Merge branches 'auto_restart' and 'auto_restart' of framagit.org:simgrid/simgrid

Also, don't run doxygen manually on framagit/gitlab-ci

diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
index be34650..3ef1530 100644 (file)
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@@ -3,12 +3,8 @@ image: debian:testing-slim
 .build: &build
   script:
   - apt-get update
-  - apt-get install -y python3-pip cmake doxygen libboost-all-dev libboost-dev fig2dev
+  - apt-get install -y python3-pip doxygen libboost-all-dev libboost-dev fig2dev
   - pip3 install --requirement docs/requirements.txt 
-  - cmake -Denable_documentation=ON .
-  - make documentation
-  - mkdir docs/doxyoutput
-  - cp -r doc/xml docs/doxyoutput
   - cd docs
   - sphinx-build -M html source/ build/
   - mv build/html ../public

diff --git a/examples/msg/platform-failures/platform-failures.c b/examples/msg/platform-failures/platform-failures.c
index 7771e50..f1d5d5b 100644 (file)
--- a/examples/msg/platform-failures/platform-failures.c
+++ b/examples/msg/platform-failures/platform-failures.c
@@ -25,13 +25,13 @@ static int master(int argc, char *argv[])
   for (i = 0; i < number_of_tasks; i++) {
     char mailbox[256];
     snprintf(mailbox, 255, "worker-%ld", i % workers_count);
-
+    XBT_INFO("Send a message to %s", mailbox);
     msg_task_t task = MSG_task_create("Task", task_comp_size, task_comm_size, xbt_new0(double, 1));
     *((double *) task->data) = MSG_get_clock();
 
     switch ( MSG_task_send_with_timeout(task,mailbox,10.0) ) {
     case MSG_OK:
-      XBT_INFO("Send completed");
+      XBT_INFO("Send to %s completed", mailbox);
       break;
 
     case MSG_HOST_FAILURE:
@@ -103,21 +103,20 @@ static int worker(int argc, char *argv[])
   while (1) {
     double time1 = MSG_get_clock();
     msg_task_t task = NULL;
+    XBT_INFO("Waiting a message on %s", mailbox);
     int retcode = MSG_task_receive( &(task), mailbox);
     double time2 = MSG_get_clock();
     if (retcode == MSG_OK) {
-      XBT_INFO("Received \"%s\"", MSG_task_get_name(task));
       if (MSG_task_get_data(task) == FINALIZE) {
         MSG_task_destroy(task);
         break;
       }
       if (time1 < *((double *) task->data))
         time1 = *((double *) task->data);
-      XBT_INFO("Communication time : \"%f\"", time2 - time1);
-      XBT_INFO("Processing \"%s\"", MSG_task_get_name(task));
+      XBT_INFO("Start execution...");
       retcode = MSG_task_execute(task);
       if (retcode == MSG_OK) {
-        XBT_INFO("\"%s\" done", MSG_task_get_name(task));
+        XBT_INFO("Execution complete.");
         free(task->data);
         MSG_task_destroy(task);
       } else if (retcode == MSG_HOST_FAILURE) {

diff --git a/examples/msg/platform-failures/platform-failures.tesh b/examples/msg/platform-failures/platform-failures.tesh
index a169ce4..33043db 100644 (file)
--- a/examples/msg/platform-failures/platform-failures.tesh
+++ b/examples/msg/platform-failures/platform-failures.tesh
@@ -6,94 +6,106 @@ p Testing a simple master/worker example application handling failures TCP cross
 $ $SG_TEST_EXENV ${bindir:=.}/platform-failures$EXEEXT --log=xbt_cfg.thres:critical --log=no_loc ${platfdir}/small_platform_with_failures.xml ${srcdir}/../app-masterworker/app-masterworker_d.xml --cfg=path:${srcdir} --cfg=network/crosstraffic:0 "--log=root.fmt:[%10.6r]%e(%i:%P@%h)%e%m%n"
 > [  0.000000] (0:maestro@) Cannot launch process 'worker' on failed host 'Fafard'
 > [  0.000000] (1:master@Tremblay) Got 5 workers and 20 tasks to process
-> [  0.010309] (1:master@Tremblay) Send completed
-> [  0.010309] (2:worker@Tremblay) Received "Task"
-> [  0.010309] (2:worker@Tremblay) Communication time : "0.010309"
-> [  0.010309] (2:worker@Tremblay) Processing "Task"
+> [  0.000000] (1:master@Tremblay) Send a message to worker-0
+> [  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
+> [  0.000000] (3:worker@Jupiter) Waiting a message on worker-1
+> [  0.000000] (4:worker@Ginette) Waiting a message on worker-3
+> [  0.000000] (5:worker@Bourassa) Waiting a message on worker-4
+> [  0.010309] (1:master@Tremblay) Send a message to worker-1
 > [  1.000000] (0:maestro@) Restart processes on host Fafard
+> [  1.000000] (6:worker@Fafard) Waiting a message on worker-2
 > [  1.000000] (1:master@Tremblay) Mmh. Something went wrong with 'worker-1'. Nevermind. Let's keep going!
+> [  1.000000] (1:master@Tremblay) Send a message to worker-2
 > [  1.000000] (3:worker@Jupiter) Gloups. The cpu on which I'm running just turned off!. See you!
+> [  2.000000] (1:master@Tremblay) Mmh. Something went wrong with 'worker-2'. Nevermind. Let's keep going!
+> [  2.000000] (6:worker@Fafard) Gloups. The cpu on which I'm running just turned off!. See you!
 > [  2.000000] (0:maestro@) Restart processes on host Jupiter
-> [  2.010309] (2:worker@Tremblay) "Task" done
-> [ 11.000000] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
-> [ 12.030928] (1:master@Tremblay) Send completed
-> [ 12.030928] (4:worker@Ginette) Received "Task"
-> [ 12.030928] (4:worker@Ginette) Communication time : "1.030928"
-> [ 12.030928] (4:worker@Ginette) Processing "Task"
-> [ 13.061856] (1:master@Tremblay) Send completed
-> [ 13.061856] (5:worker@Bourassa) Received "Task"
-> [ 13.061856] (5:worker@Bourassa) Communication time : "1.030928"
-> [ 13.061856] (5:worker@Bourassa) Processing "Task"
-> [ 13.072165] (1:master@Tremblay) Send completed
-> [ 13.072165] (2:worker@Tremblay) Received "Task"
-> [ 13.072165] (2:worker@Tremblay) Communication time : "0.010309"
-> [ 13.072165] (2:worker@Tremblay) Processing "Task"
-> [ 14.030928] (4:worker@Ginette) "Task" done
-> [ 14.103093] (1:master@Tremblay) Send completed
-> [ 14.103093] (6:worker@Jupiter) Received "Task"
-> [ 14.103093] (6:worker@Jupiter) Communication time : "1.030928"
-> [ 14.103093] (6:worker@Jupiter) Processing "Task"
-> [ 15.061856] (5:worker@Bourassa) "Task" done
-> [ 15.072165] (2:worker@Tremblay) "Task" done
-> [ 16.103093] (6:worker@Jupiter) "Task" done
-> [ 24.103093] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
-> [ 24.103093] (1:master@Tremblay) Mmh. Something went wrong with 'worker-3'. Nevermind. Let's keep going!
-> [ 24.103093] (4:worker@Ginette) Mmh. Something went wrong. Nevermind. Let's keep going!
-> [ 25.134021] (1:master@Tremblay) Send completed
-> [ 25.134021] (5:worker@Bourassa) Received "Task"
-> [ 25.134021] (5:worker@Bourassa) Communication time : "1.030928"
-> [ 25.134021] (5:worker@Bourassa) Processing "Task"
-> [ 25.144330] (1:master@Tremblay) Send completed
-> [ 25.144330] (2:worker@Tremblay) Received "Task"
-> [ 25.144330] (2:worker@Tremblay) Communication time : "0.010309"
-> [ 25.144330] (2:worker@Tremblay) Processing "Task"
-> [ 26.175258] (1:master@Tremblay) Send completed
-> [ 26.175258] (6:worker@Jupiter) Received "Task"
-> [ 26.175258] (6:worker@Jupiter) Communication time : "1.030928"
-> [ 26.175258] (6:worker@Jupiter) Processing "Task"
-> [ 27.134021] (5:worker@Bourassa) "Task" done
-> [ 27.144330] (2:worker@Tremblay) "Task" done
-> [ 28.175258] (6:worker@Jupiter) "Task" done
-> [ 36.175258] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
-> [ 37.206186] (1:master@Tremblay) Send completed
-> [ 37.206186] (1:master@Tremblay) Mmh. Something went wrong with 'worker-4'. Nevermind. Let's keep going!
-> [ 37.206186] (4:worker@Ginette) Received "Task"
-> [ 37.206186] (4:worker@Ginette) Communication time : "1.030928"
-> [ 37.206186] (4:worker@Ginette) Processing "Task"
-> [ 37.206186] (5:worker@Bourassa) Mmh. Something went wrong. Nevermind. Let's keep going!
-> [ 37.216495] (1:master@Tremblay) Send completed
-> [ 37.216495] (2:worker@Tremblay) Received "Task"
-> [ 37.216495] (2:worker@Tremblay) Communication time : "0.010309"
-> [ 37.216495] (2:worker@Tremblay) Processing "Task"
-> [ 38.247423] (1:master@Tremblay) Send completed
-> [ 38.247423] (6:worker@Jupiter) Received "Task"
-> [ 38.247423] (6:worker@Jupiter) Communication time : "1.030928"
-> [ 38.247423] (6:worker@Jupiter) Processing "Task"
-> [ 39.206186] (4:worker@Ginette) "Task" done
-> [ 39.216495] (2:worker@Tremblay) "Task" done
-> [ 40.247423] (6:worker@Jupiter) "Task" done
-> [ 48.247423] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
-> [ 49.278351] (1:master@Tremblay) Send completed
-> [ 49.278351] (4:worker@Ginette) Received "Task"
-> [ 49.278351] (4:worker@Ginette) Communication time : "1.030928"
-> [ 49.278351] (4:worker@Ginette) Processing "Task"
-> [ 50.000000] (4:worker@Ginette) Gloups. The cpu on which I'm running just turned off!. See you!
-> [ 50.309278] (1:master@Tremblay) Send completed
-> [ 50.309278] (1:master@Tremblay) All tasks have been dispatched. Let's tell everybody the computation is over.
-> [ 50.309278] (2:worker@Tremblay) Received "finalize"
-> [ 50.309278] (2:worker@Tremblay) I'm done. See you!
-> [ 50.309278] (5:worker@Bourassa) Received "Task"
-> [ 50.309278] (5:worker@Bourassa) Communication time : "1.030928"
-> [ 50.309278] (5:worker@Bourassa) Processing "Task"
-> [ 50.309278] (6:worker@Jupiter) Received "finalize"
-> [ 50.309278] (6:worker@Jupiter) I'm done. See you!
-> [ 51.309278] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
-> [ 52.309278] (0:maestro@) Simulation time 52.3093
-> [ 52.309278] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-3'. Nevermind. Let's keep going!
-> [ 52.309278] (1:master@Tremblay) Goodbye now!
-> [ 52.309278] (5:worker@Bourassa) "Task" done
-> [ 52.309278] (5:worker@Bourassa) Received "finalize"
-> [ 52.309278] (5:worker@Bourassa) I'm done. See you!
+> [  2.000000] (1:master@Tremblay) Send a message to worker-3
+> [  2.000000] (7: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
+> [  3.030928] (1:master@Tremblay) Send a message to worker-4
+> [  3.030928] (4:worker@Ginette) Start execution...
+> [  4.061856] (1:master@Tremblay) Send to worker-4 completed
+> [  4.061856] (1:master@Tremblay) Send a message to worker-0
+> [  4.061856] (5:worker@Bourassa) Start execution...
+> [  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...
+> [  5.030928] (4:worker@Ginette) Execution complete.
+> [  5.030928] (4: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] (7:worker@Jupiter) Start execution...
+> [  6.061856] (5:worker@Bourassa) Execution complete.
+> [  6.061856] (5: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] (7:worker@Jupiter) Execution complete.
+> [  7.103093] (7: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. Something went wrong with 'worker-3'. Nevermind. Let's keep going!
+> [ 15.103093] (1:master@Tremblay) Send a message to worker-4
+> [ 15.103093] (4:worker@Ginette) Mmh. Something went wrong. Nevermind. Let's keep going!
+> [ 15.103093] (4:worker@Ginette) Waiting a message on worker-3
+> [ 16.134021] (1:master@Tremblay) Send to worker-4 completed
+> [ 16.134021] (1:master@Tremblay) Send a message to worker-0
+> [ 16.134021] (5:worker@Bourassa) Start execution...
+> [ 16.144330] (1:master@Tremblay) Send to worker-0 completed
+> [ 16.144330] (1:master@Tremblay) Send a message to worker-1
+> [ 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] (7:worker@Jupiter) Start execution...
+> [ 18.134021] (5:worker@Bourassa) Execution complete.
+> [ 18.134021] (5: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] (7:worker@Jupiter) Execution complete.
+> [ 19.175258] (7:worker@Jupiter) Waiting a message on worker-1
+> [ 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
+> [ 28.206186] (1:master@Tremblay) Send a message to worker-4
+> [ 28.206186] (1:master@Tremblay) Mmh. Something went wrong with 'worker-4'. Nevermind. Let's keep going!
+> [ 28.206186] (1:master@Tremblay) Send a message to worker-0
+> [ 28.206186] (4:worker@Ginette) Start execution...
+> [ 28.206186] (5:worker@Bourassa) Mmh. Something went wrong. Nevermind. Let's keep going!
+> [ 28.206186] (5:worker@Bourassa) Waiting a message on worker-4
+> [ 28.216495] (1:master@Tremblay) Send to worker-0 completed
+> [ 28.216495] (1:master@Tremblay) Send a message to worker-1
+> [ 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] (7:worker@Jupiter) Start execution...
+> [ 30.206186] (4:worker@Ginette) Execution complete.
+> [ 30.206186] (4: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] (7:worker@Jupiter) Execution complete.
+> [ 31.247423] (7:worker@Jupiter) Waiting a message on worker-1
+> [ 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
+> [ 40.278351] (1:master@Tremblay) Send a message to worker-4
+> [ 40.278351] (4:worker@Ginette) Start execution...
+> [ 41.000000] (4:worker@Ginette) Gloups. The cpu on which I'm running just turned off!. See you!
+> [ 41.309278] (1:master@Tremblay) Send to worker-4 completed
+> [ 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] (5:worker@Bourassa) Start execution...
+> [ 41.309278] (7: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!
+> [ 43.309278] (1:master@Tremblay) Goodbye now!
+> [ 43.309278] (5:worker@Bourassa) Execution complete.
+> [ 43.309278] (5:worker@Bourassa) Waiting a message on worker-4
+> [ 43.309278] (5:worker@Bourassa) I'm done. See you!
 
 p Testing a simple master/worker example application handling failures. TCP crosstraffic ENABLED
 
@@ -101,186 +113,210 @@ p Testing a simple master/worker example application handling failures. TCP cros
 $ $SG_TEST_EXENV ${bindir:=.}/platform-failures$EXEEXT --log=xbt_cfg.thres:critical --log=no_loc ${platfdir}/small_platform_with_failures.xml ${srcdir}/../app-masterworker/app-masterworker_d.xml --cfg=path:${srcdir} "--log=root.fmt:[%10.6r]%e(%i:%P@%h)%e%m%n"
 > [  0.000000] (0:maestro@) Cannot launch process 'worker' on failed host 'Fafard'
 > [  0.000000] (1:master@Tremblay) Got 5 workers and 20 tasks to process
-> [  0.010825] (1:master@Tremblay) Send completed
-> [  0.010825] (2:worker@Tremblay) Received "Task"
-> [  0.010825] (2:worker@Tremblay) Communication time : "0.010825"
-> [  0.010825] (2:worker@Tremblay) Processing "Task"
+> [  0.000000] (1:master@Tremblay) Send a message to worker-0
+> [  0.000000] (2:worker@Tremblay) Waiting a message on worker-0
+> [  0.000000] (3:worker@Jupiter) Waiting a message on worker-1
+> [  0.000000] (4:worker@Ginette) Waiting a message on worker-3
+> [  0.000000] (5:worker@Bourassa) Waiting a message on worker-4
+> [  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 processes on host Fafard
+> [  1.000000] (6:worker@Fafard) Waiting a message on worker-2
 > [  1.000000] (1:master@Tremblay) Mmh. Something went wrong with 'worker-1'. Nevermind. Let's keep going!
+> [  1.000000] (1:master@Tremblay) Send a message to worker-2
 > [  1.000000] (3:worker@Jupiter) Gloups. The cpu on which I'm running just turned off!. See you!
 > [  2.000000] (0:maestro@) Restart processes on host Jupiter
-> [  2.010825] (2:worker@Tremblay) "Task" done
-> [ 11.000000] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
-> [ 12.082474] (1:master@Tremblay) Send completed
-> [ 12.082474] (4:worker@Ginette) Received "Task"
-> [ 12.082474] (4:worker@Ginette) Communication time : "1.082474"
-> [ 12.082474] (4:worker@Ginette) Processing "Task"
-> [ 13.164948] (1:master@Tremblay) Send completed
-> [ 13.164948] (5:worker@Bourassa) Received "Task"
-> [ 13.164948] (5:worker@Bourassa) Communication time : "1.082474"
-> [ 13.164948] (5:worker@Bourassa) Processing "Task"
-> [ 13.175773] (1:master@Tremblay) Send completed
-> [ 13.175773] (2:worker@Tremblay) Received "Task"
-> [ 13.175773] (2:worker@Tremblay) Communication time : "0.010825"
-> [ 13.175773] (2:worker@Tremblay) Processing "Task"
-> [ 14.082474] (4:worker@Ginette) "Task" done
-> [ 14.258247] (1:master@Tremblay) Send completed
-> [ 14.258247] (6:worker@Jupiter) Received "Task"
-> [ 14.258247] (6:worker@Jupiter) Communication time : "1.082474"
-> [ 14.258247] (6:worker@Jupiter) Processing "Task"
-> [ 15.164948] (5:worker@Bourassa) "Task" done
-> [ 15.175773] (2:worker@Tremblay) "Task" done
-> [ 16.258247] (6:worker@Jupiter) "Task" done
-> [ 24.258247] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
-> [ 24.258247] (1:master@Tremblay) Mmh. Something went wrong with 'worker-3'. Nevermind. Let's keep going!
-> [ 24.258247] (4:worker@Ginette) Mmh. Something went wrong. Nevermind. Let's keep going!
-> [ 25.340722] (1:master@Tremblay) Send completed
-> [ 25.340722] (5:worker@Bourassa) Received "Task"
-> [ 25.340722] (5:worker@Bourassa) Communication time : "1.082474"
-> [ 25.340722] (5:worker@Bourassa) Processing "Task"
-> [ 25.351546] (1:master@Tremblay) Send completed
-> [ 25.351546] (2:worker@Tremblay) Received "Task"
-> [ 25.351546] (2:worker@Tremblay) Communication time : "0.010825"
-> [ 25.351546] (2:worker@Tremblay) Processing "Task"
-> [ 26.434021] (1:master@Tremblay) Send completed
-> [ 26.434021] (6:worker@Jupiter) Received "Task"
-> [ 26.434021] (6:worker@Jupiter) Communication time : "1.082474"
-> [ 26.434021] (6:worker@Jupiter) Processing "Task"
-> [ 27.340722] (5:worker@Bourassa) "Task" done
-> [ 27.351546] (2:worker@Tremblay) "Task" done
-> [ 28.434021] (6:worker@Jupiter) "Task" done
-> [ 36.434021] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
-> [ 37.516495] (1:master@Tremblay) Send completed
-> [ 37.516495] (1:master@Tremblay) Mmh. Something went wrong with 'worker-4'. Nevermind. Let's keep going!
-> [ 37.516495] (4:worker@Ginette) Received "Task"
-> [ 37.516495] (4:worker@Ginette) Communication time : "1.082474"
-> [ 37.516495] (4:worker@Ginette) Processing "Task"
-> [ 37.516495] (5:worker@Bourassa) Mmh. Something went wrong. Nevermind. Let's keep going!
-> [ 37.527320] (1:master@Tremblay) Send completed
-> [ 37.527320] (2:worker@Tremblay) Received "Task"
-> [ 37.527320] (2:worker@Tremblay) Communication time : "0.010825"
-> [ 37.527320] (2:worker@Tremblay) Processing "Task"
-> [ 38.609794] (1:master@Tremblay) Send completed
-> [ 38.609794] (6:worker@Jupiter) Received "Task"
-> [ 38.609794] (6:worker@Jupiter) Communication time : "1.082474"
-> [ 38.609794] (6:worker@Jupiter) Processing "Task"
-> [ 39.516495] (4:worker@Ginette) "Task" done
-> [ 39.527320] (2:worker@Tremblay) "Task" done
-> [ 40.609794] (6:worker@Jupiter) "Task" done
-> [ 48.609794] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
-> [ 49.692268] (1:master@Tremblay) Send completed
-> [ 49.692268] (4:worker@Ginette) Received "Task"
-> [ 49.692268] (4:worker@Ginette) Communication time : "1.082474"
-> [ 49.692268] (4:worker@Ginette) Processing "Task"
-> [ 50.000000] (4:worker@Ginette) Gloups. The cpu on which I'm running just turned off!. See you!
-> [ 50.774742] (1:master@Tremblay) Send completed
-> [ 50.774742] (1:master@Tremblay) All tasks have been dispatched. Let's tell everybody the computation is over.
-> [ 50.774742] (2:worker@Tremblay) Received "finalize"
-> [ 50.774742] (2:worker@Tremblay) I'm done. See you!
-> [ 50.774742] (5:worker@Bourassa) Received "Task"
-> [ 50.774742] (5:worker@Bourassa) Communication time : "1.082474"
-> [ 50.774742] (5:worker@Bourassa) Processing "Task"
-> [ 50.774742] (6:worker@Jupiter) Received "finalize"
-> [ 50.774742] (6:worker@Jupiter) I'm done. See you!
-> [ 51.774742] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
-> [ 52.774742] (0:maestro@) Simulation time 52.7747
-> [ 52.774742] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-3'. Nevermind. Let's keep going!
-> [ 52.774742] (1:master@Tremblay) Goodbye now!
-> [ 52.774742] (5:worker@Bourassa) "Task" done
-> [ 52.774742] (5:worker@Bourassa) Received "finalize"
-> [ 52.774742] (5:worker@Bourassa) I'm done. See you!
+> [  2.000000] (7:worker@Jupiter) Waiting a message on worker-1
+> [  2.000000] (1:master@Tremblay) Mmh. Something went wrong with 'worker-2'. Nevermind. Let's keep going!
+> [  2.000000] (1:master@Tremblay) Send a message to worker-3
+> [  2.000000] (6:worker@Fafard) Gloups. The cpu on which I'm running just turned off!. See you!
+> [  2.010825] (2:worker@Tremblay) Execution complete.
+> [  2.010825] (2:worker@Tremblay) Waiting a message on worker-0
+> [  3.082474] (4:worker@Ginette) Start execution...
+> [  3.082474] (1:master@Tremblay) Send to worker-3 completed
+> [  3.082474] (1:master@Tremblay) Send a message to worker-4
+> [  4.164948] (5:worker@Bourassa) Start execution...
+> [  4.164948] (1:master@Tremblay) Send to worker-4 completed
+> [  4.164948] (1:master@Tremblay) Send a message to worker-0
+> [  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
+> [  5.082474] (4:worker@Ginette) Execution complete.
+> [  5.082474] (4:worker@Ginette) Waiting a message on worker-3
+> [  5.258247] (7: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
+> [  6.164948] (5:worker@Bourassa) Execution complete.
+> [  6.164948] (5: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] (7:worker@Jupiter) Execution complete.
+> [  7.258247] (7: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] (4:worker@Ginette) Mmh. Something went wrong. Nevermind. Let's keep going!
+> [ 15.258247] (4:worker@Ginette) Waiting a message on worker-3
+> [ 15.258247] (1:master@Tremblay) Mmh. Something went wrong with 'worker-3'. Nevermind. Let's keep going!
+> [ 15.258247] (1:master@Tremblay) Send a message to worker-4
+> [ 16.340722] (5:worker@Bourassa) Start execution...
+> [ 16.340722] (1:master@Tremblay) Send to worker-4 completed
+> [ 16.340722] (1:master@Tremblay) Send a message to worker-0
+> [ 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] (7: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] (5:worker@Bourassa) Execution complete.
+> [ 18.340722] (5: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] (7:worker@Jupiter) Execution complete.
+> [ 19.434021] (7:worker@Jupiter) Waiting a message on worker-1
+> [ 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] (4:worker@Ginette) Start execution...
+> [ 28.516495] (1:master@Tremblay) Send to worker-3 completed
+> [ 28.516495] (1:master@Tremblay) Send a message to worker-4
+> [ 28.516495] (5:worker@Bourassa) Mmh. Something went wrong. Nevermind. Let's keep going!
+> [ 28.516495] (5:worker@Bourassa) Waiting a message on worker-4
+> [ 28.516495] (1:master@Tremblay) Mmh. Something went wrong with 'worker-4'. Nevermind. Let's keep going!
+> [ 28.516495] (1:master@Tremblay) Send a message to worker-0
+> [ 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] (7: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] (4:worker@Ginette) Execution complete.
+> [ 30.516495] (4: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] (7:worker@Jupiter) Execution complete.
+> [ 31.609794] (7:worker@Jupiter) Waiting a message on worker-1
+> [ 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] (4:worker@Ginette) Start execution...
+> [ 40.692268] (1:master@Tremblay) Send to worker-3 completed
+> [ 40.692268] (1:master@Tremblay) Send a message to worker-4
+> [ 41.000000] (4:worker@Ginette) Gloups. The cpu on which I'm running just turned off!. See you!
+> [ 41.774742] (5:worker@Bourassa) Start execution...
+> [ 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] (7: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] (5:worker@Bourassa) Execution complete.
+> [ 43.774742] (5:worker@Bourassa) Waiting a message on worker-4
+> [ 43.774742] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-3'. Nevermind. Let's keep going!
+> [ 43.774742] (5:worker@Bourassa) I'm done. See you!
+> [ 43.774742] (1:master@Tremblay) Goodbye now!
+> [ 43.774742] (0:maestro@) Simulation time 43.7747
 
 p Testing a simple master/worker example application handling failures. CPU_TI optimization enabled
 
 ! output sort 19
-$ $SG_TEST_EXENV ${bindir:=.}/platform-failures$EXEEXT --log=xbt_cfg.thres:critical --log=no_loc ${platfdir}/small_platform_with_failures.xml ${srcdir}/../app-masterworker/app-masterworker_d.xml --cfg=path:${srcdir} -cfg=cpu/optim:TI "--log=root.fmt:[%10.6r]%e(%i:%P@%h)%e%m%n"
+$ $SG_TEST_EXENV ${bindir:=.}/platform-failures$EXEEXT --log=xbt_cfg.thres:critical --log=no_loc ${platfdir}/small_platform_with_failures.xml ${srcdir}/../app-masterworker/app-masterworker_d.xml --cfg=path:${srcdir} --cfg=cpu/optim:TI "--log=root.fmt:[%10.6r]%e(%i:%P@%h)%e%m%n"
 > [  0.000000] (0:maestro@) Cannot launch process 'worker' on failed host 'Fafard'
 > [  0.000000] (1:master@Tremblay) Got 5 workers and 20 tasks to process
-> [  0.010825] (1:master@Tremblay) Send completed
-> [  0.010825] (2:worker@Tremblay) Received "Task"
-> [  0.010825] (2:worker@Tremblay) Communication time : "0.010825"
-> [  0.010825] (2:worker@Tremblay) Processing "Task"
+> [  0.000000] (1:master@Tremblay) Send a message to worker-0
+> [  0.000000] (2:worker@Tremblay) Waiting a message on worker-0
+> [  0.000000] (3:worker@Jupiter) Waiting a message on worker-1
+> [  0.000000] (4:worker@Ginette) Waiting a message on worker-3
+> [  0.000000] (5:worker@Bourassa) Waiting a message on worker-4
+> [  0.010825] (1:master@Tremblay) Send to worker-0 completed
+> [  0.010825] (1:master@Tremblay) Send a message to worker-1
+> [  0.010825] (2:worker@Tremblay) Start execution...
 > [  1.000000] (0:maestro@) Restart processes on host Fafard
 > [  1.000000] (1:master@Tremblay) Mmh. Something went wrong with 'worker-1'. Nevermind. Let's keep going!
+> [  1.000000] (1:master@Tremblay) Send a message to worker-2
 > [  1.000000] (3:worker@Jupiter) Gloups. The cpu on which I'm running just turned off!. See you!
+> [  1.000000] (6:worker@Fafard) Waiting a message on worker-2
 > [  2.000000] (0:maestro@) Restart processes on host Jupiter
-> [  2.010825] (2:worker@Tremblay) "Task" done
-> [ 11.000000] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
-> [ 12.082474] (1:master@Tremblay) Send completed
-> [ 12.082474] (4:worker@Ginette) Received "Task"
-> [ 12.082474] (4:worker@Ginette) Communication time : "1.082474"
-> [ 12.082474] (4:worker@Ginette) Processing "Task"
-> [ 13.164948] (1:master@Tremblay) Send completed
-> [ 13.164948] (5:worker@Bourassa) Received "Task"
-> [ 13.164948] (5:worker@Bourassa) Communication time : "1.082474"
-> [ 13.164948] (5:worker@Bourassa) Processing "Task"
-> [ 13.175773] (1:master@Tremblay) Send completed
-> [ 13.175773] (2:worker@Tremblay) Received "Task"
-> [ 13.175773] (2:worker@Tremblay) Communication time : "0.010825"
-> [ 13.175773] (2:worker@Tremblay) Processing "Task"
-> [ 14.082474] (4:worker@Ginette) "Task" done
-> [ 14.258247] (1:master@Tremblay) Send completed
-> [ 14.258247] (6:worker@Jupiter) Received "Task"
-> [ 14.258247] (6:worker@Jupiter) Communication time : "1.082474"
-> [ 14.258247] (6:worker@Jupiter) Processing "Task"
-> [ 15.164948] (5:worker@Bourassa) "Task" done
-> [ 15.175773] (2:worker@Tremblay) "Task" done
-> [ 16.258247] (6:worker@Jupiter) "Task" done
-> [ 24.258247] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
-> [ 24.258247] (1:master@Tremblay) Mmh. Something went wrong with 'worker-3'. Nevermind. Let's keep going!
-> [ 24.258247] (4:worker@Ginette) Mmh. Something went wrong. Nevermind. Let's keep going!
-> [ 25.340722] (1:master@Tremblay) Send completed
-> [ 25.340722] (5:worker@Bourassa) Received "Task"
-> [ 25.340722] (5:worker@Bourassa) Communication time : "1.082474"
-> [ 25.340722] (5:worker@Bourassa) Processing "Task"
-> [ 25.351546] (1:master@Tremblay) Send completed
-> [ 25.351546] (2:worker@Tremblay) Received "Task"
-> [ 25.351546] (2:worker@Tremblay) Communication time : "0.010825"
-> [ 25.351546] (2:worker@Tremblay) Processing "Task"
-> [ 26.434021] (1:master@Tremblay) Send completed
-> [ 26.434021] (6:worker@Jupiter) Received "Task"
-> [ 26.434021] (6:worker@Jupiter) Communication time : "1.082474"
-> [ 26.434021] (6:worker@Jupiter) Processing "Task"
-> [ 27.340722] (5:worker@Bourassa) "Task" done
-> [ 27.351546] (2:worker@Tremblay) "Task" done
-> [ 28.434021] (6:worker@Jupiter) "Task" done
-> [ 36.434021] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
-> [ 37.516495] (1:master@Tremblay) Send completed
-> [ 37.516495] (1:master@Tremblay) Mmh. Something went wrong with 'worker-4'. Nevermind. Let's keep going!
-> [ 37.516495] (4:worker@Ginette) Received "Task"
-> [ 37.516495] (4:worker@Ginette) Communication time : "1.082474"
-> [ 37.516495] (4:worker@Ginette) Processing "Task"
-> [ 37.516495] (5:worker@Bourassa) Mmh. Something went wrong. Nevermind. Let's keep going!
-> [ 37.527320] (1:master@Tremblay) Send completed
-> [ 37.527320] (2:worker@Tremblay) Received "Task"
-> [ 37.527320] (2:worker@Tremblay) Communication time : "0.010825"
-> [ 37.527320] (2:worker@Tremblay) Processing "Task"
-> [ 38.609794] (1:master@Tremblay) Send completed
-> [ 38.609794] (6:worker@Jupiter) Received "Task"
-> [ 38.609794] (6:worker@Jupiter) Communication time : "1.082474"
-> [ 38.609794] (6:worker@Jupiter) Processing "Task"
-> [ 39.516495] (4:worker@Ginette) "Task" done
-> [ 39.527320] (2:worker@Tremblay) "Task" done
-> [ 40.609794] (6:worker@Jupiter) "Task" done
-> [ 48.609794] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
-> [ 49.692268] (1:master@Tremblay) Send completed
-> [ 49.692268] (4:worker@Ginette) Received "Task"
-> [ 49.692268] (4:worker@Ginette) Communication time : "1.082474"
-> [ 49.692268] (4:worker@Ginette) Processing "Task"
-> [ 50.000000] (4:worker@Ginette) Gloups. The cpu on which I'm running just turned off!. See you!
-> [ 50.774742] (1:master@Tremblay) Send completed
-> [ 50.774742] (1:master@Tremblay) All tasks have been dispatched. Let's tell everybody the computation is over.
-> [ 50.774742] (2:worker@Tremblay) Received "finalize"
-> [ 50.774742] (2:worker@Tremblay) I'm done. See you!
-> [ 50.774742] (5:worker@Bourassa) Received "Task"
-> [ 50.774742] (5:worker@Bourassa) Communication time : "1.082474"
-> [ 50.774742] (5:worker@Bourassa) Processing "Task"
-> [ 50.774742] (6:worker@Jupiter) Received "finalize"
-> [ 50.774742] (6:worker@Jupiter) I'm done. See you!
-> [ 51.774742] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
-> [ 52.774742] (0:maestro@) Simulation time 52.7747
-> [ 52.774742] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-3'. Nevermind. Let's keep going!
-> [ 52.774742] (1:master@Tremblay) Goodbye now!
-> [ 52.774742] (5:worker@Bourassa) "Task" done
-> [ 52.774742] (5:worker@Bourassa) Received "finalize"
-> [ 52.774742] (5:worker@Bourassa) I'm done. See you!
+> [  2.000000] (1:master@Tremblay) Mmh. Something went wrong with 'worker-2'. Nevermind. Let's keep going!
+> [  2.000000] (1:master@Tremblay) Send a message to worker-3
+> [  2.000000] (6:worker@Fafard) Gloups. The cpu on which I'm running just turned off!. See you!
+> [  2.000000] (7:worker@Jupiter) Waiting a message on worker-1
+> [  2.010825] (2:worker@Tremblay) Execution complete.
+> [  2.010825] (2:worker@Tremblay) Waiting a message on worker-0
+> [  3.082474] (1:master@Tremblay) Send to worker-3 completed
+> [  3.082474] (1:master@Tremblay) Send a message to worker-4
+> [  3.082474] (4:worker@Ginette) Start execution...
+> [  4.164948] (1:master@Tremblay) Send to worker-4 completed
+> [  4.164948] (1:master@Tremblay) Send a message to worker-0
+> [  4.164948] (5:worker@Bourassa) Start execution...
+> [  4.175773] (1:master@Tremblay) Send to worker-0 completed
+> [  4.175773] (1:master@Tremblay) Send a message to worker-1
+> [  4.175773] (2:worker@Tremblay) Start execution...
+> [  5.082474] (4:worker@Ginette) Execution complete.
+> [  5.082474] (4:worker@Ginette) Waiting a message on worker-3
+> [  5.258247] (1:master@Tremblay) Send to worker-1 completed
+> [  5.258247] (1:master@Tremblay) Send a message to worker-2
+> [  5.258247] (7:worker@Jupiter) Start execution...
+> [  6.164948] (5:worker@Bourassa) Execution complete.
+> [  6.164948] (5: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] (7:worker@Jupiter) Execution complete.
+> [  7.258247] (7: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] (1:master@Tremblay) Mmh. Something went wrong with 'worker-3'. Nevermind. Let's keep going!
+> [ 15.258247] (1:master@Tremblay) Send a message to worker-4
+> [ 15.258247] (4:worker@Ginette) Mmh. Something went wrong. Nevermind. Let's keep going!
+> [ 15.258247] (4:worker@Ginette) Waiting a message on worker-3
+> [ 16.340722] (1:master@Tremblay) Send to worker-4 completed
+> [ 16.340722] (1:master@Tremblay) Send a message to worker-0
+> [ 16.340722] (5:worker@Bourassa) Start execution...
+> [ 16.351546] (1:master@Tremblay) Send to worker-0 completed
+> [ 16.351546] (1:master@Tremblay) Send a message to worker-1
+> [ 16.351546] (2:worker@Tremblay) Start execution...
+> [ 17.434021] (1:master@Tremblay) Send to worker-1 completed
+> [ 17.434021] (1:master@Tremblay) Send a message to worker-2
+> [ 17.434021] (7:worker@Jupiter) Start execution...
+> [ 18.340722] (5:worker@Bourassa) Execution complete.
+> [ 18.340722] (5: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] (7:worker@Jupiter) Execution complete.
+> [ 19.434021] (7:worker@Jupiter) Waiting a message on worker-1
+> [ 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] (1:master@Tremblay) Send to worker-3 completed
+> [ 28.516495] (1:master@Tremblay) Send a message to worker-4
+> [ 28.516495] (1:master@Tremblay) Mmh. Something went wrong with 'worker-4'. Nevermind. Let's keep going!
+> [ 28.516495] (1:master@Tremblay) Send a message to worker-0
+> [ 28.516495] (4:worker@Ginette) Start execution...
+> [ 28.516495] (5:worker@Bourassa) Mmh. Something went wrong. Nevermind. Let's keep going!
+> [ 28.516495] (5:worker@Bourassa) Waiting a message on worker-4
+> [ 28.527320] (1:master@Tremblay) Send to worker-0 completed
+> [ 28.527320] (1:master@Tremblay) Send a message to worker-1
+> [ 28.527320] (2:worker@Tremblay) Start execution...
+> [ 29.609794] (1:master@Tremblay) Send to worker-1 completed
+> [ 29.609794] (1:master@Tremblay) Send a message to worker-2
+> [ 29.609794] (7:worker@Jupiter) Start execution...
+> [ 30.516495] (4:worker@Ginette) Execution complete.
+> [ 30.516495] (4: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] (7:worker@Jupiter) Execution complete.
+> [ 31.609794] (7:worker@Jupiter) Waiting a message on worker-1
+> [ 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] (1:master@Tremblay) Send to worker-3 completed
+> [ 40.692268] (1:master@Tremblay) Send a message to worker-4
+> [ 40.692268] (4:worker@Ginette) Start execution...
+> [ 41.000000] (4:worker@Ginette) Gloups. The cpu on which I'm running just turned off!. See you!
+> [ 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] (5:worker@Bourassa) Start execution...
+> [ 41.774742] (7: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] (0:maestro@) Simulation time 43.7747
+> [ 43.774742] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-3'. Nevermind. Let's keep going!
+> [ 43.774742] (1:master@Tremblay) Goodbye now!
+> [ 43.774742] (5:worker@Bourassa) Execution complete.
+> [ 43.774742] (5:worker@Bourassa) Waiting a message on worker-4
+> [ 43.774742] (5:worker@Bourassa) I'm done. See you!

diff --git a/examples/platforms/trace/ginette_state.trace b/examples/platforms/trace/ginette_state.trace
index e3fbe40..108bce3 100644 (file)
--- a/examples/platforms/trace/ginette_state.trace
+++ b/examples/platforms/trace/ginette_state.trace
@@ -1,2 +1,2 @@
-50 0
-60 1
+41 0
+50 1

diff --git a/examples/platforms/trace/link3_state.trace b/examples/platforms/trace/link3_state.trace
index 8cad9d0..aa52029 100644 (file)
--- a/examples/platforms/trace/link3_state.trace
+++ b/examples/platforms/trace/link3_state.trace
@@ -1,4 +1,6 @@
 13 0
 14 1
+15 0
+16 1
 20 0
 25 1

diff --git a/examples/platforms/trace/link4_state.trace b/examples/platforms/trace/link4_state.trace
index 006aa06..fab0dd2 100644 (file)
--- a/examples/platforms/trace/link4_state.trace
+++ b/examples/platforms/trace/link4_state.trace
@@ -1,2 +1,2 @@
-35 0
-40 1
+25 0
+30 1

diff --git a/examples/s4u/CMakeLists.txt b/examples/s4u/CMakeLists.txt
index c8a987e..dae1364 100644 (file)
--- a/examples/s4u/CMakeLists.txt
+++ b/examples/s4u/CMakeLists.txt
@@ -32,7 +32,6 @@ foreach(variant fun class)
 endforeach()
 set(tesh_files    ${tesh_files}    ${CMAKE_CURRENT_SOURCE_DIR}/app-masterworkers/s4u-app-masterworkers.tesh)
 
-
 # CHORD EXAMPLE
 add_executable       (s4u-dht-chord dht-chord/s4u-dht-chord.cpp dht-chord/s4u-dht-chord-node.cpp)
 target_link_libraries(s4u-dht-chord simgrid)
@@ -102,8 +101,13 @@ foreach(example actor-create actor-daemon actor-join actor-kill
                 energy-exec energy-boot energy-link energy-vm
                 engine-filtering
                 exec-async exec-basic exec-dvfs exec-monitor exec-ptask exec-remote
+<<<<<<< HEAD
                 platform-properties plugin-hostload mutex
                 io-async io-file-system io-file-remote io-storage-raw
+=======
+                platform-failures platform-properties plugin-hostload mutex
+                io-file-system io-file-remote io-storage-raw
+>>>>>>> 4ccbacb51eb49323847a906c3e79ea838d76e2a7
                 replay-comm replay-storage
                 routing-get-clusters
                 )

diff --git a/examples/s4u/platform-failures/s4u-platform-failures.cpp b/examples/s4u/platform-failures/s4u-platform-failures.cpp
index 941ea2a..8b54502 100644 (file)
--- a/examples/s4u/platform-failures/s4u-platform-failures.cpp
+++ b/examples/s4u/platform-failures/s4u-platform-failures.cpp
@@ -25,8 +25,9 @@ static int master(int argc, char* argv[])
     mailbox         = simgrid::s4u::Mailbox::by_name(std::string("worker-") + std::to_string(i % workers_count));
     double* payload = new double(comp_size);
     try {
+      XBT_INFO("Send a message to %s", mailbox->get_cname());
       mailbox->put(payload, comm_size, 10.0);
-      XBT_INFO("Send completed");
+      XBT_INFO("Send to %s completed", mailbox->get_cname());
     } catch (xbt_ex& e) {
       switch (e.category) {
         case host_error:
@@ -84,8 +85,27 @@ static int worker(int argc, char* argv[])
   double comp_size                 = -1;
   while (1) {
     try {
+      XBT_INFO("Waiting a message on %s", mailbox->get_cname());
       payload   = static_cast<double*>(mailbox->get());
       comp_size = *payload;
+      xbt_assert(payload != nullptr, "mailbox->get() failed");
+      if (comp_size < 0) { /* - Exit when -1.0 is received */
+        XBT_INFO("I'm done. See you!");
+        break;
+      }
+      /*  - Otherwise, process the task */
+      try {
+        XBT_INFO("Start execution...");
+        simgrid::s4u::this_actor::execute(comp_size);
+        XBT_INFO("Execution complete.");
+      } catch (xbt_ex& e) {
+        if (e.category == host_error) {
+          XBT_INFO("Gloups. The cpu on which I'm running just turned off!. See you!");
+          return -1;
+        } else
+          xbt_die("Unexpected behavior");
+      }
+
       delete payload;
     } catch (xbt_ex& e) {
       switch (e.category) {
@@ -99,23 +119,7 @@ static int worker(int argc, char* argv[])
           xbt_die("Unexpected behavior");
       }
     }
-    xbt_assert(payload != nullptr, "mailbox->get() failed");
-    if (comp_size < 0) { /* - Exit when -1.0 is received */
-      XBT_INFO("I'm done. See you!");
-      break;
-    }
-    /*  - Otherwise, process the task */
-    try {
-      simgrid::s4u::this_actor::execute(comp_size);
-    } catch (xbt_ex& e) {
-      if (e.category == host_error) {
-        XBT_INFO("Gloups. The cpu on which I'm running just turned off!. See you!");
-        return -1;
-      } else
-        xbt_die("Unexpected behavior");
-    }
   }
-  XBT_INFO("I'm done. See you!");
   return 0;
 }
 

diff --git a/examples/s4u/platform-failures/s4u-platform-failures.tesh b/examples/s4u/platform-failures/s4u-platform-failures.tesh
index 5738a23..4b365e8 100644 (file)
--- a/examples/s4u/platform-failures/s4u-platform-failures.tesh
+++ b/examples/s4u/platform-failures/s4u-platform-failures.tesh
@@ -6,37 +6,210 @@ p Testing a simple master/worker example application handling failures TCP cross
 $ $SG_TEST_EXENV ${bindir:=.}/s4u-platform-failures$EXEEXT --log=xbt_cfg.thres:critical --log=no_loc ${platfdir}/small_platform_with_failures.xml ${bindir}/../app-masterworker/s4u-app-masterworker_d.xml --cfg=path:${srcdir} --cfg=network/crosstraffic:0 "--log=root.fmt:[%10.6r]%e(%i:%P@%h)%e%m%n"
 > [  0.000000] (0:maestro@) Cannot launch process 'worker' on failed host 'Fafard'
 > [  0.000000] (1:master@Tremblay) Got 5 workers and 20 tasks to process
-> [  0.010309] (1:master@Tremblay) Send completed
+> [  0.000000] (1:master@Tremblay) Send a message to worker-0
+> [  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
+> [  0.000000] (3:worker@Jupiter) Waiting a message on worker-1
+> [  0.000000] (4:worker@Ginette) Waiting a message on worker-3
+> [  0.000000] (5:worker@Bourassa) Waiting a message on worker-4
+> [  0.010309] (1:master@Tremblay) Send a message to worker-1
 > [  1.000000] (0:maestro@) Restart processes on host Fafard
+> [  1.000000] (6:worker@Fafard) Waiting a message on worker-2
 > [  1.000000] (1:master@Tremblay) Mmh. Something went wrong with 'worker-1'. Nevermind. Let's keep going!
+> [  1.000000] (1:master@Tremblay) Send a message to worker-2
 > [  1.000000] (3:worker@Jupiter) Gloups. The cpu on which I'm running just turned off!. See you!
+> [  2.000000] (1:master@Tremblay) Mmh. Something went wrong with 'worker-2'. Nevermind. Let's keep going!
+> [  2.000000] (6:worker@Fafard) Gloups. The cpu on which I'm running just turned off!. See you!
 > [  2.000000] (0:maestro@) Restart processes on host Jupiter
-> [ 11.000000] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
-> [ 12.030928] (1:master@Tremblay) Send completed
-> [ 13.061856] (1:master@Tremblay) Send completed
-> [ 13.072165] (1:master@Tremblay) Send completed
-> [ 14.103093] (1:master@Tremblay) Send completed
-> [ 24.103093] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
-> [ 24.103093] (1:master@Tremblay) Mmh. Something went wrong with 'worker-3'. Nevermind. Let's keep going!
-> [ 24.103093] (4:worker@Ginette) Mmh. Something went wrong. Nevermind. Let's keep going!
-> [ 25.134021] (1:master@Tremblay) Send completed
-> [ 25.144330] (1:master@Tremblay) Send completed
-> [ 26.175258] (1:master@Tremblay) Send completed
-> [ 36.175258] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
-> [ 37.206186] (1:master@Tremblay) Send completed
-> [ 37.206186] (1:master@Tremblay) Mmh. Something went wrong with 'worker-4'. Nevermind. Let's keep going!
-> [ 37.206186] (5:worker@Bourassa) Mmh. Something went wrong. Nevermind. Let's keep going!
-> [ 38.247423] (1:master@Tremblay) Send completed
-> [ 48.247423] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
-> [ 49.278351] (1:master@Tremblay) Send completed
-> [ 50.000000] (4:worker@Ginette) Gloups. The cpu on which I'm running just turned off!. See you!
-> [ 50.309278] (1:master@Tremblay) Send completed
-> [ 50.309278] (1:master@Tremblay) All tasks have been dispatched. Let's tell everybody the computation is over.
-> [ 50.309278] (2:worker@Tremblay) I'm done. See you!
-> [ 50.309278] (6:worker@Jupiter) I'm done. See you!
-> [ 51.309278] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-2'. Nevermind. Let's keep going!
-> [ 52.309278] (0:maestro@) Simulation time 52.3093
-> [ 52.309278] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-3'. Nevermind. Let's keep going!
-> [ 52.309278] (1:master@Tremblay) Goodbye now!
-> [ 52.309278] (5:worker@Bourassa) I'm done. See you!
+> [  2.000000] (1:master@Tremblay) Send a message to worker-3
+> [  2.000000] (7: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
+> [  3.030928] (1:master@Tremblay) Send a message to worker-4
+> [  3.030928] (4:worker@Ginette) Start execution...
+> [  4.061856] (1:master@Tremblay) Send to worker-4 completed
+> [  4.061856] (1:master@Tremblay) Send a message to worker-0
+> [  4.061856] (5:worker@Bourassa) Start execution...
+> [  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...
+> [  5.030928] (4:worker@Ginette) Execution complete.
+> [  5.030928] (4: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] (7:worker@Jupiter) Start execution...
+> [  6.061856] (5:worker@Bourassa) Execution complete.
+> [  6.061856] (5: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] (7:worker@Jupiter) Execution complete.
+> [  7.103093] (7: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. Something went wrong with 'worker-3'. Nevermind. Let's keep going!
+> [ 15.103093] (1:master@Tremblay) Send a message to worker-4
+> [ 15.103093] (4:worker@Ginette) Mmh. Something went wrong. Nevermind. Let's keep going!
+> [ 15.103093] (4:worker@Ginette) Waiting a message on worker-3
+> [ 16.134021] (1:master@Tremblay) Send to worker-4 completed
+> [ 16.134021] (1:master@Tremblay) Send a message to worker-0
+> [ 16.134021] (5:worker@Bourassa) Start execution...
+> [ 16.144330] (1:master@Tremblay) Send to worker-0 completed
+> [ 16.144330] (1:master@Tremblay) Send a message to worker-1
+> [ 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] (7:worker@Jupiter) Start execution...
+> [ 18.134021] (5:worker@Bourassa) Execution complete.
+> [ 18.134021] (5: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] (7:worker@Jupiter) Execution complete.
+> [ 19.175258] (7:worker@Jupiter) Waiting a message on worker-1
+> [ 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
+> [ 28.206186] (1:master@Tremblay) Send a message to worker-4
+> [ 28.206186] (1:master@Tremblay) Mmh. Something went wrong with 'worker-4'. Nevermind. Let's keep going!
+> [ 28.206186] (1:master@Tremblay) Send a message to worker-0
+> [ 28.206186] (4:worker@Ginette) Start execution...
+> [ 28.206186] (5:worker@Bourassa) Mmh. Something went wrong. Nevermind. Let's keep going!
+> [ 28.206186] (5:worker@Bourassa) Waiting a message on worker-4
+> [ 28.216495] (1:master@Tremblay) Send to worker-0 completed
+> [ 28.216495] (1:master@Tremblay) Send a message to worker-1
+> [ 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] (7:worker@Jupiter) Start execution...
+> [ 30.206186] (4:worker@Ginette) Execution complete.
+> [ 30.206186] (4: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] (7:worker@Jupiter) Execution complete.
+> [ 31.247423] (7:worker@Jupiter) Waiting a message on worker-1
+> [ 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
+> [ 40.278351] (1:master@Tremblay) Send a message to worker-4
+> [ 40.278351] (4:worker@Ginette) Start execution...
+> [ 41.000000] (4:worker@Ginette) Gloups. The cpu on which I'm running just turned off!. See you!
+> [ 41.309278] (1:master@Tremblay) Send to worker-4 completed
+> [ 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] (5:worker@Bourassa) Start execution...
+> [ 41.309278] (7: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!
+> [ 43.309278] (1:master@Tremblay) Goodbye now!
+> [ 43.309278] (5:worker@Bourassa) Execution complete.
+> [ 43.309278] (5:worker@Bourassa) Waiting a message on worker-4
+> [ 43.309278] (5:worker@Bourassa) I'm done. See you!
 
+p Testing a simple master/worker example application handling failures. TCP crosstraffic ENABLED
+
+! output sort 19
+$ $SG_TEST_EXENV ${bindir:=.}/s4u-platform-failures$EXEEXT --log=xbt_cfg.thres:critical --log=no_loc ${platfdir}/small_platform_with_failures.xml ${bindir}/../app-masterworker/s4u-app-masterworker_d.xml --cfg=path:${srcdir} "--log=root.fmt:[%10.6r]%e(%i:%P@%h)%e%m%n"
+> [  0.000000] (0:maestro@) Cannot launch process 'worker' on failed host 'Fafard'
+> [  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] (2:worker@Tremblay) Waiting a message on worker-0
+> [  0.000000] (3:worker@Jupiter) Waiting a message on worker-1
+> [  0.000000] (4:worker@Ginette) Waiting a message on worker-3
+> [  0.000000] (5:worker@Bourassa) Waiting a message on worker-4
+> [  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 processes on host Fafard
+> [  1.000000] (6:worker@Fafard) Waiting a message on worker-2
+> [  1.000000] (1:master@Tremblay) Mmh. Something went wrong with 'worker-1'. Nevermind. Let's keep going!
+> [  1.000000] (1:master@Tremblay) Send a message to worker-2
+> [  1.000000] (3:worker@Jupiter) Gloups. The cpu on which I'm running just turned off!. See you!
+> [  2.000000] (0:maestro@) Restart processes on host Jupiter
+> [  2.000000] (7:worker@Jupiter) Waiting a message on worker-1
+> [  2.000000] (1:master@Tremblay) Mmh. Something went wrong with 'worker-2'. Nevermind. Let's keep going!
+> [  2.000000] (1:master@Tremblay) Send a message to worker-3
+> [  2.000000] (6:worker@Fafard) Gloups. The cpu on which I'm running just turned off!. See you!
+> [  2.010825] (2:worker@Tremblay) Execution complete.
+> [  2.010825] (2:worker@Tremblay) Waiting a message on worker-0
+> [  3.082474] (4:worker@Ginette) Start execution...
+> [  3.082474] (1:master@Tremblay) Send to worker-3 completed
+> [  3.082474] (1:master@Tremblay) Send a message to worker-4
+> [  4.164948] (5:worker@Bourassa) Start execution...
+> [  4.164948] (1:master@Tremblay) Send to worker-4 completed
+> [  4.164948] (1:master@Tremblay) Send a message to worker-0
+> [  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
+> [  5.082474] (4:worker@Ginette) Execution complete.
+> [  5.082474] (4:worker@Ginette) Waiting a message on worker-3
+> [  5.258247] (7: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
+> [  6.164948] (5:worker@Bourassa) Execution complete.
+> [  6.164948] (5: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] (7:worker@Jupiter) Execution complete.
+> [  7.258247] (7: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] (4:worker@Ginette) Mmh. Something went wrong. Nevermind. Let's keep going!
+> [ 15.258247] (4:worker@Ginette) Waiting a message on worker-3
+> [ 15.258247] (1:master@Tremblay) Mmh. Something went wrong with 'worker-3'. Nevermind. Let's keep going!
+> [ 15.258247] (1:master@Tremblay) Send a message to worker-4
+> [ 16.340722] (5:worker@Bourassa) Start execution...
+> [ 16.340722] (1:master@Tremblay) Send to worker-4 completed
+> [ 16.340722] (1:master@Tremblay) Send a message to worker-0
+> [ 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] (7: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] (5:worker@Bourassa) Execution complete.
+> [ 18.340722] (5: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] (7:worker@Jupiter) Execution complete.
+> [ 19.434021] (7:worker@Jupiter) Waiting a message on worker-1
+> [ 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] (4:worker@Ginette) Start execution...
+> [ 28.516495] (1:master@Tremblay) Send to worker-3 completed
+> [ 28.516495] (1:master@Tremblay) Send a message to worker-4
+> [ 28.516495] (5:worker@Bourassa) Mmh. Something went wrong. Nevermind. Let's keep going!
+> [ 28.516495] (5:worker@Bourassa) Waiting a message on worker-4
+> [ 28.516495] (1:master@Tremblay) Mmh. Something went wrong with 'worker-4'. Nevermind. Let's keep going!
+> [ 28.516495] (1:master@Tremblay) Send a message to worker-0
+> [ 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] (7: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] (4:worker@Ginette) Execution complete.
+> [ 30.516495] (4: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] (7:worker@Jupiter) Execution complete.
+> [ 31.609794] (7:worker@Jupiter) Waiting a message on worker-1
+> [ 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] (4:worker@Ginette) Start execution...
+> [ 40.692268] (1:master@Tremblay) Send to worker-3 completed
+> [ 40.692268] (1:master@Tremblay) Send a message to worker-4
+> [ 41.000000] (4:worker@Ginette) Gloups. The cpu on which I'm running just turned off!. See you!
+> [ 41.774742] (5:worker@Bourassa) Start execution...
+> [ 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] (7: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] (5:worker@Bourassa) Execution complete.
+> [ 43.774742] (5:worker@Bourassa) Waiting a message on worker-4
+> [ 43.774742] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'worker-3'. Nevermind. Let's keep going!
+> [ 43.774742] (5:worker@Bourassa) I'm done. See you!
+> [ 43.774742] (1:master@Tremblay) Goodbye now!
+> [ 43.774742] (0:maestro@) Simulation time 43.7747

diff --git a/src/s4u/s4u_Actor.cpp b/src/s4u/s4u_Actor.cpp
index c1d7128..b933c63 100644 (file)
--- a/src/s4u/s4u_Actor.cpp
+++ b/src/s4u/s4u_Actor.cpp
@@ -8,7 +8,9 @@
 #include "simgrid/s4u/Exec.hpp"
 #include "simgrid/s4u/Host.hpp"
 #include "src/kernel/activity/ExecImpl.hpp"
+#include "src/simix/smx_host_private.hpp"
 #include "src/simix/smx_private.hpp"
+#include "src/surf/HostImpl.hpp"
 
 #include <sstream>
 
@@ -73,7 +75,16 @@ void Actor::join(double timeout)
 
 void Actor::set_auto_restart(bool autorestart)
 {
-  simgrid::simix::simcall([this, autorestart]() { pimpl_->set_auto_restart(autorestart); });
+  simgrid::simix::simcall([this, autorestart]() {
+    pimpl_->set_auto_restart(autorestart);
+
+    std::map<std::string, kernel::actor::ProcessArg*> actors_map = pimpl_->host_->pimpl_->actors_at_boot_;
+    if (actors_map.find(pimpl_->name_) == actors_map.end()) {
+      simgrid::kernel::actor::ProcessArg* arg = new simgrid::kernel::actor::ProcessArg(pimpl_->host_, pimpl_);
+      XBT_DEBUG("Adding Process %s to the actors_at_boot_ list of Host %s", arg->name.c_str(), arg->host->get_cname());
+      actors_map.insert({arg->name, arg});
+    }
+  });
 }
 
 void Actor::on_exit(int_f_pvoid_pvoid_t fun, void* data) /* deprecated */

diff --git a/src/s4u/s4u_Host.cpp b/src/s4u/s4u_Host.cpp
index 8e5edcb..e78c4eb 100644 (file)
--- a/src/s4u/s4u_Host.cpp
+++ b/src/s4u/s4u_Host.cpp
@@ -86,8 +86,8 @@ void Host::turn_on()
 {
   if (is_off()) {
     simgrid::simix::simcall([this] {
-      this->pimpl_->turn_on();
       this->pimpl_cpu->turn_on();
+      this->pimpl_->turn_on();
       on_state_change(*this);
     });
   }

diff --git a/src/simix/ActorImpl.cpp b/src/simix/ActorImpl.cpp
index c27e6d0..8c60d57 100644 (file)
--- a/src/simix/ActorImpl.cpp
+++ b/src/simix/ActorImpl.cpp
@@ -450,7 +450,9 @@ void SIMIX_process_kill(smx_actor_t process, smx_actor_t issuer) {
 
   /* destroy the blocking synchro if any */
   if (process->waiting_synchro != nullptr) {
-
+    if (process->host_->is_off()) {
+      SMX_EXCEPTION(process, host_error, 0, "Host failed");
+    }
     simgrid::kernel::activity::ExecImplPtr exec =
         boost::dynamic_pointer_cast<simgrid::kernel::activity::ExecImpl>(process->waiting_synchro);
     simgrid::kernel::activity::CommImplPtr comm =
@@ -698,10 +700,14 @@ void SIMIX_process_yield(smx_actor_t self)
     self->finished_ = true;
     /* execute the on_exit functions */
     SIMIX_process_on_exit_runall(self);
-    /* Add the process to the list of process to restart, only if the host is down */
-    if (self->auto_restart_ && self->host_->is_off()) {
-      SIMIX_host_add_auto_restart_process(self->host_, self);
+
+    if (self->auto_restart_ && self->host_->is_off() &&
+        watched_hosts.find(self->host_->get_cname()) == watched_hosts.end()) {
+      XBT_DEBUG("Push host %s to watched_hosts because it's off and %s needs to restart", self->host_->get_cname(),
+                self->get_cname());
+      watched_hosts.insert(self->host_->get_cname());
     }
+
     XBT_DEBUG("Process %s@%s is dead", self->get_cname(), self->host_->get_cname());
     self->context_->stop();
   }

diff --git a/src/simix/smx_global.cpp b/src/simix/smx_global.cpp
index c527f79..eecd1d4 100644 (file)
--- a/src/simix/smx_global.cpp
+++ b/src/simix/smx_global.cpp
@@ -506,7 +506,7 @@ void SIMIX_run()
     /* Autorestart all process */
     for (auto const& host : host_that_restart) {
       XBT_INFO("Restart processes on host %s", host->get_cname());
-      SIMIX_host_autorestart(host);
+      host->turn_on();
     }
     host_that_restart.clear();
 

diff --git a/src/simix/smx_host.cpp b/src/simix/smx_host.cpp
index 05dc306..dc7f150 100644 (file)
--- a/src/simix/smx_host.cpp
+++ b/src/simix/smx_host.cpp
@@ -24,42 +24,6 @@ const char* sg_host_self_get_name()
   return host->get_cname();
 }
 
-/**
- * @brief Add a process to the list of the processes that the host will restart when it comes back
- * This function add a process to the list of the processes that will be restarted when the host comes
- * back. It is expected that this function is called when the host is down.
- * The processes will only be restarted once, meaning that you will have to register the process
- * again to restart the process again.
- */
-void SIMIX_host_add_auto_restart_process(sg_host_t host, simgrid::kernel::actor::ActorImpl* actor)
-{
-  simgrid::kernel::actor::ProcessArg* arg = new simgrid::kernel::actor::ProcessArg(host, actor);
-
-  if (host->is_off() && watched_hosts.find(host->get_cname()) == watched_hosts.end()) {
-    watched_hosts.insert(host->get_cname());
-    XBT_DEBUG("Push host %s to watched_hosts because state == SURF_RESOURCE_OFF", host->get_cname());
-  }
-  XBT_DEBUG("Adding Process %s to the auto-restart list of Host %s", arg->name.c_str(), arg->host->get_cname());
-  host->pimpl_->auto_restart_processes_.push_back(arg);
-}
-
-/** @brief Restart the list of processes that have been registered to the host */
-void SIMIX_host_autorestart(sg_host_t host)
-{
-  std::vector<simgrid::kernel::actor::ProcessArg*> process_list = host->pimpl_->auto_restart_processes_;
-
-  for (auto const& arg : process_list) {
-    XBT_DEBUG("Restarting Process %s@%s right now", arg->name.c_str(), arg->host->get_cname());
-    smx_actor_t actor = simix_global->create_process_function(arg->name.c_str(), arg->code, nullptr, arg->host,
-                                                              arg->properties.get(), nullptr);
-    if (arg->kill_time >= 0)
-      simcall_process_set_kill_time(actor, arg->kill_time);
-    if (arg->auto_restart)
-      actor->auto_restart_ = arg->auto_restart;
-  }
-  process_list.clear();
-}
-
 simgrid::kernel::activity::ExecImplPtr SIMIX_execution_start(std::string name, std::string category,
                                                              double flops_amount, double priority, double bound,
                                                              sg_host_t host)

diff --git a/src/simix/smx_host_private.hpp b/src/simix/smx_host_private.hpp
index fe4c5dc..1a6da74 100644 (file)
--- a/src/simix/smx_host_private.hpp
+++ b/src/simix/smx_host_private.hpp
@@ -10,9 +10,6 @@
 
 #include <boost/intrusive/list.hpp>
 
-XBT_PRIVATE void SIMIX_host_add_auto_restart_process(sg_host_t host, simgrid::kernel::actor::ActorImpl* actor);
-XBT_PRIVATE void SIMIX_host_autorestart(sg_host_t host);
-
 XBT_PRIVATE void SIMIX_execution_finish(smx_activity_t synchro);
 
 XBT_PRIVATE void SIMIX_set_category(smx_activity_t synchro, std::string category);

diff --git a/src/surf/HostImpl.cpp b/src/surf/HostImpl.cpp
index 1084bc0..8fa9326 100644 (file)
--- a/src/surf/HostImpl.cpp
+++ b/src/surf/HostImpl.cpp
@@ -102,6 +102,7 @@ HostImpl::HostImpl(s4u::Host* host) : piface_(host)
   delete piface_->pimpl_;
   piface_->pimpl_ = this;
 }
+
 HostImpl::~HostImpl()
 {
   /* All processes should be gone when the host is turned off (by the end of the simulation). */
@@ -113,12 +114,9 @@ HostImpl::~HostImpl()
     SIMIX_display_process_status();
     THROWF(arg_error, 0, "%s", msg.c_str());
   }
-  for (auto const& arg : auto_restart_processes_)
-    delete arg;
-  auto_restart_processes_.clear();
-  for (auto const& arg : boot_processes_)
-    delete arg;
-  boot_processes_.clear();
+  for (auto const& arg : actors_at_boot_)
+    delete arg.second;
+  actors_at_boot_.clear();
 }
 
 /** Re-starts all the actors that are marked as restartable.
@@ -127,8 +125,9 @@ HostImpl::~HostImpl()
  */
 void HostImpl::turn_on()
 {
-  for (auto const& arg : boot_processes_) {
-    XBT_DEBUG("Booting Process %s(%s) right now", arg->name.c_str(), arg->host->get_cname());
+  for (auto const& elm : actors_at_boot_) {
+    kernel::actor::ProcessArg* arg = elm.second;
+    XBT_DEBUG("Booting Actor %s(%s) right now", arg->name.c_str(), arg->host->get_cname());
     smx_actor_t actor = simix_global->create_process_function(arg->name.c_str(), arg->code, nullptr, arg->host,
                                                               arg->properties.get(), nullptr);
     if (arg->kill_time >= 0)
@@ -142,11 +141,21 @@ void HostImpl::turn_off()
 {
   if (not process_list_.empty()) {
     for (auto& actor : process_list_) {
-      SIMIX_process_kill(&actor, SIMIX_process_self());
-      XBT_DEBUG("Killing %s@%s on behalf of %s which turned off that host.", actor.get_cname(),
+      XBT_DEBUG("Killing Actor %s@%s on behalf of %s which turned off that host.", actor.get_cname(),
                 actor.host_->get_cname(), SIMIX_process_self()->get_cname());
+      SIMIX_process_kill(&actor, SIMIX_process_self());
     }
   }
+  // When a host is turned off, we want to keep only the actors that should restart for when it will boot again.
+  // Then get rid of the others.
+  auto elm = actors_at_boot_.begin();
+  while (elm != actors_at_boot_.end()) {
+    if (not elm->second->auto_restart) {
+      delete elm->second;
+      actors_at_boot_.erase(elm);
+    } else
+      ++elm;
+  }
 }
 
 std::vector<s4u::ActorPtr> HostImpl::get_all_actors()

diff --git a/src/surf/HostImpl.hpp b/src/surf/HostImpl.hpp
index 6672d7a..cca54d6 100644 (file)
--- a/src/surf/HostImpl.hpp
+++ b/src/surf/HostImpl.hpp
@@ -66,8 +66,7 @@ public:
 
   // FIXME: make these private
   ActorList process_list_;
-  std::vector<kernel::actor::ProcessArg*> auto_restart_processes_;
-  std::vector<kernel::actor::ProcessArg*> boot_processes_;
+  std::map<std::string, kernel::actor::ProcessArg*> actors_at_boot_;
 };
 }
 }

diff --git a/src/surf/cpu_cas01.cpp b/src/surf/cpu_cas01.cpp
index 62e69e2..b594980 100644 (file)
--- a/src/surf/cpu_cas01.cpp
+++ b/src/surf/cpu_cas01.cpp
@@ -130,16 +130,17 @@ void CpuCas01::apply_event(tmgr_trace_event_t event, double value)
     xbt_assert(get_core_count() == 1, "FIXME: add state change code also for constraint_core[i]");
 
     if (value > 0) {
-      if (is_off())
+      if (is_off()) {
         host_that_restart.push_back(get_host());
-      turn_on();
+        get_host()->turn_on();
+      }
     } else {
       kernel::lmm::Constraint* cnst = get_constraint();
       kernel::lmm::Variable* var    = nullptr;
       const kernel::lmm::Element* elem = nullptr;
       double date              = surf_get_clock();
 
-      turn_off();
+      get_host()->turn_off();
 
       while ((var = cnst->get_variable(&elem))) {
         kernel::resource::Action* action = static_cast<kernel::resource::Action*>(var->get_id());

diff --git a/src/surf/cpu_ti.cpp b/src/surf/cpu_ti.cpp
index 99d32a6..c7f6266 100644 (file)
--- a/src/surf/cpu_ti.cpp
+++ b/src/surf/cpu_ti.cpp
@@ -398,11 +398,12 @@ void CpuTi::apply_event(tmgr_trace_event_t event, double value)
 
   } else if (event == state_event_) {
     if (value > 0) {
-      if (is_off())
+      if (is_off()) {
         host_that_restart.push_back(get_host());
-      turn_on();
+        get_host()->turn_on();
+      }
     } else {
-      turn_off();
+      get_host()->turn_off();
       double date = surf_get_clock();
 
       /* put all action running on cpu to failed */

diff --git a/src/surf/ptask_L07.cpp b/src/surf/ptask_L07.cpp
index bffa333..6e75461 100644 (file)
--- a/src/surf/ptask_L07.cpp
+++ b/src/surf/ptask_L07.cpp
@@ -315,10 +315,13 @@ void CpuL07::apply_event(tmgr_trace_event_t triggered, double value)
     tmgr_trace_event_unref(&speed_.event);
 
   } else if (triggered == state_event_) {
-    if (value > 0)
-      turn_on();
-    else
-      turn_off();
+    if (value > 0) {
+      if (is_off()) {
+        host_that_restart.push_back(get_host());
+        get_host()->turn_on();
+      }
+    } else
+      get_host()->turn_off();
     tmgr_trace_event_unref(&state_event_);
 
   } else {

diff --git a/src/surf/sg_platf.cpp b/src/surf/sg_platf.cpp
index a3a9c52..55de705 100644 (file)
--- a/src/surf/sg_platf.cpp
+++ b/src/surf/sg_platf.cpp
@@ -444,7 +444,7 @@ void sg_platf_new_actor(simgrid::kernel::routing::ActorCreationArgs* actor)
   simgrid::kernel::actor::ProcessArg* arg =
       new simgrid::kernel::actor::ProcessArg(actor_name, code, nullptr, host, kill_time, properties, auto_restart);
 
-  host->pimpl_->boot_processes_.push_back(arg);
+  host->pimpl_->actors_at_boot_.insert({actor_name, arg});
 
   if (start_time > SIMIX_get_clock()) {
 

diff --git a/teshsuite/msg/host_on_off/host_on_off.c b/teshsuite/msg/host_on_off/host_on_off.c
index 8c34453..9922503 100644 (file)
--- a/teshsuite/msg/host_on_off/host_on_off.c
+++ b/teshsuite/msg/host_on_off/host_on_off.c
@@ -17,6 +17,10 @@ static int slave(int argc, char *argv[])
 
   while (1) {
     res = MSG_task_receive(&(task), mailbox);
+    if (res == MSG_HOST_FAILURE) {
+      XBT_DEBUG("The host has been turned off, this was expected");
+      return 1;
+    }
     xbt_assert(res == MSG_OK, "MSG_task_get failed");
 
     if (!strcmp(MSG_task_get_name(task), "finalize")) {

diff --git a/teshsuite/msg/host_on_off_processes/host_on_off_processes.cpp b/teshsuite/msg/host_on_off_processes/host_on_off_processes.cpp
index f84aaed..8f0b5b2 100644 (file)
--- a/teshsuite/msg/host_on_off_processes/host_on_off_processes.cpp
+++ b/teshsuite/msg/host_on_off_processes/host_on_off_processes.cpp
@@ -27,10 +27,13 @@ static int process_daemon(int /*argc*/, char** /*argv*/)
     msg_task_t task = MSG_task_create("daemon", MSG_host_get_speed(MSG_host_self()), 0, NULL);
     MSG_process_set_data(self, task);
     XBT_INFO("  Execute daemon");
-    MSG_task_execute(task);
-    MSG_process_set_data(self, NULL);
+    msg_error_t res = MSG_task_execute(task);
     MSG_task_destroy(task);
     tasks_done++;
+    if (res == MSG_HOST_FAILURE) {
+      XBT_INFO("Host as died as expected, do nothing else");
+      return 0;
+    }
   }
   XBT_INFO("  daemon done. See you!");
   return 0;
@@ -247,7 +250,6 @@ int main(int argc, char* argv[])
 
   MSG_create_environment(argv[1]);
 
-  MSG_process_set_data_cleanup(task_cleanup_handler);
   MSG_process_create("test_launcher", test_launcher, NULL, MSG_get_host_by_name("Tremblay"));
 
   res = MSG_main();

diff --git a/teshsuite/msg/host_on_off_processes/host_on_off_processes.tesh b/teshsuite/msg/host_on_off_processes/host_on_off_processes.tesh
index ba402ab..f89a77e 100644 (file)
--- a/teshsuite/msg/host_on_off_processes/host_on_off_processes.tesh
+++ b/teshsuite/msg/host_on_off_processes/host_on_off_processes.tesh
@@ -65,6 +65,8 @@ $ ${bindir}/host_on_off_processes ${platfdir}/small_platform.xml 5 --log=no_loc
 > [Tremblay:test_launcher:(1) 20.000000] [msg_test/INFO]   Turn Jupiter off
 > [Tremblay:test_launcher:(1) 20.000000] [msg_test/INFO] Test 5 seems ok (number of Process: 2, it should be 2)
 > [Tremblay:test_launcher:(1) 20.000000] [msg_test/INFO]   Test done. See you!
+> [Jupiter:commRX:(2) 20.000000] [msg_test/INFO]   Receive message: HOST_FAILURE
+> [Jupiter:commRX:(2) 20.000000] [msg_test/INFO]   RX Done
 > [Tremblay:commTX:(3) 40.000000] [msg_test/INFO]   TX done
 > [40.000000] [msg_test/INFO] Simulation time 40
 
@@ -85,6 +87,7 @@ $ ${bindir}/host_on_off_processes ${platfdir}/small_platform.xml 6 --log=no_loc
 > [Jupiter:process_daemonJUPI:(3) 9.000011] [msg_test/INFO]   Execute daemon
 > [Tremblay:test_launcher:(1) 10.000000] [msg_test/INFO]   Turn Jupiter off
 > [Tremblay:test_launcher:(1) 10.000000] [msg_test/INFO]   Shutdown vm0
+> [Jupiter:process_daemonJUPI:(3) 10.000000] [msg_test/INFO] Host as died as expected, do nothing else
 > [Tremblay:test_launcher:(1) 10.000000] [msg_test/INFO]   Destroy vm0
 > [Tremblay:test_launcher:(1) 10.000000] [msg_test/INFO] Test 6 is also weird: when the node Jupiter is turned off once again, the VM and its daemon are not killed. However, the issue regarding the shutdown of hosted VMs can be seen a feature not a bug ;)
 > [Tremblay:test_launcher:(1) 10.000000] [msg_test/INFO]   Test done. See you!

diff --git a/teshsuite/msg/host_on_off_recv/host_on_off_recv.c b/teshsuite/msg/host_on_off_recv/host_on_off_recv.c
index 97363f8..9755c8d 100644 (file)
--- a/teshsuite/msg/host_on_off_recv/host_on_off_recv.c
+++ b/teshsuite/msg/host_on_off_recv/host_on_off_recv.c
@@ -41,7 +41,10 @@ static int slave(int argc, char *argv[])
   msg_task_t task = NULL;
   msg_error_t error = MSG_task_receive(&(task), mailbox);
   if (error) {
-    XBT_ERROR("Error while receiving message");
+    if (error != MSG_HOST_FAILURE)
+      XBT_ERROR("Error while receiving message");
+    else
+      XBT_DEBUG("The host has been turned off, this was expected");
     return 1;
   }
 

diff --git a/teshsuite/s4u/CMakeLists.txt b/teshsuite/s4u/CMakeLists.txt
index f541016..a0eb9f6 100644 (file)
--- a/teshsuite/s4u/CMakeLists.txt
+++ b/teshsuite/s4u/CMakeLists.txt
@@ -11,7 +11,7 @@ endforeach()
 
 ## Add the tests.
 ## Some need to be run with all factories, some need not tesh to run
-foreach(x actor actor-migration cloud-interrupt-migration concurrent_rw) # TODO: actor-autorestart is disabled for now
+foreach(x actor actor-autorestart actor-migration cloud-interrupt-migration concurrent_rw) # TODO: actor-autorestart is disabled for now
   set(tesh_files    ${tesh_files}    ${CMAKE_CURRENT_SOURCE_DIR}/${x}/${x}.tesh)
   ADD_TESH_FACTORIES(tesh-s4u-${x} "thread;ucontext;raw;boost" --setenv srcdir=${CMAKE_HOME_DIRECTORY}/teshsuite/s4u/${x} --setenv platfdir=${CMAKE_HOME_DIRECTORY}/examples/platforms --cd ${CMAKE_BINARY_DIR}/teshsuite/s4u/${x} ${CMAKE_HOME_DIRECTORY}/teshsuite/s4u/${x}/${x}.tesh)
 endforeach()

diff --git a/teshsuite/s4u/actor-autorestart/actor-autorestart.cpp b/teshsuite/s4u/actor-autorestart/actor-autorestart.cpp
index bb2d964..47e132a 100644 (file)
--- a/teshsuite/s4u/actor-autorestart/actor-autorestart.cpp
+++ b/teshsuite/s4u/actor-autorestart/actor-autorestart.cpp
@@ -4,14 +4,24 @@
  * under the terms of the license (GNU LGPL) which comes with this package. */
 
 #include "simgrid/s4u.hpp"
+#include <xbt/ex.hpp>
 
 XBT_LOG_NEW_DEFAULT_CATEGORY(s4u_test, "Messages specific for this s4u example");
 
 static void dummy()
 {
   XBT_INFO("I start");
-  simgrid::s4u::this_actor::sleep_for(200);
-  XBT_INFO("I stop");
+  try {
+    simgrid::s4u::this_actor::sleep_for(200);
+    XBT_INFO("I stop");
+  } catch (xbt_ex& e) {
+    if (e.category == host_error) {
+      XBT_DEBUG("The host has died ... as expected. This actor silently stops");
+    } else {
+      XBT_ERROR("An unexpected exception has been raised.");
+      throw;
+    }
+  }
 }
 
 static void autostart()