Extend the platf-failure example to show how to create an host with its trace program...

diff --git a/examples/cpp/platform-failures/s4u-platform-failures.cpp b/examples/cpp/platform-failures/s4u-platform-failures.cpp
index 4a5cc0f..b47d78e 100644 (file)
--- a/examples/cpp/platform-failures/s4u-platform-failures.cpp
+++ b/examples/cpp/platform-failures/s4u-platform-failures.cpp
@@ -21,13 +21,15 @@
 #include "simgrid/kernel/ProfileBuilder.hpp"
 #include "simgrid/s4u.hpp"
 
+namespace sg4 = simgrid::s4u;
+
 XBT_LOG_NEW_DEFAULT_CATEGORY(s4u_test, "Messages specific for this s4u example");
 
 static void master(std::vector<std::string> args)
 {
   xbt_assert(args.size() == 5, "Expecting one parameter");
 
-  simgrid::s4u::Mailbox* mailbox;
+  sg4::Mailbox* mailbox;
   long number_of_tasks = std::stol(args[1]);
   double comp_size     = std::stod(args[2]);
   long comm_size       = std::stol(args[3]);
@@ -36,7 +38,7 @@ static void master(std::vector<std::string> args)
   XBT_INFO("Got %ld workers and %ld tasks to process", workers_count, number_of_tasks);
 
   for (int i = 0; i < number_of_tasks; i++) {
-    mailbox         = simgrid::s4u::Mailbox::by_name(std::string("worker-") + std::to_string(i % workers_count));
+    mailbox         = sg4::Mailbox::by_name(std::string("worker-") + std::to_string(i % workers_count));
     auto* payload   = new double(comp_size);
     try {
       XBT_INFO("Send a message to %s", mailbox->get_cname());
@@ -54,7 +56,7 @@ static void master(std::vector<std::string> args)
   XBT_INFO("All tasks have been dispatched. Let's tell everybody the computation is over.");
   for (int i = 0; i < workers_count; i++) {
     /* - Eventually tell all the workers to stop by sending a "finalize" task */
-    mailbox         = simgrid::s4u::Mailbox::by_name(std::string("worker-") + std::to_string(i));
+    mailbox         = sg4::Mailbox::by_name(std::string("worker-") + std::to_string(i));
     auto* payload   = new double(-1.0);
     try {
       mailbox->put(payload, 0, 1.0);
@@ -73,8 +75,8 @@ static void master(std::vector<std::string> args)
 static void worker(std::vector<std::string> args)
 {
   xbt_assert(args.size() == 2, "Expecting one parameter");
-  long id                          = std::stol(args[1]);
-  simgrid::s4u::Mailbox* mailbox   = simgrid::s4u::Mailbox::by_name(std::string("worker-") + std::to_string(id));
+  long id               = std::stol(args[1]);
+  sg4::Mailbox* mailbox = sg4::Mailbox::by_name(std::string("worker-") + std::to_string(id));
   while (true) {
     try {
       XBT_INFO("Waiting a message on %s", mailbox->get_cname());
@@ -87,7 +89,7 @@ static void worker(std::vector<std::string> args)
       }
       /*  - Otherwise, process the task */
       XBT_INFO("Start execution...");
-      simgrid::s4u::this_actor::execute(comp_size);
+      sg4::this_actor::execute(comp_size);
       XBT_INFO("Execution complete.");
     } catch (const simgrid::NetworkFailureException&) {
       XBT_INFO("Mmh. Something went wrong. Nevermind. Let's keep going!");
@@ -97,12 +99,12 @@ static void worker(std::vector<std::string> args)
 
 int main(int argc, char* argv[])
 {
-  simgrid::s4u::Engine e(&argc, argv);
+  sg4::Engine e(&argc, argv);
 
   // This is how to attach a profile to an host that is created from the XML file.
   // This should be done before calling load_platform(), as the on_creation() event is fired when loading the platform.
   // You can never set a new profile to a resource that already have one.
-  simgrid::s4u::Host::on_creation.connect([](simgrid::s4u::Host& h) {
+  sg4::Host::on_creation.connect([](sg4::Host& h) {
     if (h.get_name() == "Bourrassa") {
       h.set_state_profile(simgrid::kernel::profile::ProfileBuilder::from_string("bourassa_profile", "67 0\n70 1\n", 0));
     }
@@ -113,8 +115,28 @@ int main(int argc, char* argv[])
   e.register_function("worker", worker);
   e.load_deployment(argv[2]);
 
+  // Add a new host programatically, and attach a state profile to it
+  auto* root            = e.get_netzone_root();
+  auto* lilibeth        = root->create_host("Lilibeth", 1e15);
+  sg4::LinkInRoute link = sg4::LinkInRoute(e.link_by_name("10"));
+  root->add_route(e.host_by_name("Tremblay")->get_netpoint(), lilibeth->get_netpoint(), nullptr, nullptr, {link}, true);
+  lilibeth->set_state_profile(simgrid::kernel::profile::ProfileBuilder::from_string("lilibeth_profile", R"(
+4 0
+5 1
+)",
+                                                                                    10));
+  lilibeth->seal();
+
+  // Create an actor on that new host, to monitor its own state
+  auto actor = sg4::Actor::create("sleeper", lilibeth, []() {
+    XBT_INFO("Start sleeping...");
+    sg4::this_actor::sleep_for(1);
+    XBT_INFO("done sleeping.");
+  });
+  actor->set_auto_restart(true);
+
   e.run();
 
-  XBT_INFO("Simulation time %g", simgrid::s4u::Engine::get_clock());
+  XBT_INFO("Simulation time %g", sg4::Engine::get_clock());
   return 0;
 }

diff --git a/examples/cpp/platform-failures/s4u-platform-failures.tesh b/examples/cpp/platform-failures/s4u-platform-failures.tesh
index 47d7d5d..eb0906d 100644 (file)
--- a/examples/cpp/platform-failures/s4u-platform-failures.tesh
+++ b/examples/cpp/platform-failures/s4u-platform-failures.tesh
@@ -8,6 +8,7 @@ $ ${bindir:=.}/s4u-platform-failures --log=xbt_cfg.thres:critical --log=no_loc $
 > [  0.000000] (0:maestro@) Deployment includes some initially turned off Hosts ... nevermind.
 > [  0.000000] (1:master@Tremblay) Got 5 workers and 20 tasks to process
 > [  0.000000] (1:master@Tremblay) Send a message to worker-0
+> [  0.000000] (7:sleeper@Lilibeth) Start sleeping...
 > [  0.010309] (1:master@Tremblay) Send to worker-0 completed
 > [  0.010309] (2:worker@Tremblay) Start execution...
 > [  0.000000] (2:worker@Tremblay) Waiting a message on worker-0
@@ -16,13 +17,13 @@ $ ${bindir:=.}/s4u-platform-failures --log=xbt_cfg.thres:critical --log=no_loc $
 > [  0.000000] (6:worker@Bourassa) Waiting a message on worker-4
 > [  0.010309] (1:master@Tremblay) Send a message to worker-1
 > [  1.000000] (0:maestro@) Restart actors on host Fafard
-> [  1.000000] (7:worker@Fafard) Waiting a message on worker-2
+> [  1.000000] (8:worker@Fafard) Waiting a message on worker-2
 > [  1.000000] (1:master@Tremblay) Mmh. The communication with 'worker-1' failed. Nevermind. Let's keep going!
 > [  1.000000] (1:master@Tremblay) Send a message to worker-2
 > [  2.000000] (1:master@Tremblay) Mmh. The communication with 'worker-2' failed. Nevermind. Let's keep going!
 > [  2.000000] (0:maestro@) Restart actors on host Jupiter
 > [  2.000000] (1:master@Tremblay) Send a message to worker-3
-> [  2.000000] (8:worker@Jupiter) Waiting a message on worker-1
+> [  2.000000] (9:worker@Jupiter) Waiting a message on worker-1
 > [  2.010309] (2:worker@Tremblay) Execution complete.
 > [  2.010309] (2:worker@Tremblay) Waiting a message on worker-0
 > [  3.030928] (1:master@Tremblay) Send to worker-3 completed
@@ -34,17 +35,20 @@ $ ${bindir:=.}/s4u-platform-failures --log=xbt_cfg.thres:critical --log=no_loc $
 > [  4.072165] (1:master@Tremblay) Send to worker-0 completed
 > [  4.072165] (1:master@Tremblay) Send a message to worker-1
 > [  4.072165] (2:worker@Tremblay) Start execution...
+> [  5.000000] (0:maestro@) Restart actors on host Lilibeth
+> [  5.000000] (10:sleeper@Lilibeth) Start sleeping...
 > [  5.030928] (5:worker@Ginette) Execution complete.
 > [  5.030928] (5:worker@Ginette) Waiting a message on worker-3
 > [  5.103093] (1:master@Tremblay) Send to worker-1 completed
 > [  5.103093] (1:master@Tremblay) Send a message to worker-2
-> [  5.103093] (8:worker@Jupiter) Start execution...
+> [  5.103093] (9:worker@Jupiter) Start execution...
+> [  6.000000] (10:sleeper@Lilibeth) done sleeping.
 > [  6.061856] (6:worker@Bourassa) Execution complete.
 > [  6.061856] (6:worker@Bourassa) Waiting a message on worker-4
 > [  6.072165] (2:worker@Tremblay) Execution complete.
 > [  6.072165] (2:worker@Tremblay) Waiting a message on worker-0
-> [  7.103093] (8:worker@Jupiter) Execution complete.
-> [  7.103093] (8:worker@Jupiter) Waiting a message on worker-1
+> [  7.103093] (9:worker@Jupiter) Execution complete.
+> [  7.103093] (9:worker@Jupiter) Waiting a message on worker-1
 > [ 15.103093] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
 > [ 15.103093] (1:master@Tremblay) Send a message to worker-3
 > [ 15.103093] (1:master@Tremblay) Mmh. The communication with 'worker-3' failed. Nevermind. Let's keep going!
@@ -59,13 +63,16 @@ $ ${bindir:=.}/s4u-platform-failures --log=xbt_cfg.thres:critical --log=no_loc $
 > [ 16.144330] (2:worker@Tremblay) Start execution...
 > [ 17.175258] (1:master@Tremblay) Send to worker-1 completed
 > [ 17.175258] (1:master@Tremblay) Send a message to worker-2
-> [ 17.175258] (8:worker@Jupiter) Start execution...
+> [ 17.175258] (9:worker@Jupiter) Start execution...
 > [ 18.134021] (6:worker@Bourassa) Execution complete.
 > [ 18.134021] (6:worker@Bourassa) Waiting a message on worker-4
 > [ 18.144330] (2:worker@Tremblay) Execution complete.
 > [ 18.144330] (2:worker@Tremblay) Waiting a message on worker-0
-> [ 19.175258] (8:worker@Jupiter) Execution complete.
-> [ 19.175258] (8:worker@Jupiter) Waiting a message on worker-1
+> [ 19.175258] (9:worker@Jupiter) Execution complete.
+> [ 19.175258] (9:worker@Jupiter) Waiting a message on worker-1
+> [ 20.000000] (0:maestro@) Restart actors on host Lilibeth
+> [ 20.000000] (11:sleeper@Lilibeth) Start sleeping...
+> [ 21.000000] (11:sleeper@Lilibeth) done sleeping.
 > [ 27.175258] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
 > [ 27.175258] (1:master@Tremblay) Send a message to worker-3
 > [ 28.206186] (1:master@Tremblay) Send to worker-3 completed
@@ -80,13 +87,16 @@ $ ${bindir:=.}/s4u-platform-failures --log=xbt_cfg.thres:critical --log=no_loc $
 > [ 28.216495] (2:worker@Tremblay) Start execution...
 > [ 29.247423] (1:master@Tremblay) Send to worker-1 completed
 > [ 29.247423] (1:master@Tremblay) Send a message to worker-2
-> [ 29.247423] (8:worker@Jupiter) Start execution...
+> [ 29.247423] (9:worker@Jupiter) Start execution...
 > [ 30.206186] (5:worker@Ginette) Execution complete.
 > [ 30.206186] (5:worker@Ginette) Waiting a message on worker-3
 > [ 30.216495] (2:worker@Tremblay) Execution complete.
 > [ 30.216495] (2:worker@Tremblay) Waiting a message on worker-0
-> [ 31.247423] (8:worker@Jupiter) Execution complete.
-> [ 31.247423] (8:worker@Jupiter) Waiting a message on worker-1
+> [ 31.247423] (9:worker@Jupiter) Execution complete.
+> [ 31.247423] (9:worker@Jupiter) Waiting a message on worker-1
+> [ 35.000000] (0:maestro@) Restart actors on host Lilibeth
+> [ 35.000000] (12:sleeper@Lilibeth) Start sleeping...
+> [ 36.000000] (12:sleeper@Lilibeth) done sleeping.
 > [ 39.247423] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
 > [ 39.247423] (1:master@Tremblay) Send a message to worker-3
 > [ 40.278351] (1:master@Tremblay) Send to worker-3 completed
@@ -96,7 +106,7 @@ $ ${bindir:=.}/s4u-platform-failures --log=xbt_cfg.thres:critical --log=no_loc $
 > [ 41.309278] (1:master@Tremblay) All tasks have been dispatched. Let's tell everybody the computation is over.
 > [ 41.309278] (2:worker@Tremblay) I'm done. See you!
 > [ 41.309278] (6:worker@Bourassa) Start execution...
-> [ 41.309278] (8:worker@Jupiter) I'm done. See you!
+> [ 41.309278] (9:worker@Jupiter) I'm done. See you!
 > [ 42.309278] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
 > [ 43.309278] (0:maestro@) Simulation time 43.3093
 > [ 43.309278] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-3'. Nevermind. Let's keep going!
@@ -117,15 +127,16 @@ $ ${bindir:=.}/s4u-platform-failures --log=xbt_cfg.thres:critical --log=no_loc $
 > [  0.000000] (3:worker@Jupiter) Waiting a message on worker-1
 > [  0.000000] (5:worker@Ginette) Waiting a message on worker-3
 > [  0.000000] (6:worker@Bourassa) Waiting a message on worker-4
+> [  0.000000] (7:sleeper@Lilibeth) Start sleeping...
 > [  0.010825] (2:worker@Tremblay) Start execution...
 > [  0.010825] (1:master@Tremblay) Send to worker-0 completed
 > [  0.010825] (1:master@Tremblay) Send a message to worker-1
 > [  1.000000] (0:maestro@) Restart actors on host Fafard
-> [  1.000000] (7:worker@Fafard) Waiting a message on worker-2
+> [  1.000000] (8:worker@Fafard) Waiting a message on worker-2
 > [  1.000000] (1:master@Tremblay) Mmh. The communication with 'worker-1' failed. Nevermind. Let's keep going!
 > [  1.000000] (1:master@Tremblay) Send a message to worker-2
 > [  2.000000] (0:maestro@) Restart actors on host Jupiter
-> [  2.000000] (8:worker@Jupiter) Waiting a message on worker-1
+> [  2.000000] (9:worker@Jupiter) Waiting a message on worker-1
 > [  2.000000] (1:master@Tremblay) Mmh. The communication with 'worker-2' failed. Nevermind. Let's keep going!
 > [  2.000000] (1:master@Tremblay) Send a message to worker-3
 > [  2.010825] (2:worker@Tremblay) Execution complete.
@@ -139,17 +150,20 @@ $ ${bindir:=.}/s4u-platform-failures --log=xbt_cfg.thres:critical --log=no_loc $
 > [  4.175773] (2:worker@Tremblay) Start execution...
 > [  4.175773] (1:master@Tremblay) Send to worker-0 completed
 > [  4.175773] (1:master@Tremblay) Send a message to worker-1
+> [  5.000000] (0:maestro@) Restart actors on host Lilibeth
+> [  5.000000] (10:sleeper@Lilibeth) Start sleeping...
 > [  5.082474] (5:worker@Ginette) Execution complete.
 > [  5.082474] (5:worker@Ginette) Waiting a message on worker-3
-> [  5.258247] (8:worker@Jupiter) Start execution...
+> [  5.258247] (9:worker@Jupiter) Start execution...
 > [  5.258247] (1:master@Tremblay) Send to worker-1 completed
 > [  5.258247] (1:master@Tremblay) Send a message to worker-2
+> [  6.000000] (10:sleeper@Lilibeth) done sleeping.
 > [  6.164948] (6:worker@Bourassa) Execution complete.
 > [  6.164948] (6:worker@Bourassa) Waiting a message on worker-4
 > [  6.175773] (2:worker@Tremblay) Execution complete.
 > [  6.175773] (2:worker@Tremblay) Waiting a message on worker-0
-> [  7.258247] (8:worker@Jupiter) Execution complete.
-> [  7.258247] (8:worker@Jupiter) Waiting a message on worker-1
+> [  7.258247] (9:worker@Jupiter) Execution complete.
+> [  7.258247] (9:worker@Jupiter) Waiting a message on worker-1
 > [ 15.258247] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
 > [ 15.258247] (1:master@Tremblay) Send a message to worker-3
 > [ 15.258247] (5:worker@Ginette) Mmh. Something went wrong. Nevermind. Let's keep going!
@@ -162,15 +176,18 @@ $ ${bindir:=.}/s4u-platform-failures --log=xbt_cfg.thres:critical --log=no_loc $
 > [ 16.351546] (2:worker@Tremblay) Start execution...
 > [ 16.351546] (1:master@Tremblay) Send to worker-0 completed
 > [ 16.351546] (1:master@Tremblay) Send a message to worker-1
-> [ 17.434021] (8:worker@Jupiter) Start execution...
+> [ 17.434021] (9:worker@Jupiter) Start execution...
 > [ 17.434021] (1:master@Tremblay) Send to worker-1 completed
 > [ 17.434021] (1:master@Tremblay) Send a message to worker-2
 > [ 18.340722] (6:worker@Bourassa) Execution complete.
 > [ 18.340722] (6:worker@Bourassa) Waiting a message on worker-4
 > [ 18.351546] (2:worker@Tremblay) Execution complete.
 > [ 18.351546] (2:worker@Tremblay) Waiting a message on worker-0
-> [ 19.434021] (8:worker@Jupiter) Execution complete.
-> [ 19.434021] (8:worker@Jupiter) Waiting a message on worker-1
+> [ 19.434021] (9:worker@Jupiter) Execution complete.
+> [ 19.434021] (9:worker@Jupiter) Waiting a message on worker-1
+> [ 20.000000] (0:maestro@) Restart actors on host Lilibeth
+> [ 20.000000] (11:sleeper@Lilibeth) Start sleeping...
+> [ 21.000000] (11:sleeper@Lilibeth) done sleeping.
 > [ 27.434021] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
 > [ 27.434021] (1:master@Tremblay) Send a message to worker-3
 > [ 28.516495] (5:worker@Ginette) Start execution...
@@ -183,15 +200,18 @@ $ ${bindir:=.}/s4u-platform-failures --log=xbt_cfg.thres:critical --log=no_loc $
 > [ 28.527320] (2:worker@Tremblay) Start execution...
 > [ 28.527320] (1:master@Tremblay) Send to worker-0 completed
 > [ 28.527320] (1:master@Tremblay) Send a message to worker-1
-> [ 29.609794] (8:worker@Jupiter) Start execution...
+> [ 29.609794] (9:worker@Jupiter) Start execution...
 > [ 29.609794] (1:master@Tremblay) Send to worker-1 completed
 > [ 29.609794] (1:master@Tremblay) Send a message to worker-2
 > [ 30.516495] (5:worker@Ginette) Execution complete.
 > [ 30.516495] (5:worker@Ginette) Waiting a message on worker-3
 > [ 30.527320] (2:worker@Tremblay) Execution complete.
 > [ 30.527320] (2:worker@Tremblay) Waiting a message on worker-0
-> [ 31.609794] (8:worker@Jupiter) Execution complete.
-> [ 31.609794] (8:worker@Jupiter) Waiting a message on worker-1
+> [ 31.609794] (9:worker@Jupiter) Execution complete.
+> [ 31.609794] (9:worker@Jupiter) Waiting a message on worker-1
+> [ 35.000000] (0:maestro@) Restart actors on host Lilibeth
+> [ 35.000000] (12:sleeper@Lilibeth) Start sleeping...
+> [ 36.000000] (12:sleeper@Lilibeth) done sleeping.
 > [ 39.609794] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
 > [ 39.609794] (1:master@Tremblay) Send a message to worker-3
 > [ 40.692268] (5:worker@Ginette) Start execution...
@@ -201,7 +221,7 @@ $ ${bindir:=.}/s4u-platform-failures --log=xbt_cfg.thres:critical --log=no_loc $
 > [ 41.774742] (1:master@Tremblay) Send to worker-4 completed
 > [ 41.774742] (1:master@Tremblay) All tasks have been dispatched. Let's tell everybody the computation is over.
 > [ 41.774742] (2:worker@Tremblay) I'm done. See you!
-> [ 41.774742] (8:worker@Jupiter) I'm done. See you!
+> [ 41.774742] (9:worker@Jupiter) I'm done. See you!
 > [ 42.774742] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
 > [ 43.774742] (6:worker@Bourassa) Execution complete.
 > [ 43.774742] (6:worker@Bourassa) Waiting a message on worker-4