X-Git-Url: http://info.iut-bm.univ-fcomte.fr/pub/gitweb/simgrid.git/blobdiff_plain/f21e6f4956e55ea1fb4c3ee5fed01f503ddb2344..cb0db70b9d93d8569647145ad6833fe3fe03153f:/examples/msg/masterslave/masterslave_failure.tesh diff --git a/examples/msg/masterslave/masterslave_failure.tesh b/examples/msg/masterslave/masterslave_failure.tesh index ab7ddd1b54..c72f58b9e3 100644 --- a/examples/msg/masterslave/masterslave_failure.tesh +++ b/examples/msg/masterslave/masterslave_failure.tesh @@ -2,7 +2,8 @@ p Testing a simple master/slave example application handling failures -$ masterslave/masterslave_failure$EXEEXT small_platform_with_failures.xml masterslave/deployment_masterslave.xml +$ 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 @@ -10,106 +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" -> [Tremblay:master:(1) 0.347192] [msg_test/INFO] Send completed -> [Fafard:slave:(4) 0.347192] [msg_test/INFO] Received "Task" -> [Fafard:slave:(4) 0.347192] [msg_test/INFO] Communication time : "0.199579" -> [Fafard:slave:(4) 0.347192] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 0.475692] [msg_test/INFO] Send completed -> [Ginette:slave:(5) 0.475692] [msg_test/INFO] Received "Task" -> [Ginette:slave:(5) 0.475692] [msg_test/INFO] Communication time : "0.128500" -> [Ginette:slave:(5) 0.475692] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 0.673184] [msg_test/INFO] Send completed -> [Bourassa:slave:(6) 0.673184] [msg_test/INFO] Received "Task" -> [Bourassa:slave:(6) 0.673184] [msg_test/INFO] Communication time : "0.197492" -> [Bourassa:slave:(6) 0.673184] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 0.675207] [msg_test/INFO] Send completed -> [Tremblay:slave:(2) 0.675207] [msg_test/INFO] Received "Task" -> [Tremblay:slave:(2) 0.675207] [msg_test/INFO] Communication time : "0.002023" -> [Tremblay:slave:(2) 0.675207] [msg_test/INFO] Processing "Task" -> [Jupiter:slave:(3) 0.802956] [msg_test/INFO] "Task" done -> [Tremblay:master:(1) 0.950569] [msg_test/INFO] Send completed -> [Jupiter:slave:(3) 0.950569] [msg_test/INFO] Received "Task" -> [Jupiter:slave:(3) 0.950569] [msg_test/INFO] Communication time : "0.147613" -> [Jupiter:slave:(3) 0.950569] [msg_test/INFO] Processing "Task" -> [Fafard:slave:(4) 1.002534] [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:slave:(2) 1.184917] [msg_test/INFO] "Task" done -> [Tremblay:master:(1) 1.202113] [msg_test/INFO] Send completed -> [Fafard:slave:(4) 1.202113] [msg_test/INFO] Received "Task" -> [Fafard:slave:(4) 1.202113] [msg_test/INFO] Communication time : "0.199579" -> [Fafard:slave:(4) 1.202113] [msg_test/INFO] Processing "Task" -> [Ginette:slave:(5) 1.506790] [msg_test/INFO] "Task" done -> [Tremblay:master:(1) 1.506790] [msg_test/INFO] Mmh. Something went wrong with 'Ginette'. Nevermind. Let's keep going! -> [Ginette:slave:(5) 1.506790] [msg_test/INFO] Mmh. Something went wrong. Nevermind. Let's keep going! -> [Bourassa:slave:(6) 1.704282] [msg_test/INFO] "Task" done -> [Fafard:slave:(4) 1.857455] [msg_test/INFO] "Task" done -> [Tremblay:master:(1) 1.901774] [msg_test/INFO] Send completed -> [Bourassa:slave:(6) 1.901774] [msg_test/INFO] Received "Task" -> [Bourassa:slave:(6) 1.901774] [msg_test/INFO] Communication time : "0.197492" -> [Bourassa:slave:(6) 1.901774] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 1.903797] [msg_test/INFO] Send completed -> [Tremblay:slave:(2) 1.903797] [msg_test/INFO] Received "Task" -> [Tremblay:slave:(2) 1.903797] [msg_test/INFO] Communication time : "0.002023" -> [Tremblay:slave:(2) 1.903797] [msg_test/INFO] Processing "Task" -> [Tremblay:slave:(2) 2.413507] [msg_test/INFO] "Task" done -> [Bourassa:slave:(6) 2.932871] [msg_test/INFO] "Task" done -> [Tremblay:master:(1) 11.903797] [msg_test/INFO] Mmh. Something went wrong with 'Jupiter'. Nevermind. Let's keep going! -> [Tremblay:master:(1) 12.103375] [msg_test/INFO] Send completed -> [Fafard:slave:(4) 12.103375] [msg_test/INFO] Received "Task" -> [Fafard:slave:(4) 12.103375] [msg_test/INFO] Communication time : "0.199579" -> [Fafard:slave:(4) 12.103375] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 12.231875] [msg_test/INFO] Send completed -> [Ginette:slave:(5) 12.231875] [msg_test/INFO] Received "Task" -> [Ginette:slave:(5) 12.231875] [msg_test/INFO] Communication time : "0.128500" -> [Ginette:slave:(5) 12.231875] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 12.429367] [msg_test/INFO] Send completed -> [Bourassa:slave:(6) 12.429367] [msg_test/INFO] Received "Task" -> [Bourassa:slave:(6) 12.429367] [msg_test/INFO] Communication time : "0.197492" -> [Bourassa:slave:(6) 12.429367] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 12.431390] [msg_test/INFO] Send completed -> [Tremblay:slave:(2) 12.431390] [msg_test/INFO] Received "Task" -> [Tremblay:slave:(2) 12.431390] [msg_test/INFO] Communication time : "0.002023" -> [Tremblay:slave:(2) 12.431390] [msg_test/INFO] Processing "Task" -> [Fafard:slave:(4) 12.758717] [msg_test/INFO] "Task" done -> [Tremblay:slave:(2) 12.941100] [msg_test/INFO] "Task" done -> [Ginette:slave:(5) 13.262973] [msg_test/INFO] "Task" done -> [Bourassa:slave:(6) 13.460465] [msg_test/INFO] "Task" done -> [Tremblay:master:(1) 22.431390] [msg_test/INFO] Mmh. Something went wrong with 'Jupiter'. Nevermind. Let's keep going! -> [Tremblay:master:(1) 22.630969] [msg_test/INFO] Send completed -> [Fafard:slave:(4) 22.630969] [msg_test/INFO] Received "Task" -> [Fafard:slave:(4) 22.630969] [msg_test/INFO] Communication time : "0.199579" -> [Fafard:slave:(4) 22.630969] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 22.630969] [msg_test/INFO] Mmh. Something went wrong with 'Ginette'. Nevermind. Let's keep going! -> [Ginette:slave:(5) 22.630969] [msg_test/INFO] Mmh. Something went wrong. Nevermind. Let's keep going! -> [Tremblay:master:(1) 22.828461] [msg_test/INFO] Send completed -> [Bourassa:slave:(6) 22.828461] [msg_test/INFO] Received "Task" -> [Bourassa:slave:(6) 22.828461] [msg_test/INFO] Communication time : "0.197492" -> [Bourassa:slave:(6) 22.828461] [msg_test/INFO] Processing "Task" -> [Tremblay:master:(1) 22.830484] [msg_test/INFO] Send completed -> [Tremblay:master:(1) 22.830484] [msg_test/INFO] All tasks have been dispatched. Let's tell everybody the computation is over. -> [Tremblay:slave:(2) 22.830484] [msg_test/INFO] Received "Task" -> [Tremblay:slave:(2) 22.830484] [msg_test/INFO] Communication time : "0.002023" -> [Tremblay:slave:(2) 22.830484] [msg_test/INFO] Processing "Task" -> [Fafard:slave:(4) 23.286311] [msg_test/INFO] "Task" done -> [Tremblay:slave:(2) 23.340194] [msg_test/INFO] "Task" done -> [Tremblay:master:(1) 23.830484] [msg_test/INFO] Mmh. Can't reach 'Jupiter'! Nevermind. Let's keep going! -> [Fafard:slave:(4) 23.832460] [msg_test/INFO] Received "finalize" -> [Fafard:slave:(4) 23.832460] [msg_test/INFO] I'm done. See you! -> [Tremblay:master:(1) 23.832460] [msg_test/INFO] Mmh. Can't reach 'Ginette'! Nevermind. Let's keep going! -> [Ginette:slave:(5) 23.832460] [msg_test/INFO] Mmh. Something went wrong. Nevermind. Let's keep going! -> [Bourassa:slave:(6) 23.859559] [msg_test/INFO] "Task" done -> [Bourassa:slave:(6) 23.861514] [msg_test/INFO] Received "finalize" -> [Bourassa:slave:(6) 23.861514] [msg_test/INFO] I'm done. See you! -> [Tremblay:master:(1) 23.861529] [msg_test/INFO] Goodbye now! -> [Tremblay:slave:(2) 23.861529] [msg_test/INFO] Received "finalize" -> [Tremblay:slave:(2) 23.861529] [msg_test/INFO] I'm done. See you! -> [23.861529] [simix_kernel/INFO] Oops ! Deadlock or code not perfectly clean. -> [23.861529] [simix_kernel/INFO] 1 processes are still running, waiting for something. -> [23.861529] [simix_kernel/INFO] Legend of the following listing: " on : ." -> [23.861529] [simix_kernel/INFO] slave on Ginette: Blocked on condition 0xdead; Waiting for the following actions: 'sleep'(0xdead). -> [23.861529] [simix_kernel/INFO] Return a Warning. -> [23.861529] [msg_test/INFO] Simulation time 23.8615 +> [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