X-Git-Url: http://info.iut-bm.univ-fcomte.fr/pub/gitweb/simgrid.git/blobdiff_plain/f398c8b20c1e1df37c49bcbbfd222dab952846c8..1a042c3771c14fdc9ec1a98ca60fc70ed933dc17:/examples/msg/masterslave/masterslave_failure.tesh diff --git a/examples/msg/masterslave/masterslave_failure.tesh b/examples/msg/masterslave/masterslave_failure.tesh index a950cf3433..c72f58b9e3 100644 --- a/examples/msg/masterslave/masterslave_failure.tesh +++ b/examples/msg/masterslave/masterslave_failure.tesh @@ -2,8 +2,8 @@ p Testing a simple master/slave example application handling failures -$ masterslave/masterslave_failure$EXEEXT small_platform_with_failures.xml masterslave/deployment_masterslave.xml -> [0.000000] simix/smx_process.c:67: [simix_process/WARNING] Cannot launch process 'slave' on failed host 'Fafard' +$ masterslave/masterslave_failure$EXEEXT --log=xbt_cfg.thres:critical --log=no_loc ${srcdir:=.}/small_platform_with_failures.xml ${srcdir:=.}/masterslave/deployment_masterslave.xml --cfg=path:${srcdir} +> [0.000000] [simix_process/WARNING] Cannot launch process 'slave' on failed host 'Fafard' > [Tremblay:master:(1) 0.000000] [msg_test/INFO] Got 5 slave(s) : > [Tremblay:master:(1) 0.000000] [msg_test/INFO] Jupiter > [Tremblay:master:(1) 0.000000] [msg_test/INFO] Fafard @@ -11,84 +11,84 @@ $ masterslave/masterslave_failure$EXEEXT small_platform_with_failures.xml master > [Tremblay:master:(1) 0.000000] [msg_test/INFO] Bourassa > [Tremblay:master:(1) 0.000000] [msg_test/INFO] Tremblay > [Tremblay:master:(1) 0.000000] [msg_test/INFO] Got 20 task to process : -> [Tremblay:master:(1) 0.147613] [msg_test/INFO] Send completed -> [Jupiter:slave:(3) 0.147613] [msg_test/INFO] Received "Task" -> [Jupiter:slave:(3) 0.147613] [msg_test/INFO] Communication time : "0.147613" -> [Jupiter:slave:(3) 0.147613] [msg_test/INFO] Processing "Task" -> [Jupiter:slave:(3) 0.802956] [msg_test/INFO] "Task" done +> [Tremblay:master:(1) 0.165962] [msg_test/INFO] Send completed +> [Jupiter:slave:(3) 0.165962] [msg_test/INFO] Received "Task" +> [Jupiter:slave:(3) 0.165962] [msg_test/INFO] Communication time : "0.165962" +> [Jupiter:slave:(3) 0.165962] [msg_test/INFO] Processing "Task" +> [Jupiter:slave:(3) 0.821304] [msg_test/INFO] "Task" done > [Jupiter:slave:(3) 1.100000] [msg_test/INFO] Gloups. The cpu on which I'm running just turned off!. See you! -> [Tremblay:master:(1) 10.147613] [msg_test/INFO] Mmh. Something went wrong with 'Fafard'. Nevermind. Let's keep going! -> [Tremblay:master:(1) 10.276113] [msg_test/INFO] Send completed -> [Ginette:slave:(4) 10.276113] [msg_test/INFO] Received "Task" -> [Ginette:slave:(4) 10.276113] [msg_test/INFO] Communication time : "0.128500" -> [Ginette:slave:(4) 10.276113] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 10.473605] [msg_test/INFO] Send completed -> [Bourassa:slave:(5) 10.473605] [msg_test/INFO] Received "Task" -> [Bourassa:slave:(5) 10.473605] [msg_test/INFO] Communication time : "0.197492" -> [Bourassa:slave:(5) 10.473605] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 10.475628] [msg_test/INFO] Send completed -> [Tremblay:slave:(2) 10.475628] [msg_test/INFO] Received "Task" -> [Tremblay:slave:(2) 10.475628] [msg_test/INFO] Communication time : "0.002023" -> [Tremblay:slave:(2) 10.475628] [msg_test/INFO] Processing "Task" -> [Tremblay:slave:(2) 10.985338] [msg_test/INFO] "Task" done -> [Ginette:slave:(4) 11.307211] [msg_test/INFO] "Task" done -> [Bourassa:slave:(5) 11.504703] [msg_test/INFO] "Task" done -> [Tremblay:master:(1) 20.475628] [msg_test/INFO] Mmh. Something went wrong with 'Jupiter'. Nevermind. Let's keep going! -> [Tremblay:master:(1) 30.475628] [msg_test/INFO] Mmh. Something went wrong with 'Fafard'. Nevermind. Let's keep going! -> [Tremblay:master:(1) 30.475628] [msg_test/INFO] Mmh. Something went wrong with 'Ginette'. Nevermind. Let's keep going! -> [Ginette:slave:(4) 30.475628] [msg_test/INFO] Mmh. Something went wrong. Nevermind. Let's keep going! -> [Tremblay:master:(1) 30.673120] [msg_test/INFO] Send completed -> [Bourassa:slave:(5) 30.673120] [msg_test/INFO] Received "Task" -> [Bourassa:slave:(5) 30.673120] [msg_test/INFO] Communication time : "0.197492" -> [Bourassa:slave:(5) 30.673120] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 30.675143] [msg_test/INFO] Send completed -> [Tremblay:slave:(2) 30.675143] [msg_test/INFO] Received "Task" -> [Tremblay:slave:(2) 30.675143] [msg_test/INFO] Communication time : "0.002023" -> [Tremblay:slave:(2) 30.675143] [msg_test/INFO] Processing "Task" -> [Tremblay:slave:(2) 31.184853] [msg_test/INFO] "Task" done -> [Bourassa:slave:(5) 31.704218] [msg_test/INFO] "Task" done -> [Tremblay:master:(1) 40.675143] [msg_test/INFO] Mmh. Something went wrong with 'Jupiter'. Nevermind. Let's keep going! -> [Tremblay:master:(1) 50.675143] [msg_test/INFO] Mmh. Something went wrong with 'Fafard'. Nevermind. Let's keep going! -> [Tremblay:master:(1) 50.803643] [msg_test/INFO] Send completed -> [Ginette:slave:(4) 50.803643] [msg_test/INFO] Received "Task" -> [Ginette:slave:(4) 50.803643] [msg_test/INFO] Communication time : "0.128500" -> [Ginette:slave:(4) 50.803643] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 51.001135] [msg_test/INFO] Send completed -> [Bourassa:slave:(5) 51.001135] [msg_test/INFO] Received "Task" -> [Bourassa:slave:(5) 51.001135] [msg_test/INFO] Communication time : "0.197492" -> [Bourassa:slave:(5) 51.001135] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 51.003158] [msg_test/INFO] Send completed -> [Tremblay:slave:(2) 51.003158] [msg_test/INFO] Received "Task" -> [Tremblay:slave:(2) 51.003158] [msg_test/INFO] Communication time : "0.002023" -> [Tremblay:slave:(2) 51.003158] [msg_test/INFO] Processing "Task" -> [Tremblay:slave:(2) 51.512868] [msg_test/INFO] "Task" done -> [Ginette:slave:(4) 51.834741] [msg_test/INFO] "Task" done -> [Bourassa:slave:(5) 52.032233] [msg_test/INFO] "Task" done -> [Tremblay:master:(1) 61.003158] [msg_test/INFO] Mmh. Something went wrong with 'Jupiter'. Nevermind. Let's keep going! -> [Tremblay:master:(1) 71.003158] [msg_test/INFO] Mmh. Something went wrong with 'Fafard'. Nevermind. Let's keep going! -> [Tremblay:master:(1) 71.131658] [msg_test/INFO] Send completed -> [Ginette:slave:(4) 71.131658] [msg_test/INFO] Received "Task" -> [Ginette:slave:(4) 71.131658] [msg_test/INFO] Communication time : "0.128500" -> [Ginette:slave:(4) 71.131658] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 71.329150] [msg_test/INFO] Send completed -> [Bourassa:slave:(5) 71.329150] [msg_test/INFO] Received "Task" -> [Bourassa:slave:(5) 71.329150] [msg_test/INFO] Communication time : "0.197492" -> [Bourassa:slave:(5) 71.329150] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 71.331173] [msg_test/INFO] Send completed -> [Tremblay:master:(1) 71.331173] [msg_test/INFO] All tasks have been dispatched. Let's tell everybody the computation is over. -> [Tremblay:slave:(2) 71.331173] [msg_test/INFO] Received "Task" -> [Tremblay:slave:(2) 71.331173] [msg_test/INFO] Communication time : "0.002023" -> [Tremblay:slave:(2) 71.331173] [msg_test/INFO] Processing "Task" -> [Tremblay:slave:(2) 71.840883] [msg_test/INFO] "Task" done -> [Ginette:slave:(4) 72.162756] [msg_test/INFO] "Task" done -> [Tremblay:master:(1) 72.331173] [msg_test/INFO] Mmh. Can't reach 'Jupiter'! Nevermind. Let's keep going! -> [Bourassa:slave:(5) 72.360248] [msg_test/INFO] "Task" done -> [Tremblay:master:(1) 73.331173] [msg_test/INFO] Mmh. Can't reach 'Fafard'! Nevermind. Let's keep going! -> [Ginette:slave:(4) 73.332446] [msg_test/INFO] Received "finalize" -> [Ginette:slave:(4) 73.332446] [msg_test/INFO] I'm done. See you! -> [Bourassa:slave:(5) 73.334401] [msg_test/INFO] Received "finalize" -> [Bourassa:slave:(5) 73.334401] [msg_test/INFO] I'm done. See you! -> [Tremblay:master:(1) 73.334416] [msg_test/INFO] Goodbye now! -> [Tremblay:slave:(2) 73.334416] [msg_test/INFO] Received "finalize" -> [Tremblay:slave:(2) 73.334416] [msg_test/INFO] I'm done. See you! -> [73.334416] [msg_test/INFO] Simulation time 73.3344 +> [Tremblay:master:(1) 10.165962] [msg_test/INFO] Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [Ginette:slave:(4) 10.306421] [msg_test/INFO] Received "Task" +> [Ginette:slave:(4) 10.306421] [msg_test/INFO] Communication time : "0.140460" +> [Ginette:slave:(4) 10.306421] [msg_test/INFO] Processing "Task" +> [Tremblay:master:(1) 10.306421] [msg_test/INFO] Send completed +> [Bourassa:slave:(5) 10.522294] [msg_test/INFO] Received "Task" +> [Bourassa:slave:(5) 10.522294] [msg_test/INFO] Communication time : "0.215872" +> [Bourassa:slave:(5) 10.522294] [msg_test/INFO] Processing "Task" +> [Tremblay:master:(1) 10.522294] [msg_test/INFO] Send completed +> [Tremblay:slave:(2) 10.524632] [msg_test/INFO] Received "Task" +> [Tremblay:slave:(2) 10.524632] [msg_test/INFO] Communication time : "0.002339" +> [Tremblay:slave:(2) 10.524632] [msg_test/INFO] Processing "Task" +> [Tremblay:master:(1) 10.524632] [msg_test/INFO] Send completed +> [Tremblay:slave:(2) 11.034342] [msg_test/INFO] "Task" done +> [Ginette:slave:(4) 11.337519] [msg_test/INFO] "Task" done +> [Bourassa:slave:(5) 11.553392] [msg_test/INFO] "Task" done +> [Tremblay:master:(1) 20.524632] [msg_test/INFO] Mmh. Got timeouted while speaking to 'Jupiter'. Nevermind. Let's keep going! +> [Tremblay:master:(1) 30.524632] [msg_test/INFO] Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [Ginette:slave:(4) 30.524632] [msg_test/INFO] Mmh. Something went wrong. Nevermind. Let's keep going! +> [Tremblay:master:(1) 30.524632] [msg_test/INFO] Mmh. Something went wrong with 'Ginette'. Nevermind. Let's keep going! +> [Bourassa:slave:(5) 30.740505] [msg_test/INFO] Received "Task" +> [Bourassa:slave:(5) 30.740505] [msg_test/INFO] Communication time : "0.215872" +> [Bourassa:slave:(5) 30.740505] [msg_test/INFO] Processing "Task" +> [Tremblay:master:(1) 30.740505] [msg_test/INFO] Send completed +> [Tremblay:slave:(2) 30.742843] [msg_test/INFO] Received "Task" +> [Tremblay:slave:(2) 30.742843] [msg_test/INFO] Communication time : "0.002339" +> [Tremblay:slave:(2) 30.742843] [msg_test/INFO] Processing "Task" +> [Tremblay:master:(1) 30.742843] [msg_test/INFO] Send completed +> [Tremblay:slave:(2) 31.252553] [msg_test/INFO] "Task" done +> [Bourassa:slave:(5) 31.771603] [msg_test/INFO] "Task" done +> [Tremblay:master:(1) 40.742843] [msg_test/INFO] Mmh. Got timeouted while speaking to 'Jupiter'. Nevermind. Let's keep going! +> [Tremblay:master:(1) 50.742843] [msg_test/INFO] Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [Ginette:slave:(4) 50.883303] [msg_test/INFO] Received "Task" +> [Ginette:slave:(4) 50.883303] [msg_test/INFO] Communication time : "0.140460" +> [Ginette:slave:(4) 50.883303] [msg_test/INFO] Processing "Task" +> [Tremblay:master:(1) 50.883303] [msg_test/INFO] Send completed +> [Bourassa:slave:(5) 51.099175] [msg_test/INFO] Received "Task" +> [Bourassa:slave:(5) 51.099175] [msg_test/INFO] Communication time : "0.215872" +> [Bourassa:slave:(5) 51.099175] [msg_test/INFO] Processing "Task" +> [Tremblay:master:(1) 51.099175] [msg_test/INFO] Send completed +> [Tremblay:slave:(2) 51.101514] [msg_test/INFO] Received "Task" +> [Tremblay:slave:(2) 51.101514] [msg_test/INFO] Communication time : "0.002339" +> [Tremblay:slave:(2) 51.101514] [msg_test/INFO] Processing "Task" +> [Tremblay:master:(1) 51.101514] [msg_test/INFO] Send completed +> [Tremblay:slave:(2) 51.611224] [msg_test/INFO] "Task" done +> [Ginette:slave:(4) 51.914401] [msg_test/INFO] "Task" done +> [Bourassa:slave:(5) 52.130273] [msg_test/INFO] "Task" done +> [Tremblay:master:(1) 61.101514] [msg_test/INFO] Mmh. Got timeouted while speaking to 'Jupiter'. Nevermind. Let's keep going! +> [Tremblay:master:(1) 71.101514] [msg_test/INFO] Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [Ginette:slave:(4) 71.241973] [msg_test/INFO] Received "Task" +> [Ginette:slave:(4) 71.241973] [msg_test/INFO] Communication time : "0.140460" +> [Ginette:slave:(4) 71.241973] [msg_test/INFO] Processing "Task" +> [Tremblay:master:(1) 71.241973] [msg_test/INFO] Send completed +> [Bourassa:slave:(5) 71.457846] [msg_test/INFO] Received "Task" +> [Bourassa:slave:(5) 71.457846] [msg_test/INFO] Communication time : "0.215872" +> [Bourassa:slave:(5) 71.457846] [msg_test/INFO] Processing "Task" +> [Tremblay:master:(1) 71.457846] [msg_test/INFO] Send completed +> [Tremblay:slave:(2) 71.460184] [msg_test/INFO] Received "Task" +> [Tremblay:slave:(2) 71.460184] [msg_test/INFO] Communication time : "0.002339" +> [Tremblay:slave:(2) 71.460184] [msg_test/INFO] Processing "Task" +> [Tremblay:master:(1) 71.460184] [msg_test/INFO] Send completed +> [Tremblay:master:(1) 71.460184] [msg_test/INFO] All tasks have been dispatched. Let's tell everybody the computation is over. +> [Tremblay:slave:(2) 71.969894] [msg_test/INFO] "Task" done +> [Ginette:slave:(4) 72.273071] [msg_test/INFO] "Task" done +> [Tremblay:master:(1) 72.460184] [msg_test/INFO] Mmh. Got timeouted while speaking to 'Jupiter'. Nevermind. Let's keep going! +> [Bourassa:slave:(5) 72.488944] [msg_test/INFO] "Task" done +> [Tremblay:master:(1) 73.460184] [msg_test/INFO] Mmh. Got timeouted while speaking to 'Fafard'. Nevermind. Let's keep going! +> [Ginette:slave:(4) 73.473416] [msg_test/INFO] Received "finalize" +> [Ginette:slave:(4) 73.473416] [msg_test/INFO] I'm done. See you! +> [Bourassa:slave:(5) 73.493752] [msg_test/INFO] Received "finalize" +> [Bourassa:slave:(5) 73.493752] [msg_test/INFO] I'm done. See you! +> [Tremblay:slave:(2) 73.493908] [msg_test/INFO] Received "finalize" +> [Tremblay:slave:(2) 73.493908] [msg_test/INFO] I'm done. See you! +> [Tremblay:master:(1) 73.493908] [msg_test/INFO] Goodbye now! +> [73.493908] [msg_test/INFO] Simulation time 73.4939