From 3ac204b84b45076f0b36d27cc56913fd8b23a796 Mon Sep 17 00:00:00 2001 From: Frederic Suter Date: Fri, 25 Mar 2016 11:24:04 +0100 Subject: [PATCH] this example is about failures, not masterslave also put w/ and w/o crosstraffic in the same tesh --- .gitignore | 3 +- examples/msg/CMakeLists.txt | 8 +- .../failures.c} | 0 examples/msg/failures/failures.tesh | 203 ++++++++++++++++++ examples/msg/masterslave/CMakeLists.txt | 2 +- .../msg/masterslave/masterslave_failure.tesh | 102 --------- .../masterslave_failure_crosstraffic.tesh | 102 --------- 7 files changed, 209 insertions(+), 211 deletions(-) rename examples/msg/{masterslave/masterslave_failure.c => failures/failures.c} (100%) create mode 100644 examples/msg/failures/failures.tesh delete mode 100644 examples/msg/masterslave/masterslave_failure.tesh delete mode 100644 examples/msg/masterslave/masterslave_failure_crosstraffic.tesh diff --git a/.gitignore b/.gitignore index a1775949b7..b0af1845f6 100644 --- a/.gitignore +++ b/.gitignore @@ -148,8 +148,7 @@ examples/msg/io-storage/io-storage examples/msg/irc_isend/peer examples/msg/irc_isend/toto.txt examples/msg/masterslave/masterslave_arg -examples/msg/masterslave/masterslave_cluster -examples/msg/masterslave/masterslave_failure +examples/msg/failures/failures examples/msg/masterslave/masterslave_forwarder examples/msg/process-kill/process-kill examples/msg/masterslave/masterslave_mailbox diff --git a/examples/msg/CMakeLists.txt b/examples/msg/CMakeLists.txt index 9aa8aa113e..d37f6f1e0f 100644 --- a/examples/msg/CMakeLists.txt +++ b/examples/msg/CMakeLists.txt @@ -1,5 +1,5 @@ foreach(x actions-mpi actions-storage async-wait async-waitall async-waitany dht-chord dht-pastry - exception energy-consumption energy-onoff energy-pstate energy-ptask energy-vm io-file io-file-unlink + exception energy-consumption energy-onoff energy-pstate energy-ptask energy-vm failures io-file io-file-unlink io-remote io-storage pmm priority process-kill process-migration process-suspend properties sendrecv set-maestro start_kill_time synchro token_ring) add_executable (${x} ${x}/${x}.c) @@ -40,9 +40,9 @@ set(xml_files ${xml_files} ${CMAKE_CURRENT_SOURCE_DIR}/actions-mpi/action ${CMAKE_CURRENT_SOURCE_DIR}/start_kill_time/start_d.xml ${CMAKE_CURRENT_SOURCE_DIR}/start_kill_time/start_kill_d.xml PARENT_SCOPE) -foreach(x actions-mpi actions-storage async-wait async-waitall async-waitany dht-chord io-file io-file-unlink io-remote - io-storage priority process-kill process-migration process-suspend properties sendrecv synchro start_kill_time - token_ring) +foreach(x actions-mpi actions-storage async-wait async-waitall async-waitany dht-chord failures io-file io-file-unlink + io-remote io-storage priority process-kill process-migration process-suspend properties sendrecv synchro + start_kill_time token_ring) ADD_TESH_FACTORIES(msg-${x} "thread;ucontext;raw;boost" --setenv bindir=${CMAKE_BINARY_DIR}/examples/msg/${x} --setenv srcdir=${CMAKE_HOME_DIRECTORY}/examples/platforms --cd ${CMAKE_HOME_DIRECTORY}/examples/msg/${x} ${x}.tesh) endforeach() diff --git a/examples/msg/masterslave/masterslave_failure.c b/examples/msg/failures/failures.c similarity index 100% rename from examples/msg/masterslave/masterslave_failure.c rename to examples/msg/failures/failures.c diff --git a/examples/msg/failures/failures.tesh b/examples/msg/failures/failures.tesh new file mode 100644 index 0000000000..597e2142a7 --- /dev/null +++ b/examples/msg/failures/failures.tesh @@ -0,0 +1,203 @@ +#! ./tesh + +p Testing a simple master/slave example application handling failures TCP crosstraffic DISABLED + +! output sort 19 +$ $SG_TEST_EXENV ${bindir:=.}/failures$EXEEXT --log=xbt_cfg.thres:critical --log=no_loc ${srcdir:=.}/small_platform_with_failures.xml ${srcdir:=.}/../msg/masterslave/deployment_masterslave.xml --cfg=path:${srcdir} --cfg=network/crosstraffic:0 "--log=root.fmt:[%10.6r]%e(%i:%P@%h)%e%m%n" +> [ 0.000000] (0:maestro@) Cannot launch process 'slave' on failed host 'Fafard' +> [ 0.000000] (1:master@Tremblay) Got 5 slave(s) : +> [ 0.000000] (1:master@Tremblay) Jupiter +> [ 0.000000] (1:master@Tremblay) Fafard +> [ 0.000000] (1:master@Tremblay) Ginette +> [ 0.000000] (1:master@Tremblay) Bourassa +> [ 0.000000] (1:master@Tremblay) Tremblay +> [ 0.000000] (1:master@Tremblay) Got 20 task to process : +> [ 1.000000] (0:maestro@) Restart processes on host: Fafard +> [ 1.000000] (1:master@Tremblay) Mmh. Something went wrong with 'Jupiter'. Nevermind. Let's keep going! +> [ 1.000000] (3:slave@Jupiter) 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 'Fafard'. Nevermind. Let's keep going! +> [ 12.030928] (1:master@Tremblay) Send completed +> [ 12.030928] (4:slave@Ginette) Received "Task" +> [ 12.030928] (4:slave@Ginette) Communication time : "1.030928" +> [ 12.030928] (4:slave@Ginette) Processing "Task" +> [ 13.061856] (1:master@Tremblay) Send completed +> [ 13.061856] (5:slave@Bourassa) Received "Task" +> [ 13.061856] (5:slave@Bourassa) Communication time : "1.030928" +> [ 13.061856] (5:slave@Bourassa) Processing "Task" +> [ 13.072165] (1:master@Tremblay) Send completed +> [ 13.072165] (2:slave@Tremblay) Received "Task" +> [ 13.072165] (2:slave@Tremblay) Communication time : "0.010309" +> [ 13.072165] (2:slave@Tremblay) Processing "Task" +> [ 14.030928] (4:slave@Ginette) "Task" done +> [ 14.103093] (1:master@Tremblay) Send completed +> [ 14.103093] (6:slave@Jupiter) Received "Task" +> [ 14.103093] (6:slave@Jupiter) Communication time : "1.030928" +> [ 14.103093] (6:slave@Jupiter) Processing "Task" +> [ 15.061856] (5:slave@Bourassa) "Task" done +> [ 15.072165] (2:slave@Tremblay) "Task" done +> [ 16.103093] (6:slave@Jupiter) "Task" done +> [ 24.103093] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [ 24.103093] (1:master@Tremblay) Mmh. Something went wrong with 'Ginette'. Nevermind. Let's keep going! +> [ 24.103093] (4:slave@Ginette) Mmh. Something went wrong. Nevermind. Let's keep going! +> [ 25.134021] (1:master@Tremblay) Send completed +> [ 25.134021] (5:slave@Bourassa) Received "Task" +> [ 25.134021] (5:slave@Bourassa) Communication time : "1.030928" +> [ 25.134021] (5:slave@Bourassa) Processing "Task" +> [ 25.144330] (1:master@Tremblay) Send completed +> [ 25.144330] (2:slave@Tremblay) Received "Task" +> [ 25.144330] (2:slave@Tremblay) Communication time : "0.010309" +> [ 25.144330] (2:slave@Tremblay) Processing "Task" +> [ 26.175258] (1:master@Tremblay) Send completed +> [ 26.175258] (6:slave@Jupiter) Received "Task" +> [ 26.175258] (6:slave@Jupiter) Communication time : "1.030928" +> [ 26.175258] (6:slave@Jupiter) Processing "Task" +> [ 27.134021] (5:slave@Bourassa) "Task" done +> [ 27.144330] (2:slave@Tremblay) "Task" done +> [ 28.175258] (6:slave@Jupiter) "Task" done +> [ 36.175258] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [ 37.206186] (1:master@Tremblay) Send completed +> [ 37.206186] (1:master@Tremblay) Mmh. Something went wrong with 'Bourassa'. Nevermind. Let's keep going! +> [ 37.206186] (4:slave@Ginette) Received "Task" +> [ 37.206186] (4:slave@Ginette) Communication time : "1.030928" +> [ 37.206186] (4:slave@Ginette) Processing "Task" +> [ 37.206186] (5:slave@Bourassa) Mmh. Something went wrong. Nevermind. Let's keep going! +> [ 37.216495] (1:master@Tremblay) Send completed +> [ 37.216495] (2:slave@Tremblay) Received "Task" +> [ 37.216495] (2:slave@Tremblay) Communication time : "0.010309" +> [ 37.216495] (2:slave@Tremblay) Processing "Task" +> [ 38.247423] (1:master@Tremblay) Send completed +> [ 38.247423] (6:slave@Jupiter) Received "Task" +> [ 38.247423] (6:slave@Jupiter) Communication time : "1.030928" +> [ 38.247423] (6:slave@Jupiter) Processing "Task" +> [ 39.206186] (4:slave@Ginette) "Task" done +> [ 39.216495] (2:slave@Tremblay) "Task" done +> [ 40.247423] (6:slave@Jupiter) "Task" done +> [ 48.247423] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [ 49.278351] (1:master@Tremblay) Send completed +> [ 49.278351] (4:slave@Ginette) Received "Task" +> [ 49.278351] (4:slave@Ginette) Communication time : "1.030928" +> [ 49.278351] (4:slave@Ginette) Processing "Task" +> [ 50.000000] (4:slave@Ginette) Gloups. The cpu on which I'm running just turned off!. See you! +> [ 50.309278] (1:master@Tremblay) Send completed +> [ 50.309278] (5:slave@Bourassa) Received "Task" +> [ 50.309278] (5:slave@Bourassa) Communication time : "1.030928" +> [ 50.309278] (5:slave@Bourassa) Processing "Task" +> [ 50.319588] (1:master@Tremblay) Send completed +> [ 50.319588] (1:master@Tremblay) All tasks have been dispatched. Let's tell everybody the computation is over. +> [ 50.319588] (2:slave@Tremblay) Received "Task" +> [ 50.319588] (2:slave@Tremblay) Communication time : "0.010309" +> [ 50.319588] (2:slave@Tremblay) Processing "Task" +> [ 50.319588] (6:slave@Jupiter) Received "finalize" +> [ 50.319588] (6:slave@Jupiter) I'm done. See you! +> [ 51.319588] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [ 52.309278] (5:slave@Bourassa) "Task" done +> [ 52.319588] (0:maestro@) Simulation time 52.3196 +> [ 52.319588] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Ginette'. Nevermind. Let's keep going! +> [ 52.319588] (1:master@Tremblay) Goodbye now! +> [ 52.319588] (2:slave@Tremblay) "Task" done +> [ 52.319588] (2:slave@Tremblay) Received "finalize" +> [ 52.319588] (2:slave@Tremblay) I'm done. See you! +> [ 52.319588] (5:slave@Bourassa) Received "finalize" +> [ 52.319588] (5:slave@Bourassa) I'm done. See you! + +p Testing a simple master/slave example application handling failures. TCP crosstraffic ENABLED + +! output sort 19 +$ $SG_TEST_EXENV ${bindir:=.}/failures$EXEEXT --log=xbt_cfg.thres:critical --log=no_loc ${srcdir:=.}/small_platform_with_failures.xml ${srcdir:=.}/../msg/masterslave/deployment_masterslave.xml --cfg=path:${srcdir} "--log=root.fmt:[%10.6r]%e(%i:%P@%h)%e%m%n" +> [ 0.000000] (0:maestro@) Cannot launch process 'slave' on failed host 'Fafard' +> [ 0.000000] (1:master@Tremblay) Got 5 slave(s) : +> [ 0.000000] (1:master@Tremblay) Jupiter +> [ 0.000000] (1:master@Tremblay) Fafard +> [ 0.000000] (1:master@Tremblay) Ginette +> [ 0.000000] (1:master@Tremblay) Bourassa +> [ 0.000000] (1:master@Tremblay) Tremblay +> [ 0.000000] (1:master@Tremblay) Got 20 task to process : +> [ 1.000000] (0:maestro@) Restart processes on host: Fafard +> [ 1.000000] (1:master@Tremblay) Mmh. Something went wrong with 'Jupiter'. Nevermind. Let's keep going! +> [ 1.000000] (3:slave@Jupiter) 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 'Fafard'. Nevermind. Let's keep going! +> [ 12.082474] (1:master@Tremblay) Send completed +> [ 12.082474] (4:slave@Ginette) Received "Task" +> [ 12.082474] (4:slave@Ginette) Communication time : "1.082474" +> [ 12.082474] (4:slave@Ginette) Processing "Task" +> [ 13.164948] (1:master@Tremblay) Send completed +> [ 13.164948] (5:slave@Bourassa) Received "Task" +> [ 13.164948] (5:slave@Bourassa) Communication time : "1.082474" +> [ 13.164948] (5:slave@Bourassa) Processing "Task" +> [ 13.175773] (1:master@Tremblay) Send completed +> [ 13.175773] (2:slave@Tremblay) Received "Task" +> [ 13.175773] (2:slave@Tremblay) Communication time : "0.010825" +> [ 13.175773] (2:slave@Tremblay) Processing "Task" +> [ 14.082474] (4:slave@Ginette) "Task" done +> [ 14.258247] (1:master@Tremblay) Send completed +> [ 14.258247] (6:slave@Jupiter) Received "Task" +> [ 14.258247] (6:slave@Jupiter) Communication time : "1.082474" +> [ 14.258247] (6:slave@Jupiter) Processing "Task" +> [ 15.164948] (5:slave@Bourassa) "Task" done +> [ 15.175773] (2:slave@Tremblay) "Task" done +> [ 16.258247] (6:slave@Jupiter) "Task" done +> [ 24.258247] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [ 24.258247] (1:master@Tremblay) Mmh. Something went wrong with 'Ginette'. Nevermind. Let's keep going! +> [ 24.258247] (4:slave@Ginette) Mmh. Something went wrong. Nevermind. Let's keep going! +> [ 25.340722] (1:master@Tremblay) Send completed +> [ 25.340722] (5:slave@Bourassa) Received "Task" +> [ 25.340722] (5:slave@Bourassa) Communication time : "1.082474" +> [ 25.340722] (5:slave@Bourassa) Processing "Task" +> [ 25.351546] (1:master@Tremblay) Send completed +> [ 25.351546] (2:slave@Tremblay) Received "Task" +> [ 25.351546] (2:slave@Tremblay) Communication time : "0.010825" +> [ 25.351546] (2:slave@Tremblay) Processing "Task" +> [ 26.434021] (1:master@Tremblay) Send completed +> [ 26.434021] (6:slave@Jupiter) Received "Task" +> [ 26.434021] (6:slave@Jupiter) Communication time : "1.082474" +> [ 26.434021] (6:slave@Jupiter) Processing "Task" +> [ 27.340722] (5:slave@Bourassa) "Task" done +> [ 27.351546] (2:slave@Tremblay) "Task" done +> [ 28.434021] (6:slave@Jupiter) "Task" done +> [ 36.434021] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [ 37.516495] (1:master@Tremblay) Send completed +> [ 37.516495] (1:master@Tremblay) Mmh. Something went wrong with 'Bourassa'. Nevermind. Let's keep going! +> [ 37.516495] (4:slave@Ginette) Received "Task" +> [ 37.516495] (4:slave@Ginette) Communication time : "1.082474" +> [ 37.516495] (4:slave@Ginette) Processing "Task" +> [ 37.516495] (5:slave@Bourassa) Mmh. Something went wrong. Nevermind. Let's keep going! +> [ 37.527320] (1:master@Tremblay) Send completed +> [ 37.527320] (2:slave@Tremblay) Received "Task" +> [ 37.527320] (2:slave@Tremblay) Communication time : "0.010825" +> [ 37.527320] (2:slave@Tremblay) Processing "Task" +> [ 38.609794] (1:master@Tremblay) Send completed +> [ 38.609794] (6:slave@Jupiter) Received "Task" +> [ 38.609794] (6:slave@Jupiter) Communication time : "1.082474" +> [ 38.609794] (6:slave@Jupiter) Processing "Task" +> [ 39.516495] (4:slave@Ginette) "Task" done +> [ 39.527320] (2:slave@Tremblay) "Task" done +> [ 40.609794] (6:slave@Jupiter) "Task" done +> [ 48.609794] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [ 49.692268] (1:master@Tremblay) Send completed +> [ 49.692268] (4:slave@Ginette) Received "Task" +> [ 49.692268] (4:slave@Ginette) Communication time : "1.082474" +> [ 49.692268] (4:slave@Ginette) Processing "Task" +> [ 50.000000] (4:slave@Ginette) Gloups. The cpu on which I'm running just turned off!. See you! +> [ 50.774742] (1:master@Tremblay) Send completed +> [ 50.774742] (5:slave@Bourassa) Received "Task" +> [ 50.774742] (5:slave@Bourassa) Communication time : "1.082474" +> [ 50.774742] (5:slave@Bourassa) Processing "Task" +> [ 50.785567] (1:master@Tremblay) Send completed +> [ 50.785567] (1:master@Tremblay) All tasks have been dispatched. Let's tell everybody the computation is over. +> [ 50.785567] (2:slave@Tremblay) Received "Task" +> [ 50.785567] (2:slave@Tremblay) Communication time : "0.010825" +> [ 50.785567] (2:slave@Tremblay) Processing "Task" +> [ 50.785567] (6:slave@Jupiter) Received "finalize" +> [ 50.785567] (6:slave@Jupiter) I'm done. See you! +> [ 51.785567] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [ 52.774742] (5:slave@Bourassa) "Task" done +> [ 52.785567] (0:maestro@) Simulation time 52.7856 +> [ 52.785567] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Ginette'. Nevermind. Let's keep going! +> [ 52.785567] (1:master@Tremblay) Goodbye now! +> [ 52.785567] (2:slave@Tremblay) "Task" done +> [ 52.785567] (2:slave@Tremblay) Received "finalize" +> [ 52.785567] (2:slave@Tremblay) I'm done. See you! +> [ 52.785567] (5:slave@Bourassa) Received "finalize" +> [ 52.785567] (5:slave@Bourassa) I'm done. See you! diff --git a/examples/msg/masterslave/CMakeLists.txt b/examples/msg/masterslave/CMakeLists.txt index cf1a238f32..1b8b586b6c 100644 --- a/examples/msg/masterslave/CMakeLists.txt +++ b/examples/msg/masterslave/CMakeLists.txt @@ -1,4 +1,4 @@ -foreach (example masterslave_failure masterslave_forwarder masterslave_mailbox) +foreach (example masterslave_forwarder masterslave_mailbox) add_executable (${example} ${example}.c) target_link_libraries(${example} simgrid) set(examples_src ${examples_src} ${CMAKE_CURRENT_SOURCE_DIR}/${example}.c) diff --git a/examples/msg/masterslave/masterslave_failure.tesh b/examples/msg/masterslave/masterslave_failure.tesh deleted file mode 100644 index f66de1fce4..0000000000 --- a/examples/msg/masterslave/masterslave_failure.tesh +++ /dev/null @@ -1,102 +0,0 @@ -#! ./tesh - -p Testing a simple master/slave example application handling failures - -! output sort 19 -$ masterslave/masterslave_failure$EXEEXT --log=xbt_cfg.thres:critical --log=no_loc ${srcdir:=.}/../platforms/small_platform_with_failures.xml ${srcdir:=.}/masterslave/deployment_masterslave.xml --cfg=path:${srcdir} --cfg=network/crosstraffic:0 "--log=root.fmt:[%10.6r]%e(%i:%P@%h)%e%m%n" -> [ 0.000000] (0:maestro@) Cannot launch process 'slave' on failed host 'Fafard' -> [ 0.000000] (1:master@Tremblay) Got 5 slave(s) : -> [ 0.000000] (1:master@Tremblay) Jupiter -> [ 0.000000] (1:master@Tremblay) Fafard -> [ 0.000000] (1:master@Tremblay) Ginette -> [ 0.000000] (1:master@Tremblay) Bourassa -> [ 0.000000] (1:master@Tremblay) Tremblay -> [ 0.000000] (1:master@Tremblay) Got 20 task to process : -> [ 1.000000] (0:maestro@) Restart processes on host: Fafard -> [ 1.000000] (1:master@Tremblay) Mmh. Something went wrong with 'Jupiter'. Nevermind. Let's keep going! -> [ 1.000000] (3:slave@Jupiter) 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 'Fafard'. Nevermind. Let's keep going! -> [ 12.030928] (1:master@Tremblay) Send completed -> [ 12.030928] (4:slave@Ginette) Received "Task" -> [ 12.030928] (4:slave@Ginette) Communication time : "1.030928" -> [ 12.030928] (4:slave@Ginette) Processing "Task" -> [ 13.061856] (1:master@Tremblay) Send completed -> [ 13.061856] (5:slave@Bourassa) Received "Task" -> [ 13.061856] (5:slave@Bourassa) Communication time : "1.030928" -> [ 13.061856] (5:slave@Bourassa) Processing "Task" -> [ 13.072165] (1:master@Tremblay) Send completed -> [ 13.072165] (2:slave@Tremblay) Received "Task" -> [ 13.072165] (2:slave@Tremblay) Communication time : "0.010309" -> [ 13.072165] (2:slave@Tremblay) Processing "Task" -> [ 14.030928] (4:slave@Ginette) "Task" done -> [ 14.103093] (1:master@Tremblay) Send completed -> [ 14.103093] (6:slave@Jupiter) Received "Task" -> [ 14.103093] (6:slave@Jupiter) Communication time : "1.030928" -> [ 14.103093] (6:slave@Jupiter) Processing "Task" -> [ 15.061856] (5:slave@Bourassa) "Task" done -> [ 15.072165] (2:slave@Tremblay) "Task" done -> [ 16.103093] (6:slave@Jupiter) "Task" done -> [ 24.103093] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! -> [ 24.103093] (1:master@Tremblay) Mmh. Something went wrong with 'Ginette'. Nevermind. Let's keep going! -> [ 24.103093] (4:slave@Ginette) Mmh. Something went wrong. Nevermind. Let's keep going! -> [ 25.134021] (1:master@Tremblay) Send completed -> [ 25.134021] (5:slave@Bourassa) Received "Task" -> [ 25.134021] (5:slave@Bourassa) Communication time : "1.030928" -> [ 25.134021] (5:slave@Bourassa) Processing "Task" -> [ 25.144330] (1:master@Tremblay) Send completed -> [ 25.144330] (2:slave@Tremblay) Received "Task" -> [ 25.144330] (2:slave@Tremblay) Communication time : "0.010309" -> [ 25.144330] (2:slave@Tremblay) Processing "Task" -> [ 26.175258] (1:master@Tremblay) Send completed -> [ 26.175258] (6:slave@Jupiter) Received "Task" -> [ 26.175258] (6:slave@Jupiter) Communication time : "1.030928" -> [ 26.175258] (6:slave@Jupiter) Processing "Task" -> [ 27.134021] (5:slave@Bourassa) "Task" done -> [ 27.144330] (2:slave@Tremblay) "Task" done -> [ 28.175258] (6:slave@Jupiter) "Task" done -> [ 36.175258] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! -> [ 37.206186] (1:master@Tremblay) Send completed -> [ 37.206186] (1:master@Tremblay) Mmh. Something went wrong with 'Bourassa'. Nevermind. Let's keep going! -> [ 37.206186] (4:slave@Ginette) Received "Task" -> [ 37.206186] (4:slave@Ginette) Communication time : "1.030928" -> [ 37.206186] (4:slave@Ginette) Processing "Task" -> [ 37.206186] (5:slave@Bourassa) Mmh. Something went wrong. Nevermind. Let's keep going! -> [ 37.216495] (1:master@Tremblay) Send completed -> [ 37.216495] (2:slave@Tremblay) Received "Task" -> [ 37.216495] (2:slave@Tremblay) Communication time : "0.010309" -> [ 37.216495] (2:slave@Tremblay) Processing "Task" -> [ 38.247423] (1:master@Tremblay) Send completed -> [ 38.247423] (6:slave@Jupiter) Received "Task" -> [ 38.247423] (6:slave@Jupiter) Communication time : "1.030928" -> [ 38.247423] (6:slave@Jupiter) Processing "Task" -> [ 39.206186] (4:slave@Ginette) "Task" done -> [ 39.216495] (2:slave@Tremblay) "Task" done -> [ 40.247423] (6:slave@Jupiter) "Task" done -> [ 48.247423] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! -> [ 49.278351] (1:master@Tremblay) Send completed -> [ 49.278351] (4:slave@Ginette) Received "Task" -> [ 49.278351] (4:slave@Ginette) Communication time : "1.030928" -> [ 49.278351] (4:slave@Ginette) Processing "Task" -> [ 50.000000] (4:slave@Ginette) Gloups. The cpu on which I'm running just turned off!. See you! -> [ 50.309278] (1:master@Tremblay) Send completed -> [ 50.309278] (5:slave@Bourassa) Received "Task" -> [ 50.309278] (5:slave@Bourassa) Communication time : "1.030928" -> [ 50.309278] (5:slave@Bourassa) Processing "Task" -> [ 50.319588] (1:master@Tremblay) Send completed -> [ 50.319588] (1:master@Tremblay) All tasks have been dispatched. Let's tell everybody the computation is over. -> [ 50.319588] (2:slave@Tremblay) Received "Task" -> [ 50.319588] (2:slave@Tremblay) Communication time : "0.010309" -> [ 50.319588] (2:slave@Tremblay) Processing "Task" -> [ 50.319588] (6:slave@Jupiter) Received "finalize" -> [ 50.319588] (6:slave@Jupiter) I'm done. See you! -> [ 51.319588] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! -> [ 52.309278] (5:slave@Bourassa) "Task" done -> [ 52.319588] (0:maestro@) Simulation time 52.3196 -> [ 52.319588] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Ginette'. Nevermind. Let's keep going! -> [ 52.319588] (1:master@Tremblay) Goodbye now! -> [ 52.319588] (2:slave@Tremblay) "Task" done -> [ 52.319588] (2:slave@Tremblay) Received "finalize" -> [ 52.319588] (2:slave@Tremblay) I'm done. See you! -> [ 52.319588] (5:slave@Bourassa) Received "finalize" -> [ 52.319588] (5:slave@Bourassa) I'm done. See you! diff --git a/examples/msg/masterslave/masterslave_failure_crosstraffic.tesh b/examples/msg/masterslave/masterslave_failure_crosstraffic.tesh deleted file mode 100644 index 1a1fbbe34b..0000000000 --- a/examples/msg/masterslave/masterslave_failure_crosstraffic.tesh +++ /dev/null @@ -1,102 +0,0 @@ -#! ./tesh - -p Testing a simple master/slave example application handling failures - -! output sort 19 -$ masterslave/masterslave_failure$EXEEXT --log=xbt_cfg.thres:critical --log=no_loc ${srcdir:=.}/../platforms/small_platform_with_failures.xml ${srcdir:=.}/masterslave/deployment_masterslave.xml --cfg=path:${srcdir} "--log=root.fmt:[%10.6r]%e(%i:%P@%h)%e%m%n" -> [ 0.000000] (0:maestro@) Cannot launch process 'slave' on failed host 'Fafard' -> [ 0.000000] (1:master@Tremblay) Got 5 slave(s) : -> [ 0.000000] (1:master@Tremblay) Jupiter -> [ 0.000000] (1:master@Tremblay) Fafard -> [ 0.000000] (1:master@Tremblay) Ginette -> [ 0.000000] (1:master@Tremblay) Bourassa -> [ 0.000000] (1:master@Tremblay) Tremblay -> [ 0.000000] (1:master@Tremblay) Got 20 task to process : -> [ 1.000000] (0:maestro@) Restart processes on host: Fafard -> [ 1.000000] (1:master@Tremblay) Mmh. Something went wrong with 'Jupiter'. Nevermind. Let's keep going! -> [ 1.000000] (3:slave@Jupiter) 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 'Fafard'. Nevermind. Let's keep going! -> [ 12.082474] (1:master@Tremblay) Send completed -> [ 12.082474] (4:slave@Ginette) Received "Task" -> [ 12.082474] (4:slave@Ginette) Communication time : "1.082474" -> [ 12.082474] (4:slave@Ginette) Processing "Task" -> [ 13.164948] (1:master@Tremblay) Send completed -> [ 13.164948] (5:slave@Bourassa) Received "Task" -> [ 13.164948] (5:slave@Bourassa) Communication time : "1.082474" -> [ 13.164948] (5:slave@Bourassa) Processing "Task" -> [ 13.175773] (1:master@Tremblay) Send completed -> [ 13.175773] (2:slave@Tremblay) Received "Task" -> [ 13.175773] (2:slave@Tremblay) Communication time : "0.010825" -> [ 13.175773] (2:slave@Tremblay) Processing "Task" -> [ 14.082474] (4:slave@Ginette) "Task" done -> [ 14.258247] (1:master@Tremblay) Send completed -> [ 14.258247] (6:slave@Jupiter) Received "Task" -> [ 14.258247] (6:slave@Jupiter) Communication time : "1.082474" -> [ 14.258247] (6:slave@Jupiter) Processing "Task" -> [ 15.164948] (5:slave@Bourassa) "Task" done -> [ 15.175773] (2:slave@Tremblay) "Task" done -> [ 16.258247] (6:slave@Jupiter) "Task" done -> [ 24.258247] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! -> [ 24.258247] (1:master@Tremblay) Mmh. Something went wrong with 'Ginette'. Nevermind. Let's keep going! -> [ 24.258247] (4:slave@Ginette) Mmh. Something went wrong. Nevermind. Let's keep going! -> [ 25.340722] (1:master@Tremblay) Send completed -> [ 25.340722] (5:slave@Bourassa) Received "Task" -> [ 25.340722] (5:slave@Bourassa) Communication time : "1.082474" -> [ 25.340722] (5:slave@Bourassa) Processing "Task" -> [ 25.351546] (1:master@Tremblay) Send completed -> [ 25.351546] (2:slave@Tremblay) Received "Task" -> [ 25.351546] (2:slave@Tremblay) Communication time : "0.010825" -> [ 25.351546] (2:slave@Tremblay) Processing "Task" -> [ 26.434021] (1:master@Tremblay) Send completed -> [ 26.434021] (6:slave@Jupiter) Received "Task" -> [ 26.434021] (6:slave@Jupiter) Communication time : "1.082474" -> [ 26.434021] (6:slave@Jupiter) Processing "Task" -> [ 27.340722] (5:slave@Bourassa) "Task" done -> [ 27.351546] (2:slave@Tremblay) "Task" done -> [ 28.434021] (6:slave@Jupiter) "Task" done -> [ 36.434021] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! -> [ 37.516495] (1:master@Tremblay) Send completed -> [ 37.516495] (1:master@Tremblay) Mmh. Something went wrong with 'Bourassa'. Nevermind. Let's keep going! -> [ 37.516495] (4:slave@Ginette) Received "Task" -> [ 37.516495] (4:slave@Ginette) Communication time : "1.082474" -> [ 37.516495] (4:slave@Ginette) Processing "Task" -> [ 37.516495] (5:slave@Bourassa) Mmh. Something went wrong. Nevermind. Let's keep going! -> [ 37.527320] (1:master@Tremblay) Send completed -> [ 37.527320] (2:slave@Tremblay) Received "Task" -> [ 37.527320] (2:slave@Tremblay) Communication time : "0.010825" -> [ 37.527320] (2:slave@Tremblay) Processing "Task" -> [ 38.609794] (1:master@Tremblay) Send completed -> [ 38.609794] (6:slave@Jupiter) Received "Task" -> [ 38.609794] (6:slave@Jupiter) Communication time : "1.082474" -> [ 38.609794] (6:slave@Jupiter) Processing "Task" -> [ 39.516495] (4:slave@Ginette) "Task" done -> [ 39.527320] (2:slave@Tremblay) "Task" done -> [ 40.609794] (6:slave@Jupiter) "Task" done -> [ 48.609794] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! -> [ 49.692268] (1:master@Tremblay) Send completed -> [ 49.692268] (4:slave@Ginette) Received "Task" -> [ 49.692268] (4:slave@Ginette) Communication time : "1.082474" -> [ 49.692268] (4:slave@Ginette) Processing "Task" -> [ 50.000000] (4:slave@Ginette) Gloups. The cpu on which I'm running just turned off!. See you! -> [ 50.774742] (1:master@Tremblay) Send completed -> [ 50.774742] (5:slave@Bourassa) Received "Task" -> [ 50.774742] (5:slave@Bourassa) Communication time : "1.082474" -> [ 50.774742] (5:slave@Bourassa) Processing "Task" -> [ 50.785567] (1:master@Tremblay) Send completed -> [ 50.785567] (1:master@Tremblay) All tasks have been dispatched. Let's tell everybody the computation is over. -> [ 50.785567] (2:slave@Tremblay) Received "Task" -> [ 50.785567] (2:slave@Tremblay) Communication time : "0.010825" -> [ 50.785567] (2:slave@Tremblay) Processing "Task" -> [ 50.785567] (6:slave@Jupiter) Received "finalize" -> [ 50.785567] (6:slave@Jupiter) I'm done. See you! -> [ 51.785567] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! -> [ 52.774742] (5:slave@Bourassa) "Task" done -> [ 52.785567] (0:maestro@) Simulation time 52.7856 -> [ 52.785567] (1:master@Tremblay) Mmh. Got timeouted while speaking to 'Ginette'. Nevermind. Let's keep going! -> [ 52.785567] (1:master@Tremblay) Goodbye now! -> [ 52.785567] (2:slave@Tremblay) "Task" done -> [ 52.785567] (2:slave@Tremblay) Received "finalize" -> [ 52.785567] (2:slave@Tremblay) I'm done. See you! -> [ 52.785567] (5:slave@Bourassa) Received "finalize" -> [ 52.785567] (5:slave@Bourassa) I'm done. See you! -- 2.20.1