6 SimGrid was conceived as a tool to study distributed algorithms. Its
7 modern :ref:`S4U interface <S4U_doc>` makes it easy to assess Cloud,
8 P2P, HPC, IoT and similar settings.
10 A typical SimGrid simulation is composed of several |Actors|_, that
11 execute user-provided functions. The actors have to explicitly use the
12 S4U interface to express their computation, communication, disk usage
13 and other |Activities|_, so that they get reflected within the
14 simulator. These activities take place on **Resources** (|Hosts|_,
15 |Links|_, |Storages|_). SimGrid predicts the time taken by each
16 activity and orchestrates accordingly the actors waiting for the
17 completion of these activities.
19 Each actor executes a user-provided function on a simulated |Host|_
20 with which it can interact. Communications are not directly sent to
21 actors, but posted onto a |Mailbox|_ that serve as rendez-vous point
22 between communicating actors.
24 .. |Actors| replace:: **Actors**
25 .. _Actors: api/classsimgrid_1_1s4u_1_1Actor.html
27 .. |Activities| replace:: **Activities**
28 .. _Activities: api/classsimgrid_1_1s4u_1_1Activity.html
30 .. |Hosts| replace:: **Hosts**
31 .. _Hosts: api/classsimgrid_1_1s4u_1_1Host.html
33 .. |Links| replace:: **Links**
34 .. _Links: api/classsimgrid_1_1s4u_1_1Link.html
36 .. |Storages| replace:: **Storages**
37 .. _Storages: api/classsimgrid_1_1s4u_1_1Storage.html
39 .. |VirtualMachines| replace:: **VirtualMachines**
40 .. _VirtualMachines: api/classsimgrid_1_1s4u_1_1VirtualMachine.html
42 .. |Host| replace:: **Host**
43 .. _Host: api/classsimgrid_1_1s4u_1_1Host.html
45 .. |Link| replace:: **Link**
46 .. _Link: api/classsimgrid_1_1s4u_1_1Link.html
48 .. |Mailbox| replace:: **Mailbox**
49 .. _Mailbox: api/classsimgrid_1_1s4u_1_1Mailbox.html
51 .. |Barrier| replace:: **Barrier**
52 .. _Barrier: api/classsimgrid_1_1s4u_1_1Barrier.html
54 .. |ConditionVariable| replace:: **ConditionVariable**
55 .. _ConditionVariable: api/classsimgrid_1_1s4u_1_1ConditionVariable.html
57 .. |Mutex| replace:: **Mutex**
58 .. _Mutex: api/classsimgrid_1_1s4u_1_1Mutex.html
61 **In the remainder of this tutorial**, you will discover a simple yet
62 fully functioning example of SimGrid simulation: the Master/Workers
63 application. We will detail each part of the code and necessary
64 configuration to make it working. After this tour, several exercises
65 are proposed to let you discover some of the SimGrid features, hands
66 on the keyboard. This practical session will be given in C++, that you
67 are supposed to know beforehand.
70 Discover the Master/Workers
71 ---------------------------
73 This section introduces a first example of SimGrid simulation. This
74 simple application is composed of two kind of actors: the **master**
75 is in charge of distributing some computational tasks to a set of
76 **workers** that execute them.
78 .. image:: /tuto_s4u/img/intro.svg
81 We first present a round-robin version of this application, where the
82 master dispatches the tasks to the workers, one after the other, until
83 all tasks are dispatched. Later in this tutorial, you will be given
84 the opportunity to improve this scheme.
89 Let's start with the code of the worker. It is represented by the
90 *master* function below. This simple function takes at least 3
91 parameters (the amount of tasks to dispatch, their computational size
92 in flops to compute and their communication size in bytes to
93 exchange). Every parameter after the third one must be the name of an
94 host on which a worker is waiting for something to compute.
96 Then, the tasks are sent one after the other, each on a mailbox named
97 after the worker's hosts. On the other side, a given worker (which
98 code is given below) wait for incoming tasks on its own
103 At the end, once all tasks are dispatched, the master dispatches
104 another task per worker, but this time with a negative amount of flops
105 to compute. Indeed, this application decided by convention, that the
106 workers should stop when encountering such a negative compute_size.
108 At the end of the day, the only SimGrid specific functions used in
109 this example are :cpp:func:`simgrid::s4u::Mailbox::by_name` and
110 :cpp:func:`simgrid::s4u::Mailbox::put`. Also, :c:macro:`XBT_INFO` is used
111 as a replacement to printf() or to cout to ensure that the messages
112 are nicely logged along with the simulated time and actor name.
115 .. literalinclude:: ../../examples/s4u/app-masterworkers/s4u-app-masterworkers-fun.cpp
117 :start-after: master-begin
118 :end-before: master-end
120 Here comes the code of the worker actors. This function expects no
121 parameter from its vector of strings. Its code is very simple: it
122 expects messages on the mailbox that is named after its own host. As long as it gets valid
123 computation requests (whose compute_amount is positive), it compute
124 this task and waits for the next one.
126 The worker retrieves its own host with
127 :cpp:func:`simgrid::s4u::this_actor::get_host`. The
128 :ref:`simgrid::s4u::this_actor <API_s4u_this_actor>`
129 namespace contains many such helping functions.
131 .. literalinclude:: ../../examples/s4u/app-masterworkers/s4u-app-masterworkers-fun.cpp
133 :start-after: worker-begin
134 :end-before: worker-end
136 Starting the Simulation
137 .......................
139 And this is it. In only a few lines, we defined the algorithm of our
140 master/workers examples.
142 That being said, an algorithm alone is not enough to define a
143 simulation: SimGrid is a library, not a program. So you need to define
144 your own ``main()`` function as follows. This function is in charge of
145 creating a SimGrid simulation engine (on line 3), register the actor
146 functions to the engine (on lines 7 and 8), load the simulated platform
147 from its description file (on line 11), map actors onto that platform
148 (on line 12) and run the simulation until its completion on line 15.
150 .. literalinclude:: ../../examples/s4u/app-masterworkers/s4u-app-masterworkers-fun.cpp
152 :start-after: main-begin
153 :end-before: main-end
156 As you can see, this also requires a platform file and a deployment
162 Platform files define the simulated platform on which the provided
163 application will take place. In contains one or several **Network
164 Zone** |api_s4u_NetZone|_ that contain both |Host|_ and |Link|_
165 Resources, as well as routing information.
167 Such files can get rather long and boring, so the example below is
168 only an excerpts of the full ``examples/platforms/small_platform.xml``
169 file. For example, most routing information are missing, and only the
170 route between the hosts Tremblay and Fafard is given. This path
171 traverses 6 links (named 4, 3, 2, 0, 1 and 8). There are several
172 examples of platforms in the archive under ``examples/platforms``.
174 .. |api_s4u_NetZone| image:: /img/extlink.png
177 .. _api_s4u_NetZone: api/classsimgrid_1_1s4u_1_1NetZone.html#class-documentation
179 .. |api_s4u_Link| image:: /img/extlink.png
182 .. _api_s4u_Link: api/classsimgrid_1_1s4u_1_1Link.html#class-documentation
184 .. literalinclude:: ../../examples/platforms/small_platform.xml
186 :lines: 1-10,12-20,56-62,192-
187 :caption: (excerpts of the small_platform.xml file)
192 Deployment files specify the execution scenario: it lists the actors
193 that should be started, along with their parameter. In the following
194 example, we start 6 actors: one master and 5 workers.
196 .. literalinclude:: ../../examples/s4u/app-masterworkers/s4u-app-masterworkers_d.xml
202 This time, we have all parts: once the program is compiled, we can
203 execute it as follows. Note how the XBT_INFO() requests turned into
204 informative messages.
206 .. literalinclude:: ../../examples/s4u/app-masterworkers/s4u-app-masterworkers.tesh
208 :start-after: s4u-app-masterworkers-fun
209 :prepend: $$$ ./masterworkers platform.xml deploy.xml
217 In this section, you will modify the example presented earlier to
218 explore the quality of the proposed algorithm. For now, it works and
219 the simulation prints things, but the truth is that we have no idea of
220 whether this is a good algorithm to dispatch tasks to the workers.
221 This very simple setting raises many interesting questions:
223 .. image:: /tuto_s4u/img/question.svg
226 - Which algorithm should the master use? Or should the worker decide
229 Round Robin is not an efficient algorithm when all tasks are not
230 processed at the same speed. It would probably be more efficient
231 if the workers were asking for tasks when ready.
233 - Should tasks be grouped in batches or sent separately?
235 The workers will starve if they don't get the tasks fast
236 enough. One possibility to reduce latency would be to send tasks
237 in pools instead of one by one. But if the pools are too big, the
238 load balancing will likely get uneven, in particular when
239 distributing the last tasks.
241 - How does the quality of such algorithm dependent on the platform
242 characteristics and on the task characteristics?
244 Whenever the input communication time is very small compared to
245 processing time and workers are homogeneous, it is likely that the
246 round-robin algorithm performs very well. Would it still hold true
247 when transfer time is not negligible? What if some tasks are
248 performed faster on some specific nodes?
250 - The network topology interconnecting the master and the workers
251 may be quite complicated. How does such a topology impact the
254 When data transfers are the bottleneck, it is likely that a good
255 modeling of the platform becomes essential. The SimGrid platform
256 models are particularly handy to account for complex platform
259 - What is the best applicative topology?
261 Is a flat master worker deployment sufficient? Should we go for a
262 hierarchical algorithm, with some forwarders taking large pools of
263 tasks from the master, each of them distributing their tasks to a
264 sub-pool of workers? Or should we introduce super-peers,
265 dupplicating the master's role in a peer-to-peer manner? Do the
266 algorithms require a perfect knowledge of the network?
268 - How is such an algorithm sensitive to external workload variation?
270 What if bandwidth, latency and computing speed can vary with no
271 warning? Shouldn't you study whether your algorithm is sensitive
272 to such load variations?
274 - Although an algorithm may be more efficient than another, how does
275 it interfere with unrelated applications executing on the same
278 **SimGrid was invented to answer such questions.** Do not believe the
279 fools saying that all you need to study such settings is a simple
280 discrete event simulator. Do you really want to reinvent the wheel,
281 debug and optimize your own tool, and validate its models against real
282 settings for ages, or do you prefer to sit on the shoulders of a
283 giant? With SimGrid, you can focus on your algorithm. The whole
284 simulation mechanism is already working.
286 Here is the visualization of a SimGrid simulation of two master worker
287 applications (one in light gray and the other in dark gray) running in
288 concurrence and showing resource usage over a long period of time. It
289 was obtained with the Triva software.
291 .. image:: /tuto_s4u/img/result.png
297 The easiest way to take the tutorial is to use the dedicated Docker
298 image. Once you `installed Docker itself
299 <https://docs.docker.com/install/>`_, simply do the following:
301 .. code-block:: shell
303 docker pull simgrid/tuto-s4u
304 docker run -it --rm --name simgrid --volume ~/simgrid-tutorial:/source/tutorial simgrid/tuto-s4u bash
306 This will start a new container with all you need to take this
307 tutorial, and create a ``simgrid-tutorial`` directory in your home on
308 your host machine that will be visible as ``/source/tutorial`` within the
309 container. You can then edit the files you want with your favorite
310 editor in ``~/simgrid-tutorial``, and compile them within the
311 container to enjoy the provided dependencies.
315 Any change to the container out of ``/source/tutorial`` will be lost
316 when you log out of the container, so don't edit the other files!
318 All needed dependencies are already installed in this container
319 (SimGrid, a C++ compiler, cmake, pajeng and R). Vite being only
320 optional in this tutorial, it is not installed to reduce the image
323 The code template is available under ``/source/simgrid-template-s4u.git``
324 in the image. You should copy it to your working directory and
325 recompile it when you first log in:
327 .. code-block:: shell
329 cp -r /source/simgrid-template-s4u.git/* /source/tutorial
334 Using your Computer Natively
335 ............................
337 To take the tutorial on your machine, you first need to :ref:`install
338 SimGrid <install>`, a C++ compiler and also ``pajeng`` to visualize
339 the traces. You may want to install `Vite
340 <http://vite.gforge.inria.fr/>`_ to get a first glance at the
341 traces. The provided code template requires cmake to compile. On
342 Debian and Ubuntu for example, you can get them as follows:
344 .. code-block:: shell
346 sudo apt install simgrid pajeng cmake g++ vite
348 An initial version of the source code is provided on framagit. This
349 template compiles with cmake. If SimGrid is correctly installed, you
350 should be able to clone the `repository
351 <https://framagit.org/simgrid/simgrid-template-s4u>`_ and recompile
352 everything as follows:
354 .. code-block:: shell
356 # (exporting SimGrid_PATH is only needed if SimGrid is installed in a non-standard path)
357 export SimGrid_PATH=/where/to/simgrid
359 git clone https://framagit.org/simgrid/simgrid.git
360 cd simgrid-template-s4u/
364 If you struggle with the compilation, then you should double check
365 your :ref:`SimGrid installation <install>`. On need, please refer to
366 the :ref:`Troubleshooting your Project Setup
367 <install_yours_troubleshooting>` section.
369 Discovering the Provided Code
370 .............................
372 Please compile and execute the provided simulator as follows:
374 .. code-block:: shell
377 ./master-workers small_platform.xml master-workers_d.xml
379 For a more "fancy" output, you can use simgrid-colorizer.
381 .. code-block:: shell
383 ./master-workers small_platform.xml master-workers_d.xml 2>&1 | simgrid-colorizer
385 If you installed SimGrid to a non-standard path, you may have to
386 specify the full path to simgrid-colorizer on the above line, such as
387 ``/opt/simgrid/bin/simgrid-colorizer``. If you did not install it at all,
388 you can find it in <simgrid_root_directory>/bin/colorize.
390 For a classical Gantt-Chart vizualisation, you can use `Vite
391 <http://vite.gforge.inria.fr/>`_ if you have it installed, as
392 follows. But do not spend too much time installing Vite, because there
393 is a better way to visualize SimGrid traces (see below).
395 .. code-block:: shell
397 ./master-workers small_platform.xml master-workers_d.xml --cfg=tracing:yes --cfg=tracing/msg/process:yes
400 .. image:: /tuto_s4u/img/vite-screenshot.png
403 If you want the full power to visualize SimGrid traces, you need
404 to use R. As a start, you can download this `starter script
405 <https://framagit.org/simgrid/simgrid/raw/master/docs/source/tuto_s4u/draw_gantt.R>`_
406 and use it as follows:
408 .. code-block:: shell
410 ./master-workers small_platform.xml master-workers_d.xml --cfg=tracing:yes --cfg=tracing/msg/process:yes
411 pj_dump --ignore-incomplete-links simgrid.trace | grep STATE > gantt.csv
412 Rscript draw_gantt.R gantt.csv
414 It produces a ``Rplots.pdf`` with the following content:
416 .. image:: /tuto_s4u/img/Rscript-screenshot.png
420 Lab 1: Simpler Deployments
421 --------------------------
423 In the provided example, adding more workers quickly becomes a pain:
424 You need to start them (at the bottom of the file), and to inform the
425 master of its availability with an extra parameter. This is mandatory
426 if you want to inform the master of where the workers are running. But
427 actually, the master does not need to have this information.
429 We could leverage the mailbox mechanism flexibility, and use a sort of
430 yellow page system: Instead of sending data to the worker running on
431 Fafard, the master could send data to the third worker. Ie, instead of
432 using the worker location (which should be filled in two locations),
433 we could use their ID (which should be filled in one location
436 This could be done with the following deployment file. It's clearly
437 not shorter than the previous one, but it's still simpler because the
438 information is only written once. It thus follows the `DRY
439 <https://en.wikipedia.org/wiki/Don't_repeat_yourself>`_ `SPOT
440 <http://wiki.c2.com/?SinglePointOfTruth>`_ design principle.
442 .. literalinclude:: tuto_s4u/deployment1.xml
446 Copy your ``master-workers.cpp`` into ``master-workers-lab1.cpp`` and
447 add a new executable into ``CMakeLists.txt``. Then modify your worker
448 function so that it gets its mailbox name not from the name of its
449 host, but from the string passed as ``args[1]``. The master will send
450 messages to all workers based on their number, for example as follows:
454 for (int i = 0; i < tasks_count; i++) {
455 std::string worker_rank = std::to_string(i % workers_count);
456 std::string mailbox_name = std::string("worker-") + worker_rank;
457 simgrid::s4u::MailboxPtr mailbox = simgrid::s4u::Mailbox::by_name(mailbox_name);
468 The mailboxes are a very powerful mechanism in SimGrid, allowing many
469 interesting application settings. They may feel surprising if you are
470 used to BSD sockets or other classical systems, but you will soon
471 appreciate their power. They are only used to match the
472 communications, but have no impact on the communication
473 timing. ``put()`` and ``get()`` are matched regardless of their
474 initiators' location and then the real communication occures between
475 the involved parties.
477 Please refer to the full `API of Mailboxes
478 <api/classsimgrid_1_1s4u_1_1Mailbox.html#class-documentation>`_ for
482 Lab 2: Using the Whole Platform
483 -------------------------------
485 It is now easier to add a new worker, but you still has to do it
486 manually. It would be much easier if the master could start the
487 workers on its own, one per available host in the platform. The new
488 deployment file should be as simple as:
490 .. literalinclude:: tuto_s4u/deployment2.xml
494 Creating the workers from the master
495 ....................................
497 For that, the master needs to retrieve the list of hosts declared in
498 the platform with :cpp:func:`simgrid::s4u::Engine::get_all_hosts`.
499 Then, the master should start the worker actors with
500 :cpp:func:`simgrid::s4u::Actor::create`.
502 ``Actor::create(name, host, func, params...)`` is a very flexible
503 function. Its third parameter is the function that the actor should
504 execute. This function can take any kind of parameter, provided that
505 you pass similar parameters to ``Actor::create()``. For example, you
506 could have something like this:
510 void my_actor(int param1, double param2, std::string param3) {
513 int main(int argc, char argv**) {
515 simgrid::s4u::ActorPtr actor;
516 actor = simgrid::s4u::Actor::create("name", simgrid::s4u::Host::by_name("the_host"),
517 &my_actor, 42, 3.14, "thevalue");
522 Master-Workers Communication
523 ............................
525 Previously, the workers got from their parameter the name of the
526 mailbox they should use. We can still do so: the master should build
527 such a parameter before using it in the ``Actor::create()`` call. The
528 master could even pass directly the mailbox as a parameter to the
531 Since we want later to study concurrent applications, it is advised to
532 use a mailbox name that is unique over the simulation even if there is
533 more than one master.
535 One possibility for that is to use the actor ID (aid) of each worker
536 as a mailbox name. The master can retrieve the aid of the newly
537 created actor with ``actor->get_pid()`` while the actor itself can
538 retrieve its own aid with ``simgrid::s4u::this_actor::get_pid()``.
539 The retrieved value is an ``aid_t``, which is an alias for ``long``.
541 Instead of having one mailbox per worker, you could also reorganize
542 completely your application to have only one mailbox per master. All
543 the workers of a given master would pull their work from the same
544 mailbox, which should be passed as parameter to the workers. This
545 reduces the amount of mailboxes, but prevents the master from taking
546 any scheduling decision. It really depends on how you want to organize
547 your application and what you want to study with your simulator. In
548 this tutorial, that's probably not a good idea.
553 In this exercise, we reduced the amount of configuration that our
554 simulator requests. This is both a good idea, and a dangerous
555 trend. This simplification is another application of the good old DRY/SPOT
556 programming principle (`Don't Repeat Yourself / Single Point Of Truth
557 <https://en.wikipedia.org/wiki/Don%27t_repeat_yourself>`_), and you
558 really want your programming artefacts to follow these software
559 engineering principles.
561 But at the same time, you should be careful in separating your
562 scientific contribution (the master/workers algorithm) and the
563 artefacts used to test it (platform, deployment and workload). This is
564 why SimGrid forces you to express your platform and deployment files
565 in XML instead of using a programming interface: it forces a clear
566 separation of concerns between things of very different nature.
568 Lab 3: Fixed Experiment Duration
569 --------------------------------
571 In the current version, the number of tasks is defined through the
572 worker arguments. Hence, tasks are created at the very beginning of
573 the simulation. Instead, have the master dispatching tasks for a
574 predetermined amount of time. The tasks must now be created on demand
575 instead of beforehand.
577 Of course, usual time functions like ``gettimeofday`` will give you the
578 time on your real machine, which is prety useless in the
579 simulation. Instead, retrieve the time in the simulated world with
580 :cpp:func:`simgrid::s4u::Engine::get_clock`.
582 You can still stop your workers with a specific task as previously,
583 or you may kill them forcefully with
584 :cpp:func:`simgrid::s4u::Actor::kill` (if you already have a reference
585 to the actor you want to kill) or
586 :cpp:func:`void simgrid::s4u::Actor::kill(aid_t)` (if you only have its ID).
589 Anyway, the new deployment `deployment3.xml` file should thus look
592 .. literalinclude:: tuto_s4u/deployment3.xml
595 Controlling the message verbosity
596 .................................
598 Not all messages are equally informative, so you probably want to
599 change some of the ``XBT_INFO`` into ``XBT_DEBUG`` so that they are
600 hidden by default. For example, you may want to use ``XBT_INFO`` once
601 every 100 tasks and ``XBT_DEBUG`` when sending all the other tasks. Or
602 you could show only the total number of tasks processed by
603 default. You can still see the debug messages as follows:
605 .. code-block:: shell
607 ./master-workers-lab3 small_platform.xml deployment3.xml --log=msg_test.thres:debug
610 Lab 4: Competing Applications
611 -----------------------------
613 It is now time to start several applications at once, with the following ``deployment4.xml`` file.
615 .. literalinclude:: tuto_s4u/deployment4.xml
618 Things happen when you do so, but it remains utterly difficult to
619 understand what's happening exactely. Even Gantt visualizations
620 contain too much information to be useful: it is impossible to
621 understand which task belong to which application. To fix this, we
622 will categorize the tasks.
624 Instead of starting the execution in one function call only with
625 ``this_actor::execute(cost)``, you need to
626 create the execution activity, set its tracing category, and then start
627 it and wait for its completion, as follows:
631 simgrid::s4u::ExecPtr exec = simgrid::s4u::this_actor::exec_init(compute_cost);
632 exec->set_tracing_category(category);
633 // exec->start() is optional here as wait() starts the activity on need
636 You can make the same code shorter as follows:
640 simgrid::s4u::this_actor::exec_init(compute_cost)->set_tracing_category(category)->wait();
642 Visualizing the result
643 .......................
645 vite is not enough to understand the situation, because it does not
646 deal with categorization. This time, you absolutely must switch to R,
647 as explained on `this page
648 <https://simgrid.org/contrib/R_visualization.html>`_.
652 Include here the minimal setting to view something in R.
655 Lab 5: Better Scheduling
656 ------------------------
658 You don't need a very advanced visualization solution to notice that
659 round-robin is completely suboptimal: most of the workers keep waiting
660 for more work. We will move to a First-Come First-Served mechanism
663 For that, your workers should explicitely request for work with a
664 message sent to a channel that is specific to their master. The name
665 of that private channel can be the one used to categorize the
666 executions, as it is already specific to each master.
668 The master should serve in a round-robin manner the requests it
669 receives, until the time is up. Changing the communication schema can
670 be a bit hairy, but once it works, you will see that such as simple
671 FCFS schema allows to double the amount of tasks handled over time
672 here. Things may be different with another platform file.
677 From this, many things can easily be added. For example, you could:
679 - Allow workers to have several pending requests so as to overlap
680 communication and computations as much as possible. Non-blocking
681 communication will probably become handy here.
682 - Add a performance measurement mechanism, enabling the master to make smart scheduling choices.
683 - Test your code on other platforms, from the ``examples/platforms``
684 directory in your archive.
686 What is the largest number of tasks requiring 50e6 flops and 1e5
687 bytes that you manage to distribute and process in one hour on
689 - Optimize not only for the amount of tasks handled, but also for the
690 total energy dissipated.
691 - And so on. If you come up with a really nice extension, please share
692 it with us so that we can extend this tutorial.
697 This tutorial is now terminated. You could keep reading the [online documentation][fn:4] or
698 [tutorials][fn:7], or you could head up to the example section to read some code.
702 Things to improve in the future:
704 - Propose equivalent exercises and skeleton in java (and Python once we have a python binding).
706 .. LocalWords: SimGrid