SimGrid  3.13
Versatile Simulation of Distributed Systems
Bindings

Java Binding

Simgrid-java is a java API that let you use Simgrid MSG and SURF API in your favorite language (java). Without it, you would be forced to use C or one of the other bindings provided.

MSG was the first distributed programming environment provided within SimGrid. While almost realistic, it remains quite simple. This describes the Java bindings to this interface.

The javadoc is accessible here

Who should use this (and who shouldn't)

You should use MSG if you want to study some heuristics for a given problem you don't really want to implement. SimGrid-java let you use MSG and SURF while coding in Java. So if your need is MSG + Java (+ SURF), you're in the right section!

Usage overview

To make a long story short, it's a JNI binding for MSG and a SWIG binding for SURF, so it implies that:

  • Most of the MSG/SURF and SimGrid documentation about behavioral aspects applies directly to what you are programming.
  • MSG/SURF data structures are mapped to Java objects. So it means that from the syntax point of view, you have to know how those objects are. Fortunately, we have generated the Javadoc for those objects. So take a look at it

Finally, it implies also that your program can crash for 3 main reasons:

  • Your Java part is not good: you'll have a good old java exception thrown, and hence you should be able to correct it by yourself.
  • Our java part is not good: you'll also have a java exception thrown, but we have real doubts this can happen, since the java part is only a JNI binding. The other option is that it crashed because you used incorrectly the MSG API, so this means also you should have an MSGException. It means you should read carefully MSG samples and/or documentation.
  • Something has crashed in the C part. Okay, here comes the tricky thing.

C crashes mainly for 2 reasons:

  • When something goes wrong in your simulation, sometimes the C part stops because you used SimGrid incorrectly, and JNI bindings are not fond of that. It means that you'll have something that looks ugly, but you should be able to identify what's going wrong in your code by carefully reading the whole error message
  • It may happen that the problem comes directly from SimGrid: in this case, the error should be uglier. In that case, you may submit a bug directly to SimGrid.

How to install Simgrid-java

To use java with Simgrid you have to install some dependencies:

  • Java JDK packages, such as openjdk7 or sun-java6-jdk (with libgcj10-dev or another version of gcj). For maximal performance and scalability, use a coroutine-enabled JVM (see How to use the coroutines context factory).

Then build Simgrid with the Java bindings enabled:

1 cmake -Denable_java=ON .

If cmake complains that jni could not be found, you need to tell it where JNI header files are located. the following command should tell you:

1 $ locate jni.h
2 /usr/lib/jvm/java-6-openjdk-amd64/include/jni.h
3 /usr/lib/jvm/java-7-openjdk-amd64/include/jni.h

If you have several version of jni installed (as in the example above), you need to check the version of java that is used by default on your machine (using javac -version), and pick the right one. Then set the JAVA_INCLUDE_PATH environment variable to the right path (note that we remove the filename jni.h from that path), and relaunch cmake.

1 $ export JAVA_INCLUDE_PATH=/usr/lib/jvm/java-6-openjdk-amd64/include/
2 $ cmake .

How to use Simgrid-java

To execute the examples you need to add the path where you installed the generated libsimgrid-java and libsimgrid libraries into the LD_LIBRARY_PATH.

Be careful on Mac, this variable is called DYLD_LIBRARY_PATH and not LD_LIBRARY_PATH.

1 $ export SIMGRID_ROOT="$HOME/Install/simgrid/" # change it to the path where you installed the SimGrid library
2 $ export LD_LIBRARY_PATH=${LD_LIBRARY_PATH:+$LD_LIBRARY_PATH:}$SIMGRID_ROOT/lib
3 $ cd examples
4 $ java -classpath .:../simgrid.jar basic/BasicTest platform.xml basic/basicDeployment.xml

If you want to make these settings permanent even after a reboot, you need to add the export lines into your ~/.bashrc file, or equivalent.

How to use the coroutines context factory

There is two main motivations to use the coroutine variant of SimGrid Java bindings: it's about 5 times faster than the default thread-based context factory, and the amount of runnable processes is then only limited by the amount of RAM that you have. The drawbacks are that it requires a specific and rather experimental JVM to run, and that this context factory itself remains a bit experimental so far.

Getting a mlvm JVM

You need to get a patched JVM from here (many thanks to Lukas Stadler for this work!).

You can either get a prebuilt binary, or recompile your own JVM. Make sure to get a coro-simple version, as we don't need to serialize nor migrate stacks in SimGrid. You should be able to follow the README.txt that you'll get in the repository, but here is how we did it, just in case. The instructions are given for a debian or Ubuntu box, but I think you should manage to convert it to your system quite easily. Finally, if you're really stuck, you can get the version compiled by Jonathan Rouzaud-Cornabas from his web page. This version is known to work with SimGrid for sure! http://graal.ens-lyon.fr/~jrouzaud/files/corosimple-linux-amd64-20120914.tgz

  1. Install mercurial and some dependencies
    1 sudo apt-get install mercurial ksh libfreetype6-dev libcups2-dev libasound2-dev gawk openjdk-7-jdk libxext-dev libxrender-dev libxtst-dev
    2 # Grab the forest extension: we need to source-install it
    3 hg clone https://bitbucket.org/gxti/hgforest hgforest
  2. Configure the mercurial extensions: Edit ~/.hgrc and paste the following lines. Don't forget to change the /path/to/forest.py to point to where you just downloaded the source.

    Forest extension is needed to download the openjdk source code and patches while the mq line is needed to apply the patches. The username is needed at the step "preparing the sources", not sure why.

    [ui]
    username = YouUserameWithoutSpaces
    [extensions]
    forest=/path/to/forest.py
    mq=
  3. Prepare the source code
    1 # create a working directory, and enter it
    2 mkdir davinci; cd davinci
    3 
    4 # Grab the sources
    5 hg fclone http://hg.openjdk.java.net/hsx/hotspot-comp sources
    6 # Grab the patches
    7 hg fclone http://hg.openjdk.java.net/mlvm/mlvm patches
    8 
    9 # Link the patch directories into the sources
    10 bash patches/make/link-patch-dirs.sh sources patches
    11 # Test wether the previous command worked with
    12 ls -i patches/hotspot/series sources/hotspot/.hg/patches/series
    13 # It should display something like the following.
    14 # (note that both file share the same inode number)
    15 # 9707849 patches/hotspot/series
    16 # 9707849 sources/hotspot/.hg/patches/series
    17 
    18 # Specify what to compile.
    19 export davinci=${pwd} guards="buildable testable coro-simple"
    20 # Apply the patches
    21 sh patches/make/each-patch-repo.sh hg qselect --reapply $guards `sh $davinci/patches/make/current-release.sh`
    22 # Check that it understood that you want the patch applied:
    23 grep -r GLOBAL_GUARDS patches/make/
    24 # this should display something like the following (maybe amonst other unrelated lines)
    25 # GLOBAL_GUARDS=buildable testable coro-simple
    26 # If this does not work, edit patches/make/Makefile,
    27 # manually coro-simple to GLOBAL_GUARDS and then
    28 # rerun the patches/make/each-patch-repo.sh script as earlier
    29 
    30 
    31 # Finish the setup
    32 cd patches/make;
    33 make setup && make force && make && make FORCE_VERSIONS=1 && echo "Sources are properly setup"
    34 # If this last command failed, check your mercurial config within ~/.hgrc (see above)
  4. Compile it all
    1 unset LD_LIBRARY_PATH
    2 export ALT_BOOTDIR=/usr/lib/jvm/java-7-openjdk-amd64/
    3 cd sources
    4 # Check that everything is fine
    5 make sanity
    6 # Go for it (it takes about half an hour on my machine)
    7 make all
    8 
    9 # Check that the coroutine library got compiled in
    10 ls sources/build/linux-amd64/classes/java/dyn/
    11 # This should display a bunch of class files. If not, something went wrong, you need to investigate further

Using coroutine contexts

SimGrid Java will automatically switch to the coroutine context factory if your JVM support it, so you will just need to execute your simulation with the correct JVM. The selected context factory gets displayed automatically.

1 export LD_LIBRARY_PATH=/path/to/simgrid.so:/path/to/libsimgrid-java.so
2 cd examples
3 $PATH_TO_COROUTINE_JVM/java -classpath .:../simgrid.jar masterslave.Masterslave masterslave/ masterslaveDeployment.xml platform.xml

Note that you may have to adjust the "coro.stacksPerThread" configuration option to run large simulations. The default is 100 and you want to increase it to run more processes.

1 $ $PATH_TO_COROUTINE_JVM/java -Dcoro.stacksPerThread=$STACKS_NUMBER -classpath .:../simgrid.jar basic/BasicTest platform.xml basic/basicDeployment.xml

If you reach the point where the creation of new simulated processes fail with the message "Can't create coroutine object", you may need to increase the relevant system limit with the following command.

1 sysctl -w vm.max_map_count = 131072

The full story is that each coroutine requires two memory maps, and that Linux puts a limit on the total amount of memory maps that each process can manage (by default, this limit is often at 65535). Since the JVM needs a few dozen of such maps on its own (three maps per dynamic library – check /proc/the_pid/maps if you don't believe it), this is enough to create over 30,000 simulated processes. But to go futher, that limit must be modified.

If you want to make this change permanent on your machine, edit your /etc/sysctl.conf file. Otherwise, you have to redo it by calling sysctl after each reboot.

Lua Binding

What is lua ?

Lua is a lightweight, reflective, imperative and functional programming language, designed as a scripting language with extensible semantics as a primary goal (see official web site here).

Why lua ?

Lua is a fast, portable and powerful script language, quite simple to use for developpers. it combines procedural features with powerful data description facilities, by using a simple, yet powerful, mechanism of tables. Lua has a relatively simple C API compared to other scripting languages, and accordingly it provides a robust, easy to use it.