From: Frederic Suter Date: Mon, 6 Aug 2018 08:06:01 +0000 (+0200) Subject: make the XBT_INFO match beetween MSG and S4U X-Git-Tag: v3_21~261^2~1^2~7 X-Git-Url: http://info.iut-bm.univ-fcomte.fr/pub/gitweb/simgrid.git/commitdiff_plain/5f97b27a617eefb95187c7b460feb19ad9aa5199 make the XBT_INFO match beetween MSG and S4U activating TI makes the test fail --- diff --git a/examples/msg/platform-failures/platform-failures.c b/examples/msg/platform-failures/platform-failures.c index 7771e50925..f1d5d5baa3 100644 --- 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 a169ce4015..33043dbc08 100644 --- 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/s4u/platform-failures/s4u-platform-failures.tesh b/examples/s4u/platform-failures/s4u-platform-failures.tesh index 9393f778e4..4b365e854f 100644 --- a/examples/s4u/platform-failures/s4u-platform-failures.tesh +++ b/examples/s4u/platform-failures/s4u-platform-failures.tesh @@ -106,3 +106,110 @@ $ $SG_TEST_EXENV ${bindir:=.}/s4u-platform-failures$EXEEXT --log=xbt_cfg.thres:c > [ 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