enable_compile_optimizations : add flags "-O3 -finline-functions -funroll-loops -fno-strict-aliasing"
428 \li enable_compile_warnings : add flags "-Wall -Wunused -Wmissing-prototypes -Wmissing-declarations -Wpointer-arith -Wchar-subscripts -Wcomment -Wformat -Wwrite-strings -Wno-unused-function -Wno-unused-parameter -Wno-strict-aliasing -Wno-format-nonliteral -Werror"
430 \li enable_maintainer_mode : set to true make doc and remake files with flex flexml.
433 /src/gras/DataDesc/ddt_parse.yy.c
434 /src/surf/simgrid_dtd.c
436 /src/simdag/dax_dtd.c
437 /include/surf/simgrid_dtd.h
438 /include/xbt/graphxml.h
439 /src/simdag/dax_dtd.h
441 \li supernovae : set to true make one file for each lib and compile with those generated files.
444 /src/supernovae_gras.c
445 /src/supernovae_smpi.c
447 \li gtnets_path : Path to gtnets install directory (ex /usr)
449 \li prefix : Path where are installed lib/ doc/ and include/ directories (ex /usr/local)
451 \li with context : specify which context the user wants to use.
453 \subsubsection faq_cmakeoption3 Initialisation
455 Those options are initialized the first time you launch \"cmake ./\" whithout specified option.
459 enable_maintainer_mode off
463 enable_compile_warnings off
464 enable_compile_optimizations off
469 \subsubsection faq_cmakeoption4 Option's cache and how to reset?
471 When options have been set they are keep into a cache file named \"CMakeCache.txt\". So if you want
472 reset values you just delete this file located to the project directory.
474 \subsection faq_cmakecompilation Cmake compilation
476 \subsubsection faq_cmakecompilation1 With command line.
479 cmake -D[name]=[value] ... ./
483 \subsubsection faq_cmakecompilation2 With ccmake tool.
488 Then follow instructions.
490 \subsubsection faq_cmakecompilation3 Resume of command line
494 cmake ./ configure the project
495 make build all tagets
496 make test test all targets and summarize
497 make package make the distrib
498 make install-simgrid install the project (doc/ lib/ include/)
499 make clean" clean all targets
502 When the project have been succesfully compiling and build you can make tests.
506 ctest launch only tests
508 ctest -D Continuous(Start|Update|Configure|Build)
509 ctest -D Continuous(Test|Coverage|MemCheck|Submit)
510 ctest -D Experimental
511 ctest -D Experimental(Start|Update|Configure|Build)
512 ctest -D Experimental(Test|Coverage|MemCheck|Submit)
514 ctest -D Nightly(Start|Update|Configure|Build)
515 ctest -D Nightly(Test|Coverage|MemCheck|Submit)
516 ctest -D NightlyMemoryCheck
519 \subsubsection faq_cmakecompilation4 Examples for different mode.
523 cmake -Denable_maintainer_mode=on ./
524 \verbatim GTnetS doesn't works : set -Ddisable_gtnets=on
525 with_context auto change to ucontext
528 Make : src/simgrid.jar with : /usr/bin/javac
529 Make examples/java with : /usr/bin/javac
531 Configuration of package `simgrid' (revision 7228M) on arch (=4):
533 SITE : Linux_Ubuntu 9.10_x86_64
535 Compiler: c++ : /usr/bin/c++
536 version: c++ (Ubuntu 4.4.1-4ubuntu9) 4.4.1
538 version: gcc (Ubuntu 4.4.1-4ubuntu9) 4.4.1
544 Context backend: ucontext
554 Simgrid dependencies: dl -llua5.1
555 Gras dependencies: pthread
559 USER_PREFIX: /usr/local
560 INSTALL_PREFIX: /usr/local
564 -- Build files have been written to: /home/navarrop/Bureau/simgrid-trunk
569 cmake -Dsupernovae=on ./
570 \verbatim GTnetS doesn't works : set -Ddisable_gtnets=on
571 with_context auto change to ucontext
574 Make : src/simgrid.jar with : /usr/bin/javac
575 Make examples/java with : /usr/bin/javac
577 Configuration of package `simgrid' (revision 7228M) on arch (=4):
578 BUILDNAME : SUPERNOVAE
579 SITE : Linux_Ubuntu 9.10_x86_64
581 Compiler: c++ : /usr/bin/c++
582 version: c++ (Ubuntu 4.4.1-4ubuntu9) 4.4.1
584 version: gcc (Ubuntu 4.4.1-4ubuntu9) 4.4.1
586 CFlags: -O3 -finline-functions -funroll-loops -fno-strict-aliasing -Wall -Wunused -Wmissing-prototypes -Wmissing-declarations -Wpointer-arith -Wchar-subscripts -Wcomment -Wformat -Wwrite-strings -Wno-unused-function -Wno-unused-parameter -Wno-strict-aliasing -Wno-format-nonliteral -Werror -g3
590 Context backend: ucontext
600 Simgrid dependencies: dl -llua5.1
601 Gras dependencies: pthread
605 USER_PREFIX: /usr/local
606 INSTALL_PREFIX: /usr/local
610 -- Build files have been written to: /home/navarrop/Bureau/simgrid-trunk
615 cmake -Dgtnets_path=/home/navarrop/Bureau/usr/ ./
616 \verbatim with_context auto change to ucontext
619 Make : src/simgrid.jar with : /usr/bin/javac
620 Make examples/java with : /usr/bin/javac
622 Configuration of package `simgrid' (revision 7228M) on arch (=4):
624 SITE : Linux_Ubuntu 9.10_x86_64
626 Compiler: c++ : /usr/bin/c++
627 version: c++ (Ubuntu 4.4.1-4ubuntu9) 4.4.1
629 version: gcc (Ubuntu 4.4.1-4ubuntu9) 4.4.1
631 CFlags: -L/home/navarrop/Bureau/usr/lib -I/home/navarrop/Bureau/usr/include/gtnets -g3
632 CPPFlags: -L/home/navarrop/Bureau/usr/lib -I/home/navarrop/Bureau/usr/include/gtnets
635 Context backend: ucontext
637 path: /home/navarrop/Bureau/usr
645 Simgrid dependencies: dl -llua5.1 -lgtnets
646 Gras dependencies: pthread
650 USER_PREFIX: /usr/local
651 INSTALL_PREFIX: /usr/local
653 INFO -->> Take care to have export LD_LIBRARY_PATH before run make command for make examples with gtnets
654 copy and paste : export LD_LIBRARY_PATH=/home/navarrop/Bureau/usr/lib/:$LD_LIBRARY_PATH
659 -- Build files have been written to: /home/navarrop/Bureau/simgrid-trunk
662 \subsection faq_cmakeinstall How to install with cmake?
664 \subsubsection faq_cmakeinstall1 From svn.
667 cmake -Denable_maintainer_mode=on -Dprefix=/home/navarrop/Bureau/install_simgrid ./
672 \subsubsection faq_cmakeinstall2 From a distrib
675 cmake -Dprefix=/home/navarrop/Bureau/install_simgrid ./
680 \subsection faq_screenshot Screenshot
683 navarrop@caraja:~$ cd Bureau/simgrid-trunk/
684 navarrop@caraja:~/Bureau/simgrid-trunk$ cmake ./
686 GTnetS doesn't works : set -Ddisable_gtnets=on <-|some warnings are printed
687 with_context auto change to ucontext <-|
688 (skaddr) <--info (needed)
689 (sksize) <--info (needed)
690 Make : src/simgrid.jar with : /usr/bin/javac <--info (if java)
691 Make examples/java with : /usr/bin/javac <--info (if java)
693 Configuration of package `simgrid' (revision 7209M) on arch (=4):
694 BUILDNAME : UCONTEXT <-- name of the compilation regarding to cdash
695 SITE : Linux_Ubuntu 9.10_x86_64 <-- distribution of the local machine regarding to cdash
697 Compiler: c++ : /usr/bin/c++
698 version: c++ (Ubuntu 4.4.1-4ubuntu9) 4.4.1
700 version: gcc (Ubuntu 4.4.1-4ubuntu9) 4.4.1
706 Context backend: ucontext
716 Simgrid dependencies: -ldl -llua5.1
717 Gras dependencies: pthread
721 USER_PREFIX: /usr/local
722 INSTALL_PREFIX: /usr/local
726 -- Build files have been written to: /home/navarrop/Bureau/simgrid-trunk
728 Here all options are checked and printed. If it doesn't match with your configuration
729 it is probably due to a wrong configuration.
731 \subsection faq_cmakehowto How to modified sources files for developers
733 \subsubsection faq_cmakehowto1 Add an executable or examples.
735 If you want make an executable you have to create a CMakeList.txt to the src directory.
736 You must specified where to create the executable, source list, dependencies and the name of the binary.
739 cmake_minimum_required(VERSION 2.6)
741 set(EXECUTABLE_OUTPUT_PATH "./")
742 set(LIBRARY_OUTPUT_PATH "${PROJECT_DIRECTORY}/lib")
744 add_executable(get_sender get_sender.c) #add_executable(<name_of_target> <src list>)
746 ### Add definitions for compile
747 target_link_libraries(get_sender simgrid m pthread -fprofile-arcs) #target_link_libraries(<name_of_targe> <dependencies>)
750 Then you have to modified <project/directory>/buildtools/Cmake/src/CMakeMakeExeLib.txt and add
753 add_subdirectory(${PROJECT_DIRECTORY}/<path_where_is_CMakeList.txt>)
756 \subsubsection faq_cmakehowto2 Delete/add sources to lib.
758 If you want modified, add or delete source files from a library you have to edit <project/directory>/buildtools/Cmake/src/CMakeDefinePackages.txt
762 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/MsgException.java
763 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/JniException.java
764 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/NativeException.java
765 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/HostNotFoundException.java
766 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/ProcessNotFoundException.java
767 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/Msg.java
768 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/Process.java
769 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/Host.java
770 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/Task.java
771 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/MsgNative.java
772 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/ApplicationHandler.java
773 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/Sem.java
777 \subsubsection faq_cmakehowto3 Add test
779 If you want modified, add or delete tests you have to edit <project/directory>/buildtools/Cmake/src/CMakeTest.txt
780 with this function : ADD_TEST(<name> <bin> <ARGS>)
783 add_test(test-simdag-1 ${PROJECT_DIRECTORY}/testsuite/simdag/sd_test --cfg=path:${PROJECT_DIRECTORY}/testsuite/simdag small_platform_variable.xml)
786 \subsection faq_cmakeExplain Explaination of sources files for cmake
790 Those files are the "main parts". One located at the project directory call all the cmake sources files. The others
791 are little projects called by the first for make examples.
793 \li CMakeCompleteInFiles.txt
795 Complete all .in files and define Variables for h files
799 This file make the html documentation.
801 \li CMakeMakeExeLib.txt
803 Here are callled all "CMakeLists.txt" for make executables and libraries.
805 \li CMakePrintArgs.txt
807 This file is called at the end of the build for summarize environment variables.
809 \li CMakeDefinePackages.txt
811 Here is defined sources packages for compiling libs.
815 Defined flags which are used for compiling sources.
817 \li CMakeSupernovae.txt
819 Here are made files for the supernovae mode.
823 Here is defined packages for install simgrid and make a distribution.
827 Part for generated sources from flex and flexml.
831 Here are defined options and initialized values.
835 All tests are listed.
837 \li CTestConfig.cmake
839 Properties which link tests with dashboard.
841 \subsection faq_cmakeList List of files added for cmake
843 Here is a list of files involved into cmake build (relative to project directory path) :
847 ./buildtools/Cmake/src/CMakeCompleteInFiles.txt
848 ./buildtools/Cmake/src/CMakeDocs.txt
849 ./buildtools/Cmake/src/CMakeMakeExeLib.txt
850 ./buildtools/Cmake/src/CMakePrintArgs.txt
851 ./buildtools/Cmake/src/CMakeDefinePackages.txt
852 ./buildtools/Cmake/src/CMakeFlags.txt
853 ./buildtools/Cmake/src/CMakeSupernovae.txt
854 ./buildtools/Cmake/src/CMakeDistrib.txt
855 ./buildtools/Cmake/src/CMakeFLEXml.txt
856 ./buildtools/Cmake/src/CMakeOption.txt
857 ./buildtools/Cmake/src/CMakeTest.txt
858 ./buildtools/Cmake/src/CTestConfig.cmake
860 Test files for define properties :
861 ./buildtools/Cmake/prog_test/prog_GRAS_ARCH.c
862 ./buildtools/Cmake/prog_test/prog_max_size.c
863 ./buildtools/Cmake/prog_test/prog_sem_init.c
864 ./buildtools/Cmake/prog_test/prog_stackgrowth.c
865 ./buildtools/Cmake/prog_test/prog_vsnprintf.c
866 ./buildtools/Cmake/prog_test/prog_AC_CHECK_MCSC.c
867 ./buildtools/Cmake/prog_test/prog_GRAS_CHECK_STRUCT_COMPACTION.c
868 ./buildtools/Cmake/prog_test/prog_mutex_timedlock.c
869 ./buildtools/Cmake/prog_test/prog_sem_timedwait.c
870 ./buildtools/Cmake/prog_test/prog_stacksetup.c
871 ./buildtools/Cmake/prog_test/prog_getline.c
872 ./buildtools/Cmake/prog_test/prog_gtnets.cpp
873 ./buildtools/Cmake/prog_test/prog_printf_null.c
874 ./buildtools/Cmake/prog_test/prog_snprintf.c
875 ./buildtools/Cmake/prog_test/prog_va_copy.c
877 CMakeLists for each binaries or examples:
879 ./teshsuite/gras/empty_main/CMakeLists.txt
880 ./teshsuite/gras/small_sleep/CMakeLists.txt
881 ./teshsuite/gras/datadesc/CMakeLists.txt
882 ./teshsuite/gras/msg_handle/CMakeLists.txt
883 ./teshsuite/simdag/CMakeLists.txt
884 ./teshsuite/simdag/partask/CMakeLists.txt
885 ./teshsuite/simdag/platforms/CMakeLists.txt
886 ./teshsuite/simdag/network/CMakeLists.txt
887 ./teshsuite/simdag/network/mxn/CMakeLists.txt
888 ./teshsuite/simdag/network/p2p/CMakeLists.txt
889 ./teshsuite/xbt/CMakeLists.txt
890 ./teshsuite/msg/CMakeLists.txt
891 ./tools/gras/CMakeLists.txt
892 ./tools/tesh/CMakeLists.txt
893 ./testsuite/simdag/CMakeLists.txt
894 ./testsuite/xbt/CMakeLists.txt
895 ./testsuite/surf/CMakeLists.txt
896 ./examples/gras/properties/CMakeLists.txt
897 ./examples/gras/ping/CMakeLists.txt
898 ./examples/gras/pmm/CMakeLists.txt
899 ./examples/gras/mmrpc/CMakeLists.txt
900 ./examples/gras/synchro/CMakeLists.txt
901 ./examples/gras/timer/CMakeLists.txt
902 ./examples/gras/mutual_exclusion/simple_token/CMakeLists.txt
903 ./examples/gras/spawn/CMakeLists.txt
904 ./examples/gras/chrono/CMakeLists.txt
905 ./examples/gras/rpc/CMakeLists.txt
906 ./examples/gras/all2all/CMakeLists.txt
907 ./examples/simdag/properties/CMakeLists.txt
908 ./examples/simdag/CMakeLists.txt
909 ./examples/simdag/metaxml/CMakeLists.txt
910 ./examples/simdag/dax/CMakeLists.txt
911 ./examples/smpi/CMakeLists.txt
912 ./examples/amok/bandwidth/CMakeLists.txt
913 ./examples/amok/saturate/CMakeLists.txt
914 ./examples/msg/priority/CMakeLists.txt
915 ./examples/msg/properties/CMakeLists.txt
916 ./examples/msg/migration/CMakeLists.txt
917 ./examples/msg/gtnets/CMakeLists.txt
918 ./examples/msg/parallel_task/CMakeLists.txt
919 ./examples/msg/trace/CMakeLists.txt
920 ./examples/msg/suspend/CMakeLists.txt
921 ./examples/msg/masterslave/CMakeLists.txt
922 ./examples/msg/actions/CMakeLists.txt
923 ./examples/msg/sendrecv/CMakeLists.txt
926 \section faq_howto Feature related questions
928 \subsection faq_MIA "Could you please add (your favorite feature here) to SimGrid?"
930 Here is the deal. The whole SimGrid project (MSG, SURF, GRAS, ...) is
931 meant to be kept as simple and generic as possible. We cannot add
932 functions for everybody's needs when these functions can easily be
933 built from the ones already in the API. Most of the time, it is
934 possible and when it was not possible we always have upgraded the API
935 accordingly. When somebody asks us a question like "How to do that?
936 Is there a function in the API to simply do this?", we're always glad
937 to answer and help. However if we don't need this code for our own
938 need, there is no chance we're going to write it... it's your job! :)
939 The counterpart to our answers is that once you come up with a neat
940 implementation of this feature (task duplication, RPC, thread
941 synchronization, ...), you should send it to us and we will be glad to
942 add it to the distribution. Thus, other people will take advantage of
943 it (and we don't have to answer this question again and again ;).
945 You'll find in this section a few "Missing In Action" features. Many
946 people have asked about it and we have given hints on how to simply do
947 it with MSG. Feel free to contribute...
949 \subsection faq_MIA_MSG MSG features
951 \subsubsection faq_MIA_examples I want some more complex MSG examples!
953 Many people have come to ask me a more complex example and each time,
954 they have realized afterward that the basics were in the previous three
957 Of course they have often been needing more complex functions like
958 MSG_process_suspend(), MSG_process_resume() and
959 MSG_process_isSuspended() (to perform synchronization), or
960 MSG_task_Iprobe() and MSG_process_sleep() (to avoid blocking
961 receptions), or even MSG_process_create() (to design asynchronous
962 communications or computations). But the examples are sufficient to
965 We know. We should add some more examples, but not really some more
966 complex ones... We should add some examples that illustrate some other
967 functionalists (like how to simply encode asynchronous
968 communications, RPC, process migrations, thread synchronization, ...)
969 and we will do it when we will have a little bit more time. We have
970 tried to document the examples so that they are understandable. Tell
971 us if something is not clear and once again feel free to participate!
974 \subsubsection faq_MIA_taskdup Missing in action: MSG Task duplication/replication
976 There is no task duplication in MSG. When you create a task, you can
977 process it or send it somewhere else. As soon as a process has sent
978 this task, he doesn't have this task anymore. It's gone. The receiver
979 process has got the task. However, you could decide upon receiving to
980 create a "copy" of a task but you have to handle by yourself the
981 semantic associated to this "duplication".
983 As we already told, we prefer keeping the API as simple as
984 possible. This kind of feature is rather easy to implement by users
985 and the semantic you associate really depends on people. Having a
986 *generic* task duplication mechanism is not that trivial (in
987 particular because of the data field). That is why I would recommand
988 that you write it by yourself even if I can give you advice on how to
991 You have the following functions to get informations about a task:
992 MSG_task_get_name(), MSG_task_get_compute_duration(),
993 MSG_task_get_remaining_computation(), MSG_task_get_data_size(),
994 and MSG_task_get_data().
996 You could use a dictionary (#xbt_dict_t) of dynars (#xbt_dynar_t). If
997 you still don't see how to do it, please come back to us...
999 \subsubsection faq_MIA_asynchronous I want to do asynchronous communications in MSG
1001 Up until now, there is no asynchronous communications in MSG. However,
1002 you can create as many process as you want so you should be able to do
1003 whatever you want... I've written a queue module to help implementing
1004 some asynchronous communications at low cost (creating thousands of
1005 process only to handle communications may be problematic in term of
1006 performance at some point). I'll add it in the distribution asap.
1008 \subsubsection faq_MIA_thread_synchronization I need to synchronize my MSG processes
1010 You obviously cannot use pthread_mutexes of pthread_conds. The best
1011 thing would be to propose similar structures. Unfortunately, we
1012 haven't found time to do it yet. However you can try to play with
1013 MSG_process_suspend() and MSG_process_resume(). You can even do some
1014 synchronization with fake communications (using MSG_task_get(),
1015 MSG_task_put() and MSG_task_Iprobe()).
1017 \subsubsection faq_MIA_host_load Where is the get_host_load function hidden in MSG?
1019 There is no such thing because its semantic wouldn't be really
1020 clear. Of course, it is something about the amount of host throughput,
1021 but there is as many definition of "host load" as people asking for
1022 this function. First, you have to remember that resource availability
1023 may vary over time, which make any load notion harder to define.
1025 It may be instantaneous value or an average one. Moreover it may be only the
1026 power of the computer, or may take the background load into account, or may
1027 even take the currently running tasks into account. In some SURF models,
1028 communications have an influence on computational power. Should it be taken
1031 First of all, it's near to impossible to predict the load beforehands in the
1032 simulator since it depends on too much parameters (background load
1033 variation, bandwidth sharing algorithmic complexity) some of them even being
1034 not known beforehands (other task starting at the same time). So, getting
1035 this information is really hard (just like in real life). It's not just that
1036 we want MSG to be as painful as real life. But as it is in some way
1037 realistic, we face some of the same problems as we would face in real life.
1039 How would you do it for real? The most common option is to use something
1040 like NWS that performs active probes. The best solution is probably to do
1041 the same within MSG, as in next code snippet. It is very close from what you
1042 would have to do out of the simulator, and thus gives you information that
1043 you could also get in real settings to not hinder the realism of your
1047 double get_host_load() {
1048 m_task_t task = MSG_task_create("test", 0.001, 0, NULL);
1049 double date = MSG_get_clock();
1051 MSG_task_execute(task);
1052 date = MSG_get_clock() - date;
1053 MSG_task_destroy(task);
1054 return (0.001/date);
1058 Of course, it may not match your personal definition of "host load". In this
1059 case, please detail what you mean on the mailing list, and we will extend
1060 this FAQ section to fit your taste if possible.
1062 \subsubsection faq_MIA_communication_time How can I get the *real* communication time?
1064 Communications are synchronous and thus if you simply get the time
1065 before and after a communication, you'll only get the transmission
1066 time and the time spent to really communicate (it will also take into
1067 account the time spent waiting for the other party to be
1068 ready). However, getting the *real* communication time is not really
1069 hard either. The following solution is a good starting point.
1074 m_task_t task = MSG_task_create("Task", task_comp_size, task_comm_size,
1075 calloc(1,sizeof(double)));
1076 *((double*) task->data) = MSG_get_clock();
1077 MSG_task_put(task, slaves[i % slaves_count], PORT_22);
1078 INFO0("Send completed");
1083 m_task_t task = NULL;
1086 time1 = MSG_get_clock();
1087 a = MSG_task_get(&(task), PORT_22);
1088 time2 = MSG_get_clock();
1089 if(time1<*((double *)task->data))
1090 time1 = *((double *) task->data);
1091 INFO1("Communication time : \"%f\" ", time2-time1);
1093 MSG_task_destroy(task);
1098 \subsection faq_MIA_SimDag SimDag related questions
1100 \subsubsection faq_SG_comm Implementing communication delays between tasks.
1102 A classic question of SimDag newcomers is about how to express a
1103 communication delay between tasks. The thing is that in SimDag, both
1104 computation and communication are seen as tasks. So, if you want to
1105 model a data dependency between two DAG tasks t1 and t2, you have to
1106 create 3 SD_tasks: t1, t2 and c and add dependencies in the following
1110 SD_task_dependency_add(NULL, NULL, t1, c);
1111 SD_task_dependency_add(NULL, NULL, c, t2);
1114 This way task t2 cannot start before the termination of communication c
1115 which in turn cannot start before t1 ends.
1117 When creating task c, you have to associate an amount of data (in bytes)
1118 corresponding to what has to be sent by t1 to t2.
1120 Finally to schedule the communication task c, you have to build a list
1121 comprising the workstations on which t1 and t2 are scheduled (w1 and w2
1122 for example) and build a communication matrix that should look like
1125 \subsubsection faq_SG_DAG How to implement a distributed dynamic scheduler of DAGs.
1127 Distributed is somehow "contagious". If you start making distributed
1128 decisions, there is no way to handle DAGs directly anymore (unless I
1129 am missing something). You have to encode your DAGs in term of
1130 communicating process to make the whole scheduling process
1131 distributed. Here is an example of how you could do that. Assume T1
1132 has to be done before T2.
1135 int your_agent(int argc, char *argv[] {
1137 T1 = MSG_task_create(...);
1138 T2 = MSG_task_create(...);
1142 if(cond) MSG_task_execute(T1);
1144 if((MSG_task_get_remaining_computation(T1)=0.0) && (you_re_in_a_good_mood))
1145 MSG_task_execute(T2)
1147 /* do something else */
1153 If you decide that the distributed part is not that much important and that
1154 DAG is really the level of abstraction you want to work with, then you should
1155 give a try to \ref SD_API.
1157 \subsection faq_MIA_generic Generic features
1159 \subsubsection faq_more_processes Increasing the amount of simulated processes
1161 Here are a few tricks you can apply if you want to increase the amount
1162 of processes in your simulations.
1164 - <b>A few thousands of simulated processes</b> (soft tricks)\n
1165 SimGrid can use either pthreads library or the UNIX98 contextes. On
1166 most systems, the number of pthreads is limited and then your
1167 simulation may be limited for a stupid reason. This is especially
1168 true with the current linux pthreads, and I cannot get more than
1169 2000 simulated processes with pthreads on my box. The UNIX98
1170 contexts allow me to raise the limit to 25,000 simulated processes
1172 The <tt>--with-context</tt> option of the <tt>./configure</tt>
1173 script allows you to choose between UNIX98 contextes
1174 (<tt>--with-context=ucontext</tt>) and the pthread version
1175 (<tt>--with-context=pthread</tt>). The default value is ucontext
1176 when the script detect a working UNIX98 context implementation. On
1177 Windows boxes, the provided value is discarded and an adapted
1178 version is picked up.\n\n
1179 We experienced some issues with contextes on some rare systems
1180 (solaris 8 and lower or old alpha linuxes comes to mind). The main
1181 problem is that the configure script detect the contextes as being
1182 functional when it's not true. If you happen to use such a system,
1183 switch manually to the pthread version, and provide us with a good
1184 patch for the configure script so that it is done automatically ;)
1186 - <b>Hundred thousands of simulated processes</b> (hard-core tricks)\n
1187 As explained above, SimGrid can use UNIX98 contextes to represent
1188 and handle the simulated processes. Thanks to this, the main
1189 limitation to the number of simulated processes becomes the
1190 available memory.\n\n
1191 Here are some tricks I had to use in order to run a token ring
1192 between 25,000 processes on my laptop (1Gb memory, 1.5Gb swap).\n
1193 - First of all, make sure your code runs for a few hundreds
1194 processes before trying to push the limit. Make sure it's
1195 valgrind-clean, ie that valgrind does not report neither memory
1196 error nor memory leaks. Indeed, numerous simulated processes
1197 result in *fat* simulation hindering debugging.
1198 - It was really boring to write 25,000 entries in the deployment
1199 file, so I wrote a little script
1200 <tt>examples/gras/mutual_exclusion/simple_token/make_deployment.pl</tt>, which you may
1201 want to adapt to your case. You could also think about hijacking
1202 the SURFXML parser (have look at \ref faq_flexml_bypassing).
1203 - The deployment file became quite big, so I had to do what is in
1204 the FAQ entry \ref faq_flexml_limit
1205 - Each UNIX98 context has its own stack entry. As debugging this is
1206 quite hairly, the default value is a bit overestimated so that
1207 user don't get into trouble about this. You want to tune this
1208 size to increse the number of processes. This is the
1209 <tt>STACK_SIZE</tt> define in
1210 <tt>src/xbt/xbt_context_sysv.c</tt>, which is 128kb by default.
1211 Reduce this as much as you can, but be warned that if this value
1212 is too low, you'll get a segfault. The token ring example, which
1213 is quite simple, runs with 40kb stacks.
1214 - You may tweak the logs to reduce the stack size further. When
1215 logging something, we try to build the string to display in a
1216 char array on the stack. The size of this array is constant (and
1217 equal to XBT_LOG_BUFF_SIZE, defined in include/xbt/log/h). If the
1218 string is too large to fit this buffer, we move to a dynamically
1219 sized buffer. In which case, we have to traverse one time the log
1220 event arguments to compute the size we need for the buffer,
1221 malloc it, and traverse the argument list again to do the actual
1223 The idea here is to move XBT_LOG_BUFF_SIZE to 1, forcing the logs
1224 to use a dynamic array each time. This allows us to lower further
1225 the stack size at the price of some performance loss...\n
1226 This allowed me to run the reduce the stack size to ... 4k. Ie,
1227 on my 1Gb laptop, I can run more than 250,000 processes!
1229 \subsubsection faq_MIA_batch_scheduler Is there a native support for batch schedulers in SimGrid?
1231 No, there is no native support for batch schedulers and none is
1232 planned because this is a very specific need (and doing it in a
1233 generic way is thus very hard). However some people have implemented
1234 their own batch schedulers. Vincent Garonne wrote one during his PhD
1235 and put his code in the contrib directory of our SVN so that other can
1236 keep working on it. You may find inspiring ideas in it.
1238 \subsubsection faq_MIA_checkpointing I need a checkpointing thing
1240 Actually, it depends on whether you want to checkpoint the simulation, or to
1241 simulate checkpoints.
1243 The first one could help if your simulation is a long standing process you
1244 want to keep running even on hardware issues. It could also help to
1245 <i>rewind</i> the simulation by jumping sometimes on an old checkpoint to
1246 cancel recent calculations.\n
1247 Unfortunately, such thing will probably never exist in SG. One would have to
1248 duplicate all data structures because doing a rewind at the simulator level
1249 is very very hard (not talking about the malloc free operations that might
1250 have been done in between). Instead, you may be interested in the Libckpt
1251 library (http://www.cs.utk.edu/~plank/plank/www/libckpt.html). This is the
1252 checkpointing solution used in the condor project, for example. It makes it
1253 easy to create checkpoints (at the OS level, creating something like core
1254 files), and rerunning them on need.
1256 If you want to simulate checkpoints instead, it means that you want the
1257 state of an executing task (in particular, the progress made towards
1258 completion) to be saved somewhere. So if a host (and the task executing on
1259 it) fails (cf. #MSG_HOST_FAILURE), then the task can be restarted
1260 from the last checkpoint.\n
1262 Actually, such a thing does not exists in SimGrid either, but it's just
1263 because we don't think it is fundamental and it may be done in the user code
1264 at relatively low cost. You could for example use a watcher that
1265 periodically get the remaining amount of things to do (using
1266 MSG_task_get_remaining_computation()), or fragment the task in smaller
1269 \subsection faq_platform Platform building and Dynamic resources
1271 \subsubsection faq_platform_example Where can I find SimGrid platform files?
1273 There is several little examples in the archive, in the examples/msg
1274 directory. From time to time, we are asked for other files, but we
1275 don't have much at hand right now.
1277 You should refer to the Platform Description Archive
1278 (http://pda.gforge.inria.fr) project to see the other platform file we
1279 have available, as well as the Simulacrum simulator, meant to generate
1280 SimGrid platforms using all classical generation algorithms.
1282 \subsubsection faq_platform_alnem How can I automatically map an existing platform?
1284 We are working on a project called ALNeM (Application-Level Network
1285 Mapper) which goal is to automatically discover the topology of an
1286 existing network. Its output will be a platform description file
1287 following the SimGrid syntax, so everybody will get the ability to map
1288 their own lab network (and contribute them to the catalog project).
1289 This tool is not ready yet, but it move quite fast forward. Just stay
1292 \subsubsection faq_platform_synthetic Generating synthetic but realistic platforms
1294 The third possibility to get a platform file (after manual or
1295 automatic mapping of real platforms) is to generate synthetic
1296 platforms. Getting a realistic result is not a trivial task, and
1297 moreover, nobody is really able to define what "realistic" means when
1298 speaking of topology files. You can find some more thoughts on this
1300 <a href="http://graal.ens-lyon.fr/~alegrand/articles/Simgrid-Introduction.pdf">slides</a>.
1302 If you are looking for an actual tool, there we have a little tool to
1303 annotate Tiers-generated topologies. This perl-script is in
1304 <tt>tools/platform_generation/</tt> directory of the SVN. Dinda et Al.
1305 released a very comparable tool, and called it GridG.
1307 \subsubsection faq_SURF_dynamic Expressing dynamic resource availability in platform files
1309 A nice feature of SimGrid is that it enables you to seamlessly have
1310 resources whose availability change over time. When you build a
1311 platform, you generally declare hosts like that:
1314 <host id="host A" power="100.00"/>
1317 If you want the availability of "host A" to change over time, the only
1318 thing you have to do is change this definition like that:
1321 <host id="host A" power="100.00" availability_file="trace_A.txt" state_file="trace_A_failure.txt"/>
1324 For hosts, availability files are expressed in fraction of available
1325 power. Let's have a look at what "trace_A.txt" may look like:
1334 At time 0, our host will deliver 100 flop/s. At time 11.0, it will
1335 deliver only 50 flop/s until time 20.0 where it will will start
1336 delivering 90 flop/s. Last at time 21.0 (20.0 plus the periodicity
1337 1.0), we'll be back to the beginning and it will deliver 100 flop/s.
1339 Now let's look at the state file:
1346 A negative value means "off" while a positive one means "on". At time
1347 1.0, the host is on. At time 1.0, it is turned off and at time 2.0, it
1348 is turned on again until time 12 (2.0 plus the periodicity 10.0). It
1349 will be turned on again at time 13.0 until time 23.0, and so on.
1351 Now, let's look how the same kind of thing can be done for network
1352 links. A usual declaration looks like:
1355 <link id="LinkA" bandwidth="10.0" latency="0.2"/>
1358 You have at your disposal the following options: bandwidth_file,
1359 latency_file and state_file. The only difference with hosts is that
1360 bandwidth_file and latency_file do not express fraction of available
1361 power but are expressed directly in bytes per seconds and seconds.
1363 \subsubsection faq_platform_multipath How to express multipath routing in platform files?
1365 It is unfortunately impossible to express the fact that there is more
1366 than one routing path between two given hosts. Let's consider the
1367 following platform file:
1370 <route src="A" dst="B">
1373 <route src="B" dst="C">
1376 <route src="A" dst="C">
1381 Although it is perfectly valid, it does not mean that data traveling
1382 from A to C can either go directly (using link 3) or through B (using
1383 links 1 and 2). It simply means that the routing on the graph is not
1384 trivial, and that data do not following the shortest path in number of
1385 hops on this graph. Another way to say it is that there is no implicit
1386 in these routing descriptions. The system will only use the routes you
1387 declare (such as <route src="A" dst="C"><link:ctn
1388 id="3"/></route>), without trying to build new routes by aggregating
1391 You are also free to declare platform where the routing is not
1392 symmetric. For example, add the following to the previous file:
1395 <route src="C" dst="A">
1401 This makes sure that data from C to A go through B where data from A
1402 to C go directly. Don't worry about realism of such settings since
1403 we've seen ways more weird situation in real settings (in fact, that's
1404 the realism of very regular platforms which is questionable, but
1405 that's another story).
1407 \subsubsection faq_flexml_bypassing Bypassing the XML parser with your own C functions
1409 So you want to bypass the XML files parser, uh? Maybe doing some parameter
1410 sweep experiments on your simulations or so? This is possible, and
1411 it's not even really difficult (well. Such a brutal idea could be
1412 harder to implement). Here is how it goes.
1414 For this, you have to first remember that the XML parsing in SimGrid is done
1415 using a tool called FleXML. Given a DTD, this gives a flex-based parser. If
1416 you want to bypass the parser, you need to provide some code mimicking what
1417 it does and replacing it in its interactions with the SURF code. So, let's
1418 have a look at these interactions.
1420 FleXML parser are close to classical SAX parsers. It means that a
1421 well-formed SimGrid platform XML file might result in the following
1424 - start "platform_description" with attribute version="2"
1425 - start "host" with attributes id="host1" power="1.0"
1427 - start "host" with attributes id="host2" power="2.0"
1429 - start "link" with ...
1431 - start "route" with ...
1432 - start "link:ctn" with ...
1435 - end "platform_description"
1437 The communication from the parser to the SURF code uses two means:
1438 Attributes get copied into some global variables, and a surf-provided
1439 function gets called by the parser for each event. For example, the event
1440 - start "host" with attributes id="host1" power="1.0"
1442 let the parser do something roughly equivalent to:
1444 strcpy(A_host_id,"host1");
1449 In SURF, we attach callbacks to the different events by initializing the
1450 pointer functions to some the right surf functions. Since there can be
1451 more than one callback attached to the same event (if more than one
1452 model is in use, for example), they are stored in a dynar. Example in
1453 workstation_ptask_L07.c:
1455 /* Adding callback functions */
1456 surf_parse_reset_parser();
1457 surfxml_add_callback(STag_surfxml_host_cb_list, &parse_cpu_init);
1458 surfxml_add_callback(STag_surfxml_prop_cb_list, &parse_properties);
1459 surfxml_add_callback(STag_surfxml_link_cb_list, &parse_link_init);
1460 surfxml_add_callback(STag_surfxml_route_cb_list, &parse_route_set_endpoints);
1461 surfxml_add_callback(ETag_surfxml_link_c_ctn_cb_list, &parse_route_elem);
1462 surfxml_add_callback(ETag_surfxml_route_cb_list, &parse_route_set_route);
1464 /* Parse the file */
1465 surf_parse_open(file);
1466 xbt_assert1((!surf_parse()), "Parse error in %s", file);
1470 So, to bypass the FleXML parser, you need to write your own version of the
1471 surf_parse function, which should do the following:
1472 - Fill the A_<tag>_<attribute> variables with the wanted values
1473 - Call the corresponding STag_<tag>_fun function to simulate tag start
1474 - Call the corresponding ETag_<tag>_fun function to simulate tag end
1475 - (do the same for the next set of values, and loop)
1477 Then, tell SimGrid that you want to use your own "parser" instead of the stock one:
1479 surf_parse = surf_parse_bypass_environment;
1480 MSG_create_environment(NULL);
1481 surf_parse = surf_parse_bypass_application;
1482 MSG_launch_application(NULL);
1485 A set of macros are provided at the end of
1486 include/surf/surfxml_parse.h to ease the writing of the bypass
1487 functions. An example of this trick is distributed in the file
1488 examples/msg/masterslave/masterslave_bypass.c
1490 \subsection faq_simgrid_configuration Changing SimGrid's behavior
1492 A number of options can be given at runtime to change the default
1493 SimGrid behavior. In particular, you can change the default cpu and
1496 \subsubsection faq_simgrid_configuration_gtnets Using GTNetS
1498 It is possible to use a packet-level network simulator
1499 instead of the default flow-based simulation. You may want to use such
1500 an approach if you have doubts about the validity of the default model
1501 or if you want to perform some validation experiments. At the moment,
1502 we support the GTNetS simulator (it is still rather experimental
1503 though, so leave us a message if you play with it).
1507 To enable GTNetS model inside SimGrid it is needed to patch the GTNetS simulator source code
1508 and build/install it from scratch
1511 - <b>Download and enter the recent downloaded GTNetS directory</b>
1514 svn checkout svn://scm.gforge.inria.fr/svn/simgrid/contrib/trunk/GTNetS/
1519 - <b>Use the following commands to unzip and patch GTNetS package to work within SimGrid.</b>
1522 unzip gtnets-current.zip
1523 tar zxvf gtnets-current-patch.tgz
1525 cat ../00*.patch | patch -p1
1528 - <b>OPTIONALLY</b> you can use a patch for itanium 64bit processor family.
1531 cat ../AMD64-FATAL-Removed-DUL_SIZE_DIFF-Added-fPIC-compillin.patch | patch -p1
1534 - <b>Compile GTNetS</b>
1536 Due to portability issues it is possible that GTNetS does not compile in your architecture. The patches furnished in SimGrid SVN repository are intended for use in Linux architecture only. Unfortunately, we do not have the time, the money, neither the manpower to guarantee GTNetS portability. We advice you to use one of GTNetS communication channel to get more help in compiling GTNetS.
1540 ln -sf Makefile.linux Makefile
1546 - <b>NOTE</b> A lot of warnings are expected but the application should compile
1547 just fine. If the makefile insists in compiling some QT libraries
1548 please try a make clean before asking for help.
1551 - <b>To compile optimized version</b>
1558 - <b>Installing GTNetS</b>
1560 It is important to put the full path of your libgtsim-xxxx.so file when creating the symbolic link. Replace < userhome > by some path you have write access to.
1563 ln -sf /<absolute_path>/gtnets_current/libgtsim-debug.so /<userhome>/usr/lib/libgtnets.so
1564 export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/<userhome>/usr/lib/libgtnets.so
1565 mkdir /<userhome>/usr/include/gtnets
1566 cp -fr SRC/*.h /<userhome>/usr/include/gtnets
1570 - <b>Enable GTNetS support in SimGrid</b>
1573 ./configure --with-gtnets=/<userhome>/usr
1576 - <b>Once you have followed all the instructions for compiling and
1577 installing successfully you can activate this feature at
1578 runntime with the following options:</b>
1581 cd simgrid/example/msg/
1587 - <b>Or try the GTNetS model dogbone example with</b>
1590 gtnets/gtnets gtnets/onelink-p.xml gtnets/onelink-d.xml --cfg=network_model:GTNets
1594 A long version of this <a href="http://gforge.inria.fr/docman/view.php/12/6283/GTNetS HowTo.html">HowTo</a> it is available
1597 More about GTNetS simulator at <a href="http://www.ece.gatech.edu/research/labs/MANIACS/GTNetS/index.html">GTNetS Website</a>
1601 The patches provided by us worked successfully with GTNetS found
1602 <a href="http://www.ece.gatech.edu/research/labs/MANIACS/GTNetS/software/gtnets-current.zip">here</a>,
1603 dated from 12th June 2008. Due to the discontinuing development of
1604 GTNetS it is impossible to precise a version number. We STRONGLY recommend you
1605 to download and install the GTNetS version found in SimGrid repository as explained above.
1610 \subsubsection faq_simgrid_configuration_alternate_network Using alternative flow models
1612 The default simgrid network model uses a max-min based approach as
1613 explained in the research report
1614 <a href="ftp://ftp.ens-lyon.fr/pub/LIP/Rapports/RR/RR2002/RR2002-40.ps.gz">A Network Model for Simulation of Grid Application</a>.
1615 Other models have been proposed and implemented since then (see for example
1616 <a href="http://mescal.imag.fr/membres/arnaud.legrand/articles/simutools09.pdf">Accuracy Study and Improvement of Network Simulation in the SimGrid Framework</a>)
1617 and can be activated at runtime. For example:
1619 ./mycode platform.xml deployment.xml --cfg=workstation_model:compound --cfg=network_model:LV08 -cfg=cpu_model:Cas01
1622 Possible models for the network are currently "Constant", "CM02",
1623 "LegrandVelho", "GTNets", Reno", "Reno2", "Vegas". Others will
1624 probably be added in the future and many of the previous ones are
1625 experimental and are likely to disappear without notice...
1627 \section faq_troubleshooting Troubleshooting
1629 \subsection faq_trouble_lib_compil SimGrid compilation and installation problems
1631 \subsubsection faq_trouble_lib_config ./configure fails!
1633 We know only one reason for the configure to fail:
1635 - <b>You are using a broken build environment</b>\n
1636 If symptom is that configure complains about gcc not being able to build
1637 executables, you are probably missing the libc6-dev package. Damn Ubuntu.
1639 If you experience other kind of issue, please get in touch with us. We are
1640 always interested in improving our portability to new systems.
1642 \subsubsection faq_trouble_distcheck Dude! "make check" fails on my machine!
1644 Don't assume we never run this target, because we do. Check
1645 http://bob.loria.fr:8010 if you don't believe us.
1647 There is several reasons which may cause the make check to fail on your
1650 - <b>You are using a broken libc (probably concerning the contextes)</b>.\n
1651 The symptom is that the "make check" fails within the examples/msg directory.\n
1652 By default, SimGrid uses something called ucontexts. This is part of the
1653 libc, but it's quite undertested. For example, some (old) versions of the
1654 glibc on alpha do not implement these functions, but provide the stubs
1655 (which return ENOSYS: not implemented). It may fool our detection mechanism
1656 and leads to segfaults. There is not much we can do to fix the bug.
1657 A workaround is to compile with --with-context=pthread to avoid
1658 ucontext completely. You'll be a bit more limited in the number
1659 of simulated processes you can start concurrently, but 5000
1660 processes is still enough for most purposes, isn't it?\n
1661 This limitation is the reason why we insist on using this piece of ...
1662 software even if it's so troublesome.\n
1663 <b>=> use --with-pthread on AMD64 architecture that do not have an
1664 ultra-recent libc.</b>
1666 - <b>There is a bug in SimGrid we aren't aware of</b>.\n
1667 If none of the above apply, please drop us a mail on the mailing list so
1668 that we can check it out. Make sure to read \ref faq_bugrepport
1671 \subsection faq_trouble_compil User code compilation problems
1673 \subsubsection faq_trouble_err_logcat "gcc: _simgrid_this_log_category_does_not_exist__??? undeclared (first use in this function)"
1675 This is because you are using the log mecanism, but you didn't created
1676 any default category in this file. You should refer to \ref XBT_log
1677 for all the details, but you simply forgot to call one of
1678 XBT_LOG_NEW_DEFAULT_CATEGORY() or XBT_LOG_NEW_DEFAULT_SUBCATEGORY().
1680 \subsubsection faq_trouble_pthreadstatic "gcc: undefined reference to pthread_key_create"
1682 This indicates that one of the library SimGrid depends on (libpthread
1683 here) was missing on the linking command line. Dependencies of
1684 libsimgrid are expressed directly in the dynamic library, so it's
1685 quite impossible that you see this message when doing dynamic linking.
1687 If you compile your code statically (and if you use a pthread version
1688 of SimGrid -- see \ref faq_more_processes), you must absolutely
1689 specify <tt>-lpthread</tt> on the linker command line. As usual, this should
1690 come after <tt>-lsimgrid</tt> on this command line.
1692 \subsection faq_trouble_errors Runtime error messages
1694 \subsubsection faq_flexml_limit "surf_parse_lex: Assertion `next limit' failed."
1696 This is because your platform file is too big for the parser.
1698 Actually, the message comes directly from FleXML, the technology on top of
1699 which the parser is built. FleXML has the bad idea of fetching the whole
1700 document in memory before parsing it. And moreover, the memory buffer size
1701 must be determined at compilation time.
1703 We use a value which seems big enough for our need without bloating the
1704 simulators footprints. But of course your mileage may vary. In this case,
1705 just edit src/surf/surfxml.l modify the definition of
1706 FLEXML_BUFFERSTACKSIZE. E.g.
1709 #define FLEXML_BUFFERSTACKSIZE 1000000000
1712 Then recompile and everything should be fine, provided that your version of
1713 Flex is recent enough (>= 2.5.31). If not the compilation process should
1716 A while ago, we worked on FleXML to reduce a bit its memory consumption, but
1717 these issues remain. There is two things we should do:
1719 - use a dynamic buffer instead of a static one so that the only limit
1720 becomes your memory, not a stupid constant fixed at compilation time
1721 (maybe not so difficult).
1722 - change the parser so that it does not need to get the whole file in
1723 memory before parsing
1724 (seems quite difficult, but I'm a complete newbe wrt flex stuff).
1726 These are changes to FleXML itself, not SimGrid. But since we kinda hijacked
1727 the development of FleXML, I can grant you that any patches would be really
1728 welcome and quickly integrated.
1730 <b>Update:</b> A new version of FleXML (1.7) was released. Most of the work
1731 was done by William Dowling, who use it in his own work. The good point is
1732 that it now use a dynamic buffer, and that the memory usage was greatly
1733 improved. The downside is that William also changed some things internally,
1734 and it breaks the hack we devised to bypass the parser, as explained in
1735 \ref faq_flexml_bypassing. Indeed, this is not a classical usage of the
1736 parser, and Will didn't imagine that we may have used (and even documented)
1737 such a crude usage of FleXML. So, we now have to repair the bypassing
1738 functionality to use the lastest FleXML version and fix the memory usage in
1741 \subsubsection faq_trouble_gras_transport GRAS spits networking error messages
1743 Gras, on real platforms, naturally use regular sockets to communicate. They
1744 are deeply hidden in the gras abstraction, but when things go wrong, you may
1745 get some weird error messages. Here are some example, with the probable
1748 - <b>Transport endpoint is not connected</b>: several processes try to open
1749 a server socket on the same port number of the same machine. This is
1750 naturally bad and each process should pick its own port number for this.\n
1751 Maybe, you just have some processes remaining from a previous experiment
1753 Killing them may help, but again if you kill -KILL them, you'll have to
1754 wait for a while: they didn't close there sockets properly and the system
1755 needs a while to notice that this port is free again.
1757 - <b>Socket closed by remote side</b>: if the remote process is not
1758 supposed to close the socket at this point, it may be dead.
1760 - <b>Connection reset by peer</b>: I found this on Internet about this
1761 error. I think it's what's happening here, too:\n
1762 <i>This basically means that a network error occurred while the client was
1763 receiving data from the server. But what is really happening is that the
1764 server actually accepts the connection, processes the request, and sends
1765 a reply to the client. However, when the server closes the socket, the
1766 client believes that the connection has been terminated abnormally
1767 because the socket implementation sends a TCP reset segment telling the
1768 client to throw away the data and report an error.\n
1769 Sometimes, this problem is caused by not properly closing the
1770 input/output streams and the socket connection. Make sure you close the
1771 input/output streams and socket connection properly. If everything is
1772 closed properly, however, and the problem persists, you can work around
1773 it by adding a one-second sleep before closing the streams and the
1774 socket. This technique, however, is not reliable and may not work on all
1776 Since GRAS sockets are closed properly (repeat after me: there is no bug
1777 in GRAS), it is either that you are closing your sockets on server side
1778 before the client get a chance to read them (use gras_os_sleep() to delay
1779 the server), or the server died awfully before the client got the data.
1781 \subsubsection faq_trouble_errors_big_fat_warning I'm told that my XML files are too old.
1783 The format of the XML platform description files is sometimes
1784 improved. For example, we decided to change the units used in SimGrid
1785 from MBytes, MFlops and seconds to Bytes, Flops and seconds to ease
1786 people exchanging small messages. We also reworked the route
1787 descriptions to allow more compact descriptions.
1789 That is why the XML files are versionned using the 'version' attribute
1790 of the root tag. Currently, it should read:
1792 <platform version="2">
1795 If your files are too old, you can use the simgrid_update_xml.pl
1796 script which can be found in the tools directory of the archive.
1798 \subsection faq_trouble_valgrind Valgrind-related and other debugger issues
1800 If you don't, you really should use valgrind to debug your code, it's
1803 \subsubsection faq_trouble_vg_longjmp longjmp madness in valgrind
1805 This is when valgrind starts complaining about longjmp things, just like:
1807 \verbatim ==21434== Conditional jump or move depends on uninitialised value(s)
1808 ==21434== at 0x420DBE5: longjmp (longjmp.c:33)
1810 ==21434== Use of uninitialised value of size 4
1811 ==21434== at 0x420DC3A: __longjmp (__longjmp.S:48)
1814 This is the sign that you didn't used the exception mecanism well. Most
1815 probably, you have a <tt>return;</tt> somewhere within a <tt>TRY{}</tt>
1816 block. This is <b>evil</b>, and you must not do this. Did you read the section
1819 \subsubsection faq_trouble_vg_libc Valgrind spits tons of errors about backtraces!
1821 It may happen that valgrind, the memory debugger beloved by any decent C
1822 programmer, spits tons of warnings like the following :
1823 \verbatim ==8414== Conditional jump or move depends on uninitialised value(s)
1824 ==8414== at 0x400882D: (within /lib/ld-2.3.6.so)
1825 ==8414== by 0x414EDE9: (within /lib/tls/i686/cmov/libc-2.3.6.so)
1826 ==8414== by 0x400B105: (within /lib/ld-2.3.6.so)
1827 ==8414== by 0x414F937: _dl_open (in /lib/tls/i686/cmov/libc-2.3.6.so)
1828 ==8414== by 0x4150F4C: (within /lib/tls/i686/cmov/libc-2.3.6.so)
1829 ==8414== by 0x400B105: (within /lib/ld-2.3.6.so)
1830 ==8414== by 0x415102D: __libc_dlopen_mode (in /lib/tls/i686/cmov/libc-2.3.6.so)
1831 ==8414== by 0x412D6B9: backtrace (in /lib/tls/i686/cmov/libc-2.3.6.so)
1832 ==8414== by 0x8076446: xbt_dictelm_get_ext (dict_elm.c:714)
1833 ==8414== by 0x80764C1: xbt_dictelm_get (dict_elm.c:732)
1834 ==8414== by 0x8079010: xbt_cfg_register (config.c:208)
1835 ==8414== by 0x806821B: MSG_config (msg_config.c:42)
1838 This problem is somewhere in the libc when using the backtraces and there is
1839 very few things we can do ourselves to fix it. Instead, here is how to tell
1840 valgrind to ignore the error. Add the following to your ~/.valgrind.supp (or
1841 create this file on need). Make sure to change the obj line according to
1842 your personnal mileage (change 2.3.6 to the actual version you are using,
1843 which you can retrieve with a simple "ls /lib/ld*.so").
1846 name: Backtrace madness
1848 obj:/lib/ld-2.3.6.so
1853 fun:__libc_dlopen_mode
1856 Then, you have to specify valgrind to use this suppression file by passing
1857 the <tt>--suppressions=$HOME/.valgrind.supp</tt> option on the command line.
1858 You can also add the following to your ~/.bashrc so that it gets passed
1859 automatically. Actually, it passes a bit more options to valgrind, and this
1860 happen to be my personnal settings. Check the valgrind documentation for
1863 \verbatim export VALGRIND_OPTS="--leak-check=yes --leak-resolution=high --num-callers=40 --tool=memcheck --suppressions=$HOME/.valgrind.supp" \endverbatim
1865 \subsubsection faq_trouble_backtraces Truncated backtraces
1867 When debugging SimGrid, it's easier to pass the
1868 --disable-compiler-optimization flag to the configure if valgrind or
1869 gdb get fooled by the optimization done by the compiler. But you
1870 should remove these flag when everything works before going in
1871 production (before launching your 1252135 experiments), or everything
1872 will run only one half of the true SimGrid potential.
1874 \subsection faq_deadlock There is a deadlock in my code!!!
1876 Unfortunately, we cannot debug every code written in SimGrid. We
1877 furthermore believe that the framework provides ways enough
1878 information to debug such informations yourself. If the textual output
1879 is not enough, Make sure to check the \ref faq_visualization FAQ entry to see
1880 how to get a graphical one.
1882 Now, if you come up with a really simple example that deadlocks and
1883 you're absolutely convinced that it should not, you can ask on the
1884 list. Just be aware that you'll be severely punished if the mistake is
1885 on your side... We have plenty of FAQ entries to redact and new
1886 features to implement for the impenitents! ;)
1888 \subsection faq_surf_network_latency I get weird timings when I play with the latencies.
1890 OK, first of all, remember that units should be Bytes, Flops and
1891 Seconds. If you don't use such units, some SimGrid constants (e.g. the
1892 SG_TCP_CTE_GAMMA constant used in most network models) won't have the
1893 right unit and you'll end up with weird results.
1895 Here is what happens with a single transfer of size L on a link
1896 (bw,lat) when nothing else happens.
1899 0-----lat--------------------------------------------------t
1900 |-----|**** real_bw =min(bw,SG_TCP_CTE_GAMMA/(2*lat)) *****|
1903 In more complex situations, this min is the solution of a complex
1904 max-min linear system. Have a look
1905 <a href="http://lists.gforge.inria.fr/pipermail/simgrid-devel/2006-April/thread.html">here</a>
1906 and read the two threads "Bug in SURF?" and "Surf bug not
1907 fixed?". You'll have a few other examples of such computations. You
1908 can also read "A Network Model for Simulation of Grid Application" by
1909 Henri Casanova and Loris Marchal to have all the details. The fact
1910 that the real_bw is smaller than bw is easy to understand. The fact
1911 that real_bw is smaller than SG_TCP_CTE_GAMMA/(2*lat) is due to the
1912 window-based congestion mechanism of TCP. With TCP, you can't exploit
1913 your huge network capacity if you don't have a good round-trip-time
1914 because of the acks...
1916 Anyway, what you get is t=lat + L/min(bw,SG_TCP_CTE_GAMMA/(2*lat)).
1918 * if I you set (bw,lat)=(100 000 000, 0.00001), you get t = 1.00001 (you fully
1920 * if I you set (bw,lat)=(100 000 000, 0.0001), you get t = 1.0001 (you're on the
1922 * if I you set (bw,lat)=(100 000 000, 0.001), you get t = 10.001 (ouch!)
1924 This bound on the effective bandwidth of a flow is not the only thing
1925 that may make your result be unexpected. For example, two flows
1926 competing on a saturated link receive an amount of bandwidth inversely
1927 proportional to their round trip time.
1929 \subsection faq_bugrepport So I've found a bug in SimGrid. How to report it?
1931 We do our best to make sure to hammer away any bugs of SimGrid, but this is
1932 still an academic project so please be patient if/when you find bugs in it.
1933 If you do, the best solution is to drop an email either on the simgrid-user
1934 or the simgrid-devel mailing list and explain us about the issue. You can
1935 also decide to open a formal bug report using the
1936 <a href="https://gforge.inria.fr/tracker/?atid=165&group_id=12&func=browse">relevant
1937 interface</a>. You need to login on the server to get the ability to submit
1940 We will do our best to solve any problem repported, but you need to help us
1941 finding the issue. Just telling "it segfault" isn't enough. Telling "It
1942 segfaults when running the attached simulator" doesn't really help either.
1943 You may find the following article interesting to see how to repport
1944 informative bug repports:
1945 http://www.chiark.greenend.org.uk/~sgtatham/bugs.html (it is not SimGrid
1946 specific at all, but it's full of good advices).
1948 \author Arnaud Legrand (arnaud.legrand::imag.fr)
1949 \author Martin Quinson (martin.quinson::loria.fr)
1954 ******************************************************************
1955 * OLD CRUFT NOT USED ANYMORE *
1956 ******************************************************************
1959 \subsection faq_crosscompile Cross-compiling a Windows DLL of SimGrid from linux
1961 At the moment, we do not distribute Windows pre-compiled version of SimGrid
1962 because the support for this platform is still experimental. We know that
1963 some parts of the GRAS environment do not work, and we think that the others
1964 environments (MSG and SD) have good chances to work, but we didn't test
1965 ourselves. This section explains how we generate the SimGrid DLL so that you
1966 can build it for yourself. First of all, you need to have a version more
1967 recent than 3.1 (ie, a SVN version as time of writting).
1969 In order to cross-compile the package to windows from linux, you need to
1970 install mingw32 (minimalist gnu win32). On Debian, you can do so by
1971 installing the packages mingw32 (compiler), mingw32-binutils (linker and
1972 so), mingw32-runtime.
1974 You can use the VPATH support of configure to compile at the same time for
1975 linux and windows without dupplicating the source nor cleaning the tree
1976 between each. Just run bootstrap (if you use the SVN) to run the autotools.
1977 Then, create a linux and a win directories. Then, type:
1978 \verbatim cd linux; ../configure --srcdir=.. <usual configure flags>; make; cd ..
1979 cd win; ../configure --srcdir=.. --host=i586-mingw32msvc <flags>; make; cd ..
1981 The trick to VPATH builds is to call configure from another directory,
1982 passing it an extra --srcdir argument to tell it where all the sources are.
1983 It will understand you want to use VPATH. Then, the trick to cross-compile
1984 is simply to add a --host argument specifying the target you want to build
1985 for. The i586-mingw32msvc string is what you have to pass to use the mingw32
1986 environment as distributed in Debian.
1988 After that, you can run all make targets from both directories, and test
1989 easily that what you change for one arch does not break the other one.
1991 It is possible that this VPATH build thing breaks from time to time in the
1992 SVN since it's quite fragile, but it's granted to work in any released
1993 version. If you experience problems, drop us a mail.
1995 Another possible source of issue is that at the moment, building the
1996 examples request to use the gras_stub_generator tool, which is a compiled
1997 program, not a script. In cross-compilation, you need to cross-execute with
1998 wine for example, which is not really pleasant. We are working on this, but
1999 in the meanwhile, simply don't build the examples in cross-compilation
2000 (<tt>cd src</tt> before running make).
2002 Program (cross-)compiled with mingw32 do request an extra DLL at run-time to be
2003 usable. For example, if you want to test your build with wine, you should do
2004 the following to put this library where wine looks for DLLs.
2006 cp /usr/share/doc/mingw32-runtime/mingwm10.dll.gz ~/.wine/c/windows/system/
2007 gunzip ~/.wine/c/windows/system/mingwm10.dll.gz
2010 The DLL is built in src/.libs, and installed in the <i>prefix</i>/bin directory
2011 when you run make install.
2013 If you want to use it in a native project on windows, you need to use
2014 simgrid.dll and mingwm10.dll. For each DLL, you need to build .def file
2015 under linux (listing the defined symbols), and convert it into a .lib file
2016 under windows (specifying this in a way that windows compilers like). To
2017 generate the def files, run (under linux):
2018 \verbatim echo "LIBRARY libsimgrid-0.dll" > simgrid.def
2019 echo EXPORTS >> simgrid.def
2020 nm libsimgrid-0.dll | grep ' T _' | sed 's/.* T _//' >> simgrid.def
2021 nm libsimgrid-0.dll | grep ' D _' | sed 's/.* D _//' | sed 's/$/ DATA/' >> simgrid.def
2023 echo "LIBRARY mingwm10.dll" > mingwm10.def
2024 echo EXPORTS >> mingwm10.def
2025 nm mingwm10.dll | grep ' T _' | sed 's/.* T _//' >> mingwm10.def
2026 nm mingwm10.dll | grep ' D _' | sed 's/.* D _//' | sed 's/$/ DATA/' >> mingwm10.def
2029 To create the import .lib files, use the <tt>lib</tt> windows tool (from
2030 MSVC) the following way to produce simgrid.lib and mingwm10.lib
2031 \verbatim lib /def:simgrid.def
2032 lib /def:mingwm10.def
2035 If you happen to use Borland C Builder, the right command line is the
2036 following (note that you don't need any file.def to get this working).
2037 \verbatim implib simgrid.lib libsimgrid-0.dll
2038 implib mingwm10.lib mingwm10.dll
2041 Then, set the following parameters in Visual C++ 2005:
2042 Linker -> Input -> Additional dependencies = simgrid.lib mingwm10.lib
2044 Just in case you wonder how to generate a DLL from libtool in another
2045 project, we added -no-undefined to any lib*_la_LDFLAGS variables so that
2046 libtool accepts to generate a dynamic library under windows. Then, to make
2047 it true, we pass any dependencies (such as -lws2 under windows or -lpthread
2048 on need) on the linking line. Passing such deps is a good idea anyway so
2049 that they get noted in the library itself, avoiding the users to know about
2050 our dependencies and put them manually on their compilation line. Then we
2051 added the AC_LIBTOOL_WIN32_DLL macro just before AC_PROG_LIBTOOL in the
2052 configure.ac. It means that we exported any symbols which need to be.
2053 Nowadays, functions get automatically exported, so we don't need to load our
2054 header files with tons of __declspec(dllexport) cruft. We only need to do so
2055 for data, but there is no public data in SimGrid so we are good.