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 targets
496 make VERBOSE=1 build all targets and print build command lines
497 make test test all targets and summarize
498 make package make the distrib
499 make install-simgrid install the project (doc/ lib/ include/)
500 make clean clean all targets
501 make html Create simgrid documentation
504 When the project have been succesfully compiling and build you can make tests.
508 ctest launch only tests
510 ctest -D Continuous(Start|Update|Configure|Build)
511 ctest -D Continuous(Test|Coverage|MemCheck|Submit)
512 ctest -D Experimental
513 ctest -D Experimental(Start|Update|Configure|Build)
514 ctest -D Experimental(Test|Coverage|MemCheck|Submit)
516 ctest -D Nightly(Start|Update|Configure|Build)
517 ctest -D Nightly(Test|Coverage|MemCheck|Submit)
518 ctest -D NightlyMemoryCheck
521 \subsubsection faq_cmakecompilation4 Examples for different mode.
525 cmake -Denable_maintainer_mode=on ./
526 \verbatim GTnetS doesn't works : set -Ddisable_gtnets=on
527 with_context auto change to ucontext
530 Make : src/simgrid.jar with : /usr/bin/javac
531 Make examples/java with : /usr/bin/javac
533 Configuration of package `simgrid' (revision 7228M) on arch (=4):
535 SITE : Linux_Ubuntu 9.10_x86_64
537 Compiler: c++ : /usr/bin/c++
538 version: c++ (Ubuntu 4.4.1-4ubuntu9) 4.4.1
540 version: gcc (Ubuntu 4.4.1-4ubuntu9) 4.4.1
546 Context backend: ucontext
556 Simgrid dependencies: dl -llua5.1
557 Gras dependencies: pthread
561 USER_PREFIX: /usr/local
562 INSTALL_PREFIX: /usr/local
566 -- Build files have been written to: /home/navarrop/Bureau/simgrid-trunk
571 cmake -Dsupernovae=on ./
572 \verbatim GTnetS doesn't works : set -Ddisable_gtnets=on
573 with_context auto change to ucontext
576 Make : src/simgrid.jar with : /usr/bin/javac
577 Make examples/java with : /usr/bin/javac
579 Configuration of package `simgrid' (revision 7228M) on arch (=4):
580 BUILDNAME : SUPERNOVAE
581 SITE : Linux_Ubuntu 9.10_x86_64
583 Compiler: c++ : /usr/bin/c++
584 version: c++ (Ubuntu 4.4.1-4ubuntu9) 4.4.1
586 version: gcc (Ubuntu 4.4.1-4ubuntu9) 4.4.1
588 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
592 Context backend: ucontext
602 Simgrid dependencies: dl -llua5.1
603 Gras dependencies: pthread
607 USER_PREFIX: /usr/local
608 INSTALL_PREFIX: /usr/local
612 -- Build files have been written to: /home/navarrop/Bureau/simgrid-trunk
617 cmake -Dgtnets_path=/home/navarrop/Bureau/usr/ ./
618 \verbatim with_context auto change to ucontext
621 Make : src/simgrid.jar with : /usr/bin/javac
622 Make examples/java with : /usr/bin/javac
624 Configuration of package `simgrid' (revision 7228M) on arch (=4):
626 SITE : Linux_Ubuntu 9.10_x86_64
628 Compiler: c++ : /usr/bin/c++
629 version: c++ (Ubuntu 4.4.1-4ubuntu9) 4.4.1
631 version: gcc (Ubuntu 4.4.1-4ubuntu9) 4.4.1
633 CFlags: -L/home/navarrop/Bureau/usr/lib -I/home/navarrop/Bureau/usr/include/gtnets -g3
634 CPPFlags: -L/home/navarrop/Bureau/usr/lib -I/home/navarrop/Bureau/usr/include/gtnets
637 Context backend: ucontext
639 path: /home/navarrop/Bureau/usr
647 Simgrid dependencies: dl -llua5.1 -lgtnets
648 Gras dependencies: pthread
652 USER_PREFIX: /usr/local
653 INSTALL_PREFIX: /usr/local
655 INFO -->> Take care to have export LD_LIBRARY_PATH before run make command for make examples with gtnets
656 copy and paste : export LD_LIBRARY_PATH=/home/navarrop/Bureau/usr/lib/:$LD_LIBRARY_PATH
661 -- Build files have been written to: /home/navarrop/Bureau/simgrid-trunk
664 \subsection faq_cmakeinstall How to install with cmake?
666 \subsubsection faq_cmakeinstall1 From svn.
669 cmake -Denable_maintainer_mode=on -Dprefix=/home/navarrop/Bureau/install_simgrid ./
674 \subsubsection faq_cmakeinstall2 From a distrib
677 cmake -Dprefix=/home/navarrop/Bureau/install_simgrid ./
682 \subsection faq_screenshot Screenshot
685 navarrop@caraja:~$ cd Bureau/simgrid-trunk/
686 navarrop@caraja:~/Bureau/simgrid-trunk$ cmake ./
688 GTnetS doesn't works : set -Ddisable_gtnets=on <-|some warnings are printed
689 with_context auto change to ucontext <-|
690 (skaddr) <--info (needed)
691 (sksize) <--info (needed)
692 Make : src/simgrid.jar with : /usr/bin/javac <--info (if java)
693 Make examples/java with : /usr/bin/javac <--info (if java)
695 Configuration of package `simgrid' (revision 7209M) on arch (=4):
696 BUILDNAME : UCONTEXT <-- name of the compilation regarding to cdash
697 SITE : Linux_Ubuntu 9.10_x86_64 <-- distribution of the local machine regarding to cdash
699 Compiler: c++ : /usr/bin/c++
700 version: c++ (Ubuntu 4.4.1-4ubuntu9) 4.4.1
702 version: gcc (Ubuntu 4.4.1-4ubuntu9) 4.4.1
708 Context backend: ucontext
718 Simgrid dependencies: -ldl -llua5.1
719 Gras dependencies: pthread
723 USER_PREFIX: /usr/local
724 INSTALL_PREFIX: /usr/local
728 -- Build files have been written to: /home/navarrop/Bureau/simgrid-trunk
730 Here all options are checked and printed. If it doesn't match with your configuration
731 it is probably due to a wrong configuration.
733 \subsection faq_cmakehowto How to modified sources files for developers
735 \subsubsection faq_cmakehowto1 Add an executable or examples.
737 If you want make an executable you have to create a CMakeList.txt to the src directory.
738 You must specified where to create the executable, source list, dependencies and the name of the binary.
741 cmake_minimum_required(VERSION 2.6)
743 set(EXECUTABLE_OUTPUT_PATH "./")
744 set(LIBRARY_OUTPUT_PATH "${PROJECT_DIRECTORY}/lib")
746 add_executable(get_sender get_sender.c) #add_executable(<name_of_target> <src list>)
748 ### Add definitions for compile
749 target_link_libraries(get_sender simgrid m pthread -fprofile-arcs) #target_link_libraries(<name_of_targe> <dependencies>)
752 Then you have to modified <project/directory>/buildtools/Cmake/src/CMakeMakeExeLib.txt and add
755 add_subdirectory(${PROJECT_DIRECTORY}/<path_where_is_CMakeList.txt>)
758 \subsubsection faq_cmakehowto2 Delete/add sources to lib.
760 If you want modified, add or delete source files from a library you have to edit <project/directory>/buildtools/Cmake/src/CMakeDefinePackages.txt
764 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/MsgException.java
765 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/JniException.java
766 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/NativeException.java
767 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/HostNotFoundException.java
768 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/ProcessNotFoundException.java
769 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/Msg.java
770 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/Process.java
771 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/Host.java
772 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/Task.java
773 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/MsgNative.java
774 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/ApplicationHandler.java
775 ${PROJECT_DIRECTORY}/src/java/simgrid/msg/Sem.java
779 \subsubsection faq_cmakehowto3 Add test
781 If you want modified, add or delete tests you have to edit <project/directory>/buildtools/Cmake/src/CMakeTest.txt
782 with this function : ADD_TEST(<name> <bin> <ARGS>)
785 add_test(test-simdag-1 ${PROJECT_DIRECTORY}/testsuite/simdag/sd_test --cfg=path:${PROJECT_DIRECTORY}/testsuite/simdag small_platform_variable.xml)
788 \subsection faq_cmakeExplain Explaination of sources files for cmake
792 Those files are the "main parts". One located at the project directory call all the cmake sources files. The others
793 are little projects called by the first for make examples.
795 \li CMakeCompleteInFiles.txt
797 Complete all .in files and define Variables for h files
801 This file make the html documentation.
803 \li CMakeMakeExeLib.txt
805 Here are callled all "CMakeLists.txt" for make executables and libraries.
807 \li CMakePrintArgs.txt
809 This file is called at the end of the build for summarize environment variables.
811 \li CMakeDefinePackages.txt
813 Here is defined sources packages for compiling libs.
817 Defined flags which are used for compiling sources.
819 \li CMakeSupernovae.txt
821 Here are made files for the supernovae mode.
825 Here is defined packages for install simgrid and make a distribution.
829 Part for generated sources from flex and flexml.
833 Here are defined options and initialized values.
837 All tests are listed.
839 \li CTestConfig.cmake
841 Properties which link tests with dashboard.
843 \subsection faq_cmakeList List of files added for cmake
845 Here is a list of files involved into cmake build (relative to project directory path) :
849 ./buildtools/Cmake/src/CMakeCompleteInFiles.txt
850 ./buildtools/Cmake/src/CMakeDocs.txt
851 ./buildtools/Cmake/src/CMakeMakeExeLib.txt
852 ./buildtools/Cmake/src/CMakePrintArgs.txt
853 ./buildtools/Cmake/src/CMakeDefinePackages.txt
854 ./buildtools/Cmake/src/CMakeFlags.txt
855 ./buildtools/Cmake/src/CMakeSupernovae.txt
856 ./buildtools/Cmake/src/CMakeDistrib.txt
857 ./buildtools/Cmake/src/CMakeFLEXml.txt
858 ./buildtools/Cmake/src/CMakeOption.txt
859 ./buildtools/Cmake/src/CMakeTest.txt
860 ./buildtools/Cmake/src/CTestConfig.cmake
862 Test files for define properties :
863 ./buildtools/Cmake/prog_test/prog_GRAS_ARCH.c
864 ./buildtools/Cmake/prog_test/prog_max_size.c
865 ./buildtools/Cmake/prog_test/prog_sem_init.c
866 ./buildtools/Cmake/prog_test/prog_stackgrowth.c
867 ./buildtools/Cmake/prog_test/prog_vsnprintf.c
868 ./buildtools/Cmake/prog_test/prog_AC_CHECK_MCSC.c
869 ./buildtools/Cmake/prog_test/prog_GRAS_CHECK_STRUCT_COMPACTION.c
870 ./buildtools/Cmake/prog_test/prog_mutex_timedlock.c
871 ./buildtools/Cmake/prog_test/prog_sem_timedwait.c
872 ./buildtools/Cmake/prog_test/prog_stacksetup.c
873 ./buildtools/Cmake/prog_test/prog_getline.c
874 ./buildtools/Cmake/prog_test/prog_gtnets.cpp
875 ./buildtools/Cmake/prog_test/prog_printf_null.c
876 ./buildtools/Cmake/prog_test/prog_snprintf.c
877 ./buildtools/Cmake/prog_test/prog_va_copy.c
879 CMakeLists for each binaries or examples:
881 ./teshsuite/gras/empty_main/CMakeLists.txt
882 ./teshsuite/gras/small_sleep/CMakeLists.txt
883 ./teshsuite/gras/datadesc/CMakeLists.txt
884 ./teshsuite/gras/msg_handle/CMakeLists.txt
885 ./teshsuite/simdag/CMakeLists.txt
886 ./teshsuite/simdag/partask/CMakeLists.txt
887 ./teshsuite/simdag/platforms/CMakeLists.txt
888 ./teshsuite/simdag/network/CMakeLists.txt
889 ./teshsuite/simdag/network/mxn/CMakeLists.txt
890 ./teshsuite/simdag/network/p2p/CMakeLists.txt
891 ./teshsuite/xbt/CMakeLists.txt
892 ./teshsuite/msg/CMakeLists.txt
893 ./tools/gras/CMakeLists.txt
894 ./tools/tesh/CMakeLists.txt
895 ./testsuite/simdag/CMakeLists.txt
896 ./testsuite/xbt/CMakeLists.txt
897 ./testsuite/surf/CMakeLists.txt
898 ./examples/gras/properties/CMakeLists.txt
899 ./examples/gras/ping/CMakeLists.txt
900 ./examples/gras/pmm/CMakeLists.txt
901 ./examples/gras/mmrpc/CMakeLists.txt
902 ./examples/gras/synchro/CMakeLists.txt
903 ./examples/gras/timer/CMakeLists.txt
904 ./examples/gras/mutual_exclusion/simple_token/CMakeLists.txt
905 ./examples/gras/spawn/CMakeLists.txt
906 ./examples/gras/chrono/CMakeLists.txt
907 ./examples/gras/rpc/CMakeLists.txt
908 ./examples/gras/all2all/CMakeLists.txt
909 ./examples/simdag/properties/CMakeLists.txt
910 ./examples/simdag/CMakeLists.txt
911 ./examples/simdag/metaxml/CMakeLists.txt
912 ./examples/simdag/dax/CMakeLists.txt
913 ./examples/smpi/CMakeLists.txt
914 ./examples/amok/bandwidth/CMakeLists.txt
915 ./examples/amok/saturate/CMakeLists.txt
916 ./examples/msg/priority/CMakeLists.txt
917 ./examples/msg/properties/CMakeLists.txt
918 ./examples/msg/migration/CMakeLists.txt
919 ./examples/msg/gtnets/CMakeLists.txt
920 ./examples/msg/parallel_task/CMakeLists.txt
921 ./examples/msg/trace/CMakeLists.txt
922 ./examples/msg/suspend/CMakeLists.txt
923 ./examples/msg/masterslave/CMakeLists.txt
924 ./examples/msg/actions/CMakeLists.txt
925 ./examples/msg/sendrecv/CMakeLists.txt
928 \section faq_howto Feature related questions
930 \subsection faq_MIA "Could you please add (your favorite feature here) to SimGrid?"
932 Here is the deal. The whole SimGrid project (MSG, SURF, GRAS, ...) is
933 meant to be kept as simple and generic as possible. We cannot add
934 functions for everybody's needs when these functions can easily be
935 built from the ones already in the API. Most of the time, it is
936 possible and when it was not possible we always have upgraded the API
937 accordingly. When somebody asks us a question like "How to do that?
938 Is there a function in the API to simply do this?", we're always glad
939 to answer and help. However if we don't need this code for our own
940 need, there is no chance we're going to write it... it's your job! :)
941 The counterpart to our answers is that once you come up with a neat
942 implementation of this feature (task duplication, RPC, thread
943 synchronization, ...), you should send it to us and we will be glad to
944 add it to the distribution. Thus, other people will take advantage of
945 it (and we don't have to answer this question again and again ;).
947 You'll find in this section a few "Missing In Action" features. Many
948 people have asked about it and we have given hints on how to simply do
949 it with MSG. Feel free to contribute...
951 \subsection faq_MIA_MSG MSG features
953 \subsubsection faq_MIA_examples I want some more complex MSG examples!
955 Many people have come to ask me a more complex example and each time,
956 they have realized afterward that the basics were in the previous three
959 Of course they have often been needing more complex functions like
960 MSG_process_suspend(), MSG_process_resume() and
961 MSG_process_isSuspended() (to perform synchronization), or
962 MSG_task_Iprobe() and MSG_process_sleep() (to avoid blocking
963 receptions), or even MSG_process_create() (to design asynchronous
964 communications or computations). But the examples are sufficient to
967 We know. We should add some more examples, but not really some more
968 complex ones... We should add some examples that illustrate some other
969 functionalists (like how to simply encode asynchronous
970 communications, RPC, process migrations, thread synchronization, ...)
971 and we will do it when we will have a little bit more time. We have
972 tried to document the examples so that they are understandable. Tell
973 us if something is not clear and once again feel free to participate!
976 \subsubsection faq_MIA_taskdup Missing in action: MSG Task duplication/replication
978 There is no task duplication in MSG. When you create a task, you can
979 process it or send it somewhere else. As soon as a process has sent
980 this task, he doesn't have this task anymore. It's gone. The receiver
981 process has got the task. However, you could decide upon receiving to
982 create a "copy" of a task but you have to handle by yourself the
983 semantic associated to this "duplication".
985 As we already told, we prefer keeping the API as simple as
986 possible. This kind of feature is rather easy to implement by users
987 and the semantic you associate really depends on people. Having a
988 *generic* task duplication mechanism is not that trivial (in
989 particular because of the data field). That is why I would recommand
990 that you write it by yourself even if I can give you advice on how to
993 You have the following functions to get informations about a task:
994 MSG_task_get_name(), MSG_task_get_compute_duration(),
995 MSG_task_get_remaining_computation(), MSG_task_get_data_size(),
996 and MSG_task_get_data().
998 You could use a dictionary (#xbt_dict_t) of dynars (#xbt_dynar_t). If
999 you still don't see how to do it, please come back to us...
1001 \subsubsection faq_MIA_asynchronous I want to do asynchronous communications in MSG
1003 Up until now, there is no asynchronous communications in MSG. However,
1004 you can create as many process as you want so you should be able to do
1005 whatever you want... I've written a queue module to help implementing
1006 some asynchronous communications at low cost (creating thousands of
1007 process only to handle communications may be problematic in term of
1008 performance at some point). I'll add it in the distribution asap.
1010 \subsubsection faq_MIA_thread_synchronization I need to synchronize my MSG processes
1012 You obviously cannot use pthread_mutexes of pthread_conds. The best
1013 thing would be to propose similar structures. Unfortunately, we
1014 haven't found time to do it yet. However you can try to play with
1015 MSG_process_suspend() and MSG_process_resume(). You can even do some
1016 synchronization with fake communications (using MSG_task_get(),
1017 MSG_task_put() and MSG_task_Iprobe()).
1019 \subsubsection faq_MIA_host_load Where is the get_host_load function hidden in MSG?
1021 There is no such thing because its semantic wouldn't be really
1022 clear. Of course, it is something about the amount of host throughput,
1023 but there is as many definition of "host load" as people asking for
1024 this function. First, you have to remember that resource availability
1025 may vary over time, which make any load notion harder to define.
1027 It may be instantaneous value or an average one. Moreover it may be only the
1028 power of the computer, or may take the background load into account, or may
1029 even take the currently running tasks into account. In some SURF models,
1030 communications have an influence on computational power. Should it be taken
1033 First of all, it's near to impossible to predict the load beforehands in the
1034 simulator since it depends on too much parameters (background load
1035 variation, bandwidth sharing algorithmic complexity) some of them even being
1036 not known beforehands (other task starting at the same time). So, getting
1037 this information is really hard (just like in real life). It's not just that
1038 we want MSG to be as painful as real life. But as it is in some way
1039 realistic, we face some of the same problems as we would face in real life.
1041 How would you do it for real? The most common option is to use something
1042 like NWS that performs active probes. The best solution is probably to do
1043 the same within MSG, as in next code snippet. It is very close from what you
1044 would have to do out of the simulator, and thus gives you information that
1045 you could also get in real settings to not hinder the realism of your
1049 double get_host_load() {
1050 m_task_t task = MSG_task_create("test", 0.001, 0, NULL);
1051 double date = MSG_get_clock();
1053 MSG_task_execute(task);
1054 date = MSG_get_clock() - date;
1055 MSG_task_destroy(task);
1056 return (0.001/date);
1060 Of course, it may not match your personal definition of "host load". In this
1061 case, please detail what you mean on the mailing list, and we will extend
1062 this FAQ section to fit your taste if possible.
1064 \subsubsection faq_MIA_communication_time How can I get the *real* communication time?
1066 Communications are synchronous and thus if you simply get the time
1067 before and after a communication, you'll only get the transmission
1068 time and the time spent to really communicate (it will also take into
1069 account the time spent waiting for the other party to be
1070 ready). However, getting the *real* communication time is not really
1071 hard either. The following solution is a good starting point.
1076 m_task_t task = MSG_task_create("Task", task_comp_size, task_comm_size,
1077 calloc(1,sizeof(double)));
1078 *((double*) task->data) = MSG_get_clock();
1079 MSG_task_put(task, slaves[i % slaves_count], PORT_22);
1080 INFO0("Send completed");
1085 m_task_t task = NULL;
1088 time1 = MSG_get_clock();
1089 a = MSG_task_get(&(task), PORT_22);
1090 time2 = MSG_get_clock();
1091 if(time1<*((double *)task->data))
1092 time1 = *((double *) task->data);
1093 INFO1("Communication time : \"%f\" ", time2-time1);
1095 MSG_task_destroy(task);
1100 \subsection faq_MIA_SimDag SimDag related questions
1102 \subsubsection faq_SG_comm Implementing communication delays between tasks.
1104 A classic question of SimDag newcomers is about how to express a
1105 communication delay between tasks. The thing is that in SimDag, both
1106 computation and communication are seen as tasks. So, if you want to
1107 model a data dependency between two DAG tasks t1 and t2, you have to
1108 create 3 SD_tasks: t1, t2 and c and add dependencies in the following
1112 SD_task_dependency_add(NULL, NULL, t1, c);
1113 SD_task_dependency_add(NULL, NULL, c, t2);
1116 This way task t2 cannot start before the termination of communication c
1117 which in turn cannot start before t1 ends.
1119 When creating task c, you have to associate an amount of data (in bytes)
1120 corresponding to what has to be sent by t1 to t2.
1122 Finally to schedule the communication task c, you have to build a list
1123 comprising the workstations on which t1 and t2 are scheduled (w1 and w2
1124 for example) and build a communication matrix that should look like
1127 \subsubsection faq_SG_DAG How to implement a distributed dynamic scheduler of DAGs.
1129 Distributed is somehow "contagious". If you start making distributed
1130 decisions, there is no way to handle DAGs directly anymore (unless I
1131 am missing something). You have to encode your DAGs in term of
1132 communicating process to make the whole scheduling process
1133 distributed. Here is an example of how you could do that. Assume T1
1134 has to be done before T2.
1137 int your_agent(int argc, char *argv[] {
1139 T1 = MSG_task_create(...);
1140 T2 = MSG_task_create(...);
1144 if(cond) MSG_task_execute(T1);
1146 if((MSG_task_get_remaining_computation(T1)=0.0) && (you_re_in_a_good_mood))
1147 MSG_task_execute(T2)
1149 /* do something else */
1155 If you decide that the distributed part is not that much important and that
1156 DAG is really the level of abstraction you want to work with, then you should
1157 give a try to \ref SD_API.
1159 \subsection faq_MIA_generic Generic features
1161 \subsubsection faq_more_processes Increasing the amount of simulated processes
1163 Here are a few tricks you can apply if you want to increase the amount
1164 of processes in your simulations.
1166 - <b>A few thousands of simulated processes</b> (soft tricks)\n
1167 SimGrid can use either pthreads library or the UNIX98 contextes. On
1168 most systems, the number of pthreads is limited and then your
1169 simulation may be limited for a stupid reason. This is especially
1170 true with the current linux pthreads, and I cannot get more than
1171 2000 simulated processes with pthreads on my box. The UNIX98
1172 contexts allow me to raise the limit to 25,000 simulated processes
1174 The <tt>--with-context</tt> option of the <tt>./configure</tt>
1175 script allows you to choose between UNIX98 contextes
1176 (<tt>--with-context=ucontext</tt>) and the pthread version
1177 (<tt>--with-context=pthread</tt>). The default value is ucontext
1178 when the script detect a working UNIX98 context implementation. On
1179 Windows boxes, the provided value is discarded and an adapted
1180 version is picked up.\n\n
1181 We experienced some issues with contextes on some rare systems
1182 (solaris 8 and lower or old alpha linuxes comes to mind). The main
1183 problem is that the configure script detect the contextes as being
1184 functional when it's not true. If you happen to use such a system,
1185 switch manually to the pthread version, and provide us with a good
1186 patch for the configure script so that it is done automatically ;)
1188 - <b>Hundred thousands of simulated processes</b> (hard-core tricks)\n
1189 As explained above, SimGrid can use UNIX98 contextes to represent
1190 and handle the simulated processes. Thanks to this, the main
1191 limitation to the number of simulated processes becomes the
1192 available memory.\n\n
1193 Here are some tricks I had to use in order to run a token ring
1194 between 25,000 processes on my laptop (1Gb memory, 1.5Gb swap).\n
1195 - First of all, make sure your code runs for a few hundreds
1196 processes before trying to push the limit. Make sure it's
1197 valgrind-clean, ie that valgrind does not report neither memory
1198 error nor memory leaks. Indeed, numerous simulated processes
1199 result in *fat* simulation hindering debugging.
1200 - It was really boring to write 25,000 entries in the deployment
1201 file, so I wrote a little script
1202 <tt>examples/gras/mutual_exclusion/simple_token/make_deployment.pl</tt>, which you may
1203 want to adapt to your case. You could also think about hijacking
1204 the SURFXML parser (have look at \ref faq_flexml_bypassing).
1205 - The deployment file became quite big, so I had to do what is in
1206 the FAQ entry \ref faq_flexml_limit
1207 - Each UNIX98 context has its own stack entry. As debugging this is
1208 quite hairly, the default value is a bit overestimated so that
1209 user don't get into trouble about this. You want to tune this
1210 size to increse the number of processes. This is the
1211 <tt>STACK_SIZE</tt> define in
1212 <tt>src/xbt/xbt_context_sysv.c</tt>, which is 128kb by default.
1213 Reduce this as much as you can, but be warned that if this value
1214 is too low, you'll get a segfault. The token ring example, which
1215 is quite simple, runs with 40kb stacks.
1216 - You may tweak the logs to reduce the stack size further. When
1217 logging something, we try to build the string to display in a
1218 char array on the stack. The size of this array is constant (and
1219 equal to XBT_LOG_BUFF_SIZE, defined in include/xbt/log/h). If the
1220 string is too large to fit this buffer, we move to a dynamically
1221 sized buffer. In which case, we have to traverse one time the log
1222 event arguments to compute the size we need for the buffer,
1223 malloc it, and traverse the argument list again to do the actual
1225 The idea here is to move XBT_LOG_BUFF_SIZE to 1, forcing the logs
1226 to use a dynamic array each time. This allows us to lower further
1227 the stack size at the price of some performance loss...\n
1228 This allowed me to run the reduce the stack size to ... 4k. Ie,
1229 on my 1Gb laptop, I can run more than 250,000 processes!
1231 \subsubsection faq_MIA_batch_scheduler Is there a native support for batch schedulers in SimGrid?
1233 No, there is no native support for batch schedulers and none is
1234 planned because this is a very specific need (and doing it in a
1235 generic way is thus very hard). However some people have implemented
1236 their own batch schedulers. Vincent Garonne wrote one during his PhD
1237 and put his code in the contrib directory of our SVN so that other can
1238 keep working on it. You may find inspiring ideas in it.
1240 \subsubsection faq_MIA_checkpointing I need a checkpointing thing
1242 Actually, it depends on whether you want to checkpoint the simulation, or to
1243 simulate checkpoints.
1245 The first one could help if your simulation is a long standing process you
1246 want to keep running even on hardware issues. It could also help to
1247 <i>rewind</i> the simulation by jumping sometimes on an old checkpoint to
1248 cancel recent calculations.\n
1249 Unfortunately, such thing will probably never exist in SG. One would have to
1250 duplicate all data structures because doing a rewind at the simulator level
1251 is very very hard (not talking about the malloc free operations that might
1252 have been done in between). Instead, you may be interested in the Libckpt
1253 library (http://www.cs.utk.edu/~plank/plank/www/libckpt.html). This is the
1254 checkpointing solution used in the condor project, for example. It makes it
1255 easy to create checkpoints (at the OS level, creating something like core
1256 files), and rerunning them on need.
1258 If you want to simulate checkpoints instead, it means that you want the
1259 state of an executing task (in particular, the progress made towards
1260 completion) to be saved somewhere. So if a host (and the task executing on
1261 it) fails (cf. #MSG_HOST_FAILURE), then the task can be restarted
1262 from the last checkpoint.\n
1264 Actually, such a thing does not exists in SimGrid either, but it's just
1265 because we don't think it is fundamental and it may be done in the user code
1266 at relatively low cost. You could for example use a watcher that
1267 periodically get the remaining amount of things to do (using
1268 MSG_task_get_remaining_computation()), or fragment the task in smaller
1271 \subsection faq_platform Platform building and Dynamic resources
1273 \subsubsection faq_platform_example Where can I find SimGrid platform files?
1275 There is several little examples in the archive, in the examples/msg
1276 directory. From time to time, we are asked for other files, but we
1277 don't have much at hand right now.
1279 You should refer to the Platform Description Archive
1280 (http://pda.gforge.inria.fr) project to see the other platform file we
1281 have available, as well as the Simulacrum simulator, meant to generate
1282 SimGrid platforms using all classical generation algorithms.
1284 \subsubsection faq_platform_alnem How can I automatically map an existing platform?
1286 We are working on a project called ALNeM (Application-Level Network
1287 Mapper) which goal is to automatically discover the topology of an
1288 existing network. Its output will be a platform description file
1289 following the SimGrid syntax, so everybody will get the ability to map
1290 their own lab network (and contribute them to the catalog project).
1291 This tool is not ready yet, but it move quite fast forward. Just stay
1294 \subsubsection faq_platform_synthetic Generating synthetic but realistic platforms
1296 The third possibility to get a platform file (after manual or
1297 automatic mapping of real platforms) is to generate synthetic
1298 platforms. Getting a realistic result is not a trivial task, and
1299 moreover, nobody is really able to define what "realistic" means when
1300 speaking of topology files. You can find some more thoughts on this
1302 <a href="http://graal.ens-lyon.fr/~alegrand/articles/Simgrid-Introduction.pdf">slides</a>.
1304 If you are looking for an actual tool, there we have a little tool to
1305 annotate Tiers-generated topologies. This perl-script is in
1306 <tt>tools/platform_generation/</tt> directory of the SVN. Dinda et Al.
1307 released a very comparable tool, and called it GridG.
1309 \subsubsection faq_SURF_dynamic Expressing dynamic resource availability in platform files
1311 A nice feature of SimGrid is that it enables you to seamlessly have
1312 resources whose availability change over time. When you build a
1313 platform, you generally declare hosts like that:
1316 <host id="host A" power="100.00"/>
1319 If you want the availability of "host A" to change over time, the only
1320 thing you have to do is change this definition like that:
1323 <host id="host A" power="100.00" availability_file="trace_A.txt" state_file="trace_A_failure.txt"/>
1326 For hosts, availability files are expressed in fraction of available
1327 power. Let's have a look at what "trace_A.txt" may look like:
1336 At time 0, our host will deliver 100 flop/s. At time 11.0, it will
1337 deliver only 50 flop/s until time 20.0 where it will will start
1338 delivering 90 flop/s. Last at time 21.0 (20.0 plus the periodicity
1339 1.0), we'll be back to the beginning and it will deliver 100 flop/s.
1341 Now let's look at the state file:
1348 A negative value means "off" while a positive one means "on". At time
1349 1.0, the host is on. At time 1.0, it is turned off and at time 2.0, it
1350 is turned on again until time 12 (2.0 plus the periodicity 10.0). It
1351 will be turned on again at time 13.0 until time 23.0, and so on.
1353 Now, let's look how the same kind of thing can be done for network
1354 links. A usual declaration looks like:
1357 <link id="LinkA" bandwidth="10.0" latency="0.2"/>
1360 You have at your disposal the following options: bandwidth_file,
1361 latency_file and state_file. The only difference with hosts is that
1362 bandwidth_file and latency_file do not express fraction of available
1363 power but are expressed directly in bytes per seconds and seconds.
1365 \subsubsection faq_platform_multipath How to express multipath routing in platform files?
1367 It is unfortunately impossible to express the fact that there is more
1368 than one routing path between two given hosts. Let's consider the
1369 following platform file:
1372 <route src="A" dst="B">
1375 <route src="B" dst="C">
1378 <route src="A" dst="C">
1383 Although it is perfectly valid, it does not mean that data traveling
1384 from A to C can either go directly (using link 3) or through B (using
1385 links 1 and 2). It simply means that the routing on the graph is not
1386 trivial, and that data do not following the shortest path in number of
1387 hops on this graph. Another way to say it is that there is no implicit
1388 in these routing descriptions. The system will only use the routes you
1389 declare (such as <route src="A" dst="C"><link:ctn
1390 id="3"/></route>), without trying to build new routes by aggregating
1393 You are also free to declare platform where the routing is not
1394 symmetric. For example, add the following to the previous file:
1397 <route src="C" dst="A">
1403 This makes sure that data from C to A go through B where data from A
1404 to C go directly. Don't worry about realism of such settings since
1405 we've seen ways more weird situation in real settings (in fact, that's
1406 the realism of very regular platforms which is questionable, but
1407 that's another story).
1409 \subsubsection faq_flexml_bypassing Bypassing the XML parser with your own C functions
1411 So you want to bypass the XML files parser, uh? Maybe doing some parameter
1412 sweep experiments on your simulations or so? This is possible, and
1413 it's not even really difficult (well. Such a brutal idea could be
1414 harder to implement). Here is how it goes.
1416 For this, you have to first remember that the XML parsing in SimGrid is done
1417 using a tool called FleXML. Given a DTD, this gives a flex-based parser. If
1418 you want to bypass the parser, you need to provide some code mimicking what
1419 it does and replacing it in its interactions with the SURF code. So, let's
1420 have a look at these interactions.
1422 FleXML parser are close to classical SAX parsers. It means that a
1423 well-formed SimGrid platform XML file might result in the following
1426 - start "platform_description" with attribute version="2"
1427 - start "host" with attributes id="host1" power="1.0"
1429 - start "host" with attributes id="host2" power="2.0"
1431 - start "link" with ...
1433 - start "route" with ...
1434 - start "link:ctn" with ...
1437 - end "platform_description"
1439 The communication from the parser to the SURF code uses two means:
1440 Attributes get copied into some global variables, and a surf-provided
1441 function gets called by the parser for each event. For example, the event
1442 - start "host" with attributes id="host1" power="1.0"
1444 let the parser do something roughly equivalent to:
1446 strcpy(A_host_id,"host1");
1451 In SURF, we attach callbacks to the different events by initializing the
1452 pointer functions to some the right surf functions. Since there can be
1453 more than one callback attached to the same event (if more than one
1454 model is in use, for example), they are stored in a dynar. Example in
1455 workstation_ptask_L07.c:
1457 /* Adding callback functions */
1458 surf_parse_reset_parser();
1459 surfxml_add_callback(STag_surfxml_host_cb_list, &parse_cpu_init);
1460 surfxml_add_callback(STag_surfxml_prop_cb_list, &parse_properties);
1461 surfxml_add_callback(STag_surfxml_link_cb_list, &parse_link_init);
1462 surfxml_add_callback(STag_surfxml_route_cb_list, &parse_route_set_endpoints);
1463 surfxml_add_callback(ETag_surfxml_link_c_ctn_cb_list, &parse_route_elem);
1464 surfxml_add_callback(ETag_surfxml_route_cb_list, &parse_route_set_route);
1466 /* Parse the file */
1467 surf_parse_open(file);
1468 xbt_assert1((!surf_parse()), "Parse error in %s", file);
1472 So, to bypass the FleXML parser, you need to write your own version of the
1473 surf_parse function, which should do the following:
1474 - Fill the A_<tag>_<attribute> variables with the wanted values
1475 - Call the corresponding STag_<tag>_fun function to simulate tag start
1476 - Call the corresponding ETag_<tag>_fun function to simulate tag end
1477 - (do the same for the next set of values, and loop)
1479 Then, tell SimGrid that you want to use your own "parser" instead of the stock one:
1481 surf_parse = surf_parse_bypass_environment;
1482 MSG_create_environment(NULL);
1483 surf_parse = surf_parse_bypass_application;
1484 MSG_launch_application(NULL);
1487 A set of macros are provided at the end of
1488 include/surf/surfxml_parse.h to ease the writing of the bypass
1489 functions. An example of this trick is distributed in the file
1490 examples/msg/masterslave/masterslave_bypass.c
1492 \subsection faq_simgrid_configuration Changing SimGrid's behavior
1494 A number of options can be given at runtime to change the default
1495 SimGrid behavior. In particular, you can change the default cpu and
1498 \subsubsection faq_simgrid_configuration_gtnets Using GTNetS
1500 It is possible to use a packet-level network simulator
1501 instead of the default flow-based simulation. You may want to use such
1502 an approach if you have doubts about the validity of the default model
1503 or if you want to perform some validation experiments. At the moment,
1504 we support the GTNetS simulator (it is still rather experimental
1505 though, so leave us a message if you play with it).
1509 To enable GTNetS model inside SimGrid it is needed to patch the GTNetS simulator source code
1510 and build/install it from scratch
1513 - <b>Download and enter the recent downloaded GTNetS directory</b>
1516 svn checkout svn://scm.gforge.inria.fr/svn/simgrid/contrib/trunk/GTNetS/
1521 - <b>Use the following commands to unzip and patch GTNetS package to work within SimGrid.</b>
1524 unzip gtnets-current.zip
1525 tar zxvf gtnets-current-patch.tgz
1527 cat ../00*.patch | patch -p1
1530 - <b>OPTIONALLY</b> you can use a patch for itanium 64bit processor family.
1533 cat ../AMD64-FATAL-Removed-DUL_SIZE_DIFF-Added-fPIC-compillin.patch | patch -p1
1536 - <b>Compile GTNetS</b>
1538 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.
1542 ln -sf Makefile.linux Makefile
1548 - <b>NOTE</b> A lot of warnings are expected but the application should compile
1549 just fine. If the makefile insists in compiling some QT libraries
1550 please try a make clean before asking for help.
1553 - <b>To compile optimized version</b>
1560 - <b>Installing GTNetS</b>
1562 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.
1565 ln -sf /<absolute_path>/gtnets_current/libgtsim-debug.so /<userhome>/usr/lib/libgtnets.so
1566 export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/<userhome>/usr/lib/libgtnets.so
1567 mkdir /<userhome>/usr/include/gtnets
1568 cp -fr SRC/*.h /<userhome>/usr/include/gtnets
1572 - <b>Enable GTNetS support in SimGrid</b>
1575 ./configure --with-gtnets=/<userhome>/usr
1578 - <b>Once you have followed all the instructions for compiling and
1579 installing successfully you can activate this feature at
1580 runntime with the following options:</b>
1583 cd simgrid/example/msg/
1589 - <b>Or try the GTNetS model dogbone example with</b>
1592 gtnets/gtnets gtnets/onelink-p.xml gtnets/onelink-d.xml --cfg=network_model:GTNets
1596 A long version of this <a href="http://gforge.inria.fr/docman/view.php/12/6283/GTNetS HowTo.html">HowTo</a> it is available
1599 More about GTNetS simulator at <a href="http://www.ece.gatech.edu/research/labs/MANIACS/GTNetS/index.html">GTNetS Website</a>
1603 The patches provided by us worked successfully with GTNetS found
1604 <a href="http://www.ece.gatech.edu/research/labs/MANIACS/GTNetS/software/gtnets-current.zip">here</a>,
1605 dated from 12th June 2008. Due to the discontinuing development of
1606 GTNetS it is impossible to precise a version number. We STRONGLY recommend you
1607 to download and install the GTNetS version found in SimGrid repository as explained above.
1612 \subsubsection faq_simgrid_configuration_alternate_network Using alternative flow models
1614 The default simgrid network model uses a max-min based approach as
1615 explained in the research report
1616 <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>.
1617 Other models have been proposed and implemented since then (see for example
1618 <a href="http://mescal.imag.fr/membres/arnaud.legrand/articles/simutools09.pdf">Accuracy Study and Improvement of Network Simulation in the SimGrid Framework</a>)
1619 and can be activated at runtime. For example:
1621 ./mycode platform.xml deployment.xml --cfg=workstation_model:compound --cfg=network_model:LV08 -cfg=cpu_model:Cas01
1624 Possible models for the network are currently "Constant", "CM02",
1625 "LegrandVelho", "GTNets", Reno", "Reno2", "Vegas". Others will
1626 probably be added in the future and many of the previous ones are
1627 experimental and are likely to disappear without notice...
1629 \section faq_troubleshooting Troubleshooting
1631 \subsection faq_trouble_lib_compil SimGrid compilation and installation problems
1633 \subsubsection faq_trouble_lib_config ./configure fails!
1635 We know only one reason for the configure to fail:
1637 - <b>You are using a broken build environment</b>\n
1638 If symptom is that configure complains about gcc not being able to build
1639 executables, you are probably missing the libc6-dev package. Damn Ubuntu.
1641 If you experience other kind of issue, please get in touch with us. We are
1642 always interested in improving our portability to new systems.
1644 \subsubsection faq_trouble_distcheck Dude! "make check" fails on my machine!
1646 Don't assume we never run this target, because we do. Check
1647 http://bob.loria.fr:8010 if you don't believe us.
1649 There is several reasons which may cause the make check to fail on your
1652 - <b>You are using a broken libc (probably concerning the contextes)</b>.\n
1653 The symptom is that the "make check" fails within the examples/msg directory.\n
1654 By default, SimGrid uses something called ucontexts. This is part of the
1655 libc, but it's quite undertested. For example, some (old) versions of the
1656 glibc on alpha do not implement these functions, but provide the stubs
1657 (which return ENOSYS: not implemented). It may fool our detection mechanism
1658 and leads to segfaults. There is not much we can do to fix the bug.
1659 A workaround is to compile with --with-context=pthread to avoid
1660 ucontext completely. You'll be a bit more limited in the number
1661 of simulated processes you can start concurrently, but 5000
1662 processes is still enough for most purposes, isn't it?\n
1663 This limitation is the reason why we insist on using this piece of ...
1664 software even if it's so troublesome.\n
1665 <b>=> use --with-pthread on AMD64 architecture that do not have an
1666 ultra-recent libc.</b>
1668 - <b>There is a bug in SimGrid we aren't aware of</b>.\n
1669 If none of the above apply, please drop us a mail on the mailing list so
1670 that we can check it out. Make sure to read \ref faq_bugrepport
1673 \subsection faq_trouble_compil User code compilation problems
1675 \subsubsection faq_trouble_err_logcat "gcc: _simgrid_this_log_category_does_not_exist__??? undeclared (first use in this function)"
1677 This is because you are using the log mecanism, but you didn't created
1678 any default category in this file. You should refer to \ref XBT_log
1679 for all the details, but you simply forgot to call one of
1680 XBT_LOG_NEW_DEFAULT_CATEGORY() or XBT_LOG_NEW_DEFAULT_SUBCATEGORY().
1682 \subsubsection faq_trouble_pthreadstatic "gcc: undefined reference to pthread_key_create"
1684 This indicates that one of the library SimGrid depends on (libpthread
1685 here) was missing on the linking command line. Dependencies of
1686 libsimgrid are expressed directly in the dynamic library, so it's
1687 quite impossible that you see this message when doing dynamic linking.
1689 If you compile your code statically (and if you use a pthread version
1690 of SimGrid -- see \ref faq_more_processes), you must absolutely
1691 specify <tt>-lpthread</tt> on the linker command line. As usual, this should
1692 come after <tt>-lsimgrid</tt> on this command line.
1694 \subsection faq_trouble_errors Runtime error messages
1696 \subsubsection faq_flexml_limit "surf_parse_lex: Assertion `next limit' failed."
1698 This is because your platform file is too big for the parser.
1700 Actually, the message comes directly from FleXML, the technology on top of
1701 which the parser is built. FleXML has the bad idea of fetching the whole
1702 document in memory before parsing it. And moreover, the memory buffer size
1703 must be determined at compilation time.
1705 We use a value which seems big enough for our need without bloating the
1706 simulators footprints. But of course your mileage may vary. In this case,
1707 just edit src/surf/surfxml.l modify the definition of
1708 FLEXML_BUFFERSTACKSIZE. E.g.
1711 #define FLEXML_BUFFERSTACKSIZE 1000000000
1714 Then recompile and everything should be fine, provided that your version of
1715 Flex is recent enough (>= 2.5.31). If not the compilation process should
1718 A while ago, we worked on FleXML to reduce a bit its memory consumption, but
1719 these issues remain. There is two things we should do:
1721 - use a dynamic buffer instead of a static one so that the only limit
1722 becomes your memory, not a stupid constant fixed at compilation time
1723 (maybe not so difficult).
1724 - change the parser so that it does not need to get the whole file in
1725 memory before parsing
1726 (seems quite difficult, but I'm a complete newbe wrt flex stuff).
1728 These are changes to FleXML itself, not SimGrid. But since we kinda hijacked
1729 the development of FleXML, I can grant you that any patches would be really
1730 welcome and quickly integrated.
1732 <b>Update:</b> A new version of FleXML (1.7) was released. Most of the work
1733 was done by William Dowling, who use it in his own work. The good point is
1734 that it now use a dynamic buffer, and that the memory usage was greatly
1735 improved. The downside is that William also changed some things internally,
1736 and it breaks the hack we devised to bypass the parser, as explained in
1737 \ref faq_flexml_bypassing. Indeed, this is not a classical usage of the
1738 parser, and Will didn't imagine that we may have used (and even documented)
1739 such a crude usage of FleXML. So, we now have to repair the bypassing
1740 functionality to use the lastest FleXML version and fix the memory usage in
1743 \subsubsection faq_trouble_gras_transport GRAS spits networking error messages
1745 Gras, on real platforms, naturally use regular sockets to communicate. They
1746 are deeply hidden in the gras abstraction, but when things go wrong, you may
1747 get some weird error messages. Here are some example, with the probable
1750 - <b>Transport endpoint is not connected</b>: several processes try to open
1751 a server socket on the same port number of the same machine. This is
1752 naturally bad and each process should pick its own port number for this.\n
1753 Maybe, you just have some processes remaining from a previous experiment
1755 Killing them may help, but again if you kill -KILL them, you'll have to
1756 wait for a while: they didn't close there sockets properly and the system
1757 needs a while to notice that this port is free again.
1759 - <b>Socket closed by remote side</b>: if the remote process is not
1760 supposed to close the socket at this point, it may be dead.
1762 - <b>Connection reset by peer</b>: I found this on Internet about this
1763 error. I think it's what's happening here, too:\n
1764 <i>This basically means that a network error occurred while the client was
1765 receiving data from the server. But what is really happening is that the
1766 server actually accepts the connection, processes the request, and sends
1767 a reply to the client. However, when the server closes the socket, the
1768 client believes that the connection has been terminated abnormally
1769 because the socket implementation sends a TCP reset segment telling the
1770 client to throw away the data and report an error.\n
1771 Sometimes, this problem is caused by not properly closing the
1772 input/output streams and the socket connection. Make sure you close the
1773 input/output streams and socket connection properly. If everything is
1774 closed properly, however, and the problem persists, you can work around
1775 it by adding a one-second sleep before closing the streams and the
1776 socket. This technique, however, is not reliable and may not work on all
1778 Since GRAS sockets are closed properly (repeat after me: there is no bug
1779 in GRAS), it is either that you are closing your sockets on server side
1780 before the client get a chance to read them (use gras_os_sleep() to delay
1781 the server), or the server died awfully before the client got the data.
1783 \subsubsection faq_trouble_errors_big_fat_warning I'm told that my XML files are too old.
1785 The format of the XML platform description files is sometimes
1786 improved. For example, we decided to change the units used in SimGrid
1787 from MBytes, MFlops and seconds to Bytes, Flops and seconds to ease
1788 people exchanging small messages. We also reworked the route
1789 descriptions to allow more compact descriptions.
1791 That is why the XML files are versionned using the 'version' attribute
1792 of the root tag. Currently, it should read:
1794 <platform version="2">
1797 If your files are too old, you can use the simgrid_update_xml.pl
1798 script which can be found in the tools directory of the archive.
1800 \subsection faq_trouble_valgrind Valgrind-related and other debugger issues
1802 If you don't, you really should use valgrind to debug your code, it's
1805 \subsubsection faq_trouble_vg_longjmp longjmp madness in valgrind
1807 This is when valgrind starts complaining about longjmp things, just like:
1809 \verbatim ==21434== Conditional jump or move depends on uninitialised value(s)
1810 ==21434== at 0x420DBE5: longjmp (longjmp.c:33)
1812 ==21434== Use of uninitialised value of size 4
1813 ==21434== at 0x420DC3A: __longjmp (__longjmp.S:48)
1816 This is the sign that you didn't used the exception mecanism well. Most
1817 probably, you have a <tt>return;</tt> somewhere within a <tt>TRY{}</tt>
1818 block. This is <b>evil</b>, and you must not do this. Did you read the section
1821 \subsubsection faq_trouble_vg_libc Valgrind spits tons of errors about backtraces!
1823 It may happen that valgrind, the memory debugger beloved by any decent C
1824 programmer, spits tons of warnings like the following :
1825 \verbatim ==8414== Conditional jump or move depends on uninitialised value(s)
1826 ==8414== at 0x400882D: (within /lib/ld-2.3.6.so)
1827 ==8414== by 0x414EDE9: (within /lib/tls/i686/cmov/libc-2.3.6.so)
1828 ==8414== by 0x400B105: (within /lib/ld-2.3.6.so)
1829 ==8414== by 0x414F937: _dl_open (in /lib/tls/i686/cmov/libc-2.3.6.so)
1830 ==8414== by 0x4150F4C: (within /lib/tls/i686/cmov/libc-2.3.6.so)
1831 ==8414== by 0x400B105: (within /lib/ld-2.3.6.so)
1832 ==8414== by 0x415102D: __libc_dlopen_mode (in /lib/tls/i686/cmov/libc-2.3.6.so)
1833 ==8414== by 0x412D6B9: backtrace (in /lib/tls/i686/cmov/libc-2.3.6.so)
1834 ==8414== by 0x8076446: xbt_dictelm_get_ext (dict_elm.c:714)
1835 ==8414== by 0x80764C1: xbt_dictelm_get (dict_elm.c:732)
1836 ==8414== by 0x8079010: xbt_cfg_register (config.c:208)
1837 ==8414== by 0x806821B: MSG_config (msg_config.c:42)
1840 This problem is somewhere in the libc when using the backtraces and there is
1841 very few things we can do ourselves to fix it. Instead, here is how to tell
1842 valgrind to ignore the error. Add the following to your ~/.valgrind.supp (or
1843 create this file on need). Make sure to change the obj line according to
1844 your personnal mileage (change 2.3.6 to the actual version you are using,
1845 which you can retrieve with a simple "ls /lib/ld*.so").
1848 name: Backtrace madness
1850 obj:/lib/ld-2.3.6.so
1855 fun:__libc_dlopen_mode
1858 Then, you have to specify valgrind to use this suppression file by passing
1859 the <tt>--suppressions=$HOME/.valgrind.supp</tt> option on the command line.
1860 You can also add the following to your ~/.bashrc so that it gets passed
1861 automatically. Actually, it passes a bit more options to valgrind, and this
1862 happen to be my personnal settings. Check the valgrind documentation for
1865 \verbatim export VALGRIND_OPTS="--leak-check=yes --leak-resolution=high --num-callers=40 --tool=memcheck --suppressions=$HOME/.valgrind.supp" \endverbatim
1867 \subsubsection faq_trouble_backtraces Truncated backtraces
1869 When debugging SimGrid, it's easier to pass the
1870 --disable-compiler-optimization flag to the configure if valgrind or
1871 gdb get fooled by the optimization done by the compiler. But you
1872 should remove these flag when everything works before going in
1873 production (before launching your 1252135 experiments), or everything
1874 will run only one half of the true SimGrid potential.
1876 \subsection faq_deadlock There is a deadlock in my code!!!
1878 Unfortunately, we cannot debug every code written in SimGrid. We
1879 furthermore believe that the framework provides ways enough
1880 information to debug such informations yourself. If the textual output
1881 is not enough, Make sure to check the \ref faq_visualization FAQ entry to see
1882 how to get a graphical one.
1884 Now, if you come up with a really simple example that deadlocks and
1885 you're absolutely convinced that it should not, you can ask on the
1886 list. Just be aware that you'll be severely punished if the mistake is
1887 on your side... We have plenty of FAQ entries to redact and new
1888 features to implement for the impenitents! ;)
1890 \subsection faq_surf_network_latency I get weird timings when I play with the latencies.
1892 OK, first of all, remember that units should be Bytes, Flops and
1893 Seconds. If you don't use such units, some SimGrid constants (e.g. the
1894 SG_TCP_CTE_GAMMA constant used in most network models) won't have the
1895 right unit and you'll end up with weird results.
1897 Here is what happens with a single transfer of size L on a link
1898 (bw,lat) when nothing else happens.
1901 0-----lat--------------------------------------------------t
1902 |-----|**** real_bw =min(bw,SG_TCP_CTE_GAMMA/(2*lat)) *****|
1905 In more complex situations, this min is the solution of a complex
1906 max-min linear system. Have a look
1907 <a href="http://lists.gforge.inria.fr/pipermail/simgrid-devel/2006-April/thread.html">here</a>
1908 and read the two threads "Bug in SURF?" and "Surf bug not
1909 fixed?". You'll have a few other examples of such computations. You
1910 can also read "A Network Model for Simulation of Grid Application" by
1911 Henri Casanova and Loris Marchal to have all the details. The fact
1912 that the real_bw is smaller than bw is easy to understand. The fact
1913 that real_bw is smaller than SG_TCP_CTE_GAMMA/(2*lat) is due to the
1914 window-based congestion mechanism of TCP. With TCP, you can't exploit
1915 your huge network capacity if you don't have a good round-trip-time
1916 because of the acks...
1918 Anyway, what you get is t=lat + L/min(bw,SG_TCP_CTE_GAMMA/(2*lat)).
1920 * if I you set (bw,lat)=(100 000 000, 0.00001), you get t = 1.00001 (you fully
1922 * if I you set (bw,lat)=(100 000 000, 0.0001), you get t = 1.0001 (you're on the
1924 * if I you set (bw,lat)=(100 000 000, 0.001), you get t = 10.001 (ouch!)
1926 This bound on the effective bandwidth of a flow is not the only thing
1927 that may make your result be unexpected. For example, two flows
1928 competing on a saturated link receive an amount of bandwidth inversely
1929 proportional to their round trip time.
1931 \subsection faq_bugrepport So I've found a bug in SimGrid. How to report it?
1933 We do our best to make sure to hammer away any bugs of SimGrid, but this is
1934 still an academic project so please be patient if/when you find bugs in it.
1935 If you do, the best solution is to drop an email either on the simgrid-user
1936 or the simgrid-devel mailing list and explain us about the issue. You can
1937 also decide to open a formal bug report using the
1938 <a href="https://gforge.inria.fr/tracker/?atid=165&group_id=12&func=browse">relevant
1939 interface</a>. You need to login on the server to get the ability to submit
1942 We will do our best to solve any problem repported, but you need to help us
1943 finding the issue. Just telling "it segfault" isn't enough. Telling "It
1944 segfaults when running the attached simulator" doesn't really help either.
1945 You may find the following article interesting to see how to repport
1946 informative bug repports:
1947 http://www.chiark.greenend.org.uk/~sgtatham/bugs.html (it is not SimGrid
1948 specific at all, but it's full of good advices).
1950 \author Arnaud Legrand (arnaud.legrand::imag.fr)
1951 \author Martin Quinson (martin.quinson::loria.fr)
1956 ******************************************************************
1957 * OLD CRUFT NOT USED ANYMORE *
1958 ******************************************************************
1961 \subsection faq_crosscompile Cross-compiling a Windows DLL of SimGrid from linux
1963 At the moment, we do not distribute Windows pre-compiled version of SimGrid
1964 because the support for this platform is still experimental. We know that
1965 some parts of the GRAS environment do not work, and we think that the others
1966 environments (MSG and SD) have good chances to work, but we didn't test
1967 ourselves. This section explains how we generate the SimGrid DLL so that you
1968 can build it for yourself. First of all, you need to have a version more
1969 recent than 3.1 (ie, a SVN version as time of writting).
1971 In order to cross-compile the package to windows from linux, you need to
1972 install mingw32 (minimalist gnu win32). On Debian, you can do so by
1973 installing the packages mingw32 (compiler), mingw32-binutils (linker and
1974 so), mingw32-runtime.
1976 You can use the VPATH support of configure to compile at the same time for
1977 linux and windows without dupplicating the source nor cleaning the tree
1978 between each. Just run bootstrap (if you use the SVN) to run the autotools.
1979 Then, create a linux and a win directories. Then, type:
1980 \verbatim cd linux; ../configure --srcdir=.. <usual configure flags>; make; cd ..
1981 cd win; ../configure --srcdir=.. --host=i586-mingw32msvc <flags>; make; cd ..
1983 The trick to VPATH builds is to call configure from another directory,
1984 passing it an extra --srcdir argument to tell it where all the sources are.
1985 It will understand you want to use VPATH. Then, the trick to cross-compile
1986 is simply to add a --host argument specifying the target you want to build
1987 for. The i586-mingw32msvc string is what you have to pass to use the mingw32
1988 environment as distributed in Debian.
1990 After that, you can run all make targets from both directories, and test
1991 easily that what you change for one arch does not break the other one.
1993 It is possible that this VPATH build thing breaks from time to time in the
1994 SVN since it's quite fragile, but it's granted to work in any released
1995 version. If you experience problems, drop us a mail.
1997 Another possible source of issue is that at the moment, building the
1998 examples request to use the gras_stub_generator tool, which is a compiled
1999 program, not a script. In cross-compilation, you need to cross-execute with
2000 wine for example, which is not really pleasant. We are working on this, but
2001 in the meanwhile, simply don't build the examples in cross-compilation
2002 (<tt>cd src</tt> before running make).
2004 Program (cross-)compiled with mingw32 do request an extra DLL at run-time to be
2005 usable. For example, if you want to test your build with wine, you should do
2006 the following to put this library where wine looks for DLLs.
2008 cp /usr/share/doc/mingw32-runtime/mingwm10.dll.gz ~/.wine/c/windows/system/
2009 gunzip ~/.wine/c/windows/system/mingwm10.dll.gz
2012 The DLL is built in src/.libs, and installed in the <i>prefix</i>/bin directory
2013 when you run make install.
2015 If you want to use it in a native project on windows, you need to use
2016 simgrid.dll and mingwm10.dll. For each DLL, you need to build .def file
2017 under linux (listing the defined symbols), and convert it into a .lib file
2018 under windows (specifying this in a way that windows compilers like). To
2019 generate the def files, run (under linux):
2020 \verbatim echo "LIBRARY libsimgrid-0.dll" > simgrid.def
2021 echo EXPORTS >> simgrid.def
2022 nm libsimgrid-0.dll | grep ' T _' | sed 's/.* T _//' >> simgrid.def
2023 nm libsimgrid-0.dll | grep ' D _' | sed 's/.* D _//' | sed 's/$/ DATA/' >> simgrid.def
2025 echo "LIBRARY mingwm10.dll" > mingwm10.def
2026 echo EXPORTS >> mingwm10.def
2027 nm mingwm10.dll | grep ' T _' | sed 's/.* T _//' >> mingwm10.def
2028 nm mingwm10.dll | grep ' D _' | sed 's/.* D _//' | sed 's/$/ DATA/' >> mingwm10.def
2031 To create the import .lib files, use the <tt>lib</tt> windows tool (from
2032 MSVC) the following way to produce simgrid.lib and mingwm10.lib
2033 \verbatim lib /def:simgrid.def
2034 lib /def:mingwm10.def
2037 If you happen to use Borland C Builder, the right command line is the
2038 following (note that you don't need any file.def to get this working).
2039 \verbatim implib simgrid.lib libsimgrid-0.dll
2040 implib mingwm10.lib mingwm10.dll
2043 Then, set the following parameters in Visual C++ 2005:
2044 Linker -> Input -> Additional dependencies = simgrid.lib mingwm10.lib
2046 Just in case you wonder how to generate a DLL from libtool in another
2047 project, we added -no-undefined to any lib*_la_LDFLAGS variables so that
2048 libtool accepts to generate a dynamic library under windows. Then, to make
2049 it true, we pass any dependencies (such as -lws2 under windows or -lpthread
2050 on need) on the linking line. Passing such deps is a good idea anyway so
2051 that they get noted in the library itself, avoiding the users to know about
2052 our dependencies and put them manually on their compilation line. Then we
2053 added the AC_LIBTOOL_WIN32_DLL macro just before AC_PROG_LIBTOOL in the
2054 configure.ac. It means that we exported any symbols which need to be.
2055 Nowadays, functions get automatically exported, so we don't need to load our
2056 header files with tons of __declspec(dllexport) cruft. We only need to do so
2057 for data, but there is no public data in SimGrid so we are good.
